Research studies led by Dr. Shah, in collaboration with the United States Food and Drug Administration (FDA), have developed explainable AI and machine learning systems that learn from diverse and inclusive datasets for ethical clinical use and testing of experimental medicines. 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 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 is the lead Principal Investigator on the Memorandum of Understanding (MOU) 'Health 0.0' between MIT and the United States FDA signed to engender AI and ML research for computational medicine and clinical development. Research activities 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 for 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 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).
- Dr. Shah, with collaborators from Harvard Medical School and biostatisticians, are investigating the use of observational RWD and RWE to supplement randomized data to train neural networks cognizant of causal inference.