Michigan Data Science Team | Winter 2026
Identifying key clinical factors that distinguish patient survival from mortality using statistical analysis and machine learning techniques.
Our analysis confirms the groundbreaking finding from Chicco & Jurman (2020): machine learning models can predict heart failure survival using just two biomarkers, performing comparably to models using all 13 features.
Kidney function indicator
Heart pumping efficiency
Random Forest (2 features)
Random Forest (All 13 features)
Simpler models achieve comparable performance
This project replicates and extends the findings from peer-reviewed medical informatics research.
Chicco & Jurman (2020) published in BMC Medical Informatics, demonstrating ML prediction of heart failure survival.
Random Forest, Gradient Boosting, SVM, and other classifiers were compared for predictive performance.
Both serum creatinine and ejection fraction are routinely measured, enabling practical clinical application.
A structured approach to learning data science through hands-on medical data analysis.
Load the dataset, understand features, create visualizations, and identify patterns in heart failure data.
Apply hypothesis testing, correlation analysis, feature importance, and multicollinearity detection.
Dimensionality reduction with PCA and clustering to find natural groupings in patient data.
Build and evaluate machine learning models to predict patient survival outcomes.
A comprehensive toolkit for medical data analysis and machine learning.
Rigorous hypothesis testing to identify significant differences between patient groups.
Machine learning techniques to rank predictive power of clinical features.
Discover hidden patterns and natural groupings in patient data.
Build robust classifiers to predict patient survival outcomes.
Clone the repository and start exploring in minutes.
# Clone the repository git clone https://github.com/MichiganDataScienceTeam/W26-MDST-Project_Heart-Failure-Survival-Analysis.git cd W26-MDST-Project_Heart-Failure-Survival-Analysis # Set up virtual environment python -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate # Install dependencies and launch pip install -r requirements.txt jupyter notebook
Guiding the project with expertise in data science and machine learning.
Project Lead
Project Lead
Documentation, tutorials, and references to deepen your understanding.