01 Jul 2026
Off
View Post
MVC June Workgroups Highlight Cardiac Rehab Telehealth & Using AI for Physician Feedback and QI in the ED

MVC June Workgroups Highlight Cardiac Rehab Telehealth & Using AI for Physician Feedback and QI in the ED

July 1, 2026 | Comments Closed | , , , , , ,

In June, the Michigan Value Collaborative (MVC) hosted two virtual workgroup presentations. The first was a cardiac rehabilitation (CR) workgroup that doubled as a Michigan Cardiac Rehab network (MiCR) telehealth forum focused on virtual group CR programming with a live action demonstration. The second workgroup, health in action, focused on how artificial intelligence (AI) can be utilized to improve follow-up care for patients. The MVC Coordinating Center hosts workgroup presentations once or twice per month, covering a variety of topics including CR, post-discharge follow-up, sepsis, rural health, preoperative testing, and health in action.

Cardiac Rehab – MiCR Telehealth Forum

MVC and the Blue Cross Blue Shield of Michigan Cardiovascular Consortium (BMC2) co-lead MiCR, an initiative to improve CR utilization across Michigan. In April, MiCR launched a new virtual forum series to help programs implement and sustain telehealth services under recently extended Medicare reimbursement policies. MVC’s June workgroup hosted the second MiCR telehealth forum in the series, this time featuring a demonstration of group virtual CR by Henry Ford Health’s Steven Keteyian, PhD, Director of Cardiac Rehabilitation & Preventive Cardiology, and Robert Berry, MS, ACSM-CEP FAACVPR, Clinical Coordinator for Cardiac Rehabilitation. The demonstration was followed by a discussion led by MiCR’s Co-Directors, Jessica Golbus, MD, MS, and Mike Thompson, PhD, MPH.

Telehealth Group Example

The workgroup began with a live mock CR telehealth session led by Berry and Keteyian. Three actors representing patients (played by MVC’s Jessie Souva, MSN, RN, C-ONQS; Emily Woltmann, PhD, MSW; and Rachel Folk, MHA) were guided through a simulated telehealth group CR session.

After presenter introductions, Berry began the group CR class greeting the patient actors, who each represented a specific patient profile and common cardiac condition (Figure 1).

Figure 1. Patient Profiles for Cardiac Rehabilitation Mock Session

Illustration featuring three female characters representing patients with heart conditions, each accompanied by brief medical histories and personal details. Key information includes ages, specific diagnoses like myocardial infarction, coronary artery bypass surgery, and chronic heart failure, along with lifestyle notes and emotional states, presented with distinct colors and icons for clarity.

To begin the session, Berry checked in with each patient on the Zoom session to document the type of exercise or equipment they would be using. As Figure 2 shows, the group session looked similar to a Zoom meeting with all patients exercising simultaneously from locations they established with their instructor in advance. Each patient confirmed their exercise modality, weight, and heart rate as they engaged in their chosen activity. Throughout the exercise process, patients were asked questions about how the exercise was feeling and whether it was causing any pain or discomfort. If a patient was having symptoms, Berry would follow up with more specific questions to help pinpoint the problem area and would give advice for either modifying the exercise, utilizing intentional breathing techniques, or taking a break.

Figure 2. Screenshot of Mock Telehealth CR Session

Screen capture showing what a virtual cardiac rehabilitation group session looks like. Shows three female participants and one clinical professional.

The patients had an opportunity to ask Berry follow-up questions before the end of the session such as:

  1. How will I know when it’s safe to push harder?
  2. Should I continue with CR exercises if my energy level is low today?
  3. When/how do I share my tracked vitals and symptoms with my providers?
  4. How do I get in touch with you between sessions?
  5. Can I still participate in virtual sessions if I’m at my home in Florida?

Following the live demonstration, Golbus and Thompson led participants in a question-and-answer discussion that further clarified how virtual and telehealth CR programs can work. Keteyian and Berry shared that patients must be at their home address for certain payers (Medicare/Medicaid), but patients with other insurance such as Blue Cross Blue Shield of Michigan (BCBSM) can be at any location within the state of Michigan.

Some attendees wondered about confidentiality considerations during the group session. Henry Ford Health said their programming has not required participants to sign an additional Health Information Portability Insurance Portability and Accountability Act (HIPAA) release form; however, they do remind patients to be aware of what information they share in the presence of others during the group session. For people who may be uncomfortable sharing personal information such as weight, different wording can be used. For example, “has your weight changed since your last visit?”

For patients who are unsure about participating in a virtual setting, Keteyian pointed out that they often have the patient come into the facility for the first session to participate as if they were at home in a virtual environment. This often alleviates any concerns about fully participating in a telehealth setting in the future. For those patients who do not have exercise equipment at home, Berry shared that patients can usually find some form of exercise equipment to borrow from a family member, church, or neighbor, or will choose to walk during their session.

A poll of participants showed the current state of CR programming for sites represented at the forum (Figure 3-4), with most sites indicating an interest in exploring both group and individual telehealth CR.

Figure 3. Polling Question: What format of virtual CR is your site considering?

Polling bar chart showing frequency of four formats of virtual cardiac rehab being utilized: Both, Group, Individual, and Neither. Both has highest value near 19, followed by Neither at 13, Group at 8, and Individual at 7, with vertical axis ranging from 0 to 20.

Figure 4. Polling Question: What best describes your site's status on starting a virtual CR program?

Pie chart displays stages of virtual cardiac rehabilitation (CR) implementation among organizations. Largest segment (21) represents organizations considering virtual CR, followed by 12 having conversations with staff or leadership, and smaller segments of 3 each for program development and piloting or delivering virtual CR, with color-coded legend for clarity.

According to the polls, most workgroup participants are still considering CR program development and starting to have conversations with staff and leadership. The MiCR team encouraged participants to take these poll questions back to their teams and leadership to inspire discussion on developing a hybrid or telehealth CR program.

MiCR Telehealth Virtual Forum: June 9, 2026

Health in Action Workgroup – Michigan Medicine

MVC was joined by the University of Michigan’s Alexander Janke, MD, MHS, MSc, Assistant Professor of Emergency Medicine, and Florian Schmitzberger, MD, MS, Clinical Assistant Professor of Emergency Medicine, for the health in action workgroup. Their presentation focused on how AI can be used for clinical feedback and quality improvement workflows in various healthcare settings.

Janke shared that emergency clinicians often make high-stakes clinical decisions when treating patients but then have limited feedback on how their patients do as they move through their care pathway. The rapid patient traffic through the emergency department (ED) continuously pulls these providers into new patient cases, preventing them from having the time to manually review past patient charts. A feedback loop project was intended to help address practice variation, missed learning opportunities, and potential quality blind spots. In preparation for the launch of the project, Michigan Medicine sought approval from the institutional review board (IRB), utilized a large language model (LLM) that is HIPAA compliant, and completed a health information technology services review. They also gathered clinical intelligence committee input, Epic database integration support, and input from the division of clinical informatics.

Methods

Previous approaches to reviewing patient progress included manual chart reviews (time consuming), self-imposed reminders via Epic’s in-basket messaging system, or by hearing about a patient’s follow-up by word-of-mouth. With the introduction of AI as a feedback tool, clinicians would have access to LLMs that can read charts faster than a human reviewer, create tailored summaries for the emergency medicine context, and provide another means for learning by supporting clinicians within their limited time. The AI feedback process follows this flow:

  1. Flag the case – A clinician marks a patient of interest during the shift via a health education research (HER)-integrated workflow
  2. Wait – A specified time later—three to 14 days—the platform queries downstream documentation
  3. AI summary – The University of Michigan generative pre-trained transformer (GPT) Toolkit (HIPAA-compliant LLM) generates a tailored clinical summary with a structured prompt
  4. Deliver – An email arrives in the clinician’s institutional inbox and includes a patient identifier for recall, an emergency medicine-focused summary, and answers to any free-text questions
  5. Reflect – The clinician reviews, learns from the outcome, and adjusts future practice enabling the adaptive learning cycle

The process begins with the provider flagging a patient case they would like educational feedback on in the future. Flagging a case is done in the “Disposition View” of the clinician decision tree in Epic (Figure 5). After the waiting period of the patient progressing through levels of care and finally discharging from the hospital, the HIPAA compliant UM GPT will send the provider a summary directly to their institutional email.

Figure 5. Disposition View in Epic MyChart

Screenshot of a medical software interface showing a disposition view with color-coded task categories and a follow-up order section. Tasks include work/school/sport excuses and patient portal letters in green and blue boxes, with a follow-up question form on the right allowing email summary timing selection and additional patient questions.

To validate that the AI summary was providing impactful and meaningful patient information, Schmitzberger and Janke developed a structured validation procedure for 200 AI-generated case summaries measuring for accuracy, conciseness, helpfulness, and completeness. The initial scoring showed that the AI summaries were quite accurate and helpful (Figure 6). This early positive feedback has prompted continued work on developing the use of this program in other areas of the institution.

Figure 6. Structured Validation of 200 AI-Generated Case Summaries

A table displays four performance metrics for validation of 200 AI-generated case summaries with scores out of 5: Accuracy (4.79), Conciseness (4.86), Helpfulness (4.60), and Completeness (4.28). Each metric is labeled in red text below the blue numerical scores.

Results

Currently the program includes 170+ unique users including faculty, residents, and physician assistants, who are averaging approximately 40 – 70 requests each week, and 30+ power users (a clinical or other staff member who maximizes Epic electronic health record (EHR) efficiency using advanced tools and navigation).

The top three case follow up themes for requested summaries included diagnosis/etiology (~40%), disposition/course/ICU (~17%), and test/imaging results (~10%). With strong approval in the emergency department and endorsement from other committees, the goal is to expand this feedback program to multiple areas within the institution.

Next Steps & Discussion

Janke presented two pathways in which they would like to proceed with expanding the AI feedback program. The first would be horizontal scaling across the institution, including integration into the graduate medical education program for internal medicine/hospitalist care. Second, they would like to apply their approach to a quality measure from the Michigan Emergency Department Improvement Collaborative (MEDIC).

The presenters addressed participant questions about sharing learnings between providers, patient record privacy, and potential applications in other areas like pediatric care and fall prevention, with participants suggesting connections with the Michigan Hospital Medicine Safety Consortium (HMS) metrics and exploring CEUs as incentives for provider participation.

MVC Health in Action Workgroup: June 25, 2026

MVC welcomes workgroup presenters from across Michigan to share their expertise, success stories, initiatives, and solution-focused ideas with MVC members. Please reach out to us by email if you are interested in being a workgroup presenter or submit a presentation proposal here.

19 Aug 2021
0

Predictive Analytics Assist with Chronic Disease Prevention

August 19, 2021 | 0 Comments | , ,

The healthcare system has an immense wealth of information at its digital fingertips. Big data is constantly expanding from sources such as digitized patient records, patient wearables, medical apps, genome datasets, monitoring devices, and more. A critical challenge facing hospitals and health systems today is in effectively identifying strategies and personnel to utilize big data in a way that influences clinical care. Those that succeed in this task will find themselves in a much better position to advance care and improve patient outcomes.

One developing strategy to convert big data sets into improved patient outcomes is the use of predictive analytics, an approach that differs from what many hospital quality improvement departments are currently utilizing. For example, the Michigan Value Collaborative (MVC) Coordinating Center has been helping hospitals identify opportunities for quality improvement since 2013 by aggregating and analyzing payor claims data and presenting the results on the registry and in analytics reports. The goal of these efforts is to help hospitals compare utilization against peers and draw important insights across a range of medical and surgical procedures. This retrospective approach helps MVC members to learn from their past performance in order to pursue meaningful, observable improvements within their buildings. It is one piece of the big data puzzle. Predictive analytics, on the other hand, allows clinicians to utilize big data before their patient experiences significant healthcare services or treatments. As its name denotes, this approach identifies prevention opportunities before the incidence of disease by predicting a patient’s risk. This is especially important for diseases that require early detection for optimal treatment and survival.

Unlike Robotic Process Automation (RPA), which is also on the rise in health systems across the country, predictive analytics is performed by Artificial Intelligence (AI). This means that computer systems will perform tasks typically requiring human intelligence, including analyses and decision-making. In some ways, this strategy mimics what physicians have long been doing at a patient’s bedside: collecting a patient’s medical history and risk factors in order to tailor their treatment and advice. This process is essential in evaluating a patient’s risk of developing chronic diseases, which often run in their family or are more likely due to socioeconomic factors. An article from the University of Illinois Chicago posits that predictive analytics represent a significant potential for cost savings if they help clinicians and their patients prevent the onset of chronic diseases, one of healthcare’s costliest areas.

“On a population-wide level, predictive analytics can help greatly cut costs by predicting which patients are at higher risk for disease and arrange early intervention, before problems develop,” the article stated. “This involves aggregating data that are related to a variety of factors. These include medical history, demographic or socioeconomic profile, and comorbidities.”

The Centers for Disease Control and Prevention (CDC) states that, “90% of the nation’s $3.8 trillion in annual health care expenditures are for people with chronic and mental health conditions.” So the potential cost savings from reducing chronic disease treatment are significant.

Using predictive analytics in a clinical setting can leverage both patient records and socioeconomic factors. Medical records will often include family history of chronic diseases such as cancer, diabetes, and heart disease, which would make a patient more likely to develop the condition themselves. In addition to family history, a patient’s socioeconomic factors (e.g., education, employment, and environment) and lifestyle choices are significant predictors of chronic disease. A study in the American Journal of Preventive Medicine outlines how researchers used predictive analytics to screen for cardiovascular disease risk from social determinants of health, and ultimately guide clinician treatment options. The researchers also suggest that large databases about social determinants of health variables, especially environmental ones, are not as readily available as they should be, and are an important area of opportunity for future data collection efforts.

A similar application of this technology was used in a study published by Cancer Immunology Research to predict lung cancer immunotherapy success. In the study, researchers used an AI algorithm to identify changes in patterns from CT scans that were previously not detected by clinicians, which ultimately predicted how well a patient would respond to immunotherapy. This suggests that predictive analytics can help improve the accuracy of diagnoses and treatment.

Of course, the applications for predictive analytics extend beyond chronic disease prevention and treatment. In the past year, researchers have also used predictive analytics to forecast outcomes for patients positive for COVID-19. In The American Journal of Emergency Department Medicine, a published study validated a tool that helps physicians predict adverse events among patients presenting with suspected COVID-19. The study suggests that the algorithm and scores can help physicians decide when to hospitalize or discharge patients during the pandemic. Therefore, predictive analytics appear to also provide insights that enhance treatment.

Many additional articles (such as one article from Health IT Analytics) and published studies recommend predictive analytics for its potential benefits. As with any technology, however, it is not without its risks. The use of AI brings about concerns for privacy, especially since hospitals must properly steward patient data and comply with HIPAA regulations. But there are several other considerations identified in a recent Deloitte analysis (see Figure 1), not the least of which is ensuring the algorithm doesn’t introduce bias that disproportionately harms minorities and communities of color. Predictive analytics may also present evaluation challenges. Once algorithms are validated, their widespread use in clinical settings should be confirmed for their efficacy, which requires measuring the absence of disease.

The potential benefits of predictive analytics are variable and significant; however, as healthcare learns to integrate AI technologies, it will be important to keep its risks in mind and address them accordingly. The MVC Coordinating Center endeavors to assist its members through their data analytics journey by providing insights into specific data sets. When pursuing additional technologies or analytic tools, the Coordinating Center encourages members to volunteer as a sounding board and resource for other members. If your hospital or physician organization is currently utilizing AI or considering it with your patient data, we encourage you to reach out so MVC can share your experience with others. You can reach the MVC Coordinating Center at michiganvaluecollaborative@gmail.com.