AI

Grand Rounds April 17, 2026: Keeping a Human in the Loop: Scientific Publishing and AI (Roy Perlis, MD, MSc)

Posted on by Sophia Ramirez

Speaker

Roy Perlis, MD, MSc
Editor in Chief, JAMA+ AI
Director, MGH Center for Quantitative Health
Vice Chair for Research, Mass General-Brigham Psychiatry
Professor of Psychiatry, Harvard Medical School

Keywords

Artificial Intelligence; Publishing; Medical Publishing; Peer Review; Trust

Key Points

  • Though medical publishing was in flux before artificial intelligence (AI) became ubiquitous, the contemporary state of the industry is defined by AI-driven trends: an increased volume of submissions, an increased volume of low-quality submissions, and increased complexity of submissions. Academics are concurrently less willing to participate in the peer-review process – paradoxically making peer review into an area ripe for AI intervention.
  • Scientific communities are divided about the appropriate role of AI in manuscript preparation and review. In mid-2023, JAMA Network journals began requiring authors and peer reviewers to answer questions about their use of AI to create or assist with creation or editing of submitted manuscripts, or with preparation of reviews. While author disclosure of AI use is low, those figures likely represent an underestimate.
  • That peer review improves manuscript quality is a fringe benefit; its real value is instilling trust in the contents. The age of AI poses twin dangers: the simulation and politicization of expertise. AI may be capable of handling rote tasks like checking protocols, human subjects approval, and reporting checklists, but it comes with a potential cost in terms of the public’s already-eroded faith in scientific expertise.

Discussion Themes

The most commonly disclosed use of AI in manuscripts is for language and grammar cleanup, particularly by non-native English speakers. On the whole, AI has improved the clarity of international submissions.

Perlis predicted that administrative editorial tasks will be automated but human editors will remain essential for scientific taste: the ability to curate impactful stories and select which of hundreds of AI-generated hypotheses are worth pursuing.

Researchers were encouraged to master the use of AI agents as local analytic partners or writing assistants to automate aspects of their workflow without losing human oversight.

Grand Rounds April 3, 2026: AI for Diabetes Prevention (Nestoras Mathioudakis, MD, MHS)

Posted on by Sophia Ramirez

Speaker

Nestoras Mathioudakis, MD, MHS
Associate Professor of Medicine
Johns Hopkins University School of Medicine

Keywords

Artificial Intelligence; Diabetes; Prevention; Coaching; Automation

Key Points

  • Of the nearly 100 million U.S. adults with prediabetes, approximately 70% will progress to type 2 diabetes in their lifetime. The Diabetes Prevention Program (DPP), a gold-standard program focused on lifestyle interventions, has demonstrated a 58% reduction in diabetes incidence. However, an effort to implement the program nationally fails to reach 99% of eligible individuals.
  • The research team sought to investigate whether a fully automated, AI-based DPP could effectively replicate the outcomes of the human coach-based DPP and potentially bridge this access gap. This was the first trial comparing a fully automated versus human DPP. It adds to a limited evidence base evaluating AI interventions against established standards in medicine.
  • The research team found that the AI-driven DPP delivered without human intervention was non-inferior to the traditional human coach-based DPP. Participants in the AI-driven DPP arm had comparable health outcomes and adequate engagement – though they were less likely to express a preference for their intervention than those in the human coach-based arm. The study team concluded that diabetes prevention remains an implementation challenge, not an efficacy problem.

Discussion Themes

While absolute weight loss was modest when compared to the effect of new medications like GLP-1s, Dr. Dakis argued that lifestyle interventions remain more cost-effective and that future automation efforts may bridge the effectiveness gap.

In the future, large language models could bolster the trust and human connection lacking in fully automated digital interventions.

April 1, 2026: AI for Diabetes Prevention, in This Week’s Rethinking Clinical Trials Grand Rounds

Posted on by Sophia Ramirez

In this Friday’s Rethinking Clinical Trials Grand Rounds, Nestoras Mathioudakis of the Johns Hopkins University School of Medicine will present “AI for Diabetes Prevention.”

The Grand Rounds session will be held on Friday, April 3, 2026, at 1:00 pm eastern.

Mathioudakis is an assistant professor of medicine at the Johns Hopkins University School of Medicine.

Join the online meeting

Add to your calendar:
Google
iCal
Outlook

Or join the Grand Rounds mailing list to receive calendar invitations.

Grand Rounds January 30, 2026: A Pragmatic Randomized Controlled Trial of Ambient Artificial Intelligence to Improve Health Practitioner Well-Being (Majid Afshar, MD, MS; Mary Ryan Baumann, PhD)

Posted on by Sophia Ramirez

Speakers

Majid Afshar, MD, MS
Associate Professor
Director, Learning Health Systems
Departments of Medicine and Biostatistics & Medical Informatics
University of Wisconsin-Madison

Mary Ryan Baumann, PhD
Assistant Professor
Departments of Population Health Sciences and Biostatistics & Medical Informatics
University of Wisconsin-Madison

Keywords

Artificial Intelligence; Burnout; Provider Well-Being; Learning Health System

Key Points

  • Documentation in the Electronic Health Record (EHR) is a driver of clinician burnout; it can reduce their capacity to connect with patients during an appointment and spill over into daily life, i.e. “work outside of work.” The research team sought to assess whether the use of an ambient Artificial Intelligence (AI) scribe could improve clinician well-being by automating the documentation process.
  • The stepped-wedge, individually randomized trial took place over 24 weeks at UW Health. 66 providers across various specialties were randomized to receive access to ambient AI at Week 1, Week 7, or Week 13. The primary endpoint was physician well-being, measured by the Professional Fulfillment subscale and a burnout composite.
  • The research team found a 20% reduction in burnout and a trend towards improvement in professional fulfillment. These effects were sustained over the course of the trial. Use of the technology also decreased “work outside of work” by an average of 30 minutes and “time in notes” by 21 minutes.

Discussion Themes

Qualitative interviews found that patients of the clinicians in the trial appreciated the reduced computer interaction and felt that communication was clearer and more open.

The research team worked with the EHR company to develop a rubric for evaluating the AI-generated notes for accuracy, i.e. the presence of AI hallucinations or falsifications.

Following the trial’s success, UW Health scaled the project from 66 to over 600 licenses. An operational dashboard was developed for real-time monitoring of utilization and documentation metrics to ensure sustained performance and coding compliance.

January 28, 2025: Assessing Whether Ambient Artificial Intelligence Can Improve Health Practitioner Well-Being, in This Week’s Rethinking Clinical Trials Grand Rounds

Posted on by Sophia Ramirez

In this Friday’s Rethinking Clinical Trials Grand Rounds, Majid Afshar and Mary Ryan Baumann of the University of Wisconsin-Madison will present “A Pragmatic Randomized Controlled Trial of Ambient Artificial Intelligence to Improve Health Practitioner Well-Being.”

The Grand Rounds session will be held on Friday, January 30, 2026, at 1:00 pm eastern.

Afshar is an associate professor and director of Learning Health Systems in the Departments of Medicine and Biostatistics & Medical Informatics. Baumann is an assistant professor in the Departments of Population Health Sciences and Biostatistics & Medical Informatics.

Join the online meeting.

Grand Rounds August 1, 2025: Clinical Trial Notifications Triggered by Artificial Intelligence-Detected Cancer Progression (Kenneth L. Kehl, MD, MPH)

Posted on by Sophia Ramirez

Speaker

Kenneth L. Kehl, MD, MPH
Assistant Professor of Medicine and Physician
Dana-Farber Cancer Institute

Keywords

Artificial Intelligence; Cancer; Notification; Enrollment; Patient Identification

Key Points

  • Historically, less than 10% of adults with cancer enroll in clinical trials. At the same time, many trials struggle to reach their accrual goals. One possible contributor is that many trials of novel therapies for cancer have specific molecular criteria.
  • Dana Farber Cancer Institute (DFCI) developed MatchMiner, a computational matching tool, to connect patients to trials. However, identified patients often weren’t at a place in their treatment when information about trials was relevant. The research team was interested in whether they could train an artificial intelligence (AI) model to identify “trial-ready” patients.
  • The team conducted an implementation pilot, providing clinicians and research staff with weekly spreadsheets containing predictions of clinical trial “readiness” as identified by AI. The majority of identified patients were found to be ineligible upon RN review. Of those who were eligible, the majority opted not to move forward with the trial referral. At the end of the 9-month pilot, 6 AI-identified patients had been consented and enrolled in a therapeutic trial.
  • To assess the impact of AI-driven identification of trial-ready patients, the team launched OPTIONS (Optimizing Precision Trials with an artificial Intelligence driven Oncologist Notification System). The primary outcome of the trial was enrollment in any DFCI therapeutic clinical trial.
  • Patients with solid tumors were randomized into either a control group, in which they could be identified by the standard MatchMiner workflow, or 1 of 2 intervention groups. In the intervention arms, treating oncologists for genomically-matched patients with progressive disease and anticipated changes in treatment were contacted via email. In group 3, patients who met the readiness criteria were manually reviewed before the oncologists were contacted.
  • They found that, though the AI models successfully predicted which patients with active or progressive cancer may need treatment changes, sharing the trial information with oncologists did not increase trial enrollment.
  • This intervention addressed 1 barrier to trial participation. Other barriers may include eligibility criteria that goes beyond genomics and recent progression; and factors related to patient or oncologist preference, such as the motivation for participating, the complexity of the trial, and time toxicity.
  • Dr. Kehl concluded with a reminder that while AI can accelerate clinical cancer research by rapidly identifying clinical trial options for patients, impact requires integration. AI must be applied thoughtfully and continuously evaluated, and researchers should be aware of the pitfalls and shortcuts associated with the technology.

Discussion Themes

The DFCI team is currently working on MatchMiner-AI: an open-source tool that they hope will improve the accessibility of clinical trials for all patients by providing a list of relevant clinical trials. They’re running a pilot study focused on incorporating MatchMiner-AI with the historical tool.

It’s easier to train a model than it is to deploy it in a complicated healthcare context. Given that the tool performs as hoped, there are evidently implementation challenges that still need to be worked out.

The study team considered training the model on a more proximal task – i.e., “Predict whether this patient will enroll in a clinical trial.” However, they were concerned that this would introduce biases – a pertinent concern with AI models – based on which patients typically have the opportunity to enroll in clinical trials.

While there may be use cases in which providing the trial information directly to patients would be more efficient, this would need to be done carefully. Information about worsening cancer, for instance, is best contextualized in a conversation with an oncologist.

Grand Rounds April 25, 2025: Automated Response Technology Integrated into EMR and Physician-Patient Communication (Ming Tai-Seale, PhD, MPH)

Posted on by Sophia Ramirez

Speaker

Ming Tai-Seale, PhD, MPH
Professor
Departments of Family Medicine and Medicine (Bioinformatics)
University of California San Diego School of Medicine
Director of UC San Diego Learning Health Systems Science Center

Keywords

Electronic Health Record; Artificial Intelligence; MyChart; Patient Messages; Large Language Models; Clinician Well-Being; Mental Health

Key Points

  • Physician work is increasingly centered around the electronic health record (EHR). It consumes nearly 50% of scheduled clinic time. The volume of patient messages in MyChart increased significantly from 2020 to 2022, and remains much higher than pre-pandemic levels.
  • Research published in Health Affairs and JAMA Network Open suggests that this influx of inbox messages is detrimental to physicians’ well-being. The emotional timbre of messages from patients plays a role, as well; in an analysis of EHR inbasket messages, the research team found messages from patients that contained expletives, vitriol and personal attacks.
  • The research team sought to examine the association between generative AI (GenAI)-drafted replies for patient messages and physician time spent on answering messages. They were also looking at the quality of GenAI-drafted replies for messages dealing with mental heath concerns.
  • The team created a prompt within the EHR that gave physicians the option to either use an AI-generated response as a starting point or to start with a blank reply. Messages eligible for responses drafted by GenAI included refills, results, paperwork, and general questions.
  • The pilot study took place from June 16 to July 12, 2023, targeting primary care attending physicians at University of California San Diego. 52 physician volunteers received the intervention; the 70 physicians in the control arm did not.
  • In the pilot study, clinicians who were given the option of a GenAI-drafted reply spent more time reading patient messages. There was no change in average reply time.
  • When clinicians received messages dealing with mental health issues, replies drafted by more recent versions of GenAI had more utility than older versions.
  • The physicians expressed that they valued the GenAI-drafted replies as a compassionate starting point for their communication. They noted areas for improvement, like a robotic tone, and emphasized the continued need for human oversight and intervention.
  • The study team acknowledged potential risks when using large language models (LLMs) in mental health communication. These included a loss of human touch and empathy; overreliance and deskilling; and privacy and security risks.
  • This is an ongoing effort. Next steps include using LLMs to facilitate analyses of qualitative data on electronic patient-clinician communication; triangulating qualitative and quantitative data in the EHR; and aiming for a more comprehensive understanding of mental health communication and how LLMs might improve its quality.

Discussion Themes

Anecdotally, the researchers have heard from physicians that ART technology – which Epic and Microsoft continue to refine – seems to have improved. But issues still remain, such as GenAI recommending patients see clinicians from external hospital systems.

When a modified GenAI-drafted reply was sent to a patient, a disclaimer was included: “Part of this message was generated automatically.” The research team felt that it was important to provide this transparency and disclose to patients when AI contributed to the messaging they received.

Health systems and professional organizations must develop standards advocating for equity in the implementation of and access to these tools.

Grand Rounds March 28, 2025: A Cross-Sectional Study of GPT-4–Based Plain Language Translation of Clinical Notes to Improve Patient Comprehension of Disease Course and Management (Anivarya Kumar, BA; Matthew Engelhard, MD, PhD)

Posted on by Sophia Ramirez

Speakers

Anivarya Kumar, BA
Fourth-Year Medical Student
Duke University School of Medicine

Matthew Engelhard, MD, PhD
Assistant Professor, Department of Biostatistics & Bioinformatics
Duke University School of Medicine

Keywords

Health Literacy; Large Language Models; Artificial Intelligence; Electronic Health Records

Key Points

  • Limited health literacy (HL) has tangible effects on morbidity and mortality: it’s associated with higher rates of hospital admissions and readmissions; medication nonadherence; healthcare costs; and all-cause mortality. 9 in 10 adults have limited HL, and rates are 2 – 3 times lower in marginalized populations.
  • 71% of patients report accessing their electronic health records (EHRs) to read documentation from their clinical visits, particularly the discharge summary notes (DSNs). But clinical notes have low levels of readability, hindering patients’ ability to engage in shared decision-making.
  • The research team looked at whether a Generative-Pre-trained-Transformer-4 (GPT-4)-based plain language translation of DSNs could improve patient comprehension of disease course and management.
  • 533 patients, recruited from a pool of EHR users, were randomly assigned 4 DSNs to assess. After reading the DSNs – 2 translated into more accessible language, 2 untranslated – patients answered questions assessing their objective comprehension, subjective comprehension, confidence, and time spent on each DSN.
  • Compared to the untranslated DSNs, objective understanding of the translated DSNs increased by 6.1%; subjective understanding increased 18%; confidence increased 45%; and average time spent with the DSNs decreased 51%.
  • The research team concluded that GPT translation of DSNs significantly improved patient comprehension of disease course and management and optimized time spent reading them. The effect was significantly greater in marginalized populations with historically low health literacy, reducing the gap in comprehension scores between patient populations.
  • Limitations included the use of standardized DSNs as opposed to real-world DSNs; the use of MyChart when enrolling patients, leading to a participant group with a higher baseline HL; and the modest number of Hispanic patients enrolled in the study.
  • Race is a significant and independent factor for HL. Preliminary data suggests that GPT translation can help close this gap. The research team identified this as an area for further study.

Discussion Themes

While discharge instructions alone can be great for providing patients with action items, they lack some of the context that DSNs can provide, lending the patient a more complete understanding of their condition.

The advantages of providing pre-generated materials, as opposed to pointing patients to an large language model (LLM) like Chat GPT for a more interactive explanation of their condition, include the potential for screening by a healthcare professional and less of a burden on the patient.

The study team ended up favoring “semantically-focused” translations over translations that focused solely on simplifying the language or avoiding jargon. When the LLM was asked to focus on semantics, it was more likely to define concepts and their implications.

Health literacy and reading level are not necessarily on par, and patient-centric or accessible language/LLMs are very important to consider. This may require further investigation, e.g. through qualitative interviews.

Grand Rounds March 21, 2025: Generative Artificial Intelligence in Clinical Trials: A Driver of Efficiency and Democratization of Care (Alexander J. “AJ” Blood, MD, MSc)

Posted on by Sophia Ramirez

Speaker

Alexander J. “AJ” Blood, MD, MSc
Associate Director, Accelerator for Clinical Transformation Research Group
Instructor of Medicine at Harvard Medical School
Cardiologist and Intensivist
Brigham and Women’s Hospital

Keywords

Artificial Intelligence; Cost; Large Language Models; Enrollment; Eligibility; Recruitment

Key Points

  • The Accelerator for Clinical Transformation (ACT) is a research group that seeks to use emerging technology to try and expand access to healthcare and improve quality and quantity of healthcare delivery. They focus on team-based models and scalable applications.
  • It’s becoming more expensive and time-consuming to move a drug from the clinical trial stage to approval. Patient recruitment is the leading driver of costs in clinical trials, and 55% of trials that fail to complete cite low accrual rate as the reason for study termination. There’s pressure from industry to conduct clinical trials in a way that is faster, cheaper, and better for both the patients and the research environment.
  • ACT conducted a pilot study in which they embedded a Large Language Model (LLM) tool called RECTIFIER into an active clinical trial of patients with heart failure. RECTIFIER is an AI-powered, comprehensive software application able to ask and answer questions about unstructured clinical data. In a pilot study, RECTIFIER determined patient eligibility with higher accuracy and specificity than study staff, indicating its potential to streamline screening.
  • LLMs are the engines that power the software. There are two key challenges that need to be taken into consideration to use these tools effectively: 1) there’s a content window – a limit to the amount of Electronic Health Record (EHR) data you can pull in; and 2) Using LLMs is expensive.
  • Following up on the pilot study results, ACT conducted a prospective randomized controlled trial: The Manual Versus AI-Assisted Clinical Trial Screening Using LLMs (MAPS-LLM) trial. MAPS-LLM compared two methods for analyzing a randomized pool of potentially eligible participants: manual review by study staff, and RECITIFIER-augmented review by study staff. Their primary endpoint was eligibility determination.
  • They found that AI-assisted patient screening using the RECTIFIER system significantly improved eligibility determination and enrollment compared with manual screening in a heart failure clinical trial.
  • ACT concluded that implementing AI-assisted tools like RECTIFIER can enhance clinical trial efficiency, reduce resource utilization, and promote equitable recruitment, potentially leading to faster trial completion and earlier patient access to novel therapies. Generative AI is likely to play a significant role in the future of clinical trials.

Discussion Themes

Study staff in the MAPS-LLM intervention arm were able to direct more time and effort towards contacting patients and managing patients with the time they would have spent reviewing charts and manually screening the EHR.

The rate of eligibility between the two arms was equivalent; the difference was, the AI-augmented group was able to assess twice as many potentially eligible patients.

While this tool can do a lot of analytical work, a human element will be essential to utilizing it effectively and to bringing “human intelligence” to participant enrollment.

The ACT team has started to pilot this technology in other disease areas, including cardiology more broadly, endocrinology, oncology, and gastroenterology.

Grand Rounds February 21, 2025: Texting for Behavior Change: Lessons Learned Across 2 Interventions to Improve Chronic Care Management (Michael Ho, MD, PhD; Sheana Bull, PhD)

Posted on by Sophia Ramirez

Speakers

Michael Ho, MD, PhD
Kaiser Permanente Colorado

Sheana Bull, PhD
University of Colorado School of Public Health

Keywords

Text Messaging; Artificial Intelligence; Chatbots; Health Behaviors

Key Points

  • Ample evidence now exists demonstrating the benefit of using text messaging in support of health behavior and access to care. It’s ubiquitous, increasing reach; theory in message design is impactful; and it can improve adherence to medical appointments and health behaviors.
  • Two NIH Collaboratory Trials, Nudge and Chat 4 Heart Health (C4HH), test the effectiveness of text messaging interventions to support behavior change. Nudge randomized patients to receive usual care, generic texts, behavioral texts, or behavioral texts plus chatbot messages. Their primary outcome was medication adherence.
  • C4HH, the subsequent trial, is randomizing patients to receive a generic text message curriculum; an AI chatbot messaging curriculum; or AI chatbot messages plus proactive pharmacist support. Their primary outcome is cardiovascular risk factors, as measured by the American Heart Association’s “Life’s Essential 8” adherence.
  • Nudge used an opt-out consent approach where CC4H used an opt-in consent approach. In the former, the research team noted, patients who identified as Black, Hispanic, and primary Spanish speakers were more likely to remain in the study. An opt-out approach in the appropriate context may be a way to diversify clinical trial populations and improve external validity of results.
  • The use of AI chatbots allows users to generate questions in their own words and the system to retrieve a response from a closed, curated library.
  • Message engagement is key to text messaging interventions. Participants in the Nudge study who were randomized to optimized texts had more questions. Questions were related to medications, refill logistics, and costs. The study team hypothesizes that the optimized texts may have led to greater patient engagement, and therefore more questions about their medications.
  • Over 12 months, the Nudge study found no significant difference in the rates of prescription refills, between the 3 intervention arms and usual care. CC4H is ongoing, and will send a higher volume of messages in an effort to engage patients and change patient behavior.
  • So far, the top 5 topics in messages initiated by C4HH participants have been healthy eating, physical activity, managing cholesterol, quitting smoking, and medication management.

Discussion Themes

The study team had to be very careful to ensure that patient health data, including cell phone numbers and the messages sent, were encrypted. Vendors and phone carriers were not able to access this data and it was not stored on their servers.

One of the challenges they encountered was that their systems weren’t integrated into the health care organizations’ pharmacies or electronic health records. The integration piece will be key to any future sustainability.

As technology evolves significantly over the course of, say, a 5-year study, developing the skillset to utilize interactive interventions or a SMART design could be helpful for investigators interested in conducting research in this area.