Lab profile
About Duke AI Health
Duke AI Health connects, strengthens, amplifies, and grows multiple streams of theoretical and applied research on artificial intelligence and machine learning to answer urgent and difficult challenges in medicine and population health. Designed as a multidisciplinary, campus-spanning initiative, AI Health harnesses expertise across multiple schools, centers, and institutes at Duke to bring to bear the power of machine learning and related quantitative fields on medicine, healthcare delivery, and the health of individuals and communities.
01 · Research focus
Research areas and highlights
Topics and recent work as stated on the lab’s own site.
- CACHE - Collaborative to Advance Clinical Health EquityProjects leveraging data science and predictive modeling to identify and mitigate healthcare disparities.
- Reducing Maternal MorbidityAddressing elevated maternal mortality rates, especially for Black women, tied to cardiovascular disease risk factors.
- Prostate Cancer Screening ReferralImproving timely follow-up with urology specialists for Black men following abnormal PSA test results.
- Colorectal Cancer ScreeningAddressing disparities in CRC screening rates, particularly among African American adults.
- Cardiovascular Disease Risk Prediction for Women with Adverse Pregnancy OutcomesApplying machine learning methods to predict and prevent cardiovascular disease in women with adverse pregnancy outcomes.
- Evaluation of AI Tools in HealthcareDeveloping structured frameworks to evaluate generative AI and large language models in clinical settings.
- Early Prediction of Mental Health Risk in AdolescentsUsing AI advances to accurately predict psychiatric outcomes for individuals.
02 · People
Leadership and researchers
People listed on the lab’s team pages, by role.
03 · Research intelligence
Research Intelligence evidence
Publications, grants and clinical trials linked to the lab’s researchers in Health AI Central’s research data.
Publications & preprints
- MAGIC: an international network for evaluating generative artificial intelligence in global health.Nature medicine · 2026
- A distribution-aware optimization model for improving operating room utilization and out-patient flow.Health care management science · 2026
- SegmentAnyMuscle: A universal muscle segmentation model across different locations in MRI.Computers in biology and medicine · 2026
Active NIH grants
- AI-driven Multimodal Model for PrEP Candidacy Assessment in Women (AiM-PrEP)Nrupen Bhavsar · NIMH · FY 2026
- Model and Data Sharing CoreNrupen Bhavsar · NIAID · FY 2026
- Assimilating high-resolution behavioral and neural data across heterogeneous experimental configurationsTimothy Dunn · NIDA · FY 2026
04 · Updates
Updates and lab news
News and events from the lab’s own site.
- Discovering how neighborhoods and built environments intersect with health through the SEED Health AtlasEventSep 11, 2026 · aihealth.duke.edu
- Registration now open: Third Annual Duke Summit on AI for Health InnovationAnnouncementAug 5, 2026 · aihealth.duke.edu
- Please Save the Date for our Third Annual Duke Summit on AI for Health InnovationNewsMay 5, 2026 · aihealth.duke.edu
- Tackling Hypertension at Duke Health: The HTN MAP ProgramNewsMay 4, 2026 · aihealth.duke.edu
- REWIND: AI Health Seminar Series, The Protected Research Compute Cluster (PRCC)NewsApr 28, 2026 · aihealth.duke.edu
- AI Health Director of Data Science Takes Part in Department of Medicine AI SymposiumNewsApr 27, 2026 · aihealth.duke.edu
- Case Study by Duke Authors Highlights Ethical, Clinical Tensions in AI-Generated Health InformationNewsApr 23, 2026 · aihealth.duke.edu
- PREVENT Study Highlighted at International Stroke ConferenceNewsApr 22, 2026 · aihealth.duke.edu
05 · Official presence
Lab sources and channels
The lab’s own pages and accounts.
06 · Related
Related labs and centers
Labs at the same institution and labs working on similar topics.