Novel machine learning and pragmatic computational medicine approaches to improve health outcomes for patients
In the first part of the talk, I describe machine learning algorithms and methods to identify disease characteristics such as physician labels, fluorescent biomarkers and histological dyes from simple white light images. In the second part, I share novel phase 2 and 3 clinical trials designed by unorthodox “self-learning” AI and machine learning systems to accelerate clinical development to bring new innovations and advances to patients safely. Our clinical trial designs achieves significant reduction in tumor sizes during oncology care, and offers personalized and precision dosing recommendations for individual patients. We conclude by outlining a strategic plan to conduct clinical trials with devices, algorithms and real world evidence in accordance with the 21st Century Cures Act.