An empirical study on machine learning algorithms for heart disease prediction

Tsehay Admassu Assegie, Prasanna Kumar Rangarajan, Napa Komal Kumar, Dhamodaran Vigneswari

Abstract


In recent years, machine learning is attaining higher precision and accuracy on clinical heart disease dataset classification. However, literature shows that the quality of heart disease feature used for training model has significant impact on the outcome of predictive model. Thus, this study focuses on exploring the impact of the quality of heart disease feature on the performance of machine learning model on heart disease prediction by employing recursive feature elimination with cross validation (RFECV). Furthermore, the study explores heart disease feature with significant effect on model output. The dataset for experimentation is obtained from University of California Irvine (UCI) machine learning dataset. In the experiment is implemented using support vector machine (SVM), logistic regression (LR), decision tree (DT) and random forest (RF) are employed. The performance of SVM, LR, DT and RF model. The result appears to prove that the quality of feature significantly affects performance of the model. Overall, the experiment evidently proves that RF outperforms as compared to other algorithms. In conclusion, predictive accuracy of 99.7% is achieved with RF.

Keywords


Decision tree; Heart disease prediction; Random forest; Recursive feature elimination; Support vector machine



DOI: http://doi.org/10.11591/ijai.v11.i3.pp%25p

Refbacks

  • There are currently no refbacks.


View IJAI Stats

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.