Heart Failure prediction

The Heart Failure Prediction project aims to predict the likelihood of heart disease based on patient clinical data. The workflow included Exploratory Data Analysis (EDA), model development using Logistic Regression, deployment on Streamlit, and presentation preparation in PowerPoint. The EDA phase focused on analyzing variables such as ChestPainType, Cholesterol, FastingBS, RestingECG, MaxHR, ExerciseAngina, Oldpeak, and ST_Slope to understand their relationship with heart disease. Logistic Regression was applied to estimate the relationship between the outcome variable (heart disease) and the predictors, achieving balanced and interpretable results. Additional models including Random Forest, KNN, SVM, Decision Tree, and Naive Bayes were also tested for comparison. The final Streamlit web app allows users to input medical data and receive predictions in real time, while the PowerPoint report summarizes the analysis, model performance, and insights.