A Physician-Data Scientist Grand Vision: A Virtual Medical Oracle

Abstract: The ultimate accomplishment for deep learning and cognitive architecture in medicine will be the creation of a “virtual medical oracle”: a real-time, all knowing medical and healthcare resource based on not only deep learning of existing medical data (such as radiological and pathological images) but also cognitive architecture based on expert opinions and patient experiences. With deep learning as well as cloud computing, a virtual medical imaging center can now be built as a valuable resource for all clinicians and patients. This imaging center requires GPUs and sophisticated deep reinforcement and/or one-shot learning as well as the novel capsule network architecture. While deep learning is currently deployed frequently in artificial intelligence in medicine, a future man-machine cognitive synergy involving more clinicians will be needed for the synthesis of the highest level of artificial/human intelligence in medicine and healthcare.

The 10 necessary steps for this astounding pinnacle of “medical” intelligence to be realized will be outlined; among these requisite steps are: an AI-inspired acquisition of medical data; an universal common medical data repository; an internet of everything strategy for medical data; a close physician-data scientist collaboration; and a true deep learning/cognitive architecture hybrid structure for medical knowledge.

Bio: Dr. Chang attended Johns Hopkins University for his B.A. in molecular biology prior to entering Georgetown University School of Medicine for his M.D. He then completed his pediatric residency at Children’s Hospital National Medical Center and his pediatric cardiology fellowship at Children’s Hospital of Philadelphia.

He is currently the Chief Intelligence and Innovation Officer and Medical Director of the Heart Failure Program at Children’s Hospital of Orange County.

He recently completed his Masters of Science (MS) in Data Science with a sub-specialization in artificial intelligence from Stanford School of Medicine. He is also a computer scientist-in-residence at Chapman University.

He is known for several innovations in pediatric cardiac care, including introducing the cardiac drug milrinone and co-designing (with Dr. Michael DeBakey) an axial-type ventricular assist device in children. He has helped to build a successful cardiology practice as a company and was able to complete a deal on Wall Street. He is the founder and medical director of the nascent Medical Intelligence and Innovation Institute (MI3) that is supported by the Sharon Disney Lund Foundation. He intends to build a clinician-computer scientist interface to enhance all aspects of data science and artificial intelligence in health and medicine. He currently lectures widely on big data and artificial intelligence in medicine (he has been called “Dr. A.I.” and has given a TEDx talk and on the faculty of Singularity University)

Open Data Science Conference