People > Profile
Harry Hochheiser, PhD
- Professor of Biomedical Informatics
- Director, Biomedical Informatics Training Program
Department of Biomedical Informatics (DBMI) | University of Pittsburgh School of Medicine
Biography
Harry Hochheiser is a Professor in the Department of Biomedical Informatics at the University of Pittsburgh and Director of the Biomedical Informatics Training Program. He holds secondary appointments in the Intelligent Systems Program, the Clinical and Translational Science Institute, and the UPMC Hillman Cancer Center. Trained as a computer scientist, Dr. Hochheiser’s research spans biomedical informatics, human-computer interaction, data visualization, natural language processing, and the design and evaluation of health information systems. He has contributed to interactive phenotype modeling, clinical NLP for cancer registry abstraction, infectious disease modeling reproducibility, and the development of user-centered tools that make complex biomedical data more accessible for clinicians and researchers.
Research Interests
Dr. Hochheiser’s research focuses on biomedical informatics, human-computer interaction, and methods for making complex biomedical and clinical data more accessible and useful. His work has advanced interactive visualization, phenotype modeling, natural language processing for clinical text (including cancer registry abstraction through the DeepPhe project), and the design of tools supporting clinicians and researchers. He is currently leading work on AI-enabled cancer chatbots for symptom education, infectious disease modeling reproducibility, and a biomedical informatics training program funded by the NIH National Library of Medicine.
Specialties
- Human-Computer Interaction
- Population Health Informatics
- Clinical Natural Language Processing
- Biomedical Data Visualization
- Phenotype Modeling
Websites & Links
Education & Training
- B.S./M.S., Electrical Engineering and Computer ScienceMassachusetts Institute of Technology, Cambridge, MA1985–1991
- Ph.D., Computer ScienceUniversity of Maryland, College Park, MD1998–2003
- Postdoctoral FellowNational Institute on Aging, Baltimore, MD2003–2006
Representative Publications
Horvat CM, Barda AJ, Perez Claudio E, et al. Interoperable Models for Identifying Critically Ill Children. JAMIA. 2025.
Pokutnaya D, Van Panhuis W, Childers B, et al. Inter-rater reliability of the infectious disease modeling reproducibility checklist. BMC Infectious Diseases. 2024.
Barda AJ, Horvat CM, Hochheiser H. A qualitative research framework for user-centered displays of ML model explanations in healthcare. BMC Medical Informatics and Decision Making. 2023.
Savova GK, Tseytlin E, Finan S, et al. DeepPhe: A natural language processing system for extracting cancer phenotypes from clinical notes. JAMIA. 2017.
Lazar J, Feng JH, Hochheiser H. Research Methods in Human-Computer Interaction. Morgan Kaufmann. 2017.
Research Grants
| Grant / Funding Agency | Role | Grant Number | Years |
|---|---|---|---|
| AI-CChaSE: AI-enabled Cancer CHatbots for Symptom Education NIH/NCI | MPI | R01CA311924 | 2026–2031 |
| MIDAS Coordination Center – Year 6–10 NIH/NIGMS | PI | R24GM153920 | 2024–2029 |
| Cancer Deep Phenotype Extraction from Electronic Medical Records (renewal) NIH/NCI | MPI | U24CA248010 | 2025–2030 |
| Pittsburgh Biomedical Informatics Training Program NIH/NLM | PI | T15LM007059 | 2022–2027 |
| Bio-digital Rapid Alert to Identify Neuromorbidity NIH/NINDS | MPI | R01NS118716 | 2021–2026 |