Table 12.

Multi-class prediction task comparison of three respiratory class diseases: COVID-19 vs. Pneumonia vs. Normal.

Reference	AI Architecture	ACC	PRE	SEN	F1_Score
(Pham 2020)	Inception-V3	0.90	0.89	0.91	0.89
	MobileNet-V2	0.90	0.90	0.89	0.90
(Wu et al., 2020)	ResNet-V2	0.88	0.87	0.86	0.86
(Khan et al., 2020)	Xception	0.90	0.92	0.87	0.90
(Oh et al., 2020)	DenseNet-121	0.88	0.90	0.85	0.87
(Luz et al., 2021),	EfficientNet-B0	0.89	0.88	0.89	0.88
(Perumal et al., 2021)	VGG-16	0.87	0.87	0.85	0.86
(Shome et al., 2021)	COVID-Transformer	0.92	0.93	0.89	0.91
(Chowdhury et al., 2021)	ECOVNet (pre-trained EfficientNet)	0.95	0.95	0.95	0.95
(Chakraborty et al., 2022)	ResNet18 + TransferLearning	0.96	–	0.94	0.93
(Perumal et al., 2022)	INASNET (Inception Nasnet)	0.94	0.94	0.94	0.94
(Ho et al., 2022)	Feature-based Ensemble	0.94	0.95	0.94	0.94
Ours (2023)	The Proposed XAI Model	0.96	0.95	0.95	0.95