Novel ethical and explainable artificial intelligence based digital medicines and treatments
We have described validation of novel machine learning architectures for designing faster, safer, and more efficacious digital medicines in our published research findings . This work has significant impact on the ethical decisions facing patients and their families, and regulatory decisions for the United States Food and Drug Administration (FDA) and European Medical Agencies (EMA). For example: Phase 3 clinical outcome trials evaluating new therapies, and vaccines are among the most complex experiments performed in medicine. Around 50% of Phase 3 trials fail. The US FDA states that a common theme is the difficulty of predicting clinical results in a wide patient base. More importantly, the barriers to this cost healthcare industries, government, and academic research hospitals millions of dollars each year, as well as drive up costs, delay life-saving treatments to patients, and in some cases lead to adverse events . We invent ethical and explainable AI and machine learning systems which learn from diverse and inclusive datasets. Our research classifies, predicts and enriches novel digital endpoints to benefit patient health, eliminate adverse events, and improve outcomes while managing diseases and pioneers a regulatory path for AI and ML in medical care.
Reinforcement learning with action-derived rewards for chemotherapy and clinical trial dosing regimen selection. 2018. [Abstract] [Full Paper]
Gregory Yauney, Shah P*
(*Senior author supervising research)
Proceedings of the 3rd Machine Learning for Healthcare Conference, PMLR 85:161-226
Machine learning and Artificial Intelligence in clinical development: a translational perspective. 2019.
Pratik Shah* et al.
Nature Digital Medicine-(Accepted for publication)
Artificial Intelligence for clinical trial design. 2019.
Stefan Harrer, Shah P, Antony P, Hu J
Trends in Pharmacological Sciences-(Accepted for publication)
- 22 Case Studies Where Phase 2 and Phase 3 Trials had Divergent Results [PDF]
- 2019 - Artificial intelligence and machine learning for regulatory science and clinical development applications
- 2019 - Machine learning and computational medicine for clinical development, patients and regulators
- 2018 - Data regulation and privacy for clinical trials
- 2018 - Digital clinical trials for oncology patients with novel machine learning and AI architectures
- 2018 - Future of digital medicine and clinical trials with novel machine learning and AI architectures
- 2018 - Panel discussion: The ethics and governance of Artificial Intelligence
- 2017 - Artificial Intelligence in Clinical Development to Improve Public Health
- 2019 - Pratik Shah invited to join editorial leadership of The American Society for Clinical Pharmacology & Therapeutics flagship journal Clinical Pharmacology & Therapeutics
- 2018 - Artificial intelligence model “learns” from patient data to make cancer treatment less toxic