Table 2.

Precision, Recall, Accuracy, and F-statistic for SQLServer (Sentence), SQLServer (Report), and NegEx

		Fracture Status as Determined by Gold Standard
		Positive	Negative
Fractures identified by SQLServer (report)	Positive	2 reportsa	0 reportsb	Precision: 1.00
	Negative	11 reportsc	387 reportsd	Negative predictive value: 1.00
				Accuracy: 0.97
		Recall: 0.15	Specificity: 1.00	F-statistic: 0.26
Fractures identified by SQLServer (sentence)	Positive	12 reportsa	0 reportb	Precision: 1.00
	Negative	1 reportsc	387 reportsd	Negative predictive value: 0.99
				Accuracy: 0.92
		Recall: 0.92	Specificity: 1.00	F-statistic: 0.96
Fractures identified by NegEx	Positive	13 reportsa	0 reportsb	Precision: 1.00
	Negative	0 reportsc	387 reportsd	Negative predictive value: 1.00
				Accuracy: 1.00
		Recall: 1.00	Specificity: 1.00	F-statistic: 1.00

Notes:

Accuracy: (true positives + true negatives)/(true positives + true negatives + false positives + false negatives)

Precision: (true positives)/(true positives + false positives)

Recall: (true positives)/(true positives + false negatives)

Negative predictive value: (true negatives)/(true negatives + false negatives)

Specificity: (true negatives)/(true negatives + false positives)

F-statistic: 2 ^* (precision ^* recall)/(precision + recall)

^atrue positives

^bfalse positives

^cfalse negatives

^dtrue negatives