Healthcare Transformation Using Artificial Intelligence.

Format:

Book

Author/Creator:

Morris, Robert Jt.

Language:

English

Physical Description:

1 online resource (455 pages)

Edition:

1st ed.

Place of Publication:

Chantilly : Elsevier Science & Technology, 2025.

Summary:

Healthcare Transformation Using Artificial Intelligence provides insights into executing healthcare transformation through AI, and deploying health technology at scale.It focuses on improving patient outcomes while managing costs, highlighting selected use of AI and contrasting it with a "tech push" approach.

Contents:

Front Cover

Healthcare Transformation using Artificial Intelligence

Copyright

Contents

About the author

Preface: How to read this book

Acknowledgments

Introduction

References

1 - Setting the stage for transformation and the role of technology

1 - The healthcare industry

1.1 What is a healthcare system, and what are its objectives?

1.2 What is the "business of healthcare," and why is it important in our transformational quest?

1.3 Lessons in transformation from various countries around the world

1.4 Other considerations in transforming healthcare

2 - Systematic analysis of opportunities for healthcare transformation

2.1 Opportunities for healthcare transformation

2.2 A systems approach to understanding transformation

2.3 Using data, information, and real facts to identify and focus targets of change in healthcare

2.4 The predominant determinants of health outcomes

2.5 Putting it all together

3 - The role of information and technology in transforming industries and how it could transform healthcare

3.1 Lessons from other industries as they have used information to transform: Methods of industry transformation

3.2 Technology and healthcare transformation-Why now?

3.3 A "Bird's eye view" of future needs: Tech enablers of disruption

3.4 Annexes A and B: Lessons of transformation from other industries

3.4.1 Annex A: Lessons from the information technology industry's transformation

3.4.2 Annex B: Lessons from the manufacturing industry

2 - How AI works and its promise in healthcare

4 - Basic concepts and prerequisites to AI

4.1 Basic curve-fitting, prediction, optimization, and classification.

4.2 AI's first breakouts: Chess, go, speech recognition, image analysis, etc.

4.3 Brief review of probability concepts

4.4 Bayesian networks and reasoning with the causality chain of disease, symptoms, tests, and outcomes

4.5 Introducing machine learning

4.6 Chapter annex

5 - Neural networks and deep learning

5.1 Neural network basics

5.2 Training neural networks and backpropagation

5.3 Using neural networks for image analysis-Convolutional neural networks

5.4 Chapter 5 Annex

6 - Using neural networks for sequential information, including natural language understanding and generation

6.1 Sequential problems, RNNs, and LSTMs

6.2 Sequences of words in natural language: First we have to represent words

6.3 Purpose of attention networks, "query, key, value" (q, k, v) terminology and how they are used in transformers

6.4 How attention, the basic ingredient of transformers, is calculated

6.5 Using attention to build transformers

6.6 Using transformers to build an autoregressive next word predictor

6.7 LLM alignment: Pretraining, fine tuning, and reinforcement learning by human feedback (RLHF)

7 - Natural language processing and large language models use in healthcare

7.1 Introduction

7.2 Interpreting free text notes and reports and how LLMs are changing the game

7.3 General medical question and answer

7.4 Summarization and other uses of LLMs in healthcare

7.5 General purpose QA systems and adaptions to the medical domain

7.6 Arbitrary medical question answering extending into multimodal analysis

7.7 Testing a comprehensive medical LLM

7.8 Where do we stand?

3 - A tour through healthcare settings and how they could be transformed by technology and AI

8 - In the Doctor's office.

8.1 Assessing the excitement surrounding the medical use of AI

8.2 Using more systematic approaches in the medical setting-Clinical practice guidelines

8.3 How AI is beginning to fit into this framework of clinician + AI

8.4 A simple approach: Predictive risk models with smart guidelines

8.5 Full use of foundation models as a clinician's assistant

9 - Outside the Doctor's office: Patients at home and in the community, use of remote monitoring

9.1 Use of monitoring in chronic disease management

9.2 Use of monitoring devices and AI-based nudges in the community

9.3 Use of wearables and machine learning algorithms in atrial fibrillation

9.4 Fall detection

9.5 Takeaways

10 - Patients outside the system and mental health

10.1 Mental health

10.2 Apps and bots for mental health-Do they really work?

10.3 Using AI for mental health peer and online therapist support

10.4 The role of GenAI in mental health apps

11 - Post-discharge, generalizing monitoring, intervention, and recovery

11.1 Generalizing monitoring and intervention

11.2 Use of digital phenotyping and intervention in management of serious mental illness

11.3 Other methods for detection of mental health conditions

11.4 Other uses of digital phenotyping in post-discharge management

12 - The radiology office and medical imaging

12.1 Why medical imaging?

12.2 Chest X-rays, the first and largest foray of AI into radiology

12.3 Other radiology modalities: Ultrasound, CT, and MRI

12.4 Rethinking the comparison of man versus machine

12.5 Integrating AI into a radiology practice, interfacing with existing systems and maintaining "freedom of action"

12.6 Do's and Don'ts for AI implementation in radiology

12.7 The future of radiology

References.

13 - How AI can transform healthcare in emerging economies

13.1 Case study 1: Symptom checkers

13.2 Case study 2: Mild-moderate mental health, digital, and AI resources

13.3 Case study 3: Use of smart calling strategies in emerging countries for maternal and infant health

13.4 Case study 4: Use of low-cost medical imaging

13.5 Do's and Don'ts

4 - AI's adoption in healthcare and the future

14 - Ethics, safety and regulation

14.1 The basics of AI safety in healthcare

14.2 Healthcare ethics

14.3 AI safety

14.4 AI safety and open source

14.5 AI in healthcare national regulation regimes

14.6 Case study 1: The controversy about harms of social media and will "Section 230" protect AI?

14.7 Case study 2: LLMs mining everything, is it fair use?

14.8 Future healthcare experiences: The 4Es and empathy

15 - The future

15.1 Where do we stand now with AI in healthcare?

15.2 The hope for AI

15.3 Fears about AI and human failings

15.4 The limits of AI: High computing costs, are we running out of data, and a digital twin for the human body?

15.5 Synthetic data: Mirage or goldmine?

15.6 Putting it all together: A realistic outlook for AI in health

Index

Back Cover.

Notes:

Description based on publisher supplied metadata and other sources.

Other Format:

Print version: Morris, Robert Jt Healthcare Transformation Using Artificial Intelligence

ISBN:

9780443289705

OCLC:

1526056293