Skip to main content

Michael J Pencina

Adjunct Professor in the Department of Biostatistics & Bioinformatics
Biostatistics & Bioinformatics, Division of Biostatistics
Duke Box 2927, Durham, NC 27710
200 Trent Drive, M144 Davison Bldg, Durham, NC 27705
Office hours

8:00am - 5:00pm ET

  

Overview


Positions

  • Adjunct Professor in the Department of Biostatistics & Bioinformatics
  • Former Chief Data Scientist for Duke Health


Michael J. Pencina, PhD

Adjunct Professor, Biostatistics & Bioinformatics
Former Chief Data Scientist, Duke Health
Duke University School of Medicine

Michael J. Pencina, PhD, currently serves as UnitedHealth Group chief AI scientist, where he leads data science initiatives to enhance the organization’s innovative use of responsible AI systems that deliver real-world impact at scale for patients, providers, consumers and health plan members.  He is also adjunct professor of biostatistics and bioinformatics at Duke University School of Medicine.  He formerly served as Chief Data Scientist at Duke Health.

Dr. Pencina is an internationally recognized authority in the development, evaluation and responsible application of AI algorithms. His work pioneered new methods for assessment of predictive algorithms and helped establish frameworks for intentional governance of health AI systems. Expert societies and guideline groups have relied on his work to advance best practices for the application of clinical decision support tools in health delivery.  Since 2014, Thomson Reuters/Clarivate Analytics has regularly recognized Dr. Pencina as one of the world’s "highly cited researchers" in clinical medicine and social sciences, with more than 400 publications cited over 150,000 times.

He co-founded the national Coalition for Health AI (CHAI), a multi-stakeholder effort whose mission is to increase trustworthiness of AI by developing guidelines to drive high-quality health care through the implementation of innovative, credible, and transparent health AI systems. He also spearheaded establishing and co-led Duke Health’s Algorithm-Based Clinical Decision Support (ABCDS) Oversight Committee.

Dr. Pencina joined the Duke University faculty in 2013, and served as director of biostatistics for the Duke Clinical Research Institute until 2018. Previously, he was an associate professor in the Department of Biostatistics at Boston University and the Framingham Heart Study, and director of statistical consulting at the Harvard Clinical Research Institute. He received his PhD in Mathematics and Statistics from Boston University in 2003 and holds master’s degrees from the University of Warsaw in actuarial mathematics and business culture.

Email: michael.pencina@duke.edu

Web Sites:  medschool.duke.eduaihealth.duke.eduhttps://scholars.duke.edu/person/michael.pencina

Phone:  919.613.9066

Address:  Duke University School of Medicine; 2424 Erwin Road, Suite 903; Durham, NC 27705

Current Appointments & Affiliations


Adjunct Professor in the Department of Biostatistics & Bioinformatics · 2025 - Present Biostatistics & Bioinformatics, Division of Biostatistics, Biostatistics & Bioinformatics
Director of Duke AI Health · 2021 - Present School of Medicine

In the News


Published May 23, 2025
Provost Launches AI Initiative and Steering Committee
Published March 13, 2024
Coalition for Health AI (CHAI) Announces Founding Partners
Published March 11, 2024
New consortium of healthcare leaders announces formation of Trustworthy & Responsible AI Network (TRAIN), making safe and fair AI accessible to every healthcare organization

View All News

Recent Publications


Lifetime Adverse Pregnancy Outcome History and Cardiovascular Risk.

Journal Article Hypertension · March 20, 2026 BACKGROUND: Few studies have examined how multiple types of adverse pregnancy outcomes across women's reproductive lives relate to long-term cardiovascular disease. METHODS: In 59 154 parous participants in Nurses' Health Study II, lifetime history of gest ... Full text Link to item Cite

Criteria to Assess the Predictive and Clinical Utility of Novel Models, Biomarkers, and Tools for Risk of Cardiovascular Disease: A Scientific Statement From the American Heart Association.

Journal Article Circulation · March 17, 2026 Risk prediction has been used in the primary prevention of cardiovascular disease for >3 decades. Contemporary cardiovascular risk assessment relies on multivariable models, which integrate established cardiovascular risk factors and have evolved over time ... Full text Link to item Cite
View All Publications

Recent Grants


1/3 CTSA UM1 at Duke University

ResearchFaculty Member · Awarded by National Institutes of Health · 2025 - 2032

2/3 CTSA K12 Program at Duke University

ResearchMentor · Awarded by National Institutes of Health · 2025 - 2030

Implementation partner-guided strategy to promote health equity in ICU prognostication

ResearchCo-Principal Investigator · Awarded by National Institutes of Health · 2025 - 2029

View All Grants

Education


Boston University · 2003 Ph.D.