A hybrid cost-sensitive ensemble for heart disease prediction

Abstract

Background: Heart disease is the primary cause of morbidity and mortality in the world. It includes numerous problems and symptoms. The diagnosis of heart disease is difficult because there are too many factors to analyze. What's more, the misclassification cost could be very high. Methods: A cost-sensitive ensemble method was proposed to improve the efficiency of diagnosis and reduce the misclassification cost. The proposed method contains five heterogeneous classifiers: random forest, logistic regression, support vector machine, extreme learning machine and k-nearest neighbor. T-test was used to investigate if the performance of the ensemble was better than individual classifiers and the contribution of Relief algorithm. Results: The best performance was achieved by the proposed method according to ten-fold cross validation. The statistical tests demonstrated that the performance of the proposed ensemble was significantly superior to individual classifiers, and the efficiency of classification was distinctively improved by Relief algorithm. Conclusions: The proposed ensemble gained significantly better results compared with individual classifiers and previous studies, which implies that it can be used as a promising alternative tool in medical decision making for heart disease diagnosis.

Optimized encryption based elliptical curve diffie-hellman approach for secure heart disease prediction

“…From the results, it is found that existing methods like RF showed E value as 80.43%, precision as 75.52%, recall as 60.19%, G-mean as 71.04, MC as 87.93%, specificity as 86.34% and AUC as 74.07%. On the other hand, traditional methods like LR, SVM, ELM, KNN and [36] showed better results concerning all the metrics. However, in comparison with the proposed system, existing methods showed low performance.…”

“…In addition, proposed and conventional systems are analyzed in the Hungarian dataset. The obtained outcomes are presented in Table 8 [36]. From the results, it is found that existing methods like RF showed E value as 80.43%, precision as 75.52%, recall as 60.19%, G-mean as 71.04, MC as 87.93%, specificity as 86.34% and AUC as 74.07%.…”

“…From Table 7, it is found that the proposed system showed effective performance with E as 95.62%, precision as 96.32%, recall as 94.85%, G-mean as 93.68%, MC as 20.96%, specificity as 23.47% and AUC as 96.99%. Hence, the proposed system is effective in predicting heart disease than conventional [36]. Accuracy is a significant parameter in the medical domain.…”

“…The graphs visualized the optimal security achieved in the proposed model compared to other techniques. Figure 5 Encryption time comparison of proposed and existing study [35] Figure 6 Decryption time comparison of proposed and existing study [35] Figure 7 Key size evaluation of proposed and existing [35] From Table 7 [36], it is found that existing methods such as Random Forest (RF), Logistic Regression (LR), Support Vector Machine (SVM), Extreme Learning Machine (ELM), K-Nearest Neighbour (KNN) and [36] showed better precision, recall, Gme an, MC, AUC, specificity and E. However the proposed system showed a high rate of E with 95.01%, precision with 97.03%, recall with 96.36%, G-mean with 95.09%, MC with 17.43%, specificity with 96.63% and AUC with 97.63%. This proved its efficacy than conventional systems [36].…”