rss
J Am Med Inform Assoc 13:516-525 doi:10.1197/jamia.M2077
  • Focus on Automated Categorization Technique

Automating the Assignment of Diagnosis Codes to Patient Encounters Using Example-based and Machine Learning Techniques

Table 2

Macro-average Precision/Recall Results for Type A, B and C Data. The Cells for Precision Recall Contain the Macro-averaged Value for Precision/Recall, Followed by the Total Number of Test Instances, Followed by the Width of a 95% Confidence Interval

Precision avg. precision (N samples) 95% CI Recall avg. precision (N samples) 95% CI F-score
Type A data 98.0(2,981) ±0.5 98.3(2,981) ±0.4 98.2
Type B data 90.1(3,000) ±0.7 95.6(3,000) ±0.6 93.1
Type C data 58.5(2,218) ±1.9 50.7(2,218) ±1.8 54.4

This Article

Access policy for JAMIA

All content published in JAMIA is deposited with PubMed Central by the publisher with a 12 month embargo. Authors/funders may pay an Unlocked fee of $2,000 to make the article free on the JAMIA website and PMC immediately on publication.

All content older than 12 months is freely available on this website.

AMIA members can log in with their JAMIA user name (email address) and password or via the AMIA website.