AI

Grand Rounds August 28, 2026: Evaluating Clinical Agentic AI (Haider Warraich, MD)

Posted on by Sophia Ramirez

Speaker

Haider Warraich, MD
Program Manager
ARPA-H (Advanced Research Projects Agency for Health)

Keywords

AI; Outpatient Care; Agentic AI; Heart Failure; Clinical Care

Key Points

  • The current state of outpatient care is sporadic and reactive. Low-value care leads to excess costs and harms, and clinical resources are wasted on administrative tasks. Clinical agentic AI could provide patients with round-the-clock access to specialty care and unlock the full potential of the Electronic Health Record and wearables.
  • ADVOCATE is envisioned as a patient-facing agentic AI system that can provide 24/7 clinical care as an extension of the care team. It would include administrative and wellness functions, like care navigation and diet and exercise recommendations; advanced decision support in regard to treatment and diagnosis; and high-risk functions, like prescription management. The ARPA-H team hopes it will transform advanced cardiovascular disease management.
  • Their current focuses are the development of an agent for patients with heart failure; the development of an independent supervisory agent to ensure continued agent accuracy and patient safety, particularly after clinical deployment; and recruitment of health systems for the design, development, and deployment of the technologies.
  • The clinical evaluation strategy for ADVOCATE will involve 3 phases: Human Factors Evaluation and simulated virtual patient testing; shadow-mode evaluation in clinically deployed settings; and a stepped-wedge multicenter cardiovascular outcomes trial.

Discussion Themes

While underlying foundation AI models possess broad medical knowledge, their autonomous actions must be strictly constrained to their labeled, intended use to maintain safety.

Heart failure was selected – as opposed to upstream prevention – in part because it is characterized by a highly algorithmic care path, a high event rate that generates clinical study data quickly, and strong financial incentives.

While the program initially targeted non-inferiority compared to a cardiologist, the metric was updated to require a superiority analysis against usual care.

Grand Rounds August 7, 2026: Adaptive AI for CV Adjudication: Adjudication Across Different Definitions in the ODYSSEY OUTCOMES and EUCLID Trials (Sreek Vemulapalli, MD; Ricardo Henao, PhD)

Posted on by Sophia Ramirez

Speakers

Sreek Vemulapalli, MD
Associate Professor of Medicine with Tenure
Director, CV Imaging, DUHS
Duke Clinical Research Institute
Duke-Margolis Institute for Health Policy

Ricardo Henao, PhD
Associate Professor
Department of Biostatistics & Bioinformatics
Department of Electrical and Computer Engineering
Department of Surgery
Associate Director of Clinical Trials AI, Duke Clinical Research Institute (DCRI)
Duke University

Keywords

Adjudication; AI; Clinical Event; Clinical Event Committees; Scalability

Key Points

  • The promise of clinical endpoint or event adjudication is standardization and the improvement of endpoint credibility. However, a human-centered review model utilizing Clinical Endpoint Committees (CECs) represents a major scalability constraint due to cost pressure, operational drag, and between-group variability.
  • AI could reduce the burden on CECs by separating confident events from cases requiring human review. Previous trials testing this concept have derived separate models for each event type and have no demonstrated ability to adapt to new definitions or endpoints across trials. The research team sought to develop and train an AI algorithm to perform clinical endpoint adjudication that can extend to new endpoint and trials. They then compared that algorithm’s performance to Chat GPT 4.0 and hybrid (AI + human) adjudication.
  • The research team found that a single AI algorithm trained on a single trial can, after brief adaptation, identify the same events with a new definition and identify new events. This was validated in the EUCLID trial, when the algorithm alone or as a hybrid strategy reproduced the EUCLID primary endpoint and effect size. While further prospective studies are needed, the potential impact of AI-enabled automated adjudication of outcomes on developing evidence is substantial.

Discussion Themes

The role of clinical adjudicators could shift toward auditing the AI, similar to the evolution of EKG reading, where experts focus on the 10% of cases where the algorithm is most likely to be wrong or uncertain.

The primary barriers to implementing AI systems that comb through electronic health records for trial data are governance, data security, and access rights, rather than a lack of technological capability.

While demonstrated here in cardiovascular trials, this methodology is theoretically applicable to other complex domains. To gain regulatory acceptance, the presenters suggested that prospective validation across multiple clinical research groups and a wide variety of endpoints will be necessary.

July 7, 2026: AI, Ethics, and Pragmatic Trials: An Interview With Jeremy Sugarman and Adrian Hernandez

Posted on by Damon Seils

The increasing presence of AI in healthcare settings and the use of AI tools in clinical trials raise questions about how these tools can be rigorously evaluated to generate the best evidence base for their potential benefits and harms. At the NIH Collaboratory’s 2026 Annual Steering Committee Meeting, we spoke with Jeremy Sugarman and Adrian Hernandez about AI, research ethics, and the role of pragmatic trials in evaluating new technologies.

“The are so many ways AI is being used in healthcare and in clinical trials; the key challenge is that the technologies are rapidly evolving,” Hernandez said. “Can we keep up with the evidence generation around that? And how do we deploy things into the healthcare system knowing that they can be trusted and won’t change over time?” Hernandez is a co–principal investigator for the NIH Pragmatic Trials Collaboratory Coordinating Center, professor of medicine at Duke University, and executive director of the Duke Clinical Research Institute.

Go to the full video.

“The hope for medicine is that [AI will] improve something in the way we deliver healthcare. There are multiple ways that might happen, through better therapeutics, through increasing efficiencies within healthcare systems, but we don’t know if any of that’s true,” added Sugarman, a cochair of the NIH Collaboratory’s Ethics and Regulatory Core and the Harvey M. Meyerhoff Professor of Bioethics and Medicine at Johns Hopkins University.

“That’s the point where pragmatic clinical trials can come in and say, if there’s some evidence, not just somebody’s hope or whim or aspiration, that one of these things could actually help with healthcare, then we want to test that, and we want to test it to make sure that it doesn’t make things actually worse—and that’s where the ethics comes in,” Sugarman said.

In the coming weeks, we will share more highlights from the 2026 Annual Steering Committee Meeting. Access the complete meeting materials.

Video still from an interview with Dr. Jeremy Sugarman and Dr. Adrian Hernandez
Dr. Jeremy Sugarman and Dr. Adrian Hernandez

May 21, 2026: New Podcast Episode Provides an Editor’s Perspective on the Role of AI in Scientific Publishing

Posted on by Sophia Ramirez

In a new episode of the Rethinking Clinical Trials Podcast, Roy Perlis of Harvard Medical School and JAMA+ AI expanded on key takeaways from his recent Grand Rounds presentation, “Keeping a Human in the Loop: Scientific Publishing and AI.”

Listen to the podcast. For alerts about new episodes, subscribe for free on Spotify, Amazon Music, Apple Podcasts, or SoundCloud.

Scientific communities are divided about the appropriate role of artificial intelligence (AI) in manuscript preparation or review. In the podcast, Perlis revealed some ways AI has made things harder for journals (the increased volume of “slop” submissions); ways it’s made things easier (the writing is better); and ways it might be leveraged to address the industry’s longstanding issues.

“I think AI is going to be very helpful to us in helping to streamline aspects of the peer review process,” Perlis said. “One of the big frustrations I hear from authors, one of my big frustrations as an author, is the incredibly long lag time between submitting something, getting reviews back, and turning it around. In my mind, it’s one way that we slow down science unnecessarily.”

The use of AI may save time and energy when it comes to the rote aspects of manuscript review, such as confirming that a research team followed their analytic protocol or met the criteria mandated by their study design.

“The part where I really value human input, and I think that the machines are still not great at, is: Is this innovative? Is it impactful? Is it significant? Is this really, for the average reader of this journal, going to be useful to them or important to them? I think that’s still very hard to automate,” said Perlis.

He identified trust and discovery as other institutional values that will be maintained through human intervention.

Perlis is a professor of psychiatry at Harvard Medical School. He serves as the director of the MGH Center for Quantitative Health and the editor in chief of JAMA+ AI.

Podcast May 20, 2026: Scientific Publishing and AI (Roy Perlis, MD, MSc)

Posted on by Sophia Ramirez

In this episode of the NIH Collaboratory Podcast, Roy Perlis of Harvard Medical School and JAMA+ AI expands on key takeaways from his recent Grand Rounds presentation, “Keeping a Human in the Loop: Scientific Publishing and AI.”

Transcript coming soon. For alerts about new episodes, subscribe for free on Spotify, Amazon Music, Apple Podcasts, or SoundCloud.

May 4, 2026: New Podcast Episode Considers Impact of New Digital Technologies on Pragmatic Trial Design

Posted on by Sophia Ramirez

In a new episode of the Rethinking Clinical Trials Podcast, Majid Afshar and Mary Ryan Baumann of the University of Wisconsin-Madison expanded on key takeaways from their recent Grand Rounds presentation, “A Pragmatic Randomized Controlled Trial of Ambient Artificial Intelligence (AI) to Improve Health Practitioner Well-Being.”

Listen to the podcast. For alerts about new episodes, subscribe for free on Spotify, Amazon Music, Apple Podcasts, or SoundCloud.

The need to document patient visits in the electronic health record is a driver of clinician burnout. The research team sought to assess whether the use of an ambient AI scribe could improve clinician well-being by automating the documentation process. In the podcast, Afshar and Ryan Baumann reflected on some of the forces that guided their trial design.

“The technology itself is in silo, right? The speech-to-text and text-to-speech and [large language models] are very good,” said Afshar. “I think the challenge is actually adapting it to the human use case… We spent a lot of time with our human factors engineering implementation scientists to make sure that the training and onboarding and the use of the tool was appropriate for given end users.”

According to Afshar, this predeployment step led to a fidelity rate of over of 70%.

Once the research team began collecting data, the combination of new digital technologies and a pragmatic setting posed its own set of challenges.

“The pure amount of information that’s coming from each participant is astounding,” said Baumann. “It’s not on a scale that you can look at each individual data point and necessarily understand: Is this an outlier? Did something weird happen on this one day? What are the other elements and factors within a health system that’s still operating as it normally does?”

Ultimately, the research team found a 20% reduction in burnout and a trend towards improvement in professional fulfillment. UW Health scaled the project from 66 to over 600 licenses.

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.

Podcast April 30, 2026: Ambient AI to Improve Health Practitioner Well-Being (Majid Afshar, MD, MS; Mary Ryan Baumann, PhD)

Posted on by Sophia Ramirez

In this episode of the NIH Collaboratory Podcast, Majid Afshar and Mary Ryan Baumann discuss the conduct and results of their pragmatic trial.

Transcript coming soon. For alerts about new episodes, subscribe for free on Spotify, Amazon Music, Apple Podcasts, or SoundCloud.

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.