Disease Prediction for Smart Healthcare System using Supervised Machine Learning Approach: A Review

Abstract

Disease prediction plays a vital role in modern healthcare systems by enabling early diagnosis, timely treatment, and effective patient management. Traditional healthcare diagnosis methods are often time-consuming and highly dependent on medical experts, which may lead to delays and inaccuracies in disease identification. With the rapid growth of healthcare data and artificial intelligence technologies, supervised machine learning approaches have become highly effective for predicting various diseases using patient medical records, clinical parameters, and diagnostic datasets. This review study presents an analysis of different supervised machine learning algorithms used in smart healthcare systems for disease prediction applications. Various techniques such as Decision Tree, Random Forest, Support Vector Machine (SVM), Naïve Bayes, K-Nearest Neighbor (KNN), Logistic Regression, and Gradient Boosting are discussed based on their performance, accuracy, and applicability in healthcare diagnosis. The study also examines different datasets, preprocessing methods, feature selection techniques, and evaluation metrics used in disease prediction systems. Comparative analysis indicates that supervised machine learning models can significantly improve prediction accuracy, reduce diagnostic time, and assist healthcare professionals in decision-making processes. The review concludes that machine learning-based smart healthcare systems provide reliable, cost-effective, and efficient solutions for disease prediction and patient care management.