Predictive Modeling for Cardiovascular Mortality

Heart failure is a major public health concern with high mortality rates. In this research, I developed a predictive model to estimate mortality risk based on clinical features such as age, ejection fraction, serum creatinine, and other biomarkers.

Using a dataset of heart failure patients, I applied logistic regression to analyze the relationship between these variables and the likelihood of death. My model achieved 85.6% accuracy, demonstrating the potential of machine learning in clinical decision support.