Skip to main content

Table 5 Performance of model verification for identifying CABG SSIs (verification data: medical center B)

From: Is it possible to identify cases of coronary artery bypass graft postoperative surgical site infection accurately from claims data?

 

Sensitivity

Specificity

PPV

NPV

Accuracy

ICD-9-CM-based model

35.29 (6/17)

96.98 (803/828)

19.35 (6/31)

98.65 (803/814)

95.74 (809/845)

Model 1

5.88 (1/17)

99.76 (826/828)

33.33 (1/3)

98.10 (826/842)

97.87 (827/845)

Model 2

52.94 (9/17)

97.46 (807/828)

30.00 (9/30)

99.02 (807/815)

96.57 (816/845)

Model 3

100.00 (17/17)

2.42 (20/828)

2.06 (17/825)

100.00 (20/20)

4.38 (37/845)

Model 4

94.12 (16/17)

94.93 (786/828)

27.59 (16/58)

99.87 (786/787)

94.91 (802/845)

Model 5

88.24 (15/17)

99.28 (822/828)

71.43 (15/21)

99.76 (822/824)

99.05 (838/845)

  1. % (numerator/denominator).
  2. ICD-9-CM: The International Classification of Diseases, Ninth Revision, Clinical Modification; PPV: positive predictive value; NPV: negative predictive value. Model 1: the classification algorithms (strict); Model 2: the classification algorithms (moderate); Model 3: the classification algorithms (loose); Model 4: the multivariable regression model: Model 5: data mining-decision tree model.