A Systematic Review of Machine Learning Techniques for Disease Classification in Healthcare Systems

Abstract

The increasing availability of healthcare data and advancements in computational technologies have accelerated the adoption of machine learning (ML) techniques for disease classification. This systematic review examines the application of various ML approaches in healthcare systems, focusing on their effectiveness in improving diagnostic accuracy and clinical decision-making. The study analyzes a wide range of algorithms, including supervised learning methods such as decision trees, support vector machines, and random forests, as well as deep learning models like artificial neural networks and convolutional neural networks. The review highlights how these techniques are applied across multiple disease domains, including cardiovascular diseases, cancer, diabetes, neurological disorders, and infectious diseases.

Furthermore, the paper critically evaluates the performance of these models based on key metrics such as accuracy, precision, recall, and computational efficiency. It also identifies major challenges, including data quality issues, class imbalance, lack of interpretability, and ethical concerns related to privacy and bias. The findings suggest that while machine learning significantly enhances disease classification capabilities, its integration into real-world healthcare systems requires improved transparency, standardized evaluation frameworks, and interdisciplinary collaboration. The study concludes by outlining future research directions, emphasizing the importance of explainable artificial intelligence and hybrid models to ensure reliable and scalable healthcare solutions.