Machine Learning and AI for Healthcare

This updated second edition offers a guided tour of machine learning algorithms and architecture design. It provides real-world applications of intelligent systems in healthcare and covers the challenges of managing big data.

The book has been updated with the latest research in massive data, machine learning, and AI ethics. It covers new topics in managing the complexities of massive data, and provides examples of complex machine learning models. Updated case studies from global healthcare providers showcase the use of big data and AI in the fight against chronic and novel diseases, including COVID-19. The ethical implications of digital healthcare, analytics, and the future of AI in population health management are explored. You will learn how to create a machine learning model, evaluate its performance, and operationalize its outcomes within your organization. Case studies from leading healthcare providers cover scaling global digital services. Techniques are presented to evaluate the efficacy, suitability, and efficiency of AI machine learning applications through case studies and best practice, including the Internet of Things.

You will understand how machine learning can be used to develop health intelligence–with the aim of improving patient health, population health, and facilitating significant care-payer cost savings.

WHAT YOU WILL LEARN

* Understand key machine learning algorithms and their use and implementation within healthcare
* Implement machine learning systems, such as speech recognition and enhanced deep learning/AI
* Manage the complexities of massive data
* Be familiar with AI and healthcare best practices, feedback loops, and intelligent agents

WHO THIS BOOK IS FOR

Health care professionals interested in how machine learning can be used to develop health intelligence – with the aim of improving patient health, population health and facilitating significant care-payer cost savings.

ARJUN PANESAR is the founder of Diabetes Digital Media (DDM), the world’s largest diabetes community and provider of evidence-based digital health interventions. He holds an honors degree (MEng) in computing and artificial intelligence from Imperial College, London. He has a decade of experience in big data and affecting user outcomes, and leads the development of intelligent, evidence-based digital health interventions that harness the power of big data and machine learning to provide precision patient care to patients, health agencies, and governments worldwide.

Arjun’s work has received international recognition and was featured by the BBC, Forbes, New Scientist, and The Times. He has received innovation, business, and technology awards, including being named the top app for prevention of type 2 diabetes.

Arjun is an advisor to the Information School, at the University of Sheffield, Fellow to the NHS Innovation Accelerator, and was recognized by Imperial College as an Emerging Leader in 2020 for his contribution and impact to society.

Chapter 1: Introduction: Learning for Healthcare

Chapter Goal: Introduction to book and topics to be covered

No of pages 10

Sub -Topics

1. What is AI, data science, machine and deep learning

2. The case for learning from data

3. Evolution of big data/learning/Analytics 3.0

4. Practical examples of how data can be used to learn within healthcare settings

5. Conclusion

Chapter 2: Big Data

Chapter Goal: To understand data required for learning and how to ensure valid data for outcome veracity

No of pages: 35

Sub - Topics

1. What is data, sources of data and what types of data is there? little vs big data and the advantages/disadvantages with such data sets. Structured vs. unstructured data.

2. Massive data - management and complexities

3. The key aspects required of data, in particular, validity to ensure that only useful and relevant information

4. How to use big data for learning (use cases)

5. Turning data into information – how to collect data that can be used to improve health outcomes and examples of how to collect such data

6. Challenges faced as part of the use of big data

7. Data governance

Chapter 3: What is Machine learning?

Chapter Goal: To introduce machine learning, identify/demystify types of learning and provide information of popular algorithms and their applications

No of pages: 45

Sub - Topics:

1. Introduction – what is learning?

2. Differences/similarities between: what is AI, data science, machine learning, deep learning

3. History/evolution of learning

4. Learning algorithms – popular types/categories, complex examples of machine learning models, applications and their mathematical basis

5. Software(s) used for learning

6. Code samples

Chapter 4: Machine Learning in Healthcare

Chapter Goal: A comprehensive understanding of key concepts related to learning systems and the practical application of machine learning within healthcare settings

No of pages: 50

Sub - Topics:

1. Understanding Tasks, Performance and Experience to optimize algorithms and outcomes

2. Identification of algorithms to be used in healthcare applications for: predictive analysis, perspective analysis, inference, modeling, probability estimation, NLP etc and common uses

3. Real-time analysis and analytics

4. Machine learning best practices

5. Neural networks, ANNs, deep learning

6. Code samples

Chapter 5: Evaluating Learning for Intelligence

Chapter Goal: To understand how to evaluate learning algorithms, how to choose the best evaluation technique/approach for analysis

No of pages: 30

1. How to evaluate machine learning systems

2. Methodologies for evaluating outputs

3. Improving your intelligence

4. Advanced analytics

5. Real-world examples of evaluations

Chapter 6: Ethics of intelligence

Chapter Goal: To understand the hurdles that must be addressed in AI/machine learning and also overcome on both a micro- and macro-level to enable enhanced health intelligence

No of pages: 25

1. The benefits of big data and machine learning

2. The disadvantages of big data and machine learning – who owns the data, distributing the data, should patients/people be told what the results are (e.g. data demonstrates risk of cancer)

3. Data for good, or data for bad?

4. Topics that require addressing in order to ensure ease, efficiency and safety of outputs

5. Do we need to govern our intelligence?

6. Example: COVID-19 response and data/privacy sharing

Chapter 7: The Future of Healthcare

Chapter Goal: Outline the direction of AI and machine/deep learning within healthcare and the future applications of intelligent systems

No of pages: 30

1. Evidence-based medicine

2. Patient data as the evidence base

3. Healthcare disruption fueling innovation

4. How generalisations on precise audiences enables personalized medicine

5. Impact of data and IoT on realizing personalized medicine

6. AI ethics

7. Conclusion

Chapter 8: Case studies

Chapter Goal: Real world applications of AI and machine/deep learning in healthcare

No of pages: 50

1. Real world case studies of organizations implementing machine learning and the challenges, methodologies, algorithms and analytics used to determine optimal performance/outcomes

2. COVID-related case studies: how data was used, how rapid interventions were deployed, agile development methodolodies