Table 1.

Average recall, precision, and F-measure of the deep learning model and Clinical Query Broad filter according to the Clinical Hedges gold standard (N=20).

Parameter	Deep learning (%)	CQa broad (%)	P value
Recall	96.9	98.4	<.001
Precision	34.6	22.4	<.001
F-measure	51.0	36.5	<.001

^aCQ: PubMed Clinical Query Treatment filter