Table 5.

Results of the Western Ontario and McMaster Universities Osteoarthritis Index–based processing approach (n=463) in terms of accuracy, precision, sensitivity, specificity, and F1-score for each model.

Model		Accuracy (%)	Precision (%)	Sensitivity (%)	Specificity (%)	F1-score (%)
Word_Tokenize
	BiLSTMa	0.90	0.91	0.93	0.87	0.92
	GRUb	0.88	0.88	0.93	0.81	0.90
	CNNc	0.90	0.91	0.92	0.87	0.92
DeepCut
	BiLSTM	0.89	0.88	0.94	0.81	0.91
	GRU	0.89	0.90	0.91	0.86	0.91
	CNN	0.90	0.91	0.92	0.87	0.91
AttaCut
	BiLSTM	0.91	0.91	0.94	0.87	0.93
	GRU	0.89	0.89	0.93	0.84	0.91
	CNN	0.90	0.92	0.92	0.88	0.92

^aBiLSTM: bidirectional long short-term memory.

^bGRU: gated recurrent unit.

^cCNN: convolutional neural network.