. 2016 Sep 20;24(3):472–480. doi: 10.1093/jamia/ocw136

Table 2.

Summary statistics for human-authored order set use within the first 24 hours of hospitalization for 4820 validation patients

Metric (per first 24 hours of each hospitalization)	Mean (std dev)	Median interquartile range
A: Order sets used	3.0	3
A: Order sets used	(1.4)	(2, 4)
B: Orders entered (including non-order set)	32.7	30
B: Orders entered (including non-order set)	(15.7)	(22, 41)
C: Orders entered from order sets	13.3	12
C: Orders entered from order sets	(7.9)	(8, 18)
D: Orders available from used order sets	129.0	130
D: Orders available from used order sets	(47.5)	(102, 153)
E: Order set precision = (C/D)	11%	9.5%
E: Order set precision = (C/D)	(7.2%)	(6.3%, 13.8%)
F: Order set recall = (C/B)	43%	42%
F: Order set recall = (C/B)	(20%)	(28%, 58%)

Metrics count only orders used in the final set of 1512 preprocessed clinical orders after normalization of medication orders and exclusion of rare orders and common process orders.