Skip to main content

Table 1 The accuracy of ICD9, HITEx and the combinations of ICD9 and HITEx for principal diagnosis and co-morbidity extraction.

From: Extracting principal diagnosis, co-morbidity and smoking status for asthma research: evaluation of a natural language processing system

  

ICD9

HITEx

ICD9 and HITEx

ICD9 or HITEx

Exclude Insufficient Data

Principal

80.08%

81.64%

75.78%

85.94%

 

Co-morbidity

82.57%

86.72%

88.80%

80.50%

Insufficient Data = Yes

Principal

71.57%

73.20%

66.34%

78.43%

 

Co-morbidity

74.18%

77.45%

79.41%

72.22%

Insufficient Data = No

Principal

78.76%

79.74%

76.80%

81.70%

 

Co-morbidity

83.33%

84.64%

90.52%

77.45%