People > Profile
Gregory F. Cooper, MD, PhD
- Distinguished Professor of Biomedical Informatics
- Vice Chair, Department of Biomedical Informatics
- Professor of Intelligent Systems
Department of Biomedical Informatics (DBMI) | University of Pittsburgh School of Medicine
Biography
Dr. Gregory F. Cooper is Distinguished Professor of Biomedical Informatics at the University of Pittsburgh and serves as Vice Chair of the Department of Biomedical Informatics. Trained in computer science, medical information sciences, and medicine, he has been a leader in biomedical artificial intelligence for several decades. His research focuses on Bayesian networks, causal discovery, clinical decision support, biosurveillance, and predictive modeling from biomedical data. He has also held leadership roles in the Center for Biomedical Informatics and the Biomedical Informatics Training Program at the University of Pittsburgh.
Computational & Clinical Expertise
Dr. Cooper’s expertise lies at the intersection of medicine, biomedical informatics, and artificial intelligence. His work has focused on computer-based clinical decision support, probabilistic diagnosis, predictive modeling, and the analysis of electronic clinical data to improve diagnosis, surveillance, and patient care.
Research Interests
Dr. Cooper’s research centers on the development and application of probabilistic and causal methods in biomedicine. His work has advanced Bayesian networks, causal discovery algorithms, predictive modeling, and anomaly detection using clinical, genomic, and public health data. He has applied these methods to areas such as diagnostic reasoning, outbreak detection, precision oncology, patient-specific prediction, and learning from electronic medical records. A major theme of his research is building interpretable AI methods that support biomedical discovery and clinical decision-making.
Specialties
- Bayesian Networks
- Causal Discovery
- Clinical Decision Support
- Machine Learning in Medicine
- Biosurveillance
- Biomedical Artificial Intelligence
Education & Training
- B.S., Computer ScienceMassachusetts Institute of Technology, Cambridge, MA1973-1977
- Ph.D, Medical Information SciencesStanford University, Palo Alto, CA1977-1985
- M.D., MedicineStanford University, Palo Alto, CA1977-1986
- Postdoctoral Training, Medical InformaticsStanford University, Palo Alto, CA1986-1987
Awards & Distinctions
- FellowAmerican College of Medical Informatics1991
- Distinguished Paper AwardAmerican Medical Informatics Association Annual Symposium2005
- FellowAssociation for the Advancement of Artificial Intelligence2006
- UPMC Endowed ChairUniversity of Pittsburgh2018–present
Representative Publications
Cooper GF, Herskovits EH. (1992). A Bayesian method for the induction of probabilistic networks from data. Machine Learning, 9, 309–347.
Chapman WW, Bridewell W, Hanbury P, Cooper GF, Buchanan BG. (2002). A simple algorithm for identifying negated findings and diseases in discharge summaries. Journal of Biomedical Informatics, 34, 301–310.
Seymour CW, Kennedy JN, Wang S, et al. (2019). Derivation, validation, and potential treatment implications of novel clinical phenotypes for sepsis. JAMA, 321(20), 2003–2017.
Aronis JM, Ye Y, Espino J, Hochheiser H, Michaels MG, Cooper GF. (2024). A Bayesian system to detect and track outbreaks of influenza-like illnesses including novel diseases. JMIR Public Health and Surveillance, 10.
Ren S, Cooper GF, Chen L, Lu X. (2024). An interpretable deep learning framework for genome-informed precision oncology. Nature Machine Intelligence, 6, 864–875.