AI Technology for Molecular Phenotyping and Clinical Decision Making

AI Technology for Molecular Phenotyping and Clinical Decision Making

Research studies led by Dr. Shah have developed explainable AI and machine learning systems that learn from diverse and inclusive datasets for ethical clinical use and testing of experimental medicines and biologically relevant disease subtypes. Real World Data (RWD) and Real World Evidence (RWE) are playing an increasing role in healthcare decisions to support innovative use of Electronic Health Records, genomic sequencing and other digital sources to benefit from experimental and existing treatments often tested on smaller cohorts of patients (Project and publication link). For example: phase 3 clinical trials evaluating new therapies and vaccines are among the most complex experiments performed in medicine on small numbers of eligible patients. Around 50% of phase 3 trials fail and in some cases lead to adverse events. This high failure rate also counteracts patients consenting to treatments by experimental therapies as the last resort discussed in a review co-authored by Dr. Shah in a Cell press journal (Publication link) . The FDA states that another significant challenge is the difficulty of predicting clinical results in a wider patient base in the real world vs. phase 3 randomized trials. Example of research projects, collaborations and resulting peer-reviewed publications led by Dr. Shah are listed.

  • In a research study led by Dr. Shah novel and non-trivial reward functions for self-learning Reinforcement Learning (RL) algorithms for dose de-escalation studies during clinical trials to alleviate chemotherapy toxicity have been developed . These algorithms learn reward contribution from physician actions and patient states/health without future survival/outcomes information to solve fundamental problems in clinical development of medicines (Project and publication link).
  • Dr. Shah served as the sole principal investigator on the Memorandum of Understanding (MOU) with the United States FDA signed to engender AI and ML research for computational medicine and clinical development. Research activities led by Dr. Shah as the Principal Investigator under this MOU focus on three key themes for development of next-generation medicines by adoption of digital evidence generated by AI and ML: (1) validation and modernizing the clinical trials process, (2) strategies for rational use of AI- and ML-driven learning from real-world data and evidence and, (3) regulatory framework to improve health outcomes for patients and oversight for integration, explanation, and de-risking of AI/ML digital analytics in medical care to patients. Key summary of this MOU was published as a perspective in Nature Digital Medicine (Publication link).
  • In collaboration with regulatory agencies and clinical partners, a regulatory path for AI and ML software as a medical device and digital medicines developed by Dr. Shah and his laboratory has been initiated (Project and publication link, Presentation link). This research classifies, predicts and enriches novel digital endpoints from molecular data to benefit patient health, eliminate adverse events, and improve outcomes. This work has significant impact on the ethical decisions facing patients and their families, and regulatory decisions for US FDA and European Medical Agency (Project and publication link).


Reinforcement learning with action-derived rewards for chemotherapy and clinical trial dosing regimen selection

Gregory Yauney, Shah P*

(*Senior author supervising research)

Proceedings of the 3rd Machine Learning for Healthcare Conference. PMLR 85:161-226



Artificial intelligence and machine learning in clinical development: a translational perspective

Pratik Shah* et al.

(*Corresponding author)

Nature Digital Medicine. DOI: 10.1038/s41746-019-0148-3



Artificial Intelligence for clinical trial design

Stefan Harrer, Shah P, Antony P, Hu J

Trends in Pharmacological Sciences. PMID: 31326235


Improving cancer diagnosis and care: clinical application of computational methods in precision oncology

Proceedings of a Workshop, National Academies of Sciences, Engineering, and Medicine. Washington, DC: The National Academies Press. PMID: 31386317



Artificial neural networks detect and classify hematologic malignancies or solid tumors using electronic medical records prior to clinical diagnosis

Yujia Zhou, Barnes C, Magoc T, Lipori G, Shah P, Cogle CR

Published at 61st American Society of Hematology Annual Meeting, Orlando, FL

Published at 61st American Society of Hematology Annual Meeting, Orlando, FL


Data science in clinical pharmacology and drug development for improving health outcomes in patients

Pratik Shah, Peck R, Vamvakas S, van der Graaf, Piet H

Clinical Pharmacology and Therapeutics. PMID: 32202650

AI for drug discovery sketch


  • R1 - Framework for FDA’s Real-World Evidence Program [PDF]
  • R2 - 22 Case Studies Where Phase 2 and Phase 3 Trials had Divergent Results [PDF]
  • R3 - FDA MOU [Link]

Select Talks



Pratik Shah invited to speak at Brown University

November 19, 2018
Providence, RI

Digital Clinical Trials with Novel Machine Learning and AI Architectures
Digital Clinical Trials with Novel Machine Learning and AI Architectures

October 29, 2018 - October 30, 2018
Washington, DC

Pratik Shah @ Conference on Neural Information Processing Systems

December 2, 2018 - December 8, 2018