Diagnosis of Chronic Ischemic Heart Disease Using Machine Learning Techniques

Table 2

Machine learning approach to predict heart diseases.

Reference	Method	Accuracy
[1]	Fuzzy-expert system	94%
[28]	Svm, KNN, LG, RF, NB, & LSTM	58%, 76%, 78%, 79%, 82% & 94%
[29]	Hybrid model	85.71%
[30]	KNN with parameter weighting	81.9%
[19]	ANN & BPNN	83%
[20]	LR, RF, NB, GB & SVM	86%, 80%, 84%, 84% & 79%
[21]	NB, SVM & KNN	75%, 45.11% & 50.44%,
[22]	Fuzzy logic	98%
[26]	GUI and WAC	81.51%
[27]	KNN	80%
[31]	CNN-UDRP (KNN, NB)	82%,
[32]	GDB tree algorithm & RF	96.75% & 97.98%
[33]	CSHCP	97%
[34]	CA-SHR	96.02%
[9]	CervDetect	93.6%
[35]	Modified YOLOv5	96.50%
[25]	K-means/MAFIA with ID3 & C4.5	89.0% & 81.9%