Find in Library

The goal of this research is to develop a reliable decision-support system for the survival prediction of heart failure patients by utilizing their clinical records and laboratory test results. Forecasting heart-failure related events in clinical practice tend to be quite inaccurate and highly variable. Identifying the key drivers of heart failure is also clinically very important. In this regard, we develop a model to accurately identify the patients who are at risk utilizing machine learning techniques. This can help clinicians make informed decisions regarding the intensity of treatment required for a patient. For this study, we have utilized a heart failure dataset originally collected from the Faisalabad Institute of Cardiology and the Allied Hospital in Faisalabad, Pakistan. Sampling strategy is incorporated into the ensemble learning framework to develop a more robust Random Forest Classifier that can effectively deal with the imbalanced nature of the data and provide a more generalizable result with higher accuracy. Two different feature selection techniques - Chi-square test and Recursive Feature Elimination are utilized to identify the features that are most significant in terms of survival prediction of heart failure patients. Using our proposed approach, a maximum G-mean score of 76.83% with a sensitivity score of 80.21% was achieved, which is significantly higher than what has been reported by other researchers. Thus, our proposed framework has the potential to be an effective tool to identify the patients who are at risk and guide clinicians accordingly to take pertinent measures.