Table 8.

Metrics for the training and testing (external) cohorts for the W2V^a-Bi-LSTM^b model.

Training data size	AUCc score	Sensitivity	Specificity	Precision	F1-score
10,000	0.78	0.32	0.95	0.59	0.41
100,000	0.81	0.42	0.92	0.52	0.46
1,000,000	0.84	0.46	0.94	0.62	0.52

^cW2V: Word-2-Vec.

^cBi-LSTM: bidirectional long short-term memory.

^cAUC: area under the receiver operating characteristic curve.