Abstract: The rapid digitization of healthcare has accelerated the adoption of artificial intelligence for clinical applications. A major opportunity for predictive clinical analytics is the ability to provide faster diagnoses and treatment plans tailored to individuals. Applications have been developed for multiple care settings, with many novel point-of-care diagnostics that can assess for diseases ranging from malaria to skin cancer. In this talk, we will demonstrate how to apply machine learning algorithms to identify regions of interest for detection of the pupil for point-of-care drug screening. We will highlight state-of-the-art technology to support real-time image analysis, approaches for the use of real-world clinical and patient-generated data, and best practices for translating novel AI algorithms from controlled research and development environments into real-world, clinical settings. Finally, we will review current regulatory requirements for training, validating, and providing ongoing quality assurance for algorithms that are deployed to clinical settings. Attendees will gain an understanding for good machine learning practices, be able to describe approaches to develop high-quality clinical data sets, and design practical validation plans to ensure algorithm generalizability. As healthcare continues to evolve into a digital enterprise where data are reagents and software is the analytic engine, an understanding of best practices to develop, implement, and assess clinical predictive models is critical for the safe and rapid deployment of AI in healthcare.
Bio: Dr. Schulz is an Assistant Professor of Laboratory Medicine and computational health care researcher at Yale School of Medicine. He received a PhD in Microbiology, Immunology, and Cancer Biology and an MD from the University of Minnesota. He is the Director of Informatics for the Department of Laboratory Medicine, Director of the CORE Center for Computational Health, and Medical Director of Data Science for Yale New Haven Health System. Dr. Schulz has over 20 years’ experience in software development with a focus on enterprise system architecture and has a research interests in the management of large, biomedical data sets and the use of real-world data for predictive modeling. At Yale, he has led the implementation of a distributed data analysis and predictive modeling platform, for which he received the Data Summit IBM Cognitive Honors award. Other projects within his research group include computational phenotyping and the development of clinical prescriptive models for precision medicine initiatives. His clinical areas of expertise include molecular diagnostics and transfusion medicine, where he has ongoing work assessing the use, safety, and efficacy of pathogen-reduced blood products.