Skip to main content

View full-text article in PMC

. 2020 May 8;8(5):e15992. doi: 10.2196/15992

Table 1.

Performance metrics of the models.

Model	Training data					Test data
	Accuracy	Specificity	Sensitivity	MCC^a	AUC^b (95% CI)	Accuracy	Specificity	Sensitivity	MCC	AUC (95% CI)
MLP^c	0.97	1.00	0.00	0.00	0.60 (0.59-0.61)	0.97	1.00	0.00	0.00	0.57 (0.55-0.59)
MLP^d	0.68	0.39	0.97	0.44	0.84 (0.83-0.85)	0.84	0.82	0.23	0.02	0.54 (0.53-0.55)
CNN^e	0.97	1.00	0.00	0.00	0.58 (0.56-0.60)	0.97	1.00	0.00	0.00	0.55 (0.54-0.56)
CNN^d	0.63	0.56	0.70	0.26	0.79 (0.78-0.80)	0.95	0.97	0.06	0.03	0.57 (0.59-0.61)
RNN^f	0.97	1.00	0.00	0.00	0.58 (0.57-0.59)	0.97	1.00	0.00	0.00	0.56 (0.55-0.57)
RNN^d	0.58	0.66	0.49	0.15	0.65 (0.64-0.66)	0.91	0.93	0.14	0.05	0.55 (0.53-0.57)

^aMCC: Matthews correlation coefficient.

^bAUC: area under curve.

^cMLP: multilayer perceptron.

^dTrained using synthetic minority oversampling technique data.

^eCNN: convolutional neural network.

^fRNN: recurrent neural network.