Table 2 Comparison of predictive performance across different models on the five-fold cross-validation dataset and multi-center independent test datasets

Dataset cohort	Methods	IDH				1p/19q				Pathology types
Dataset cohort	Methods	ACC	AUC	SPE	SEN	ACC	AUC	SPE	SEN	ACC	AUC	SPE	SEN
Validation	AHI	0.85	0.92	0.84	0.85	0.86	0.90	0.79	0.86	0.80	0.91	0.90	0.79
	MTTU	0.84	0.90	0.83	0.84	0.83	0.90	0.76	0.84	0.76	0.89	0.87	0.75
	ST	0.91	0.93	0.90	0.91	0.91	0.93	0.88	0.91	0.86	0.93	0.93	0.87
	PSNet	0.79	0.81	0.70	0.79	0.83	0.77	0.67	0.83	0.70	0.73	0.76	0.57
	MDL	0.81	0.87	0.79	0.81	0.81	0.87	0.72	0.81	0.78	0.87	0.86	0.72
	SSL-MISS-Net	0.94	0.96	0.93	0.94	0.94	0.96	0.93	0.94	0.91	0.96	0.96	0.91
Public Test Set	AHI	0.81	0.90	0.80	0.81	0.86	0.84	0.69	0.86	0.75	0.89	0.84	0.75
	MTTU	0.75	0.84	0.73	0.75	0.86	0.85	0.69	0.86	0.74	0.89	0.82	0.74
	ST	0.77	0.84	0.75	0.77	0.83	0.83	0.76	0.83	0.73	0.87	0.83	0.73
	PSNet	0.46	0.59	0.54	0.46	0.71	0.47	0.29	0.71	0.52	0.64	0.53	0.52
	MDL	0.78	0.85	0.76	0.78	0.84	0.79	0.71	0.84	0.75	0.90	0.83	0.75
	SSL-MISS-Net	0.87	0.93	0.88	0.87	0.89	0.92	0.82	0.89	0.89	0.91	0.91	0.79
In-house Test Set	AHI	0.65	0.73	0.64	0.65	0.73	0.77	0.68	0.78	0.67	0.74	0.78	0.55
	MTTU	0.67	0.72	0.67	0.67	0.68	0.71	0.69	0.74	0.65	0.70	0.75	0.55
	ST	0.68	0.68	0.69	0.67	0.70	0.71	0.70	0.76	0.64	0.69	0.75	0.51
	PSNet	0.37	0.56	0.63	0.37	0.72	0.61	0.28	0.72	0.40	0.57	0.60	0.40
	MDL	0.57	0.65	0.65	0.58	0.66	0.69	0.68	0.73	0.60	0.69	0.75	0.45
	SSL-MISS-Net	0.80	0.85	0.81	0.80	0.80	0.84	0.80	0.80	0.79	0.81	0.83	0.71

Quick links

Search