The Duke AI Health Community of Practice is pleased to announce our third Foundations of Scientific Writing Workshop Series, which will take place in the fall of 2025. Intended primarily for staff members interested in gaining experience with the basics of scholarly writing and publication, this mini-course consists of four virtual weekly classes that combine lecture and interactive elements, and culminates in the presentation of a final project in a poster session that will be held in December of this year.

REGISTER

Duke AI Health Director Michael Pencina, PhD, recently took part in webinar hosted by Newsweek. The webinar, titled “”Health Care’s AI Playbook: Building Safe, Smart and Scalable Systems,” covered topics in AI governance and implementation for an audience of healthcare system leaders and included other participants representing industry and the nonprofit Coalition for Health AI (CHAI), of which Duke is a founding member. A summary of the event by Newsweek’s Alexis Kayser, together with a complete video recording of the hour-long webinar, is available online via Newsweek (free registration required to access). READ MORE

Dr. Connor Drake, Assistant Professor, Department of Population Health Sciences, represented a team of researchers from Duke Health, Duke Department of Population Health Sciences, and CACHE as he presented the initial findings the Eat Well trial at the May 2025 annual meeting of the Society of General Internal Medicine (SGIM) in Hollywood, Florida. Eat Well is a large-scale randomized controlled trial that was conducted at Duke to test the impact of a program of “prescription produce” on cardiometabolic outcomes. The produce prescription reduces cost barriers to healthy eating and was offered to Duke patients with elevated HbA1c levels who were at risk for food insecurity. Food insecurity is a major obstacle to improve health outcomes and equity and the findings suggest that there are key implementation factors that influence the impact of these programs in real-world care settings. LEARN MORE

This spring’s Duke Critical Care Datathon brought together more than 150 clinicians, data scientists, engineers, and students from across Duke University, Research Triangle Park and beyond for a three-day exploration of critical-care data science. Held April 25–27 at the Duke Health Center for Interprofessional Education and Care, the event combined expert-led sessions, hands-on team challenges and prototype presentations to accelerate innovations in patient monitoring, predictive modeling, and clinical decision support. This event was made possible by the generous support of Mark III Systems/NVIDIA and CloudForce. Their commitment to advancing healthcare AI provided essential computing resources, seed data science mentorship and prize funding that empowered participants to push the boundaries of critical-care analytics. We also thank our mentors, judges, and organizers—Jeremy Tan, Gloria Hyunjung Kwak, Ahram Han, Yueran Jia, Nikki Boatenhamer Freeman, Hyeon-Chul Lee and Hyung-Chul Lee—whose expertise and dedication guided each team. Datasets were graciously provided by Seoul National University Hospital, CHoRUS, MIT Critical Data and Epic Cosmos.

READ MORE

Dr. Michael Cary joined an esteemed panel at the 2025 Symposium for Artificial Intelligence in Learning Health Systems (SAIL), moderated by Dr. Brendan Carr (CEO, Mount Sinai Health System), explored the transformative effects of AI on the healthcare workforce, with a special emphasis on nursing. Alongside Drs. Kenrick Cato (University of Pennsylvania) and Patricia Sengstack (Vanderbilt University), Dr. Cary discussed both the promises and concerns of AI integration, reflecting current challenges and future directions for building a workforce that is AI-ready.

READ MORE

An article that originally appeared in Duke Today describes a new AI initiative and accompanying steering committee at Duke University, helmed by Provost Alec D. Gallimore. The initiative, which encompasses the University, the School of Medicine, the School of Law, and many other departments, institutes, and centers, reflects months of development and feedback from academic leadership and faculty experts, including Duke AI Health Director Michael Pencina and Faculty Council member Ricardo Henao. Comprising four major pillars (Life with AI, Trustworthy and Responsible AI, Sustainability in AI, and Advancing Discovery with AI), the initiative is served by a new dedicated website.

READ MORE

Presented by Anthony Sorrentino, MD, Clinical Informatics Fellow at Duke University Health System and Primary Care Doctor at Duke Primary Care Riverview, this session explores the strengths and limitations of clinical registry data in research. While real-world data sources such as EHRs and medical claims are widely used, clinical registries stand out for containing detailed, manually abstracted outcomes data. Dr. Sorrentino discusses the challenges of working with registry data, including siloed storage, limited access, and complex governance. He introduces Duke’s pilot data mart, which links multiple clinical registries with EHR data to enable broader research use, and highlights design strategies, key barriers encountered, and ongoing efforts to transform registry data into a more integrated and accessible research asset. WATCH

The Duke Health team, led by Dr. Ben Goldstein and including Dr. Armando Bedoya, Dr. Michael Cary, Dr. Matt Engelhard, Dr. Chuan Hong, Dr. Rishi Kamaleswaran, and AI Health fellow Scott Sun, traveled to Singapore in April to strengthen partnerships with Duke-NUS Medical School. The team engaged with DAISI (Duke-NUS AI + Medical Sciences Initiative), Duke-NUS leadership, and SingHealth to explore collaborative opportunities. The visit culminated in the Health Data Science Symposium, featuring Dr. Goldstein’s keynote on building successful clinical AI partnerships across research, education, and clinical implementation, followed by individual talks and participation in panel discussions by team members. LEARN MORE