Leveraging GenAI for Machine Learning Education in Public Health

This book explores how ChatGPT, as a generative AI (Gen-AI) platform, can support education, research, and skill development in artificial intelligence (AI) and machine learning (ML) for public health applications. By bridging the gap between AI technology and public health expertise, the book empowers readers to harness AI/ML for data-driven decision-making, health interventions, and innovative research in the digital age.

The rapid advancement of AI and ML is transforming public health research, policy, and practice. However, many public health professionals lack the technical expertise to leverage these tools effectively. This book addresses this gap. It provides a structured approach to integrating ChatGPT into learning environments, from higher education to professional training, offering accessible explanations, hands-on exercises, and real-world applications.

The book begins with an introduction to AI and ML in public health. It then examines how ChatGPT can enhance AI/ML education through a method known as "programming by prompting" a technique where users interact with AI models by providing structured prompts to generate, modify, and refine code. This approach enables learners to write functional code without requiring extensive prior programming knowledge, and allows them to work with data relevant to public health.

As a pedagogical tool, the book provides simulated electronic health record (EHR) data to facilitate hands-on learning of ChatGPT's applications in practice. It also introduces fundamental ML concepts, algorithms, and models so that learners gain both foundational knowledge and an understanding of their real-world applications in public health. The book also explores responsible use of ChatGPT and similar Gen-AI tools, ethical considerations, data privacy, and transparency to provide a well-rounded perspective on AI's role in public health.

Leveraging GenAI for Machine Learning Education in Public Health is an invaluable resource for public health professionals, educators, researchers, and students interested in developing AI literacy and practical skills. The text also would appeal to healthcare data scientists and analysts, medical and health informatics professionals, public health policymakers, tech and AI enthusiasts in public health, executive and continuing education learners, multidisciplinary scholars, and practitioners.

Explains AI/ML concepts with real-world healthcare applications for students and professionals Integrates ChatGPT and R Studio for practical AI/ML applications in public health research Covers responsible AI, bias reduction, and the evolving role of AI in healthcare policy and practice

Autorentext

Ricky Leung is Professor and Director of Social and Behavioral Sciences at the University of Memphis School of Public Health in Tennessee, USA. A leading scholar at the intersection of artificial intelligence, machine learning, public health and management, he has published extensively on AI and other emerging technologies in high-impact journals such as Lancet, JAMA, and Organization Science. His research has received support from NSF, CDC, NIH, and other public agencies and private organizations, and he has also served as a panelist for some of these organizations. As an educator, he teaches courses in relation to AI, Health and Society, Responsible AI in Public Health, AI and Talent Management, and GenAI-assisted Machine Learning Programming, equipping future professionals with the skills to navigate the evolving AI landscape. He previously served as the Interim Director of the Global Center for AI in Mental Health at the University at Albany and is currently establishing a NIH-sponsored AI for Health Lab, and a new Center on Responsible AI in Public Health at the University of Memphis.

Inhalt

Part 1 Laying the Foundation.- Chapter 1 Introduction.- Chapter 2 Understanding AI and Machine Learning for Public Health.- Chapter 3 Getting Started with RStudio and ChapGPT.- Part 2 Machine Learning Techniques and Applications.- Chapter 4 Supervised Learning I: Classification Models.- Chapter 5 Supervised Learning II: Regression Models.- Chapter 6 Unsupervised Learning.- Chapter 7 Advanced Machine Learning Models.- Part 3 Ethical, Responsible, and Realworld AI Applications.- Chapter 8 Realworld Applications of Supervised Learning.- Chapter 9 Explainability and Reproducibility in Machine Learning.- Chapter 10 Future Directions and Continuous Learning in AI.