AI Doctor

About the Author xi
 
Foreword xiii
 
Preface xix
 
Acknowledgments xxiii
 
Part I Roadmap of AI in Healthcare 1
 
1 History of AI and Its Promise in Healthcare 3
 
1.1 What is AI? 5
 
1.2 A Classification System for Underlying AI/ML Algorithms 14
 
1.3 AI and Deep Learning in Medicine 17
 
1.4 The Emergence of Multimodal and Multipurpose Models in Healthcare 20
 
References 23
 
2 Building Robust Medical Algorithms 27
 
2.1 Obtaining Datasets That are Big Enough and Detailed Enough for Training 30
 
2.2 Data Access Laws and Regulatory Issues 33
 
2.3 Data Standardization and Its Integration into Clinical Workflows 34
 
2.4 Federated AI as a Possible Solution 36
 
2.5 Synthetic Data 40
 
2.6 Data Labeling and Transparency 43
 
2.7 Model Explainability 45
 
2.8 Model Performance in the Real World 50
 
2.9 Training on Local Data 52
 
2.10 Bias in Algorithms 53
 
2.11 Responsible AI 60
 
References 62
 
3 Barriers to AI Adoption in Healthcare 67
 
3.1 Evidence Generation 71
 
3.2 Regulatory Issues 74
 
3.3 Reimbursement 76
 
3.4 Workflow Issues with Providers and Payers 78
 
3.5 Medical- Legal Barriers 81
 
3.6 Governance 83
 
3.7 Cost and Scale of Implementation 85
 
3.8 Shortage of Talent 86
 
References 86
 
4 Drivers of AI Adoption in Healthcare 91
 
4.1 Availability of Data 92
 
4.2 Powerful Computers, Cloud Computing, and Open Source Infrastructure 93
 
4.3 Increase in Investments 94
 
4.4 Improvements in Methodology 95
 
4.5 Policy and Regulatory 95
 
4.5.1 Fda 95
 
4.5.2 Other Bodies 100
 
4.6 Reimbursement 102
 
4.7 Shortage of Healthcare Resources 105
 
4.8 Issues with Mistakes, Inefficient Care Pathways, and Non- personalized Care 106
 
References

RONALD M. RAZMI, MD is a cardiologist and the co-founder and Managing Director of Zoi Capital, a venture capital firm that invests in the applications of AI in healthcare. Dr. Razmi completed his medical training at the Mayo Clinic and holds an MBA from Northwestern University's Kellogg School of Management. He was a McKinsey consultant before launching a population health management software company at the dawn of digital health. He saw firsthand the confluence of clinical, technical, and business factors that need to come together for new technologies to gain a foothold in healthcare. He is a co-author of the Handbook of Cardiovascular Magnetic Resonance Imaging.