Details

<p>About the Author xi</p> <p>Foreword xiii</p> <p>Preface xix</p> <p>Acknowledgments xxiii</p> <p><b>Part I Roadmap of AI in Healthcare 1</b></p> <p><b>1 History of AI and Its Promise in Healthcare 3</b></p> <p>1.1 What is AI? 5</p> <p>1.2 A Classification System for Underlying AI/ML Algorithms 14</p> <p>1.3 AI and Deep Learning in Medicine 17</p> <p>1.4 The Emergence of Multimodal and Multipurpose Models in Healthcare 20</p> <p>References 23</p> <p><b>2 Building Robust Medical Algorithms 27</b></p> <p>2.1 Obtaining Datasets That are Big Enough and Detailed Enough for Training 30</p> <p>2.2 Data Access Laws and Regulatory Issues 33</p> <p>2.3 Data Standardization and Its Integration into Clinical Workflows 34</p> <p>2.4 Federated AI as a Possible Solution 36</p> <p>2.5 Synthetic Data 40</p> <p>2.6 Data Labeling and Transparency 43</p> <p>2.7 Model Explainability 45</p> <p>2.8 Model Performance in the Real World 50</p> <p>2.9 Training on Local Data 52</p> <p>2.10 Bias in Algorithms 53</p> <p>2.11 Responsible AI 60</p> <p>References 62</p> <p><b>3 Barriers to AI Adoption in Healthcare 67</b></p> <p>3.1 Evidence Generation 71</p> <p>3.2 Regulatory Issues 74</p> <p>3.3 Reimbursement 76</p> <p>3.4 Workflow Issues with Providers and Payers 78</p> <p>3.5 Medical- Legal Barriers 81</p> <p>3.6 Governance 83</p> <p>3.7 Cost and Scale of Implementation 85</p> <p>3.8 Shortage of Talent 86</p> <p>References 86</p> <p><b>4 Drivers of AI Adoption in Healthcare 91</b></p> <p>4.1 Availability of Data 92</p> <p>4.2 Powerful Computers, Cloud Computing, and Open Source Infrastructure 93</p> <p>4.3 Increase in Investments 94</p> <p>4.4 Improvements in Methodology 95</p> <p>4.5 Policy and Regulatory 95</p> <p>4.5.1 Fda 95</p> <p>4.5.2 Other Bodies 100</p> <p>4.6 Reimbursement 102</p> <p>4.7 Shortage of Healthcare Resources 105</p> <p>4.8 Issues with Mistakes, Inefficient Care Pathways, and Non- personalized Care 106</p> <p>References 110</p> <p><b>Part II Applications of AI in Healthcare 113</b></p> <p><b>5 Diagnostics 115</b></p> <p>5.1 Radiology 115</p> <p>5.2 Pathology 122</p> <p>5.3 Dermatology 124</p> <p>5.4 Ophthalmology 125</p> <p>5.5 Cardiology 127</p> <p>5.6 Neurology 132</p> <p>5.7 Musculoskeletal 133</p> <p>5.8 Oncology 134</p> <p>5.8.1 Diagnosis and Treatment of Cancer 136</p> <p>5.8.2 Histopathological Cancer Diagnosis 136</p> <p>5.8.3 Tracking Tumor Development 136</p> <p>5.8.4 Prognosis Detection 137</p> <p>5.9 Gi 139</p> <p>5.10 Covid- 19 139</p> <p>5.11 Genomics 140</p> <p>5.12 Mental Health 141</p> <p>5.13 Diagnostic Bots 142</p> <p>5.14 At Home Diagnostics/Remote Monitoring 144</p> <p>5.15 Sound AI 148</p> <p>5.16 AI in Democratizing Care 149</p> <p>References 150</p> <p><b>6 Therapeutics 157</b></p> <p>6.1 Robotics 158</p> <p>6.2 Mental Health 159</p> <p>6.3 Precision Medicine 161</p> <p>6.4 Chronic Disease Management 164</p> <p>6.5 Medication Supply and Adherence 167</p> <p>6.6 Vr 168</p> <p>References 169</p> <p><b>7 Clinical Decision Support 171</b></p> <p>7.1 AI in Decision Support 176</p> <p>7.2 Initial Use Cases 180</p> <p>7.3 Primary Care 182</p> <p>7.4 Specialty Care 185</p> <p>7.4.1 Cancer Care 185</p> <p>7.4.2 Neurology 185</p> <p>7.4.3 Cardiology 186</p> <p>7.4.4 Infectious Diseases 187</p> <p>7.4.5 Covid- 19 187</p> <p>7.5 Devices 188</p> <p>7.6 End- of- Life AI 189</p> <p>7.7 Patient Decision Support 190</p> <p>References 191</p> <p><b>8 Population Health and Wellness 195</b></p> <p>8.1 Nutrition 196</p> <p>8.2 Fitness 200</p> <p>8.3 Stress and Sleep 201</p> <p>8.4 Population Health and Management 204</p> <p>8.5 Risk Assessment 206</p> <p>8.6 Use of Real World Data 208</p> <p>8.7 Medication Adherence 208</p> <p>8.8 Remote Engagement and Automation 209</p> <p>8.9 Sdoh 211</p> <p>8.10 Aging in Place 212</p> <p>References 214</p> <p><b>9 Clinical Workflows 217</b></p> <p>9.1 Documentation Assistants 218</p> <p>9.2 Quality Measurement 225</p> <p>9.3 Nursing and Clinical Assistants 225</p> <p>9.4 Virtual Assistants 227</p> <p>References 230</p> <p><b>10 Administration and Operations 233</b></p> <p>10.1 Providers 234</p> <p>10.1.1 Documentation, Coding, and Billing 234</p> <p>10.1.2 Practice Management and Operations 238</p> <p>10.1.3 Hospital Operations 240</p> <p>10.2 Payers 243</p> <p>10.2.1 Payer Administrative Functions 244</p> <p>10.2.2 Fraud 246</p> <p>10.2.3 Personalized Communications 247</p> <p>References 248</p> <p><b>11 AI Applications in Life Sciences 251</b></p> <p>11.1 Drug Discovery 252</p> <p>11.2 Clinical Trials 261</p> <p>11.2.1 Information Engines 264</p> <p>11.2.2 Patient Stratification 267</p> <p>11.2.3 Clinical Trial Operations 268</p> <p>11.3 Medical Affairs and Commercial 271</p> <p>References 272</p> <p><b>Part III the Business Case for Ai in Healthcare 275</b></p> <p><b>12 Which Health AI Applications Are Ready for Their Moment? 277</b></p> <p>12.1 Methodology 278</p> <p>12.2 Clinical Care 281</p> <p>12.3 Administrative and Operations 289</p> <p>12.4 Life Sciences 291</p> <p>References 293</p> <p><b>13 The Business Model for Buyers of Health AI Solutions 295</b></p> <p>13.1 Clinical Care 298</p> <p>13.2 Administrative and Operations 305</p> <p>13.3 Life Sciences 309</p> <p>13.4 Guide for Buyer Assessment of Health AI Solutions 312</p> <p>References 313</p> <p><b>14 How to Build and Invest in the Best Health AI Companies 315</b></p> <p>14.1 Barriers to Entry and Intellectual Property (IP) 316</p> <p>14.1.1 Creating Defensible Products 318</p> <p>14.2 Startups Versus Large Companies 319</p> <p>14.3 Sales and Marketing 321</p> <p>14.4 Initial Customers 324</p> <p>14.5 Direct- to- Consumer (D2C) 325</p> <p>14.6 Planning Your Entrepreneurial Health AI Journey 327</p> <p>14.7 Assessment of Companies by Investors 329</p> <p>14.7.1 Key Areas to Explore for a Health AI Company for Investment 329</p> <p>References 330</p> <p>Index 333</p>

<p><b>RONALD M. RAZMI, MD</b> 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 <i>Handbook of Cardiovascular Magnetic Resonance Imaging</i>.</p>

</p> <p><b>An examination of the promise of Artificial Intelligence (AI) for the practice and business of healthcare, drivers and barriers to achieving that promise, and how stakeholders can successfully navigate them</b> <p>Over the last century, life expectancy has increased dramatically. The progress made in improving health in that time span has eclipsed all the progress made in human history up to that point combined. Much of that progress has been on a foundation of better diagnostics and collecting an increasing amount of data from the patients, which has only accelerated with the introduction of digital technologies. The next frontiers for making major progress in further improving health will be through the understanding of what all of this data means. AI is the only technology on the horizon that can translate all this data into meaningful improvements in health. <p>In <i>AI Doctor: The Rise of Artificial Intelligence in Healthcare</i>, Dr. Ronald M. Razmi provides a comprehensive and up-to-date account of the current impact and future potential of AI in the healthcare industry. Presented in a clear, non-technical narrative style, this timely guide helps those in the business and practice of healthcare understand the opportunities that AI offers to improve research for finding new medical breakthroughs, better provision of healthcare, and creating better business models. <p>Drawing from his expertise as a cardiologist, entrepreneur, and venture capitalist, the author offers invaluable insights into what it takes to successfully bring innovation into this complicated sector. He provides a 360 view of the key factors that need to come together for the health AI use cases to gain adoption. <p>Covering the clinical, technical, and economic implications of Artificial Intelligence in healthcare, <i>AI Doctor: The Rise of Artificial Intelligence in Healthcare: A Guide for Users, Buyers, Builders, and Investors</i> is a must-read for healthcare professionals, researchers, investors, entrepreneurs, medical and nursing students, and those building or designing systems for the commercial marketplace. The book's non-technical and reader-friendly narrative style also makes it an ideal read for everyone interested in learning about how AI will improve health and healthcare in the coming decades. <p>

US