Machine Learning Based Assistance to Healthcare Professionals in Disease Prediction and Classification Using Basic Patient Profile

Patient profile is critical for medical practitioners, clinicians, and researchers performing clinical evaluations, research studies, and epidemiological investigations. Analyzing patient data provides insights into symptom prevalence and trends across diverse medical illnesses, which aids in trend detection, diagnosis, treatment, and public health improvement. This work investigates the Machine Learning (ML) life cycle, which includes data balancing, feature analysis, K-fold cross-validation, and hyperparameter tuning, to develop classification models for predicting disease presence or absence. Accuracy, Recall, F1 score, Area under the Curve (AUC), and the Jaccard Index are measures used to evaluate ML classifiers like Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), and Boosting Classifier models. Gradient Boost emerges as the best-performing model, blending performance with computational economy, making it ideal for this classification challenge. This comprehensive approach enhances the understanding of illness causes, facilitates personalized treatment, and informs preventive measures.