Artificial Intelligence and Machine Learning in Health Care and Medical Sciences

Best Practices and Pitfalls

Gyorgy J. Simon, Constantin Aliferis

• Publisher: Springer
• Year: 2024
• Print ISBN: 9783031393549
• eBook ISBN: 9783031393556
• Edition: 0
• Topic: Medicina
• Subtopic: Bioinformática

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.

Table of contents

• Cover
• Front Matter
• Artificial Intelligence (AI) and Machine Learning (ML) for Healthcare and Health Sciences: The Need for Best Practices Enabling Trust in AI and ML
• Foundations and Properties of AI/ML Systems
• An Appraisal and Operating Characteristics of Major ML Methods Applicable in Healthcare and Health Science
• Foundations of Causal ML
• Principles of Rigorous Development and of Appraisal of ML and AI Methods and Systems
• The Development Process and Lifecycle of Clinical Grade and Other Safety and Performance-Sensitive AI/ML Models
• Data Design in Biomedical AI/ML
• Data Preparation, Transforms, Quality, and Management
• Evaluation
• Overfitting, Underfitting and General Model Overconfidence and Under-Performance Pitfalls and Best Practices in Machine Learning and AI
• From “Human versus Machine” to “Human with Machine”
• Lessons Learned from Historical Failures, Limitations and Successes of AI/ML in Healthcare and the Health Sciences. Enduring Problems, and the Role of Best Practices
• Characterizing, Diagnosing and Managing the Risk of Error of ML & AI Models in Clinical and Organizational Application
• Considerations for Specialized Health AI & ML Modelling and Applications: NLP
• Considerations for Specialized Health AI & ML Modelling and Applications: Imaging—Through the Perspective of Dermatology
• Regulatory Aspects and Ethical Legal Societal Implications (ELSI)
• Reporting Standards, Certification/Accreditation, and Reproducibility
• Synthesis of Recommendations, Open Problems and the Study of BPs
• Back Matter