Introduction to Machine Learning and Optimization in Healthcare
Shruthi Anandhavalli Gauthaman, Anandhavalli Muniasamy, Riyazdeen Kamaldheen, S. Sachin Kumar, Kaurish Murugesan, Mukesh Kumar Viswanathan, Harini Devendran · 2025
Machine learning (ML) and optimization techniques are revolutionizing healthcare by improving prediction accuracy and treatment efficiency. This chapter examines the evolution, integration, and application of ML algorithms—such as decision trees, SVMs, and neural networks—alongside optimization methods like linear programming and genetic algorithms in healthcare settings. A case study using a Kaggle dataset highlights ML's role in disease prediction, utilizing data preprocessing, PCA for dimensionality reduction, and a CNN for feature extraction. CART, SVM, and Logistic Regression models were tested, with SVM achieving the highest accuracy (99.63% training, 97.62% testing). The chapter also explores explainable AI, federated learning, and real-time optimization in telemedicine, while addressing ethical issues, regulatory compliance, and equitable access—emphasizing their collective impact on the future of healthcare.