Heart disease prediction using hyper parameter optimization (HPO) tuning

Coronary artery disease prediction is considered to be one of the most challenging tasks in the health care industry. In our research, we propose a prediction system to detect the heart disease. Three Hyper Parameter Optimization (HPO) techniques Grid Search, Randomized Search and Genetic programming (TPOT Classifier) were proposed to optimize the performance of Random forest classifier and XG Boost classifier model. The performance of the two models Random Forest and XG Boost were compared with the existing studies. The performance of the models is evaluated with the publicly available datasets Cleveland Heart disease Dataset (CHD) and Z-Alizadeh Sani dataset. Random Forest along with TPOT Classifier achieved the highest accuracy of 97.52%for CHD Dataset. Random Forest with Randomized Search achieved the highest accuracy of 80.2%, 73.6% and 76.9% for the diagnosis of the stenos is of three vessels LAD, LCX and RCA respectively with ZAlizadeh Sani Dataset. The results were compared with the existing studies focusing on prediction of heart disease that were found to outperform their results significantly.

Automated summary

The study proposed a prediction system to detect heart disease by optimizing the performance of Random Forest and XG Boost classifiers using three Hyper Parameter Optimization techniques. It achieved high accuracy in predicting coronary artery disease and outperformed existing studies in heart disease prediction.