Multi Disease Prediction and Hospital Recommendation

Healthcare systems worldwide face challenges in providing timely and accurate diagnoses, especially in rural areas and locations with limited resources. To address this problem, this project proposes a unified framework for predicting multiple diseases using machine learning (ML), deep learning (DL), and ensemble methods. The system employs various models, including Random Forest, Support Vector Machines, Naïve Bayes, Gradient Boosting, and Neural Networks. These models are trained on clinical datasets and symptom-based inputs to predict a range of diseases, such as diabetes, heart disease, liver disorders, kidney disease, Parkinson’s, breast cancer, and lung cancer. With a modular design, the framework can manage symptom-driven predictions and disease-specific classifiers, making it flexible and scalable. Better preprocessing, feature selection, and hyperparameter tuning improve accuracy and generalization. Big data technologies efficiently manage large-scale medical records. The system also provides hospital recommendations, making it suitable for telemedicine platforms, rural healthcare centers, and personal wellness applications. Results from several studies demonstrate high precision, recall, and sensitivity, with ensemble models like gradient boosting achieving accuracy close to 99%. This project enables proactive healthcare through early disease detection. It also reduces the burden on medical infrastructure, supports physicians in clinical decision-making, and provides individuals with access to affordable diagnostic support.