Book

This book addresses the growing global problem of diabetes, a chronic disease that has become one of the most serious public health challenges of the 21st century. With millions of people affected worldwide, diabetes leads to severe complications such as cardiovascular diseases, kidney failure, and vision loss, creating a heavy burden on healthcare systems. To respond to this urgent problem, the book presents an innovative approach based on Artificial Intelligence and Machine Learning for early prediction and prevention. It demonstrates how advanced computational methods can help detect diabetes risk at an early stage, improving diagnosis and supporting medical decision-making. Using the widely recognized Pima Indian Diabetes Dataset, the book evaluates several machine learning models including Random Forest, Support Vector Machine, Logistic Regression, and Deep Neural Networks. It also explores association rule mining and FP-Growth techniques to extract hidden patterns and enhance predictive accuracy. Beyond clinical indicators, the book integrates nutritional, environmental, and genomic factors, highlighting the complex and multifactorial nature of diabetes. Special attention is given to explainable AI methods to ensure that predictive models remain transparent, interpretable, and trustworthy for healthcare professionals. Big data technologies such as Apache Spark are also used to handle large-scale medical datasets efficiently and at high speed. Overall, this book provides a comprehensive and interdisciplinary framework for researchers, clinicians, and data scientists to better understand, predict, and combat diabetes.