Table 5.

Performance of deduplication tools in the Diabetes dataset

	TP	TN	FN	FP	Sensitivity (SE)	Specificity (SE)	Precision	F1	Time
Human	893	581	368	3	0.708 (0.013)	0.995 (0.003)	0.997	0.828	Unknown
EndNote	1218	584	43	0	0.966 (0.005)	1 (0)	1.0	0.983	< 5 min
SRA-DM	1147	514	114	70	0.91 (0.008)	0.88 (0.013)	0.942	0.926	< 5 min
ASySD	1259	584	2	0	0.998 (0.001)	1 (0)	1.0	0.999	< 5 min

TP True positives, TN True negatives, FN False negatives, FP False positives, SE Standard error