Pratik Shah

Faculty Member and Assit. Professor, Pathology
School of Medicine

Faculty Member and Professor, Biomedical Engineering
The Henry Samueli School of Engineering

Faculty Member and Professor, Electrical Engineering and Computer Science
The Henry Samueli School of Engineering

Computer Science, Biomedical Engineering, Generative AI in Healthcare, Computational Pathology, Cancer Diagnostics, Infectious Diseases, Regulatory Science, Deep Learning, Clinical Decision Making, Clinical Validation, Computer Vision

https://www.pratikfacultylab.org/

https://www.pratiks.info/

https://www.linkedin.com/in/pratikshahUCI

Media Coverage

1. FDA advisory panel sees heightened risk in connection with GenAI, BioWorld MedTech, 11/24/2024

2. Deep learning accurately stains digital biopsy slides, MIT News, 05/22/2020

3. Faster Drug Approvals Possible as AI Speeds FDA Reviews, Bloomberg Law, 04/29/2019

4. "Unorthodox" AI Helps Identify Best Cancer Treatments, IEEE Spectrum, 08/17/2018

2018 – 2022
Principal Investigator & Director
Machine Learning for Health Research Program
Program in Media Arts & Sciences & Media Lab
Massachusetts Institute of Technology
Cambridge, MA

2015 – 2018
Research Scientist & Principal Investigator
Program in Media Arts & Sciences & Media Lab
Massachusetts Institute of Technology
Cambridge, MA

2009 - 2014
ECOR Fund for Medical Discovery Fellow
Broad Institute of MIT & Harvard
Harvard Medical School
Massachusetts General Hospital
Boston, MA

Dr. Pratik Shah is the Principal Investigator and director of a computational medicine research program. The lab focuses on hypothesis-driven deep learning, generative AI, biomedical engineering, and clinical research to develop medical technologies for diagnosing and treating cancer and infectious diseases. This research invents novel deep learning, biological, and statistical methods to tackle challenges in personalized medicine. Dr. Shah's work includes advancements in generating medical images for unbiased, patient-centered care, and evaluating the impact of clinical decision-making on infectious diseases and antimicrobial therapy, within a unified theoretical and methodological framework. Recent work from the lab has been published in Cell Press journals including Cell Reports Methods and Trends in Pharmacological Sciences; Nature Digital Medicine; the Journal of the American Medical Association Network; leading machine learning conferences, and workshop proceedings of The National Academies of Sciences, Engineering, and Medicine. Dr. Shah and his research group are developing a dynamic, living-systems framework for computational medicine, transitioning from static models to real-time, systems-wide perspectives on molecular and clinical processes. Their goal is to invent, clinically validate, and deploy trustworthy generative AI medical technologies that improve patient outcomes and public health.

2026 — University of California, Irvine: Chancellor’s Award for Trainee Mentorship & Support
2024–2028 — U.S. Food & Drug Administration: Special Government Employee
2024 — TED Conferences: Fellows' Selection Committee
2022 — IEEE International Symposium on Biomedical Imaging: Conference Session Chair Selection
2019–2021 — TED Conferences: TED Senior Fellow
2018–2019 — AAAS–Lemelson Foundation: Invention Ambassador
2017–2018 — TED Conferences: TED Fellow
2016 — INK Talks: INK Fellow Selection
2016 — Gordon Research Conference: Conference Talk Award
2014 — Gordon Research Seminar: Conference Grant
2010–2011 — Massachusetts General Hospital, Harvard Medical School: ECOR Fund for Medical Discovery Postdoc Fellowship Award
2009 — American Society for Microbiology: Raymond D. Sarber Best PhD Dissertation National Award

Dr. Pratik Shah is a professor at the University of California and the principal investigator and director of a computational medicine research program. Dr. Shah holds academic appointments in Pathology & Laboratory Medicine and joint appointments in Electrical Engineering & Computer Science and Biomedical Engineering. He serves as a Special Government Employee for the U.S. Food and Drug Administration and was an invited expert panelist at the inaugural FDA Digital Health Advisory Committee meeting on generative AI-enabled devices. In 2026, he delivered the plenary keynote at SCOPE X, a national conference on data strategies and AI innovation in clinical research. Recent work from his lab has been published in Cell Press journals including Cell Reports Methods and Trends in Pharmacological Sciences; Nature Digital Medicine; the Journal of the American Medical Association Network; leading machine learning conferences, and workshop proceedings of The National Academies of Sciences, Engineering, and Medicine. Previously, Dr. Shah was a Principal Investigator at the Massachusetts Institute of Technology (MIT), where he led a computational medicine research program. He also served as principal investigator for a memorandum of understanding with the U.S. FDA and MIT, aimed at establishing AI and machine learning research ecosystems for clinical development. Dr. Shah holds a BS, MS, and PhD in biological and data sciences and completed postdoctoral fellowship training at the Broad Institute of MIT and Harvard, Massachusetts General Hospital, and Harvard Medical School.

1. Generative deep learning for computational destaining and restaining of unregistered digital pathology images. 25^th IEEE International Conference on Machine Learning and Applications (ICMLA). Accepted for publication, 2026. arXiv:2605.14251. Kulkarni A, Lowe A, Shah P*. [https://arxiv.org/abs/2605.14251]*=Senior author supervising research

2. Deep learning for generating computational PIN-4 immunohistochemistry staining from prostate biopsy H&E images. 25^th IEEE International Conference on Machine Learning and Applications (ICMLA). Accepted for publication, 2026. arXiv:2606.01871. Tran V, Shah P*. [https://arxiv.org/abs/2606.01871]*=Senior author supervising research

3. Deep learning with uncertainty quantification for predicting the segmentation dice coefficient of prostate cancer biopsy images. 23^rd IEEE International Conference on Machine Learning and Applications (ICMLA). 2024 December 18-20. DOI: 10.1109/ICMLA61862.2024.00178. Xie A, El Fatimi E, Ghosal S, Shah P*. [https://ieeexplore.ieee.org/document/10903494]*=Senior author supervising research

4. Uncertainty quantified deep learning and regression analysis framework for image segmentation of skin cancer lesions. 23^rd IEEE International Conference on Machine Learning and Applications (ICMLA). 2024 December 18-20. DOI: 10.1109/ICMLA61862.2024.00080. El Fatimi E, Shah P*. [https://ieeexplore.ieee.org/document/10903456]*=Senior author supervising research

5. A deep-learning toolkit for visualization and interpretation of segmented medical images. Cell Reports Methods. 2021 Nov 22; 1(7):100107. Ghosal S, Shah P*. [https://www.cell.com/cell-reports-methods/fulltext/S2667-2375(21)00166-1]*=Senior author supervising research

6. Use of deep learning to develop and analyze computational hematoxylin and eosin staining of prostate core biopsy images for tumor diagnosis. JAMA Network. 2020 May 01; 3(5):e205111. Rana A, Lowe A, Lithgow M, Horback K, Janovitz T, Da Silva A, Tsai H, Shanmugam V, Bayat A, Shah P*. [https://jamanetwork.com/journals/jamanetworkopen/fullarticle/2766071]*=Senior author supervising research

7. Artificial intelligence and machine learning in clinical development: a translational perspective. Nature Digital Medicine . 2019; 2:69. Shah P*, Kendall F, Khozin S, Goosen R, Hu J, Laramie J, Ringel M, Schork N. [https://www.nature.com/articles/s41746-019-0148-3]*=Senior author supervising research

8. Artificial intelligence for clinical trial design. Cell Trends Pharmacol Sci. 2019 Aug; 40(8):577-591. Harrer S, Shah P, Antony B, Hu J. [https://www.cell.com/trends/pharmacological-sciences/fulltext/S0165-6147(19)30130-0]*=Senior author supervising research

9. Reinforcement learning with action-derived rewards for chemotherapy and clinical trial dosing regimen selection. Proceedings of Machine Learning Research 2018; 85:161–226. Gregory Yauney, Pratik Shah*. [https://proceedings.mlr.press/v85/yauney18a.html]*=Senior author supervising research

10. Technology-enabled examinations of cardiac rhythm, optic nerve, oral health, tympanic membrane, gait and coordination evaluated jointly with routine health screenings. The British Medical Journal. 2018 Apr 20; 8(4):e018774. Shah P*, Yauney G, Gupta O, Patalano Ii V, Mohit M, Merchant R, Subramanian SV. [https://bmjopen.bmj.com/content/8/4/e018774.long]*=Senior author supervising research

Virtual Digital Histopathology with Explainable Deep Learning for Prostate Diagnosis. NIH/NCI R21 Sep 1, 2024 - Aug 31, 2027. Role: Principal Investigator

Biomedical Engineering

Cellular and Molecular Biosciences

Electrical Engineering and Computer Science

Link to this profile
https://faculty.uci.edu/profile/?facultyId=7154

Last updated
08/18/2026