RLMD-PA: A Reinforcement Learning-Based Myocarditis Diagnosis Combined with a Population-Based Algorithm for Pretraining Weights

Table 5

5-CV classification performance (F-measure, specificity, and G-means) obtained for automated myocarditis detection using various machine learning algorithms with the Z-Alizadeh Sani myocarditis dataset.

	F-measure					Specificity					G-means
Method	Min	Median	Max	Mean	Std.dev.	Min	Median	Max	Mean	Std.dev.	Min	Median	Max	Mean	Std.dev.
SVM	0.540	0.652	0.695	0.639	0.060	0.505	0.662	0.760	0.651	0.093	0.583	0.704	0.752	0.692	0.065
KNN	0.365	0.554	0.585	0.516	0.089	0.528	0.601	0.629	0.587	0.039	0.459	0.619	0.643	0.587	0.075
Naïve Bayes	0.391	0.522	0.623	0.520	0.092	0.610	0.642	0.692	0.645	0.031	0.499	0.608	0.682	0.600	0.072
Logistic regression	0.565	0.571	0.665	0.593	0.042	0.606	0.665	0.716	0.663	0.049	0.631	0.646	0.724	0.659	0.038
Random forests	0.408	0.533	0.559	0.509	0.063	0.342	0.471	0.529	0.459	0.071	0.429	0.567	0.605	0.545	0.071