Скачать или смотреть Heart Disease Prediction Using Machine Learning | XGBoost, SHAP, and More

🎥 Heart Disease Prediction Using Machine Learning | XGBoost, SHAP, and More

Welcome! In this video, I walk you through a heart disease prediction project using machine learning on the UCI Cleveland dataset.

🚀 Project Highlights:

Built and compared 4 ML models: Logistic Regression, Random Forest, XGBoost, and LightGBM

Achieved up to 86% accuracy and 0.91 ROC AUC using XGBoost

Applied SHAP to explain predictions and feature importance

Based on real-world healthcare data

Full Jupyter Notebook and Research Paper included

📄 Included Files:

Main-code.ipynb: Complete code for training and evaluating the models

Heart_Disease_Identification_Method_Using_Machine_Learning_Classification_in_E-Healthcare.pdf: Research paper

Dataset: UCI Cleveland Heart Disease (link below)

Github :https://github.com/Sudarshan9741/mach...

📊 Evaluation Metrics:

Accuracy

F1 Score

ROC AUC

🧠 Best Model: XGBoost
🔍 Explainability: SHAP (SHapley Additive exPlanations)

📂 Dataset Source:
UCI Heart Disease Dataset

📦 Python Libraries Used:

scikit-learn

xgboost

lightgbm

shap

pandas, matplotlib

👉 Don’t forget to like, subscribe, and drop your questions in the comments!
#HeartDiseasePrediction #MachineLearning #XGBoost #LightGBM #RandomForest #HealthcareAI #PythonML #SHAP #MLProject #DataScience #HeartDisease #UCIDataset