BookTrevor A. Cohen, Vimla L. Patel, Edward H. Shortliffe, editors.
Summary: This textbook comprehensively covers the latest state-of-the-art methods and applications of artificial intelligence (AI) in medicine, placing these developments into a historical context. Factors that assist or hinder a particular technique to improve patient care from a cognitive informatics perspective are identified and relevant methods and clinical applications in areas including translational bioinformatics and precision medicine are discussed. This approach enables the reader to attain an accurate understanding of the strengths and limitations of these emerging technologies and how they relate to the approaches and systems that preceded them. With topics covered including knowledge-based systems, clinical cognition, machine learning and natural language processing, Intelligent Systems in Medicine and Health: The Role of AI details a range of the latest AI tools and technologies within medicine. Suggested additional readings and review questions reinforce the key points covered and ensure readers can further develop their knowledge. This makes it an indispensable resource for all those seeking up-to-date information on the topic of AI in medicine, and one that provides a sound basis for the development of graduate and undergraduate course materials.
Contents:
Intro
Foreword
Preface
The State of AI in Medicine
Introducing Intelligent Systems in Medicine and Health: The Role of AI
Structure and Content
Guide to Use of This Book
Acknowledgments
Contents
Contributors
Part I: Introduction
Chapter 1: Introducing AI in Medicine
The Rise of AIM
Knowledge-Based Systems
Neural Networks and Deep Learning
Machine Learning and Medical Practice
The Scope of AIM
From Accurate Predictions to Clinically Useful AIM
The Cognitive Informatics Perspective
Why CI? The Complementarity of Human and Machine Intelligence
Mediating Safe and Effective Human Use of AI-Based Tools
Concluding Remarks
References
Chapter 2: AI in Medicine: Some Pertinent History
Introduction
Artificial Intelligence: The Early Years
Modern History of AI
AI Meets Medicine and Biology: The 1960s and 1970s
Emergence of AIM Research at Stanford University
Three Influential AIM Research Projects from the 1970s
INTERNIST-1/QMR
CASNET
MYCIN
Cognitive Science and AIM
Reflecting on the 1970s
Evolution of AIM During the 1980s and 1990s AI Spring and Summer Give Way to AI Winter
AIM Deals with the Tumult of the 80s and 90s
The Last 20 Years: Both AI and AIM Come of Age
References
Chapter 3: Data and Computation: A Contemporary Landscape
Understanding the World Through Data and Computation
Types of Data Relevant to Biomedicine
Knowing Through Computation
Motivational Example
Computational Landscape
Knowledge Representation
Machine Learning
Data Integration to Better Understand Medicine: Multimodal, Multi-Scale Models
Distributed/Networked Computing
Data Federation Models Interoperability
Computational Aspects of Privacy
Trends and Future Challenges
Ground Truth
Open Science and Mechanisms for Open data
Data as a Public Good
References
Part II: Approaches
Chapter 4: Knowledge-Based Systems in Medicine
What Is a Knowledge-Based System?
How Is Knowledge Represented in a Computer?
Rules: Inference Steps
Patterns: Matching
Probabilistic Models
Naive Bayes
Bayesian Networks
Decision Analysis and Influence Diagrams
Causal Mechanisms: How Things Work
How Is Knowledge Acquired?
Ontologies and Their Tools Knowledge in the Era of Machine Learning
Incorporating Knowledge into Machine Learning Models
Graph-Based Models
Graph Representation Learning
Biomedical Applications of Graph Machine Learning
Text-Based Models
Leveraging Expert Systems to Train Models
Looking Forward
References
Chapter 5: Clinical Cognition and AI: From Emulation to Symbiosis
Augmenting Human Expertise: Motivating Examples
Cognitive Science and Clinical Cognition
Symbolic Representations of Clinical Information
Clinical Text Understanding