Artificial Intelligence and Machine Learning in Health Care and Medical Sciences: Best Practices and Pitfalls

This open access book provides a detailed review of the latest methods and applications of artificial intelligence (AI) and machine learning (ML) in medicine. With chapters focusing on enabling the reader to develop a thorough understanding of the key concepts in these subject areas along with a range of methods and resulting models that can be utilized to solve healthcare problems, the use of causal and predictive models are comprehensively discussed. Care is taken to systematically describe the concepts to facilitate the reader in developing a thorough conceptual understanding of how different methods and resulting models function and how these relate to their applicability to various issues in health care and medical sciences. Guidance is also given on how to avoid pitfalls that can be encountered on a day-to-day basis and stratify potential clinical risks.

Artificial Intelligence and Machine Learning in Health Care and Medical Sciences: Best Practices and Pitfalls is a comprehensive guide to how AI and ML techniques can best be applied in health care. The emphasis placed on how to avoid a variety of pitfalls that can be encountered makes it an indispensable guide for all medical informatics professionals and physicians who utilize these methodologies on a day-to-day basis. Furthermore, this work will be of significant interest to health data scientists, administrators and to students in the health sciences seeking an up-to-date resource on the topic.

Dr. Gyorgy Simon earned his PhD in Computer Science with a minor in Statistics from the University of Minnesota. Subsequently, he was a senior software engineer at Yahoo! Search Engine Technologies and later joined Mayo Clinic where he developed clinical data mining techniques, before joining the University of Minnesota He is a federally-funded investigator with extensive experience developing and applying AI and ML methods in a variety of application settings. He is currently a tenured Associate Professsor in the Institute for Health Informatics with additional appointments in Medicine and Data Science.

Constantin Aliferis received an MD degree from Athens University in Greece in 1990, and an MS in 1994 and PhD in 1998 in Artificial Intelligence from the University of Pittsburgh. He also completed a post doctoral Fellowhip focusing on Machine Learning in Biomedicine. His has served as faculty in Biomedical Informatics, Computer Science, Biostatistics and Cancer Biology at Vanderbilt University; Informatics, Computational Biology, Data Science and Pathology at NYU; and Informatics, Medicine and Data Science at the University of Minnesota. He has also been a regular faculty member in the Cancer Centers of the above universities and architected/led their MS and PhD programs in Biomedical Informatics. He has also been the director of the NYU’s Center for Health Informatics and Bioinformatics, and Director of the UMN Institute for Health Informatics at the UMN where he is also Chief Research Informatics Officer and a tenured Professor. He is a federally-funded investigator who has pioneered several novel and best-of-breed AI and ML methods, applied them in dozens of areas, and has also published extensively in method benchmarking and several other best-practice-related topics.