Blood Work Analysis and Disease Prediction using Random Forest Classifier

This project focuses on predicting diseases from blood work test results using a machine learning approach. A Random Forest Classifier is implemented to analyse various clinical parameters such as glucose levels, cholesterol, hemoglobin, platelet count, and other hematological and biochemical measures. The dataset undergoes preprocessing, feature scaling, and label encoding. The model is evaluated using accuracy score, confusion matrix, cross-validation, and explainability techniques such as SHAP (SHapley Additive exPlanations). The achieved accuracy demonstrates the potential of machine learning in aiding clinical decisionmaking.