Heart Attack Risk Prediction using Machine Learning

Dataset: Heart Attack Analysis & Prediction Dataset (Kaggle)

Tech Stack: Python, Pandas, Scikit-learn, Matplotlib, Seaborn

develop and evaluate machine learning models that can predict the likelihood of a heart attack in patients, based on clinical and biometric parameters. This model can assist healthcare professionals in early risk assessment and preventive care.

Dataset Summary

Total Samples: 303

Target Variable: output (1 = Heart Attack, 0 = No Heart Attack)

Features (13):

age, sex, cp (chest pain type), trtbps (resting BP), chol (cholesterol), fbs (fasting blood sugar), restecg, thalachh (max heart rate), exang (exercise-induced angina), oldpeak (ST depression), slp (slope of ST segment), ca (major vessels), thal? Models Implemented

1. Random Forest Classifier

Ensemble method using multiple decision trees

Robust against overfitting

Provides feature importance metrics

2. Multi-Layer Perceptron (MLP) Classifier

Neural network with two hidden layers (100 and 50 neurons)

StandardScaler used to normalize input data

Captures non-linear relationships in the data