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

Table 8

Results of 5-CV classification performances (F-measure, specificity, and G-means) obtained for automated myocarditis detection using various conventional and metaheuristic 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.
CNN + GDM + RL	0.757	0.811	0.825	0.801	0.026	0.827	0.882	0.898	0.875	0.028	0.805	0.848	0.860	0.840	0.021
CNN + GDA + RL	0.765	0.799	0.811	0.792	0.019	0.834	0.863	0.902	0.860	0.028	0.812	0.839	0.850	0.834	0.015
CNN + GDMA + RL	0.771	0.806	0.849	0.808	0.033	0.838	0.880	0.909	0.877	0.026	0.815	0.843	0.878	0.846	0.026
CNN + OSS + RL	0.759	0.799	0.825	0.797	0.024	0.859	0.873	0.885	0.872	0.010	0.804	0.839	0.861	0.837	0.021
CNN + BR + RL	0.776	0.784	0.794	0.784	0.007	0.841	0.850	0.921	0.868	0.034	0.821	0.825	0.829	0.825	0.003
CNN + GWO + RL	0.779	0.797	0.828	0.801	0.021	0.856	0.880	0.889	0.877	0.013	0.821	0.836	0.863	0.840	0.018
CNN + BAT + RL	0.782	0.793	0.823	0.801	0.018	0.873	0.885	0.901	0.885	0.010	0.824	0.832	0.859	0.839	0.016
CNN + COA + RL	0.752	0.803	0.844	0.796	0.038	0.835	0.854	0.901	0.862	0.028	0.800	0.845	0.876	0.837	0.031
CNN + WOA + RL	0.768	0.793	0.798	0.785	0.014	0.832	0.869	0.888	0.866	0.021	0.812	0.832	0.839	0.827	0.012