Predictive Healthcare based on Symptoms and Regional Trends

Abstract

The advancement of the technologies like machine learning has brought remarkable improvements to modern healthcare by enabling intelligent systems that assist in disease detection and clinical decision-making. Identifying diseases at an early stage allows patients to receive prompt treatment, improving recovery outcomes while reducing the likelihood of serious medical complications. This study proposes a machine learning-driven health and disease prognosis system designed to predict multiple diseases based on patient symptoms and relevant clinical information. To evaluate predictive performance, the system implements several algorithms, including Random Forest, Decision Tree, Logistic Regression, Support Vector Machine (SVM), K-Nearest Neighbours (KNN), and Naïve Bayes. A comparative analysis is conducted to determine the most accurate and reliable model for disease prediction. The application is deployed through a Flask-based web interface that enables users to enter symptoms, receive disease predictions, and obtain appropriate health guidance and medical recommendations. Before model training, the dataset undergoes comprehensive preprocessing, including treatment of missing values, feature selection, and data normalization and predictions. The experimental type of results indicates the ensemble-based approaches, particularly Random Forest, achieve superior predictive performance when compared to the individual classification models. The proposed system is reliable, scalable, and economical approach for preliminary disease assessment, which helps individuals to make decisions while serving as a valuable decision-support tool for medical professionals.