AI Projects at the U

Cards

Projects In Queue:

81

Projects In Flight:

83

Projects Complete:

216

Accordion Group

Open All Tabs

• AI for Everyone - AI Projects

  Sub Domain	Status	Project Name	Description
  Application & Use	Completed	Copilot Adoption Sessions	Touring adoption sessions with Microsoft to drive just-in-time learning and user adoption
  Training & Upskilling	Completed	LinkedIn Learning AI Training	Available self-service, as-you-go, AI training through LinkedIn
  AI Priority Setting	In-Flight	AI for Everyone - Course & Credential Design	N/A
  Training & Upskilling	Completed	AI for Everyone - Course Production / Acquisition	N/A
  AI Priority Setting	In-Flight	AI for Everyone - Curriculum Design	N/A
  Training & Upskilling	In-Queue	AI for Everyone - Full Deployment	N/A
  Culture of Adoption	In-Flight	AI for Everyone - Monitor and Refresh	N/A
  Culture of Adoption	In-Flight	AI for Everyone - Pilot	N/A

Accordion Group

Open All Tabs

• Enhancing AI Curriculum Content - AI Projects

  Sub Domain	Status	Project Name	Description
  Assessment and Feedback	Completed	Grading AI Agent	Assists faculty in grading assignments with computer code, equations, essays, and other long-form answers through the use of Gradescope, a commercially available platform that integrates with Blackboard.
  Case Study Generation	Completed	Obstetrics Teaching Dialogue GenAI	Using Open AI gpt to generate teaching dialogue for obstetric emergency simulations.
  Sentiment Analysis	Completed	Social Media Sentiment Analysis (School of Communication)	Academic Research in the School of Communication - using generative AI to create a sentiment analysis of social media posts.
  AI Literacy	In-Queue	UOnline Instructional and Multimedia Design	Supports course design so faculty can focus on teaching and content
  Assessment and Feedback	In-Queue	UOnline Grading Solutions	Increases grading efficiency so faculty can focus on teaching and content

Accordion Group

Open All Tabs

• Enhancing Patient Care - AI Projects

  Sub Domain	Status	Project Name	Description
  Physician Satisfaction	Completed	Epic Ambient Voice Documentation for Patient Notes	Use ambient voice technology to write visit notes based on the conversation during office visits, and inpatient. Pilot for 100 users.
  Quality & Saving Lives	Completed	AIDOC (ICD10 Recommendation)	Free text indication interpretation and ICD10 recommendation.  Aims to improve ordering provider efficiency and reimbursements
  Quality & Saving Lives	Completed	Augmented Reality Surgical Guidance (Medivis)	Augmented reality surgical guidance.
  Physician Productivity	In-Flight	Automated Exam Room Allocation (Epic)	Working with Epic R&D to pilot new module for staff and exam room allocation that will provide operational lead with actionable data on the allocation and assignment of exam rooms to providers.
  Physician Productivity	In-Flight	Automated Physician Leave Requests (Workday)	Streamlining the leave request process for faculty by automate the requests for approval and directly sending the approved leave into the scheduling system eliminating manual reconciliation work performed by master scheduling team.
  Quality & Saving Lives	Completed	Brain Volume Calculations (Cortech.AI)	MS PLex and Morphometric brain volume calculations.
  Quality & Saving Lives	Completed	Calcium Scoring (Bunker Hill)	Calcium Scoring of non-typical CT valve contrast studies.
  Physician Productivity	In-Queue	CaneEvidence Agent	Integrate GPT in with Epic to provide patient-specific, evidence-based clinical assistance.
  Physician Productivity	Canceled/Deprioritized	Cardiology AI Patient Intake	Partnering with SOAP AI and the Mayo Clinic on a NCI-funded research study to study the efficacy of AI patient intake for primary care new patient visits replacing the manual questionnaires and summarizing key findings for the provider.
  Quality & Saving Lives	Completed	Cardiology Blood Flow & 3D Modeling Computer Vision Analysis	Using computer vision to support blood flow analysis, 3D modeling without invasive procedure, and coronary artery disease diagnosis.
  Quality & Saving Lives	Completed	Changes in Medication Treatment for Glaucoma Patients	Treatment plans for glaucoma patients are documented within clinical notes, making it difficult to study. NLP models are being developed to identify if there were any changes to treatment plans indicated within the clinical note, and to extract the medication information (medication name and dosage). A pre-trained model processes all relevant clinical notes and outputs notes annotated with medications, allowing clinicians to review for accuracy.
  Physician Productivity	Canceled/Deprioritized	Copilot Access in Epic	Embed Copilot within Epic via a middleware "website" that allows users to submit a prompt and then get a response back from that website in Epic.
  Quality & Saving Lives	Canceled/Deprioritized	CT Ablation Tumor Site Identification	Enhance tumor site identification.
  Quality & Saving Lives	Completed	Custom Clinical Entity Recognition - Thrombolytic/Bleeding Events in Cancer Patients	Categories
  Quality & Saving Lives	Completed	Custom Predictive Models - DVT/PE	Identifies patients at-risk of developing deep vein thrombosis (DVT) and/or pulmonary embolism (PE), which can be life-threatening if not identified earlier.
  Patient Flow	Canceled/Deprioritized	Custom Predictive Models - Hospital Ambulatory Surgery Admissions	Some hospital ambulatory surgeries end up requiring a hospital bed following surgery, putting strain on capacity planning. This model will help predict the number of patients requiring a hospital bed based on scheduled procedures.
  Physician Productivity	Completed	Electronic Outpatient Medication Prior Authorization	Automates medication prior authorization workflows with a fully integrated solution that proactively initiates prior auth requests and receives quick responses with the EHR.
  Quality & Saving Lives	In-Flight	Epic Actionable Follow-Ups for Radiology	Generative AI in Epic that supports clinical care delivery.
  Physician Satisfaction	Completed	Epic AI Text Assistant	Use Ai Text assistant or edit inbasket messages and notes to quickly enhance note to use generative AI to edit all or part of your text. You can summarize text, change the tone for a different audience, or update the formatting. You can also check your spelling and grammar.
  Quality & Saving Lives	In-Flight	Epic Clinical Documentation Improvement Suggestions	Generative AI in Epic that supports clinical care delivery.
  Value from Data	Completed	Epic Conversational Queries with SlicerDicer SideKick	Implement Epic's GenAI tool within SlicerDicer allowing users to request reports in plain language and have the session auto-built
  Value from Data	In-Flight	Epic Dashboard Insights	Generative AI in Epic that supports clinical care delivery.
  Physician Productivity	Completed	Epic Draft Hospital Course in Discharge Summary	Drafting hospital course notes with the help of generative AI can help physicians more quickly summarize the admission so they can include that information in their discharge summaries. An AI-generated draft pulls together information from notes and events documented throughout the admission, giving physicians a starting point for their note. Clinicians who have used this feature while providing early feedback have reported time savings, including one clinician who timed writing a note with and without AI and found that AI made them significantly faster: from around 4.5 minutes to about 40 seconds.
  Patient Exp. & Self-Help	In-Queue	Epic Draft Provider Bios
  Physician Productivity	Completed	Epic End-of-Shift Care Plan Notes	Generative AI in Epic that supports clinical care delivery.
  Physician Satisfaction	Completed	Epic In Basket Art: Draft Responses	automatically drafts text for a potential response to the patient’s medical advice request MyChart message based on the text of the message and information from the patient’s record, such as current prescriptions and recent results.
  Physician Satisfaction	Completed	Epic In Basket Art: Results	AI drafts a comment to send to the patient for new results based on details from the Results In Basket message or the clinician's result note. Clinicians can review and revise the response before sending—or ignore it and draft their own reply from scratch.
  Physician Satisfaction	In-Flight	Epic In Basket Art: Translations	In Basket automatically translates incoming patient messages from Spanish to English and shows a translation preview to clinicians that they can use to quickly check if the message requires urgent action, such as calling the patient with a translator. If no urgent action is needed, the clinician can send a translation request message to your in-house translator, who can start their translation with the AI-generated draft and make any necessary corrections, decreasing translation turnaround times.
  Physician Satisfaction	Completed	Epic Inpatient Insights	Insights Summary is a feature that combs through past notes and recent events to save time for a clinician who needs to quickly get up to speed about recent medical developments for a patient. The Insights Summary activity's large language model can recap care that occurred in a configurable timeframe, giving clinicians the relevant context they need to address current issues, and presented with their discipline and background knowledge in mind.
  Physician Satisfaction	Completed	Epic Outpatient Insights	Summarize previous notes in outpatient encounters
  Patient Exp. & Self-Help	In-Flight	Epic Patient-Facing Endoscopy Procedure Overview	Generative AI in Epic that supports clinical care delivery.
  Quality & Saving Lives	Completed	Epic Predictive Model - Risk of ICU Readmission or Mortality	Use this model to identify patients who are at risk of being readmitted to the ICU or dying. The model uses dozens of data points such as code status, vital signs, ventilation, and LDAs to help ICU clinicians make better informed decisions during rounding and discharge planning workflows.
  Quality & Saving Lives	Canceled/Deprioritized	Epic Predictive Model - Amb Risk of Hospital Admission or ED Visit for Asthma	Ambulatory - if implementing or has an existing population health workflow around asthma patients. Care managers and other clinicians can use this model to see an adult asthma patient's risk of a hospital admission or ED visit related to asthma in the next year. The Hospital Admissions and ED Visits for Asthma model helps clinicians and care managers identify the asthma patients who are most at risk of ending up in the ED due to asthma-related conditions. The statistically derived model uses a proprietary algorithm and 17 variables to stratify your adult asthma population into risk buckets. Identifying and stratifying these patients makes it possible for clinicians to deliver proactive, targeted interventions that are designed to prevent dangerous flare-ups. The goal of the model is to better outcomes for patients and better utilization of your resources, such as your ED.
  Quality & Saving Lives	Canceled/Deprioritized	Epic Predictive Model - Early detection of Pediatric Sepsis	Use a set of three models created by Nationwide Children's Hospital to detect and treat sepsis in pediatric patients earlier in both inpatient and emergency departments. One model scores patients in the ED and the other two models score admitted patients. One inpatient model scores the general pediatric population and one model scores pediatric patients with high-risk conditions who are predisposed to developing sepsis. These models uses data points such as temperature, BP, behavioral assessments, length of stay, and diagnoses to help clinicians identify septic pediatric patients (under 20 years old) before they worsen. The inpatient model that scores patients with high-risk conditions is not available to organizations in the EU or the UK due to locale-based differences in the regulation of decision support.
  Quality & Saving Lives	Canceled/Deprioritized	Epic Predictive Model - Hospital Acquired Acute Kidney Injury	This model identifies admitted patients who are at risk of experiencing acute kidney injury (AKI) so clinicians can determine whether it's possible to limit their use of potentially harmful treatments and closely monitor serum creatinine and urine output to detect AKI more quickly.
  Patient Flow	Canceled/Deprioritized	Epic Predictive Model - Likely Surgical Admit Destination	This model is standardly included in the Capacity Management dashboard for organizations that automatically create bed requests for surgical admit patients.
  Physician Satisfaction	Canceled/Deprioritized	Epic Predictive Model - OCR Image to Text Transcription	The model transcribes the text of scanned documents, such as notes, results, and referrals, depending on your organization’s configuration options. After the model runs on a set of image files, the transcribed text from those documents is available in your system and can appear in your clinicians’ search results. This model requires the Cognitive Computing license but doesn't count toward the ten models included with that license.
  Quality & Saving Lives	Completed	Epic Predictive Model - Risk of Hospital Admission or ED Visit (Version 2)	Version 2 of the Risk of Hospital Admission or ED Visit model is a cloud-based logistic regression model with 55 features. This version offers the potential for improved performance due to the expanded feature set and its ability to localize on your patient data.
  Quality & Saving Lives	Canceled/Deprioritized	Epic Predictive Model - Risk of Negative Diabetes Outcomes	Using this model, care managers and other clinicians can review diabetes-related complications a patient is expected to develop over the next two years. Then they can drill down into the contributing factors and determine what to do to lower that risk. Care managers can also perform outreach or bulk enroll patients in Compass Rose episodes based on the risk of negative outcomes of type 2 diabetes score.
  Quality & Saving Lives	Canceled/Deprioritized	Epic Predictive Model - Risk of Opioid Use Disorder or Overdose	The model can be used a number of ways in clinician-facing workflows, but two primary workflows are recommended for this model. The first is showing the score in Storyboard or a similarly visible location in the chart so clinicians can reference a patient’s score before ordering. This workflow is ideal for settings where opioids might be prescribed on a regular basis, such as in the emergency department, in a pain clinic, or during inpatient discharge planning. The second primary workflow is in a BestPractice Advisory (BPA) related to opioid ordering so users placing an opioid order are alerted when a patient has high risk. This workflow is ideal for outpatient and emergency department ordering. The model could also be used as additional filtering for your organization’s existing opioid-related BPAs.
  Quality & Saving Lives	Canceled/Deprioritized	Epic Predictive Model - Sepsis (version 1)	Model helps clinicians identify patients with sepsis before their condition worsens with real-time, point-of-care warnings to allow for rapid and risk-adjusted interventions. The model uses data points such as medications, lab results, vital signs, and LDAs to identify patients prior to sepsis progression and organ damage or death occurs.
  Quality & Saving Lives	Completed	Epic Predictive Model - Sepsis (Version 2)	Cloud based version 2 for early detection of sepsis in adult patients
  Quality & Saving Lives	Canceled/Deprioritized	Epic Predictive Model: Inpatient Risk of Falls	Use this model to identify patients who are at risk of falling in the ED or an inpatient unit. The model uses dozens of data points such as financial class, vitals, assessments, medications, and lab results to help your organization identify patients who are most at risk of falling. This information enables nurses to focus interventions on the patients who are most likely to fall without them. The model can improve on the performance of manual fall risk assessments, while requiring minimal additional input from clinicians or operational staff. After it is implemented, the model can run continuously, saving up to 3 minutes per patient per day.
  Quality & Saving Lives	Canceled/Deprioritized	Epic Predictive Model: Amb Pediatric Risk of Hospital Admission or ED Visit	Care managers and other clinicians can see the percent chance that a pediatric patient will end up admitted or in the emergency department in the next six months. They can review the factors contributing to that risk, reach out to the patient or the patient's guardian, and reduce the likelihood that an adverse health event occurs.
  Quality & Saving Lives	Canceled/Deprioritized	Epic Predictive Model: Amb Risk of Admission for Heart Failure	Care managers and other clinicians can use this model to see an adult patient's risk of a hospital admission related to heart failure in the next year.
  Quality & Saving Lives	Completed	Epic Predictive Model: Amb Risk of HTN	Care managers and clinicians can use this predictive model to help determine which patients have the highest risk of developing hypertension within the next two years. Due to a shift in the definition of hypertension by the American Heart Association and American College of Cardiology, the model is effectively predicting the risk of stage 2 hypertension. Refer to the Additional Considerations topic for more information.
  Quality & Saving Lives	Canceled/Deprioritized	Epic Predictive Model: Amb Risk of Initial Myocardial Infarction	Care managers and other clinicians can use this model to see an adult patient's risk of an initial myocardial infarction in the next two years so they can take preventive measures.
  Quality & Saving Lives	Canceled/Deprioritized	Epic Predictive Model: Amb Risk of Pediatric Asthma exacerbation	Ambulatory - if pop health workflow around this population Clinicians can see the risk of a pediatric asthma patient under the age of 18 having a severe asthma attack in the next 90 days. They can review the factors contributing to that risk and allocate care and resources accordingly.
  Quality & Saving Lives	Completed	Epic Predictive Model: End of Life Index	The End of Life Care Index is a logistic regression that predicts the risk of one-year mortality. This model is designed to be used on all adult patients using frequently documented features.
  Quality & Saving Lives	Canceled/Deprioritized	Epic Predictive Model: ICU In-Hospital Mortality Risk (Retrospective)	Epic's statistically derived in-hospital mortality risk model for critical care patients uses a proprietary algorithm and 49 variables to calculate a patient's expected mortality risk for retrospective risk-adjusted benchmarking of ICU mortality rates, enabling clinicians, unit managers, and hospital administrators to see outcomes and quality of care in their ICUs. This model allows you to benchmark your outcomes without the need for time-intensive manual data review and abstraction
  Patient Flow	Canceled/Deprioritized	Epic Predictive Model: ICU Length of Stay (Retrospective)	Epic's statistically derived ICU length of stay model uses a proprietary algorithm and 60 variables to calculate a patient's expected length of stay in the ICU for retrospective risk-adjusted benchmarking, enabling clinicians, unit managers, and hospital administrators to see outcomes and quality of care in their ICUs. This model allows you to benchmark your outcomes without the need for time-intensive manual data review and abstraction.
  Quality & Saving Lives	Completed	Epic Predictive Models - Deterioration Index Score	Model identifies hospitalized patients who may be clinically deteriorating, which allows clinicians to proactively intervene and treat patients earlier, which may help reduce adverse events, ICU admissions, and cardiac arrests. Model updates dynamically based on information entered into the chart, providing clinicians with the most up-to-date risk assessment information.
  Patient Flow	Canceled/Deprioritized	Epic Predictive Models - ED Patient Likelihood to Occupy an Inpatient Bed	Using this model, hospital staff can take a proactive approach to bed planning. Instead of constantly checking the ED census, staff can review the model predictions for patients who will likely need a bed in an inpatient unit and start preparing for these arrivals before an admit order is placed. This increased lead time enables capacity planning staff to proactively estimate the number of beds and staff needed at a given time. The model is integrated within the capacity dashboards already used for capacity management.
  Patient Flow	Completed	Epic Predictive Models - Forecasted Hospital Census	Model predicts expected capacity for the upcoming hour, day, week, month, or year on operational dashboards to better identify and mitigate potential overutilization or capacity problems before they arise. This information can help plan discharges, schedules, and staffing to keep up with expected capacity.
  Patient Exp. & Self-Help	Completed	Epic Predictive Models - Likelihood to Recommend	Identifies the likelihood of patient experience survey resources and correlate key variables about patients or their visit.
  Physician Productivity	Completed	Epic Predictive Models - Order Search	The cloud-based order search model learns from the sequences of search terms used across your whole organization, as well as user-level and department-level statistics that are calculated in Chronicles. Brings the most common order up when user searches for order.
  Quality & Saving Lives	Completed	Epic Predictive Models - Readmissions Risk Score	This model helps identify patients who are most at risk of an unplanned readmission in the 30 days after discharge and can be fully integrated within clinical workflows, allowing clinicians and hospital staff to focus more resources on at-risk patients. The model uses dozens of data points such as diagnoses, medications, and lab results.
  Quality & Saving Lives	Canceled/Deprioritized	Epic Predictive Models - Remaining Length of Stay	Model predicts the remaining of length of stay of all adult patients with an inpatient admission (inpatient, observation status) at all locations.
  Quality & Saving Lives	Canceled/Deprioritized	Epic Predictive Models - Risk of Surgical Site Infection	This model identifies patients prior to surgery who are most at risk of developing a surgical site infection (SSI).
  Quality & Saving Lives	In-Queue	Epic Surgical Procedure Mismatch Detection	Generative AI in Epic that supports clinical care delivery.
  Patient Exp. & Self-Help	Canceled/Deprioritized	Food Service Automation - Amazon Just Walk Out	Deploying Amazon Just Walk Out (JWO) technology on Medical Campus (Calder Library) to pilot the use of automatous food service option in areas with limited availability for staff and patients.
  Patient Exp. & Self-Help	Completed	Generate Digital Art for SoLeMia and Doral Digital Walls	Use Generative AI to create custom 4K video for large video walls.
  Patient Exp. & Self-Help	Completed	IP Emotional Recognition Monitoring	Real-time detection of patient experience in the inpatient setting through facial expressions allows for the opportunity to intervene to improve patient satisfaction prior to discharge.
  Quality & Saving Lives	Completed	Mammo Post Processing (Density Scoring)	Mammo post processing - density secondary capture scorecard.
  Quality & Saving Lives	Completed	Neurosurgical Planning (Quicktime)	Neurosurgical planning software which incorporates connectomics; utilizing cloud computing for large-volume data processing, and intuitive browser-based interfaces.
  Quality & Saving Lives	Completed	Nuclear Medicine Processing (Hermes AI)	Nuclear Medicine processing, display and analysis for SPECT-CT, PET-CT, PET-MR including dosimetry; image quantification and advanced image reconstruction.
  Patient Exp. & Self-Help	Canceled/Deprioritized	Patient Affordability	Analyzing affordability of UHealth to patients in our market.
  Patient Exp. & Self-Help	Canceled/Deprioritized	Patient Arrival with Distance Computer Vision	Deploying Microsoft facial and license plate recognition to identify patients with scheduled appointments as they approach the facility to provide a low friction arrival experience. License plate recognition for visitor management and parking integration.
  Quality & Saving Lives	Completed	Perspectum - Radiology AI Imaging	Quantitative liver analysis with software that provides clinicians with an interpretable report of liver health.
  Patient Flow	Completed	Epic Predictive Model: Likelihood of Discharge by End of Day Today or by End of Day Tomorrow	Using this model, your staff can more accurately predict whether admitted patients will be discharged today or tomorrow.
  Physician Satisfaction	Completed	Epic Predictive Models - Inbasket Categorization	The system reviews patient medical advice request messages to identify a category to apply to the message. Clinical and support staff can use these categories to sort and triage messages sent to a pool. Categories include such things as clinical actionable messages and FYI messages.
  Physician Satisfaction	Completed	Epic Predictive Models - Inbasket Language Detection	The language detection model uses cloud computing to label incoming patient medical advice request messages with the language they were written in. Organizations can set up rules based on the message’s language to allow users to forward the message to an appropriate translation pool.
  Patient Exp. & Self-Help	Completed	PX Sentiment Word Cloud	Taking all comments from patients within the Patient Experience CAHPS surveys, an NLP model is used highlight topics and keywords while removing any low impact words. The results are visualized as a word cloud.
  Quality & Saving Lives	Completed	Reduce Radiology Error with Image Analysis (Siemens)	Reduce radiologist errors by analyzing post processed images, providing confirmation of findings and/or identify findings for possible inclusion in the final report.
  Physician Satisfaction	Completed	Suki Epic Ambient Voice Docmentation for Patient Notes	Use ambient voice technology to write visit notes based on the conversation during office visits. in 2024,Abridge, Dax, and Suki were evaluated, and Suki as selected as the vendor due ability to use on both iPhone/android, multiple languages, and support model for on-boarding.
  Patient Exp. & Self-Help	In-Flight	Amelia SMS Appointment Directions
  Physician Satisfaction	In-Queue	Applied Compute
  Physician Satisfaction	Completed	Epic AI: Anesthesia Pre-Procedure Insights
  End User Experience	Canceled/Deprioritized	Suki Epic Ambient Voice for Nursing	Using Suki to document flowsheets for nursing. Used AI-powered, ambient voice recognition technology to document flowsheets. In Rover, nurses start the recording and set the phone nearby while they work with the patient. The system notifies them when the recording is processed and ready to file to the chart.
  Physician Satisfaction	Completed	Suki Epic Ambient Voice Ordering Medications
  Patient Exp. & Self-Help	Completed	Epic AI: Patient Facing Imaging Results Overview
  Patient Exp. & Self-Help	Completed	Epic AI - Suggested Care Companion Tasks
  Physician Satisfaction	In-Flight	Epic AI: Generated Referral Summaries Help Clinicians Quickly Understand Why a Patient Is Being Referred	Referral Consult Insights help specialist physicians, referral triage coordinators, and clinicians in consult workflows quickly understand why a patient is being referred without needing to dig into the patient's chart. An AI-summarized reason for the referral and related problems appear in e-consult and referral triage In Basket messages and in the encounter sidebar.
  Physician Satisfaction	Completed	Epic Ai: Draft Patient Instructions from Note
  Physician Satisfaction	Canceled/Deprioritized	Epic AI: Extract Phenotypes from Notes	Uses generative AI to extract phenotypes from patient notes, with the option to extract notes from the current encounter or unprocessed notes from the last five years. Users can extract phenotypes the from the Deep Phenotyping activity or from an ad hoc Reporting Workbench report they can also accept or dismiss phenotypes extracted.
  Physician Satisfaction	In-Flight	Epic AI: Synopsis Insights	Uses generative AI to surface relevant text from clinical notes helping clinicians understand the story behind a patient's medications—what was tried, what worked, what didn't, and why. Clinicians can hover over a medication to view Insights, which are excerpts from notes that mention medication changes with links to full notes for deeper review.
  Patient Flow	In-Flight	Epic Predictive Model: Predicted Discharge Disposition	Using the model, case managers can identify and prioritize patients who are likely to need discharge placement sooner, potentially days before a case management consult order is placed.
  Physician Satisfaction	Completed	Epic AI Text Assistant: Implement Custom Actions	Ability to perfom custom action for the use with Epic AI text assitant
  Physician Satisfaction	Completed	Epic Improve Draft Quality with Advanced Message Categorization for Art	Implementing new advanced categorization model that can identify when a patient message is about multiple topics and supports additional topic categories. This change also reduces ongoing prompt maintenance because Epic-released prompts are designed to be used out of the box and are updated automatically over Nebula.
  Physician Satisfaction	Completed	Theator AI Video - Surgery to Text pilot	Video recording of the laparoscopic procedures that uses AI to generate full operative note and integrate with Epic.
  Patient Exp. & Self-Help	In-Queue	Automated Next Step from Clinical Notes	Automate clinical next steps (care coordination)
  Value from Data	Completed	Copilot Readmission Analysis	Use Copilot to summarize the top 5 themes driving patient readmissions and top 5 strategies for reducing patient readmissions.
  Physician Satisfaction	Completed	Epic AI Context-Driven In Basket Insights - Pilot	Uses generative AI to gather relevant patient and encounter information, including demographics, medications, problems, results, allergies, and other pertinent details based on the content of the patient's message Help clinicians get up to speed quickly and respond to patient messages more efficiently How It Works A clinician opens a patient message in In Basket for a patient they haven't seen in a while. To respond effectively, they need to understand the patient's condition which has traditionally required them to spend time searching through the chart. With In Basket Insights, the system surfaces this relevant clinical information directly within the message view. After reading the message, the clinician clicks Generate Insights to pull in patient-specific details based on the context of the request. Within moments, they see an AI-generated summary of recent lab results, medications, past diagnoses, and other pertinent data, all without navigating away from the message. If they need more context, they can hover over inline reference notes to see the source of each piece of information.
  Physician Satisfaction	Completed	Epic AI Extract Sig Details	AI helps map free-text sigs to the discrete dose, route, and frequency used in your system. This feature will help with catching the significant number of free-text sigs not caught by the current string matching-based sig mapping table and save time for clinical staff who reconcile medications manually.
  Physician Productivity	Completed	Epic AI ART Drafts in Spanish	To help clinicians who speak Spanish respond more quickly to patient medical advice request messages, Augmented Response Technology (Art) now automatically generates drafts for messages written in Spanish. Note the following limitations of the first iteration of Art for Spanish Messages: Drafts for messages written in Spanish are generated in Spanish, not in English. Art for Spanish Messages cannot be to specific users or departments. If you enable Art for Spanish messages, all departments enabled for Art at your organization and your Community Connect partners will generate drafts for messages written in Spanish and all users who can see and use Art drafts will be able to see and use Spanish drafts. Build Tasks - Update Prompts & Enable Feature Flag in Nebula
  Patient Exp. & Self-Help	Completed	Epic AI Keep Patients Engaged After a Visit with AI-Suggested Reminders	Help patients turn their after-visit instructions into action and make follow-up tasks part of their daily routine by automatically suggesting helpful reminders that they can add to MyChart with one click.
  Patient Exp. & Self-Help	Canceled/Deprioritized	Epic AI: Patient-Facing Imaging Results Overview	Uses AI to create a patient-friendly summary, but not interpretation of, radiologists' impressions.
  Physician Productivity	In-Flight	Epic AI Discover Reasons for Medication Changes Using AI-Powered Insights in Synopsis	Uses generative AI to surface relevant text from clinical notes helping clinicians understand the story behind a patient's medications—what was tried, what worked, what didn't, and why. Clinicians can hover over a medication to view Insights, which are excerpts from notes that mention medication changes with links to full notes for deeper review.
  Quality & Saving Lives	Completed	Theator AI Video Analysis for OR expansion	The enhanced integration is essential to enable Theator's AI assistant capabilities, which correlate intraoperative video analysis with indexed EHR data to transform months of chart review into minutes of intelligent querying. Theator Expansion to include 20 ORs, as approved by Dr. Parekh. Three-year pricing and suggested terms attached.
  Patient Exp. & Self-Help	In-Flight	IATRION AI-Assisted Pre-Visit Intakes for Neuro Ophthalmology	IATRION is a HIPAA compliant AI-powered phone assistant designed to conduct structured, conversational interviews with patients prior to their visit and generate comprehensive pre-summaries, thus reducing staff time spent on routine intake questions and enhance clinical preparedness before patient encounters. When a new patient visit is scheduled, administrators can send an SMS text to the patient 3-5 days prior to their appointment via the IATRION app, instructing patients to call the IATRION phone number. Once called, the AI-agent will summarize the non-diagnostic conversation with the patient and populate a customizable history note, which can be copied-and-pasted into Epic.
  Patient Flow	Completed	Scope Health - Scheduling and Access Agents	Pilot implementation of an AI-driven outreach and scheduling solution to identify, engage, and schedule patients requiring imaging services (initial focus on mammography). The solution leverages AI technology integrated with Epic and Nice InContact to contact patients with existing orders, facilitate intake, route for clinical review when needed and schedule appointments. The goal is to reduce leakage, improve order-to-schedule conversion, increase access utilization and enhance patient experience through automation and timely engagement.
  Quality & Saving Lives	Completed	Predictive Model: Slot Type Utilization	The Slot Type Utilization predictive model provides template builders, clinic managers, and organizational leadership with a data driven prediction of future schedule utilization, enabling them to make informed decisions about slot types and appointment scheduling.
  Quality & Saving Lives	In-Queue	Predictive Model: Multiple Week Census Forecast	Using this model, users can proactively identify departments where planned staffing doesn't match the predicted census. This helps nurse managers make informed decisions about staffing and helps capacity managers make decisions about which departments can accept additional patients.
  Quality & Saving Lives	In-Queue	Predictive Model: Deterioration Index V2	Our model improves on traditional early warning systems and provides a trending score. The model correctly identifies 50% more deteriorating patients than MEWS and offers improvement in accuracy and workflow integration compared to the Rothman Index. Providers can use this score to stratify patient populations by risk and monitor the progression of individual patients. Our model also removes the manual score calculation of a system like MEWS, and dynamically responds to information entered into the chart in any workflow, providing clinicians with the most up-to-date risk assessment information.
  Physician Satisfaction	In-Flight	Suki Epic Ambient Voice Ordering Labs
  Quality & Saving Lives	Canceled/Deprioritized	Predictive Model: Discharge Function Score	With this model, clinicians and quality staff can track how often inpatient rehab patients or skilled nursing residents meet their risk-adjusted expected Discharge Function Scores (DFS) by the end of their stay. The model calculates each individual's admission, observed discharge, and expected discharge function score using characteristics such as age, diagnoses, and comorbidities.
  Quality & Saving Lives	Canceled/Deprioritized	Predictive Model: Patient Class After Admission	The Patient Class After Admission model uses data points already in your system, such as lab results, vitals, and diagnoses, to help utilization managers quickly review and determine whether a patient has the right patient class—inpatient or observation—for their current admission, to make sure your organization receives appropriate reimbursement. When the current patient class and the cognitive computing model's predicted patient class match, utilization managers can quickly process those reviews. If the current patient class and the model's predicted patient class do not match or the prediction is unsure, utilization managers can spend some extra time investigating those more complex reviews.
  Physician Productivity	In-Flight	Epic AI: Nursing Assignment Agent: Auto-Assign Gives Charge Nurses Faster Patient Assignments (Pioneering)	Making patient assignments for inpatient units is frequently a time-consuming process that requires charge nurses to balance assignments across nurses scheduled in their unit while considering the patients' needs and the geography of the unit. Now, an AI-powered patient assignment agent can generate assignment suggestions in the Assignment Wizard to save time and cognitive burden for charge nurses when creating equitable assignments. The name Nursing Assignment Agent is used for this feature in analyst and stakeholder documentation. In the system, this feature appears as the Auto-Assign button in the Assignment Wizard.
  Value from Data	In-Flight	Epic AI: Research Study Eligibility Analysis: Use Generative AI to Analyze Potential Participant Eligibility for Research Studies	Screening participants for a research cohort requires study team members to parse through large amounts of data to determine whether interested patients are eligible for each study. Your study team members can use AI-generated Research Study Eligibility Analysis reports that gather patient information and compare it to a study's eligibility criteria and exclusion criteria.
  Quality & Saving Lives	In-Flight	Epic AI: Discharge Planning Assistant: Integrating AI into Discharge Planning	Care team members can use the AI-powered Discharge Planning Assistant to analyze a patient's existing chart documentation and suggest follow-up actions, propose expected discharge information and delays, and apply or complete discharge milestones in the Discharge Planning activity
  Physician Productivity	Completed	Epic AI: Professional Level of Service Assistant in the Level of Service Calculator	You can help outpatient and ED clinicians select a level of service by showing them AI-generated calculations in the Level of Service Calculator. If you enable this feature for clinicians, they can use AI to help determine the appropriate level of service code based on medical decision-making documented in their encounter note. The Professional Level of Service Assistant analyzes the text of an encounter note to identify criteria considered in each category of medical decision-making (problems addressed, data reviewed, and risk) and determines the level for each category. It then calculates the overall level of service (2-5) for the visit and identifies the CPT code you have mapped for that level in the service type (LSY) record for the encounter
  Physician Satisfaction	In-Flight	Epic AI: Optical Character Recognition	The Optical Character Recognition (OCR) Image to Text Transcription model uses cloud computing to read and transcribe the text in image files, making it searchable by clinicians in Epic when using Chart Search   Optical Character Recognition can analyze scanned documents, insurance cards, and other BLOB-storage-based objects for text analysis.
  Physician Satisfaction	In-Flight	Epic AI: ED Initial Patient Presentation Insights	Epic is introducing Outpatient Insights in the ED with modifications tailored to emergency workflows. Outpatient Insights uses generative AI to review up to three years of outpatient notes and create a problem-oriented summary of a patient's medical history. This helps ED providers quickly understand unfamiliar patients and make more informed treatment decisions.
  Physician Satisfaction	In-Queue	Epic AI: Inpatient Insights: Get More Context with Restructured Inpatient Insights	Physicians, nurses, and other clinicians now automatically receive improved Inpatient Insights summaries that include expanded data types and standardized sections with collapsible mini-summaries. These restructured summaries, called state-based Insights summaries, build on continuously updated patient information to provide more clinical context by incorporating more information from throughout the patient's chart. The standardized structure with collapsible mini-summaries makes it easier for clinicians to review high-level information and access detailed context as needed.
  Quality & Saving Lives	In-Flight	Epic AI Chart Search Powered by Cloud Search	Chart Search is moving to a new cloud-based infrastructure in Nebula. Cloud search allows users to search beyond the traditional Chronicles database and find information from locations such as archived notes. It also allows us to quickly develop and deploy advanced searching technology that returns better results and will serve as the basis for future generative AI-based searching, including Ask Art.
  Quality & Saving Lives	In-Flight	Epic AI Ask Art: Have a Conversation About Your Patient's Chart	Ask Art lets clinicians ask questions about a patient's chart in plain language and get AI-generated conversational answers as if they're discussing the patient with a knowledgeable colleague. Instead of navigating to multiple activities to piece together a patient's history, providers can ask Ask Art a question and receive a synthesized, cited response that draws from data across the chart.
  Physician Productivity	In-Queue	Epic AI CDI Nudges for Physicians	Reduce the number of CDI queries that physicians need to respond to by using AI that reviews their notes and points out information that might be missing, such as diagnoses that lack the specificity needed for coding. They can then address any suggestions while they finalize the note and don't need to come back to it later. Provider nudges can now use AI-extracted evidence from clinical notes. You can implement malnutrition and pressure injury nudges from the Foundation System that use this note evidence. Benefit Note evidence allows you to use nudges for more complex conditions, including pressure injury and malnutrition, because providers likely want to reference written indications for these conditions in addition to the discrete clinical data that can already be used as evidence.
  Physician Productivity	In-Flight	Epic AI Clinician Notes to Cancer Staging Forms: Use AI to Pre-Populate Cancer Staging Information	To speed up cancer staging documentation and increase staging compliance, when a clinician signs their progress note, generative AI automatically pulls staging details from the note to pre-populate certain cancer staging forms. Clinicians can validate suggested staging values and sign the staging form right from there, so they don't have to re-type the staging information from their note.
  Patient Exp. & Self-Help	In-Flight	Epic AI Emmie - Chart Aware Q&A	Chart Aware Q&A is a feature of the Emmie Virtual Assistant that uses generative AI to assist patients in accessing various activities in MyChart, as well as helping them find, ask questions about, and interpret the clinical information that is available in their MyChart account.
  Physician Productivity	In-Queue	Epic AI Pre-procedural Screening Insights	Preprocedural Screening Insights can analyze clinical notes and find patient factors relevant to pre-admission testing (PAT) to help care teams evaluate upcoming procedures and identify which patients need additional review whether that be with an in-person appointment or a phone call. This feature is Pioneering because of the additional effort required to validate the insights are accurate and contribute to your scoring system correctly. Benefit Pre-procedural Screening Insights uses generative AI to analyze clinical notes to surface free text information that hasn't been documented discretely. These insights can then be used by existing triage scoring systems, reducing the amount of time pre-admission testing staff need to manually review each patient and allowing staff to review patients more efficiently. These insights from notes can augment existing triage scoring systems that only search for discrete data, such as problem lists or medical history.
  Quality & Saving Lives	Canceled/Deprioritized	Epic AI Surgical Procedure Mismatch Detection	Uses AI-generated suggestions to identify missing or incorrect procedures in case requests. The suggestions are based on the free text procedure description from the surgeon.
  Physician Productivity	In-Queue	Epic AI Keep a Patient's Code Status Accurate During and After a Procedure Using Temporary Code Status Orders	Accurate During and After a Procedure Using Temporary Code Status Orders
  Physician Satisfaction	In-Queue	Epic AI Visualize Data in Insights Cards with Generative AI	Offers clinicians a more centralized and intuitive way to review recent trends for patients they're rounding on, using integration with Inpatient Insights summaries to sort information so that the most important changes are highlighted.
  Physician Productivity	Completed	Epic AI Context-Driven In Basket Insights - Pilot	Generative AI in Epic that supports clinical care delivery.
  Physician Productivity	In-Flight	Epic AI Theator Enhanced Op Note Workflow	Elevate surgical documentation through an enhanced Epic-Theator integration that delivers AI-generated rich-text operative notes directly into clinician workflows and proactively alerts surgeons when documentation is ready for review, accelerating completion and improving efficiency.
  Patient Exp. & Self-Help	In-Queue	HCAHPS Early Risk Detection Pilot	Inpatient data will run thru an AI model to predict patients that may score the health system poorly on a patient satisfaction survey prior to being discharged from the hospital. This will allow for in the moment service recovery to help mitigate post discharge complaints and issues.
  Patient Exp. & Self-Help	In-Queue	LanguageLine AI Interpreter Pilot	Pilot of AI-powered language interpretation for low-risk UHealth Contact Center scheduling and administrative calls, supporting 10+ languages with a certified human-interpreter safety net. Intended to improve operational efficiency, patient/staff experience, and reduce system-wide interpretation costs
  Value from Data	In-Queue	World Class AI Tech Stack	advance the University of Miami AI Tech Stack to a world-class level and enable the accelerated development and deployment of custom predictive models tuned on UM clinical data

Accordion Group

Open All Tabs

• Enhancing Research - AI Projects

  Sub Domain	Status	Project Name	Description
  Research Tools	Completed	AIDOC (Intracranial Hemorrage Detection)	FDA-cleared AI algorithm developed by AIdoc, which estimates the likelihood of a patient having intracranial hemorrhage and then prioritizes these cases to be read by the radiologists
  Research Tools	Completed	AIDOC (PE Detection)	FDA-cleared AI algorithm that estimates the likelihood of a patient having incidental pulmonary embolism and then prioritizes these cases to be read by the radiologists.
  Research Tools	Completed	Audio Sentiment Analysis for OCD Therapy	Use of a tool that uses AI to analyze the emotional content of audio recordings.  This is used for analysis of exposure therapy in people with OCD
  Research Tools	Canceled/Deprioritized	Custom Clinical Notes LLM for UHealth	Investigating the possibility of developing a custom large language model based on clinical notes from UHealth. There are several approaches including training a model from scratch to fine-tuning an existing LLM. The latter is the most performant approach and also the most cost effective. Different existing LLMs are being evaluated and testing is ongoing.
  Research Tools	In-Flight	D3 for Dementia	Patient Digital Marker (PDM) model was developed by Indiana University to identify patients at risk of developing dementia. The model is being validated here at University of Miami and will be deployed as part of a NIH-sponsored clinical trial.
  Research Tools	Completed	DICOM Image De-identification	Image de-identification for utilization in research studies and for quality improvement. De-identification includes data within the meta-data (DICOM headers) and within the image at the pixel level. Without these models, a custom solution will have to be built for each imaging vendor and system, as well as each software version upgrade.
  Research Tools	Completed	Endoscopy Reading (Virgo)	Virgo is seeking FDA approval for their device using AI to read endoscopy procedures and detect issues. UHealth is participating in this study for follow up endoscopy procedures for patients who underwent HBOT for UC.
  Research Tools	Completed	Gartner Research Tools	Third Party Research Tools licensed for use at UM/ Includes access to AI research
  Research Tools	Completed	Scan360 Integration	Application to enhance clinical research.
  Research Tools	Completed	Text to 3D Model Generation	Generating 3D models based on text prompts.
  Research Administration	In-Flight	Lifecycle of a Grant – Copilot Faculty Assistant	AI-enabled faculty support concept intended to help faculty identify potential funding opportunities and support proposal development activities. The current description appears to overlap with the FundFit/fund matching initiative and may also include a separate publications or articles support concept.
  Research Administration	In-Flight	Lifecycle of a Grant  - Copilot ORA Assistant (Matrix)	AI-enabled assistant concept related to contract or agreement support activities. The initiative was previously identified as in flight but is currently understood to be on hold pending further internal discussions with other central contract offices.
  Research Administration	In-Queue	Lifecycle of a Grant - Analytics Reporting	AI-enabled research portfolio analytics concept intended to support natural-language querying and analysis across institutional research data, including proposals, awards, expenditures, agreements, financials, and related portfolio information. The goal is to help answer leadership and operational questions that currently require manual data pulls, keyword searches, or subject matter expert review.
  Research Administration	In-Flight	Lifecycle of a Grant - Fund Matching (FundFit)	AI-enabled solution intended to support funding opportunity matching and proposal development by connecting faculty research interests, ideas, or areas of expertise with relevant funding opportunities.
  Research Administration	In-Queue	Lifecycle of a Grant - Proposal Review (The Contract Network)	AI-enabled proposal review concept intended to evaluate proposal materials for key administrative and compliance considerations, such as budget justifications, cost share, program requirements, and other review criteria. There is interest in potentially leveraging The Contract Network for this use case as a secondary expansion beyond agreement review.
  Research Administration	In-Flight	Lifecycle of a Grant - Agreement Review (The Contract Network)	AI-enabled agreement review and contract redlining initiative using "The Contract Network" to support review of research-related agreements and identify key contract terms, risks, and clauses requiring attention. This remains the priority use case for The Contract Network.
  Research Administration	In-Flight	Lifecycle of a Grant-Robotic Process Automation (RPA)	This initiative is an automation program using UiPath, implemented through a third-party vendor, to automate selected research administration and financial processes. It is intended to reduce manual effort and improve efficiency within OVPRS/ORA workflows.
  Research Administration	In-Queue	Grants - Transaction (Compliance) Review	Payroll Accounting Adjustment (PAA) and transfer optimization. AI-enabled compliance review initiative focused on submitted payroll accounting adjustments and other cost transfers. The tool would support post-submission review by assessing justification quality, required documentation, and alignment with compliance expectations
  Research Administration	Completed	Compliance - Use AI as controlled drafting engine	AI-enabled compliance initiative used to support redaction of IBC meeting minutes prior to posting on the web.
  Research Administration	Completed	Compliance Use Claude (Copilot Chatbot) as controlled drafting engine	Use AI generated guidance and scenarios to improve IBC submission quality, shorten review turnaround time, and strengthen support for the research enterprise. Extracted common failure points (e.g., mismatches between IBC submission (BioRaft forms) and protocol narratives) and rephrased them into plain-language instructions investigators can act on; created checklists that align line-by-line with what reviewers actually assess Impact to the Research Enterprise: • Higher quality first submissions → fewer revisions and resubmissions • Shorter IBC review turnaround time by reducing avoidable administrative deferrals • More predictable study start up timelines for investigators • Scalable investigator support without proportional increases in staffing • Improved alignment between investigators, reviewers, and NIH biosafety expectations
  Research Administration	In-Flight	Copilot with Power BI for Proposals and Awards data	AI-enabled research portfolio chat capability built within a private Power BI workspace using Copilot. The workspace includes several years of proposal, award, expenditure, and research portfolio data, allowing internal users to ask natural-language questions about research activity, funding trends, award characteristics, sponsor activity, and portfolio-level metrics.
  Research Administration	In-Queue	Compliance Use Claude (Copilot Chatbot) as controlled drafting engine	Use AI generated guidance and scenarios to improve IACUC submission quality, shorten review turnaround time, and strengthen support for the research enterprise. Extracted common failure points (e.g., mismatches between IACUC submission (Huron IBIS) and protocol narratives) and rephrased them into plain-language instructions investigators can act on; created checklists that align line-by-line with what reviewers actually assess Impact to the Research Enterprise: • Higher quality first submissions → fewer revisions and resubmissions • Shorter IACUC review turnaround time by reducing avoidable administrative deferrals • More predictable study start up timelines for investigators • Scalable investigator support without proportional increases in staffing • Improved alignment between investigators, reviewers, and USDA/NIH/AAALAC Animal welfare and compliance expectations
  Research Administration	In-Flight	CoPilot Agent	IBISResearch Assistant helps researchers, faculty, departmental administrators, and research support staff quickly find answers to common IBISResearch questions. The assistant provides guidance on proposal creation, routing and approvals, sponsor submissions, award management, agreements, workflow statuses, notifications, user roles, and system navigation. It is designed to simplify the research administration process by delivering clear, consistent, and easy-to-understand answers drawn from University of Miami research administration resources.
  Research Administration	In-Flight	Research Administration Cost Transfer Copilot	Development of an AI-powered agent within Microsoft Copilot and Microsoft Teams designed to assist University sponsored programs personnel with generating compliant cost transfer justification memos for payroll accounting adjustments (PAAs) corrections on sponsored awards. The agent will leverage a curated knowledge library containing institutional guidance, policies, and example memos to generate high-quality draft justifications that can be submitted through Workday as part of the cost transfer process. The intended audience is approximately 250 sponsored programs professionals across the University.
  Research Tools	In-Flight	RoboCanes	The College's RoboCanes program demonstrates how artificial intelligence moves beyond theory into real-world innovation, with students and faculty designing autonomous robots that compete internationally while advancing research in AI, robotics, and human-robot interactions

Accordion Group

Open All Tabs

• Enhancing Teaching Delivery - AI Projects

  Sub Domain	Status	Project Name	Description
  AI-Powered Pedagogical Strat	Completed	AI Faculty Guidance	Guidance for faculty on ways they should and should not use generative AI in their courses, including examples, sample syllabus language, the use of AI detection software, and other considerations.
  AI-Powered Pedagogical Strat	Completed	Blackboard Design Assistant	A generative AI system built into Blackboard Ultra that can help faculty design syllabi, assignments, and test questions.
  Integrating into Teaching	Completed	Copilot Language Learning Bots	Using generative AI to create language learning bots to assist with acquisition of foreign languages.
  Integrating into Teaching	Completed	Legal Document Summarization	Using generative AI to analyze and summarize public legal documents.
  Student Engagement and Motivation	In-Flight	UOnline Enrollment and Student Success: Live Chat	Online chat to enrollment advisors and student success advocates.
  Student Engagement and Motivation	In-Flight	Augmented Human Intelligence, at the University of Miami Business School™	Human Intelligence @Miami Herbert™ is a competency framework that positions technological fluency and human skills as essential for success in an AI-enabled workforce. Built around the CANES domains, Communication, Analysis, Nurturance, Execution, and Strategy, the model was informed by analyses of existing frameworks and more than 6,000 job postings and is continuously updated to reflect emerging employer needs.
  Student Engagement and Motivation	In-Flight	Arts & Sciences Digital Twin	Develop an AI-powered College Digital Twin that models College requirements, courses, prerequisites, pathways, and student interests to provide personalized, real-time guidance on what students need to take and when.
  AI-Powered Pedagogical Strat	In-Flight	Quantum Intelligence Lab	The Quantum Intelligence Lab will integrate advanced research infrastructure, interdisciplinary collaboration, and workforce-focused academic programming in quantum computing and Quantum AI. Designed as both a research engine and teaching platform, the Lab will accelerate cutting-edge discovery, enable collaboration across disciplines, and prepare students with the skills needed to lead in the rapidly emerging quantum technology economy.
  Data-Driven Instructional Engagement	Completed	SoNHS AI-Powered Simulation Hospital (A.I.D.A. / L.A.I.L.A.)	AI-enabled simulation environment that supports adaptive learning, standardized learner orientation, immersive patient interactions, real-time feedback, and automated simulation content development. The initiative advances the School of Nursing and Health Studies' goal of transforming pedagogy through AI-enhanced experiential learning. A.I.D.A. (AI-enabled simulation assistant): Supports adaptive learning through avatar generation, patient role-play, simulation content development, and debriefing analytics L.A.I.L.A. (simulation staff resource assistant): Provides AI-enabled support for simulation operations and staff resources
  Data-Driven Instructional Engagement	Completed	Theator AI Video Review	Video recording of the laparoscopic procedures that uses AI to review the procedure steps and evaluate patient outcomes.

Accordion Group

Open All Tabs

• Expanding Efficient Operations: Revenue Cycle - AI Projects

  Sub Domain	Status	Project Name	Description
  Medical Coding	Completed	3M History Note Nudges	Delivers real time clinical insights ("nudges") to help clinicians document a complete patient history before a note is saved to the EHR. Reduces retrospective queries. Utilizes AI powered worklist prioritization to drive coder and CDI team efficiency.
  Patient Scheduling & Intake	Completed	Amelia Appointment Cancel Automation	AI agent to cancel patient appointments on the phone.
  Patient Scheduling & Intake	Completed	Amelia Appointment Confirmation Automation	AI agent to confirm patient appointments on the phone.
  Patient Scheduling & Intake	In-Queue	Amelia Automated Patient Appointment Scheduling via Voice	For simple and routine calls, use AI to better match the issues patients are experiencing with the right specialty.
  Patient Scheduling & Intake	Completed	Amelia Call Intent Understanding and Routing	Leveraging conversational AI to provide an optimal experience for patient scheduling management, including schedule, reschedule, confirm, cancel, recall.
  Patient Scheduling & Intake	Canceled/Deprioritized	Apple Health Submission for International and Healthcare Tourists	Investigating the ability to digitalize our intake process for international and domestic healthcare tourists to simplify the process for patients and our staff. This would provide an option for patients to submit data directly from their Apple Health into UHealth and would potentially support abstractions of PDFs and language translation services.
  Medical Coding	Completed	CodaMetrix Automated Coding - Cardiology	Autonomous coding bots to review results and determine procedure and diagnosis codes for cardiology procedures.
  Medical Coding	Completed	CodaMetrix Automated Coding - Interventional Radiology	Autonomous coding bots to review results and determine procedure and diagnosis code for interventional radiology procedures.
  Medical Coding	Completed	CodaMetrix Automated Coding - Radoiology	Automates professional coding through translation of the electronic health record into accurate set of medical codes and triages unautomated cases back to coding specialists.
  Medical Coding	Completed	CodaMetrix Automated Coding - Surgery	Autonomous coding bots to review results and determine procedure and diagnosis codes for surgical procedures.
  Medical Coding	Canceled/Deprioritized	Copilot Medical Record Coding Assistance Agent	Use AI to complete medical record coding tasks.
  Patient Scheduling & Intake	Completed	Custom Predictive Models - No Show	Identifies the likelihood of an outpatient appointment being a no show. The model predictions are aggregated at the physician, clinic, and department levels to better assist in capacity management and planning, while limiting the potential impact on model biases and limiting access to care to a single patient.
  Medical Coding	Completed	Epic Account Creation - Lab Venipuncture	Lab venipuncture outreach account creation.
  Insurance Registration	Completed	Epic Account Creation & Merger Automation - Guarantor Auto Create	Hospital and Guarantor account auto-create and merge in tandem.
  Insurance Registration	Completed	Epic Account Creation & Merger Automation - Hosipital Account and Guarantor Merge/Link	Hospital and Guarantor account auto-create and merge in tandem.
  Insurance Registration	Completed	Epic Account Creation & Merger Automation - Hospital Account Auto Create	Hospital and Guarantor account auto-create and merge in tandem.
  Medical Coding	Completed	Epic Account Merger Automation	Automated account coding merger.
  Insurance Registration	Completed	Epic Authorization Determination & Collection - Authorization Collection and Status Update	Authorization determination and auth collections in tandem.
  Insurance Registration	Completed	Epic Authorization Determination & Collection - Authorization Determiniation (Across Services)	Authorization determination and auth collections in tandem.
  Insurance Registration	Completed	Epic Automate Pulling Insurance Card Information	Using optical character recognition to pull insurance information from scanned patient insurance cards into the visit registration to reduce manual error and accelerate the financial clearance process.
  Medical Coding	Completed	Epic Automated Infusion Charging Calculator	Leveraging charge automation with Epic for CTU Infusion hospital charging
  Medical Coding	Completed	Epic Automated Pull in and Copy - Account Coding	Automate pulling in and copying for account coding.
  Medical Coding	Completed	Epic Automated Pull in and Copy - Late Charge Coding	Automate pulling in and copying for late charge coding.
  Medical Coding	Completed	Epic Automated Soft-Coded ED Procedure Charging	Leveraging charge automation with Epic to eliminating a manual step for emergency room procedures, eliminating a manual step for every account with soft-coded procedures.
  Patient Scheduling & Intake	Completed	Epic Automated Visit Reminders	Automate patient visit reminders.
  Patient Scheduling & Intake	Completed	Epic Automated Wait List Entries	Automate patient wait list entries.
  Payment Processing	Completed	Epic Claim Submission & Attachments - Automated Claim Attachments to avoid preventable denials	Complete claim submission and attachments in tandem.
  Payment Processing	Completed	Epic Claim Submission & Attachments - Automated Claim Outbound Submisson	Complete claim submission and attachments in tandem.
  Insurance Registration	Completed	Epic Corporate Guarantor Creation & Assignment	Generate and assign corporate guarantor accounts for GameChanger.
  Medical Coding	Completed	Epic Cost Center Assignment Automation	Bill Area/Cost Center auto-determination.
  Denials Management	Completed	Epic Denial Credit & Write-Off Automation	Automate credit resolution and small balance write-offs.
  Denials Management	Completed	Epic Draft HB Outpatient Denial Appeals Assistant	Generative AI solution within Epic to automate generation and sending of denial appear letters. Part of Spring Epic Upgrade. Specific to Hospital Billing
  Denials Management	Completed	Epic Draft PB Outpatient Denial Appeal Letters	Generative AI solution within Epic to automate generation and sending of denial appear letters. Part of Spring Epic Upgrade. Specific to Professional Billing
  Medical Coding	Completed	Epic External Charging Automated Load	Enhance medical coding with charge interface to external locations.
  Patient Scheduling & Intake	Completed	Epic Guided Scheduling and Self-Service Tickets	Guided scheduling project as part of Project Gateway. Neurology and ENT are live. Cardiology and Primary Care implementing.
  Medical Coding	Completed	Epic HB Coding Workqueue Prioritization	Prioritize work within hospital coding workqueues.
  Medical Coding	In-Flight	Epic Hospital Coding Assistant	Generative AI in Epic that supports revenue cycle operations.
  Patient Scheduling & Intake	In-Queue	Epic Infusion Capacity Optimization	Improve scheduling with connection to external system for orders.
  Insurance Registration	Completed	Epic Insurance Eligibility Verification	Insurance eligibility verification
  Denials Management	Completed	Epic Nightly Denial Processing Automation	Automate nightly denial actioning.
  Payment Processing	Completed	Epic Patient Payment Notification - Auto-Apply New Balance to Open Payment Plan	Complete MyChart balance notifications and self-service payment plans in tandem.
  Payment Processing	Completed	Epic Patient Payment Notification - Instant MyChart Balance Notification on Post	Complete MyChart balance notifications and self-service payment plans in tandem.
  Payment Processing	Completed	Epic Patient Payment Notification - Open Self-Service Payment Plan Enrollment	Complete MyChart balance notifications and self-service payment plans in tandem.
  Medical Coding	Completed	Epic Payer Modifier Automation	Automated payer modifier attachments
  Payment Processing	Completed	Epic Payment Posting Automation - Automated HB/PB Transfer for Relevant Balances	Automated payment posting, reconciliation, and transfers in tandem.
  Payment Processing	Completed	Epic Payment Posting Automation - Automated Payment Posting	Automated payment posting, reconciliation, and transfers in tandem.
  Payment Processing	Completed	Epic Payment Posting Automation - Automated Reconciliation (Including Adjustment Threshold)	Automated payment posting, reconciliation, and transfers in tandem.
  Medical Coding	Completed	Epic PB Coding Assistant - All Remaining Specialties	Working with Epic R&D to develop AI applications within Epic to assist professional coders in their review of clinical documentation and suggesting procedure and diagnosis codes for approval. Project focus is on specialties without established coding automation tools that are currently highly manual, full review coding practices.
  Medical Coding	Completed	Epic PB Coding Assistant - Dermatology	Working with Epic R&D to pilot and develop AI applications within Epic to assist professional coders in their review of clinical documentation and suggesting procedure and diagnosis codes for approval. Project focus is on specialties without established coding automation tools that are currently highly manual, full review coding practices.
  Medical Coding	Completed	Epic PB Coding Assistant - Ophthalmology	Working with Epic R&D to pilot and develop AI applications within Epic to assist professional coders in their review of clinical documentation and suggesting procedure and diagnosis codes for approval. Project focus is on specialties without established coding automation tools that are currently highly manual, full review coding practices.
  Medical Coding	In-Queue	Epic PB Coding Assistant - Provider Front End Deployment	Working with Epic R&D to develop AI applications within Epic to assist professional coders in their review of clinical documentation and suggesting procedure and diagnosis codes for approval. Project focus is on specialties without established coding automation tools that are currently highly manual, full review coding practices.
  Medical Coding	Completed	Epic PB Coding Assistant -Surgery	Working with Epic R&D to pilot and develop AI applications within Epic to assist professional coders in their review of clinical documentation and suggesting procedure and diagnosis codes for approval. Project focus is on specialties without established coding automation tools that are currently highly manual, full review coding practices.
  Medical Coding	Completed	Epic PB Coding Workqueue Prioritization	Prioritize work within coding workqueues.
  Patient Scheduling & Intake	Canceled/Deprioritized	Epic Predictive Model - Risk of Patient No-Show (Version 1)	Epic provided model to predict patient no shows.
  Patient Scheduling & Intake	Canceled/Deprioritized	Epic Predictive Model - Risk of Patient No-Show (Version 2)	Version 2 of the Risk of Patient No-Show model is a cloud-based, random forest model. The model is localized on your patient population and predicts a patient's likelihood to no-show. By using Nebula, Epic's cloud-based platform, version 2 of the model has better performance because it uses a different model type and expanded feature set, and it includes patient-initiated late cancels in the definition of a no-show.
  Payment Processing	Completed	Epic Predictive Models - Likelihood to Pay	Identifies the likelihood of payment for insured and self-pay patients.
  Insurance Registration	Completed	Epic Procedure Authorization Automation from Scheudling Orders	Guided scheduling project as part of Project Gateway. Neurology and ENT are live. Cardiology and Primary Care implementing.
  Patient Scheduling & Intake	Completed	Epic Registration Self-Service Bot	Patient self-service registration bot.
  Medical Coding	Completed	Epic Retrigger Late Charges	Late charge coding retrigging
  Patient Scheduling & Intake	Completed	Epic Scheduling Decision Support	Decision Support for scheduling requirements.
  Patient Scheduling & Intake	Completed	Epic Scheduling Self-Service Bot	Patient self-service scheduling bot is fulling configured, but only available for providers and departments that Opt-In.
  Insurance Registration	Completed	Epic Self-Pay Estimation Automation	Automatic patient self-pay estimates
  Medical Coding	Completed	Epic Soft-Coded Procedure Automation	Leveraging charge automation with Epic to eliminating a manual step for every account with soft-coded procedures. This expands on the soft-coded emergency room procedure charging.
  Medical Coding	Completed	Epic SVC Coding Automation - Ambulatory Services (Retail)	Epic Simple Visit Coding (SVC) logic to automate outpatient coding on hospital visits
  Medical Coding	Completed	Epic SVC Coding Automation - Family Medicine	Epic Simple Visit Coding (SVC) logic to automate outpatient coding on hospital visits
  Medical Coding	Completed	Epic SVC Coding Automation - Genetics	Epic Simple Visit Coding (SVC) logic to automate outpatient coding on hospital visits
  Medical Coding	Completed	Epic SVC Coding Automation - Neurology	Epic Simple Visit Coding (SVC) logic to automate outpatient coding on hospital visits
  Medical Coding	Completed	Epic SVC Coding Automation - Obstetrics and Gynecology	Epic Simple Visit Coding (SVC) logic to automate outpatient coding on hospital visits
  Medical Coding	Completed	Epic SVC Coding Automation - Ophthalmology	Epic Simple Visit Coding (SVC) logic to automate outpatient coding on hospital visits
  Medical Coding	Completed	Epic SVC Coding Automation - Orthopedics	Epic Simple Visit Coding (SVC) logic to automate outpatient coding on hospital visits
  Medical Coding	Completed	Epic SVC Coding Automation - Otolaryngology	Epic Simple Visit Coding (SVC) logic to automate outpatient coding on hospital visits
  Medical Coding	Completed	Epic SVC Coding Automation - Pathology	Epic Simple Visit Coding (SVC) logic to automate outpatient coding on hospital visits
  Medical Coding	Completed	Epic SVC Coding Automation - Pediatrics	Epic Simple Visit Coding (SVC) logic to automate outpatient coding on hospital visits
  Medical Coding	Completed	Epic SVC Coding Automation - Physical Medicine & Rehabilitation	Epic Simple Visit Coding (SVC) logic to automate outpatient coding on hospital visits
  Medical Coding	Completed	Epic SVC Coding Automation - Physical Therapy	Epic Simple Visit Coding (SVC) logic to automate outpatient coding on hospital visits
  Medical Coding	Completed	Epic SVC Coding Automation - Psychiatry & Behavioral Science	Epic Simple Visit Coding (SVC) logic to automate outpatient coding on hospital visits
  Medical Coding	Completed	Epic SVC Coding Automation - Urology	Epic Simple Visit Coding (SVC) logic to automate outpatient coding on hospital visits
  Medical Coding	Completed	Epic SVC Coding Automation- Executive Medicine	Epic Simple Visit Coding (SVC) logic to automate outpatient coding on hospital visits
  Medical Coding	Completed	Epic SVC Coding Automation- Neurological Surgery	Epic Simple Visit Coding (SVC) logic to automate outpatient coding on hospital visits
  Patient Scheduling & Intake	In-Queue	Epic Template Build Automation	Automate configuration of provider templates to match business requirements/rules (budget) and eliminates human intervention in administration function
  Payment Processing	Completed	Epic Visit Payment & Debt Transfer - Automated Bad Debt Transfer to Partners and Finance Reconciliation	Complete visit auto pay and bad debt transfer in tandem.
  Payment Processing	Completed	Epic Visit Payment & Debt Transfer - Automated Patient Payment for Visit Balance	Complete visit auto pay and bad debt transfer in tandem.
  Patient Scheduling & Intake	Completed	Epic Welcome Check-In Facial Recognition with CLEAR	Enhance Welcome kiosks experience with facial recognition.
  Payment Processing	Completed	HB Account Prioritization (Etyon)	Utilizing machine learning algorithms to assign account prioritization and return the scoring back into Epic for HB billing workqueues.
  Patient Scheduling & Intake	Completed	Humata PCP Referral Follow-Up	Enhance patient scheduling with PCP referral follow-up.
  Medical Coding	Completed	LOS Calculator - Surgery Center	Doctor visit level of service calculators for surgery center visits.
  Medical Coding	Completed	LOS Calculator Ambulatory Clinics	Doctor visit Level of Service calculators for ambulatory clinics.
  Patient Scheduling & Intake	Completed	MyChart Account Recovery with CLEAR	Use facial recognition for MyChart account recovery.
  Payment Processing	Completed	PB Account Prioritization (Etyon)	Utilizing machine learning algorithms to assign account prioritization and return the scoring back into Epic for PB billing workqueues.
  Medical Coding	Completed	Sunquest Charge Automation - Lab Venipuncture	Automate charging for lab venipuncture.
  Denials Management	In-Flight	Denial Appeals Assistant	Generative AI that will search the chart to appeal denials in certain areas, currently OP & ED for medical necessity and authorization but will expand with each Epic release
  Medical Coding	In-Flight	PB LOS Suggestions	Expansion of our coding assistant to provide both coding users and providers with level of service suggestions
  Medical Coding	In-Queue	CDI Improvement suggestions & Nudges	The system evaluates the patient's clinical documentation and identifies query opportunities to improve the documentation's quality, along with justification for each suggested query. CDI specialists and coders can easily review, edit, and send the suggested queries. These suggestions can help decrease the amount of time CDI specialists and coders spend reviewing documentation and writing queries, which gives them time to focus on accounts where their attention has higher value.
  Denials Management	In-Flight	Medical Necessity for Prior Auth	Give authorization users access to AI that can search for documents needed to respond to document requests and build a proposed response with the following workflows: Medical Nessicity Justification, AI-assisted document selection & a draft cover letter for authorization staff before sending to the payer
  Patient Scheduling & Intake	In-Queue	Conversational Queries w/ Slicer Dicer Side Kick	Expansion of the conversational AI model to more data models, including the HB & PB transaction data models with the upgrade to Epic's Nov 2026 version in March
  Denials Management	In-Queue	Agent Factory	Epic's new AI feature to release and give organizations the ability to customize AI agents within the system
  Patient Scheduling & Intake	In-Queue	Cogito Assistant	An AI tool to support questions on a given data set, leveraging all tools from Reporting workbench, to slicer dicer, to clarity & Cogito/Caboodle
  Patient Scheduling & Intake	In-Flight	Emmie	Epic's AI tool for patients to engage with our Electronical Medical Records (EMR)
  Payment Processing	In-Flight	Expansion of Penny	Epic's AI tool for our revenue cycle staff to complete billing office activities with our Electronical Medical Records (EMR)

Accordion Group

Open All Tabs

• Expanding Efficient Operations: Shared Services - AI Projects

  Sub Domain	Status	Project Name	Description
  Information Technology / Cybersecurity	Completed	Adobe Text to Image Generation	Generative AI that Allows for text to image
  Information Technology / Cybersecurity	Canceled/Deprioritized	Agent Management	Platform for Agent and Chat Bot management
  Academic Administration	Completed	AI 3rd Reader (Vantage)	Following an initial review and scoring of the supplemental essay response by admissions staff, AI would be used solely as a tool to augment the process by providing an additional layer of review. The system could also generate scores based on a defined rubric, with the objective of increasing the frequency of reviews while maintaining consistency and fairness. Only scores given by admissions staff would be used in the Committee's evaluation of the file.
  Information Technology / Cybersecurity	In-Queue	Automatic Assignment of Tickets in ServiceNow	Copilot agent to automatically assign tickets
  Information Technology / Cybersecurity	Canceled/Deprioritized	Azure OpenAI Chatbots	Azure OpenAI (AOAI) is similar to Copilot, but can be accessed programmatically in a secure manner, enabling OpenAI’s LLM to power chatbots. Specifically, AOAI can be used in various ways including Retrieval-Augmented Generation (RAG), which optimizes the output of a LLM so it references internal documents as the knowledge base outside of its initial training data. Use cases include creating a chatbot to look up UM’s Investigator Manual or a chatbot to help train radiology residents in use of various radiology software.
  Information Technology / Cybersecurity	Completed	Chrome Help Me Write	An experimental feature in Google Chrome that uses generative AI to assist users in writing more effectively online. It's designed to provide suggestions for short-form content like reviews and surveys.
  Human Resources	In-Flight	Copilot Ask HR Agent	The umbrella over all HR Agents and allow for one agent to be utilized as a plug and play for all other HR Agents e.g. Total Rewards, Open Enrollment, Performance Management.
  Information Technology / Cybersecurity	Completed	Copilot Epic Tip Sheet Search Assistant	Copilot agent to search Epic tip sheets
  Information Technology / Cybersecurity	In-Queue	Copilot IT Proforma Creation Agent	AI Agent that develops proformas to project the total cost of ownership of new applications.
  Information Technology / Cybersecurity	Completed	Crowdstrike Malware Protection	Protect against malware with next-gen antivirus.
  Academic Administration	Completed	Custom Student Retention Model	Utilizing machine learning to identify students at-risk of early attrition.
  Information Technology / Cybersecurity	Completed	Cybersense Data Integrity Check	Data integrity checker within the cybervault for airgap back-ups.
  University Operations	Completed	Donor Interaction GenAI	Leveraging Generative AI to analyze donor reports, generate thank you letters, provide recommendations, and generate custom news feeds based on donor interests.
  Information Technology / Cybersecurity	In-Queue	Epic Bridges Search Assistant	Generative AI in Epic that supports system maintenance.
  Marketing & Comms	In-Flight	Epic Draft Analytics Catalog Report Descriptions	Generative AI in Epithet supports system maintenance.
  Marketing & Comms	In-Queue	Epic Draft Patient Outreach Campaigns	N/A
  Information Technology / Cybersecurity	In-Flight	Epic Prompt Engineering Testbed	Generative AI in Epithet supports system maintenance.
  Information Technology / Cybersecurity	In-Queue	Epic Questionnaire Translation Utility	Generative AI in Epic that supports clinical care delivery.
  Finance	In-Flight	Expense Forecast	Forecasting expenses using past trend of expenses and forecasted future volume.
  Academic Administration	Completed	Faculty Letter Entitlement Analysis	NLP models that extract important information about faculty entitlements within faculty offer letters, such as entitlement for lab space, equipment, renovations, and research funding.
  Information Technology / Cybersecurity	Completed	Fidelis Cyber Threat Monitoring	Monitor, identify, correlate anomaly behaviors, and predict cyber threats.
  Information Technology / Cybersecurity	Canceled/Deprioritized	Gartner AI Evaluation Tool	Tool Developed with Gartner to us AI to evaluate AI project proposals
  Information Technology / Cybersecurity	Completed	Google Gemini	A multimodal suite of AI models that power a variety of Google products and services, including the Bard chatbot.
  University Operations	Completed	Hosptial Visitor Management Facial ID	Enhancement to visitor management system in the Tower to identify visitors, as well as identify individuals on a security watchlist and alert public safety.
  Information Technology / Cybersecurity	Completed	Interface Monitoring and Management Agent (Intersystems)	Improve efficiency of interface monitoring.
  Information Technology / Cybersecurity	In-Queue	ServiceNow Virtual Agent – IT Self Service	Agent to improve efficiency of IT help desk support.
  Information Technology / Cybersecurity	In-Queue	Agentic IT Help Desk Call Triage	Leveraging conversational AI in the UHIT Help desk for call triage, routing and escalations. The tool will learn and evolve with the intent of providing optimal assistance to our internal users.
  Finance	Completed	Leading & Lagging Indicator Revenue Forecast	Forecasting Net Patient Service Revenue using leading indicator of scheduled ambulatory appointments and the past trend of downstream revenue generated from completed ambulatory visits.
  Information Technology / Cybersecurity	Completed	Medigate Device Discovery	Discovery of on-network devices
  Information Technology / Cybersecurity	Completed	Palo Alto Cyber Prevention	Protects against internet threats, by automatically preventing unknown/malicious cyber-attacks.
  Information Technology / Cybersecurity	Completed	Proofpoint Email Protection	Software to automatically detect and block malicious inbound emails based on IPs.
  Information Technology / Cybersecurity	Canceled/Deprioritized	Report Automation - Data & Copilot Connection	N/A
  Finance and Administration	Completed	Revenue Plan Development	Model for creating clinical volume and gross charges plan, preserving the correlation between different types of clinical volumes and related gross charges.
  Information Technology / Cybersecurity	Completed	Splunk Cyber Threat Blocking	Monitor, identify, prevent, correlate anomaly behaviors, alert, and block malicious threats.
  Information Technology / Cybersecurity	Completed	Tanium Cybersecurity Detection	Tool leveraging ML, NLP, and RPA to enhance cyber security.
  Human Resources	Completed	UM Policy Q&A Copilot Assistant	AI assistant to help answer questions related to policy and procedure.
  Information Technology / Cybersecurity	Completed	Varonis Cybersecurity Incident Response	Generative AI security layer that enhances security team's visibility to ability to act.
  Strategy	Completed	Website Scrape Extraction Tool	Automatically find and pull content from a selected and populate it in a list.
  Human Resources	Completed	Workday Assistant and Teams Agent	Chatbot to assist with HR, finance, and supply chain questions and Teams Agent. Also provides search suggestions within Workday Web Applications
  Human Resources	In-Queue	Workday Assistant Enhancement with WorkdayHelp	Case management for employee inquiries in Workday that will replace the current Qualtrics/email system. WorkdayHelp will open a case in Workday for questions that cannot be answered directly by the agent and automate case management reporting.
  Human Resources	Completed	Workday Chatbot/WalkMe	Chatbot to assist with HR, finance, and supply chain questions. Assists with such tasks as recommending support material and flu vaccine status submissions.
  University Operations	In-Queue	UMPD - Camera AI Analytics for Crime Detection	AI program embedded in cameras that provides object and loitering detections. Auto alerts are sent to CCTV and/or Dispatch to improve rapid emergency response & investigations. Only 2% of our cameras currently have this capability. 30 security cameras are in place with AI analytics for loitering detection, potential intruder recognition, and vehicle identification in pedestrian only areas. All newer / replacement camera models will have this capability. Software program needs to be purchased to support and utilize this capability.
  Human Resources	Completed	Open Enrollment 2026 Agent	Copilot agent to answer employee questions related to benefits selection during open enrollment
  Human Resources	Completed	Phenom Recruiting Fit Score	Applies AI to evaluate candidates against job requirements and assigns a rating to highlight the strongest matches.
  Human Resources	Completed	Phenom Chatbot	Engages job seekers 24/7 to gather details on skills, experience, and interests. Based on their responses, the chatbot provides personalized job recommendations.
  Human Resources	Completed	LinkedIn Learning: Performance Management Role Play Scenarios	AI-enabled role play scenarios for performance management providing a safe environment for individuals to practice high-stakes conversations. Actively promoted in 'Spark the Right Conversation' and performance management programs. Accessible as a linked resource in the Performance Management Agent.
  Human Resources	Completed	LinkedIn Learning: AI Powered Personalized Coaching	AI-powered coaching chatbot providing personalized, real-time learning advice and resources. Available to all employees; promoted for skill development, career path guidance, and executive coaching continuity between sessions.
  Human Resources	Completed	AI Voice Over for Professional Development Videos	Creates professional voice-overs for instructional and professional development videos using AI.
  Human Resources	Completed	Powered By You AI Coach	AI agent providing analysis of Powered By You (PBY) engagement survey results, information on how to create goals based on results, and conversation starters for group feedback sessions. Since launch, leaders have generated 750+ interactions. Will be refreshed as part of the upcoming pulse survey project in fall 2026.
  Human Resources	In-Queue	AI Enabled Leadership Assessment	Interactive AI-enabled leadership assessment to replace the current external vendor tool.
  University Operations	In-Flight	Blackbaud Data Insights and Gift Officer Efficiency	Enabling AI capabilities in Blackbaud CRM that enable Gift Officers to more effectively and efficiently engage with potential donors and increase revenue from fundraising.
  University Operations	In-Flight	Space Utilization and Occupancy Analysis	Program will support enhanced data collection and modeling, enabling more accurate projections of potential cost savings from energy efficiency based on utilization patterns.
  University Operations	Completed	Parking & Transportation Agent	Chatbot on landing page to support customer service efficiencies.
  Information Technology / Cybersecurity	Completed	Social Media Threat Monitoring	Reduces institutional risk through enhanced situational awareness regarding local, state, national, and international incidents that may affect the UM campuses or community.
  University Operations	In-Flight	ParkZen Digital Parking Utilization App	New digital parking utilization app within the UM app provides real-time parking availability and utilization data, enabling drivers to locate available parking more efficiently while giving the University actionable insights to optimize parking operations, planning, and customer experience.
  University Operations	In-Queue	AI Analytics for Access Control Data	N/A
  Academic Administration	In-Queue	UOnline Enrollment and Student Success: AI Enrollment Agent	SMS chat to enrollment advisors and student success advocates.
  Academic Administration	In-Flight	UOnline Marketing: Content creation	AI to support marketing content creation.
  Information Technology / Cybersecurity	In-Queue	ServiceNow NowAssist – Augment IT Support Staff	Agent to improve efficiency of help desk ticket triage.
  Finance	In-Flight	Certificate of Insurance (COI) Verification Automation - ARK	Vendor Management - implementing software with AI features, ARK, to automate Certificate of Insurance (COI) verification, ensuring insurance compliance and more timely processing of purchase orders (many times POs are held due to expired or missing COI). This is currently a manual process and implementing the AI component will help in being proactive on maintaining complete vendor records with active COIs.
  Academic Administration	In-Queue	Classroom Optimization	N/A
  Finance	In-Flight	Contract Lifecycle Management (CLM) - Evisort	Contract Lifecycle Management (CLM) - As part of the Workday Supply Chain implementation, the CLM will have an AI component (Evisort )
  Academic Administration	In-Flight	Ideal Enrollment Analysis Tool	N/A
  Finance	Completed	Insurance Claims Review - Luminos	Risk Management - currently use Luminos for all claims, looking into activating the AI tool within Luminos' Risk Management Information System to summarize claim information without having to read through lengthy documents. This software will reduce the time it takes to review claims by providing the Risk Management team with a summary of the most critical components of the claim.
  Finance	Completed	Optimize Payment Terminals	Using AI to analyze trends in payment device activity by location, identifying legacy systems that are no longer being used. This will lower costs by reducing redundant devices by location and eliminating devices not in use . JP Morgan’s healthcare payments system, Instamed, will be rolled out this summer, replacing our previous provider BofA. JPM offers an API so we can track healthcare spend with software code instead of having to log onto their website and export the data into excel.
  Finance	Completed	Review Investment Proposals - Pension & Endowments	Use AI to perform initial review of investment proposals for Pension & Endowments, summarizing key information. This is currently reviewed manually and would reduce the time it takes to review lengthy investment proposal documents.
  Academic Administration	Completed	EAB Assistant for Students	Mobile app available to all students 24/7 to support advising and general inquiries. The tool delivers a personalized student experience by leveraging advising history and enabling more effective preparation for advising interactions. It also provides staff with analytics to identify patterns in student questions and behaviors, helping to identify opportunities for proactive intervention. Additionally, the tool will incorporate Insights survey data (administered periodically to first-year students) to support retention efforts.
  Finance	Completed	Vendor Risk Assessments - Craft	Vendor Management - implemented an AI tool, Craft, to perform vendor risk assessments. This is a new process to address an audit comment that risk assessment was not part of the vendor acceptance process. Craft aggregates data to evaluate vendor risk including but not limited to looking at the vendor's financial position, recent mergers, affiliations with countries that are on the State Department's high-risk list, etc.
  University Operations	In-Queue	News Aggregation and Analysis Automation	N/A
  Legal & General Counsel	Completed	Onbase Document Management and Search	N/A
  Legal & General Counsel	In-Flight	Subpoena/Garnishments/Billings Automation Project	N/A
  Legal & General Counsel	In-Flight	Use of AI By Outside Counsel	Began discussions with most-used outside law firms to discuss how AI can lead to more efficiencies and lower outside legal fees. As part of these discussions, we have emphasized need to use AI in creating bills, drafting documents, and reviewing large-scale document productions.
  Strategy	In-Flight	Market Intelligence Tool	N/A
  University Operations	In-Queue	Content Generation (Gemini Notebook Application)	N/A
  University Operations	In-Flight	Copilot Templeted Teams Meeting Minutes	N/A
  University Operations	Canceled/Deprioritized	Explore Microsoft Loop Application	N/A
  University Operations	In-Queue	Smartsheet's Smart Agent for Project Management	N/A
  Human Resources	Completed	LinkedIn Hiring Assistant	AI-powered recruiting agent automating repetitive administrative tasks: sourcing candidates, screening resumes, and drafting personalized outreach. Allows recruiters to focus on the human and strategic side of talent acquisition.
  Human Resources	In-Queue	Ulearn Cornerstone Pilot	Microsoft Teams app integration for ULearn (Cornerstone LMS) that allows employees to search for training courses. Currently stalled due to a security issue preventing the Cornerstone app from connecting to UM's Cornerstone instance.
  Human Resources	Canceled/Deprioritized	Optimize Orientation Roster Creation Process	Enhance the roster process for 'I Am the U' and 'We Care' new hire orientations. AI integration is not yet underway; OnBase and Workday are being explored as potential roster management solutions.
  Marketing & Comms	In-Queue	Content Lifecycle (brief → draft → versioning → optimization)	N/A
  Marketing & Comms	In-Queue	Video Production Acceleration	N/A
  Marketing & Comms	In-Flight	Paid Media Audience Targeting	N/A
  Marketing & Comms	In-Flight	AI-Assisted Social Listening and Reputation Monitoring	N/A
  Marketing & Comms	In-Queue	Automated Analytics Reporting	N/A
  Marketing & Comms	In-Queue	Initial CMS and Martech Integration	N/A
  University Operations	In-Flight	Unlocking AI Functionality in DAR's Core Software	N/A
  University Operations	In-Flight	Know Your Target Agent	N/A
  University Operations	In-Queue	Unlocking Core CRM Functionality with AI Technology	N/A
  University Operations	In-Queue	AI/Epic Integration for Grateful Patient Fundraising	N/A
  University Operations	In-Queue	AI/Ticketmaster Integration for Real-Time Athletic Event Screening	N/A
  University Operations	In-Flight	Prospective Donor Vetting	N/A
  University Operations	In-Flight	News Aggregation and Analysis Automation	Automating news and information gathering so that daily tasks and decision-making can be accessed and analyzed more effectively and efficiently.
  Academic Administration	In-Flight	MATES Course Credit Validation	MATES (Miami Acadecmic Transfer Evaluation System). The project would interact with a workflow called MATES, which helps students get credit for courses they have taken at other institutions. The AI request is fairly simple: students upload supporting documents, such as a course syllabus. We could use AI to verify that the document submitted by a student is a valid document type and qualifies as a syllabus, meaning that it should have things like a course name, faculty name, course description, contact information, office hours, grading scale, list of learning objectives, assignments, instructor name, etc. The overall workflow happens in Boomi, which can make calls to other systems.
  Human Resources	Canceled/Deprioritized	Workday Assistant Enhancement with Workday Learning	Requires investment in foundational changes to Workday by adding LMS (replacing ULearn/Cornerstone) to store knowledge directly in Workday for the Assistant to access, enabling a more copilot-like experience for learning management.
  Information Technology / Cybersecurity	In-Queue	Epic Agent Factory	Factory is Epic's platform for creating, monitoring, and evaluating AI agents and automated workflows. Factory lets you test ideas, automate repetitive tasks, and enhance experiences for staff and patients using AI that is integrated with your existing data and workflows.
  Human Resources	Completed	Performance Management Coach	AI performance coach providing UM faculty and staff with comprehensive guidance on the entire performance management lifecycle, from SMART goal setting to year-end evaluations. Offers tailored support on timelines, system navigation, and best practices.
  Human Resources	In-Flight	Total Rewards 2026 AI Agent	Dedicated AI resource for the HR Total Rewards team, streamlining high-volume inquiries by providing instant access to internal policies on benefits, retirement, and leave programs. Enhances team efficiency by drafting professional correspondence and ensuring consistent, accurate responses to employee questions. In testing phase.
  Human Resources	In-Flight	Talent & Organizational Development Website Bot	AI agent to improve access to Talent & Organizational Development resources including development, engagement, and organizational effectiveness offerings. Will initially reside under the Ask HR umbrella agent.
  Human Resources	Canceled/Deprioritized	UKG AI Payroll Agent	A Copilot Studio agent built for FAQ support around UKG/Kronos payroll navigation (e.g., differences between Kronos and UKG, pay clocking). Was never deployed beyond internal testing.
  University Operations	Completed	UMPD Crime Detection	Crime detection
  University Operations	In-Queue	Lessons Learned AI Agent	N/A
  Academic Administration	Completed	EAB Navigate AI Staff Assistant	Advances implementation of AI capabilities within Navigate to reduce administrative burden and improve service delivery for advising teams. The tool streamlines routine tasks such as report generation, student communications, and meeting preparation, including drafting messages and generating meeting transcripts. It also enhances the ability of Cane Navigators and Transitional Guides to manage appointments, to-dos, and student outreach, while supporting course recommendations aligned with student interests and degree plans. This is expected to improve the speed, consistency, and accuracy of documentation and enable more proactive engagement with students.
  Academic Administration	In-Flight	Ivy & Ocelot AI Student Engagement Platform (MHBS)	AI-powered student engagement platform that delivers 24/7, personalized communication across chat, text, email, WhatsApp, and social media to support enrollment, retention, and student success. The platform uses virtual assistants to provide instant, multilingual responses to student inquiries while integrating with core campus systems such as CRM, SIS, LMS, and financial aid to create a unified experience. Designed to reduce call center volume and automate routine interactions, it aims to reclaim staff time, lower operational costs, and allow teams to focus on higher-impact work, all while meeting security and compliance standards including FERPA, SOC 2, HIPAA, and GDPR.
  Academic Administration	In-Flight	CollegeVine’s AI Agent Admissions & Marketing Platform (MHBS)	AI-powered admissions and marketing solution designed to increase application volume, improve engagement, and generate measurable ROI for colleges and universities. According to its January 2025 report CollegeVine AI Agent Case Study…, its AI agents significantly outperform industry benchmarks in email open and click rates, handle thousands of interactions per month (many outside normal business hours), and respond to student inquiries in seconds. The platform supports both outbound marketing and 1-on-1 admissions engagement, with institutions reporting application growth, staff time savings, and strong ROI through automation and enhanced responsiveness.
  Academic Administration	Completed	Student Organization Funding Support	Student Organizations request funds from the activity fee three times annually; a student-led group, Student Activity Fee Allocation Committee (SAFAC), has developed rules and regulations for approval of funds, processes to request, and usage requirements. An AI tool creating a digestible way for students to look up policies and procedures interactively was developed. This will assist with reducing the administrative time necessary to manage questions about the fee request process.
  Academic Administration	In-Queue	Commencement Chat Bot	Parents, families, and students have numerous, yet straightforward, questions about attendance and participation in Commencement ceremonies. Implementation of a chat bot will enable staff to focus on management of the event rather than straightforward questions. This specific service is included with the current contract with Flash Photography, making its implementation a benefit to this contact.
  Academic Administration	In-Queue	Canes Central Chat Bot	Canes Central provides customer service support for aspects of student accounts, bill payments, registrar/enrollment, and financial aid. This team listens to the needs of students and families and provides a bridge to a variety of areas with decision-making for student services. To help students and families get quick information about policies, procedures, and dates before escalating more complex questions or needs to staff. This would involve integration with the case management system, Sales Force, that is used by Canes Central.
  Academic Administration	Completed	Family Weekend Customer Service Support	Family Weekend is an annual program where families visit campus, experience model classes, and attend a UM Football game. Families must register to participate. To help get quick accurate information to parents and families, we have developed an agent that contains accurate information and can address straightforward questions, such as dates, costs, and experiences.
  Information Technology / Cybersecurity	Completed	Agentic AI4E Help Desk Support	Setup an agent to provide help desk to support for AI4E DataCamp questions and issues.
  Academic Administration	In-Queue	Student Financial Risk Stratification Agent	N/A
  Strategy	In-Flight	Board Material Review Agent	N/A
  Human Resources	In-Flight	Open Enrollment 2027 Agent	Add-on branch of the Total Rewards Agent designed to guide employees through 2027 Open Enrollment benefits selection. Will incorporate all major OE 2027 updates and provide interactive support. Planned for benefits website and open enrollment website; option for interactive AI session at physical benefit fairs also under consideration.
  Human Resources	In-Flight	PWC Payroll Agent	AI payroll agent developed by PWC, integrated directly with Workday, providing employees who use UKG time tracking with access to live pay data for comparison and reference (e.g., comparing current check to prior check after payroll practice changes). Accessible via Microsoft Teams.
  Human Resources	In-Queue	Workday Self-Service Agent	Enhancement of the Workday Assistant to interpret employees' personal Workday data and facilitate Q&A for common self-service tasks (e.g., changing direct deposit, updating dependents). If the agent cannot resolve a query, it seamlessly transitions the employee into a Workday Help case for HR specialist follow-up.
  University Operations	In-Queue	PMO “Brain” Knowledge Agent	Creation of centralized PMO data repository
  Human Resources	In-Queue	AI Performance Manager Position	The AI Performance Manager position is responsible for maximizing the effectiveness, adoption, governance, and business value of artificial intelligence solutions across the organization. This role serves as the bridge between business leaders, HR, IT, data teams, and end users to ensure AI technologies improve productivity, employee experience, operational efficiency, and decision-making.
  Legal & General Counsel	In-Flight	Harvey AI	Harvey AI is domain-specific AI for legal and professional services. Harvey products streamline workflows in areas including contract analysis, due diligence, compliance, and litigation to drive efficiency and value.
  University Operations	In-Queue	Knowledge Capture Agent	Continuously collect and organize project information from meetings, emails, Teams, Smartsheet, SharePoint, and project artifacts.
  University Operations	In-Flight	Smartsheet Connector in Copilot	Allows you to interact with your Smartsheet data using natural language on your PC and wherever you use Copilot.
  University Operations	In-Queue	Risk & Dependency Agent	Identify emerging risks, dependencies, and patterns across projects and portfolios.
  University Operations	In-Queue	Project Delivery Agent	Recommend templates, deliverables, actions, and next steps based on similar past projects.
  University Operations	In-Queue	Portfolio Insights Agent	Surface trends, resource constraints, delivery risks, and executive-level insights across the portfolio.
  University Operations	Completed	Shuttles - Driver Behavior AI System	The AI Driver Behavior System uses onboard cameras and AI to identify unsafe driving behaviors and provide real-time alerts, helping improve safety, reduce incidents, and support driver coaching.
  University Operations	In-Queue	AI Dispatcher for TMA (Work Order System)	This system uses AI technology to automatically prioritize and assign work orders to the right technician, improving response times, workload balancing, and overall maintenance efficiency.
  University Operations	In-Queue	Business Automation System (BAS) to 25 Live	Automatically aligns HVAC and lighting schedules with classroom usage, improving comfort while reducing energy costs and unnecessary building operation.
  University Operations	In-Queue	Lambent and Siemens Integration	Uses real-time occupancy data to optimize HVAC and lighting operations, improving energy efficiency, sustainability, and space utilization.
  University Operations	Completed	Supply Chain Contract Review	Using Copilot to do preliminary contract clause/redline analysis against standard terms and conditions
  Finance	In-Flight	Duplicate Expense Detection	Detect duplicate expenses on expense reimbursement reports and travel expenses
  Information Technology / Cybersecurity	In-Flight	Workday Business Process Optimization Agent	An AI-powered process improvement advisor for Workday that continuously analyzes HR and financial workflows, identifies inefficiencies, and recommends changes to reduce cycle times, improve compliance, and align processes with Workday best practices.
  Information Technology / Cybersecurity	In-Flight	Workday Deployment Agent	An AI assistant for Workday administrators that helps locate configurations, understand tenant setup, and answer deployment and system configuration questions within the organization's Workday environment.
  Strategy	In-Flight	Governance & Board Records Assistant	N/A
  University Operations	In-Queue	“OTTO” AI assistant for Facilities Work Order Management System (aka TMA)	OTTO is TMA’s AI-powered assistant, designed to help users quickly access information, streamline maintenance and facility operations workflows, and make work order management more proactive vs reactive.
  Strategy	In-Queue	Executive-Ready Content Developer	N/A
  Strategy	In-Queue	AI-Enabled Board Workflow	N/A
  University Operations	In-Queue	Knowledge Capture Agent	Knowledge Capture Agent to continuously collect and organize project information from meetings, emails, Teams, Smartsheet, SharePoint, and project artifacts.
  University Operations	In-Queue	PMO Knowledge Agent	PMO Knowledge Agent to answer questions, retrieve historical decisions, lessons learned, deliverables, and best practices using natural language.
  University Operations	In-Queue	Risk & Dependency Agent	Risk & Dependency Agent to identify emerging risks, dependencies, and patterns across projects and portfolios.
  University Operations	In-Queue	Project Delivery Agent	Project Delivery Agent to recommend templates, deliverables, actions, and next steps based on similar past projects.
  University Operations	In-Queue	Portfolio Insights Agent	Portfolio Insights Agent to surface trends, resource constraints, delivery risks, and executive-level insights across the portfolio.
  Human Resources	Completed	AI Policy Agent	AI agent finds, summarizes, and answers questions about the policies at the University of Miami on policy.miami.edu website.

Accordion Group

Open All Tabs

• Supporting Athletics - AI Projects

  Sub Domain	Status	Project Name	Description
  Fan Engagement	Completed	AI Historical Image Enhancement	Enhance old footage and images to today's standards of resolution.
  Fan Engagement	Canceled/Deprioritized	Improve Degraded Videos	Improve the quality of degraded videos with Topaz Video.
  Data Analysis	Completed	Benchmark AI	Athletics contract and financial research tool
  Performance Optimization	Completed	XBoat Telemetry	A telemetry set for our sport is akin to the wearable tech that Football/Soccer/Basketball/etc. use for their players, only in our case, the boat “wears” it and it provides information on angles, timing, force application, crew cohesion, and much more data that cannot be seen or quantified by the eye. We can then “feed” the results into a trained AI program from Claude, which then provides its own analysis of the data that can be compared to the coaches’ analyses of the data and impressions from the practice
  Talent Scouting	In-Queue	Athena AI	Athena is a multi-modal tool that analyzes language, tone, and affect to deliver robust, bias-reduced insights that drive athlete growth and performance. It equips talent evaluators with deeper, objective insights for smarter scouting and recruiting.
  Game Strategy	In-Queue	Football AI Consultant	1. Advance Opponent Scouting 2. Advanced Self-Scouting 3. Situational Game Management Decisions 4. Portal Assistance
  Performance Optimization	In-Queue	Teamworks Intelligence	Teamworks Intelligence, formerly Zelus Analytics, is the leading sports analytics solution backed by a world-class team of data scientists, engineers, and product leaders. Trusted by elite teams across the globe, Intelligence uses advanced machine learning to deliver sport-specific predictive models and metrics that inform everything from athlete evaluation and roster construction to contract valuation and game strategy.
  Fan Engagement	Completed	Conversica Ticket Sales AI Agent	The Conversica AI Agent creates personalized conversations that move ticket sales leads towards meaningful outcomes, creating a more efficient sales staff.
  Performance Optimization	Completed	Athlete Management System	We have used Microsoft Fabric & Copilot to store student-athlete performance data to perform linear regression analysis to identify performance risks and course correct as quickly as possible.