rss
J Am Med Inform Assoc 15:198-202 doi:10.1197/jamia.M2585
  • The Practice of Informatics

Automatic Classification of Foot Examination Findings Using Clinical Notes and Machine Learning

Table 3

Distribution of Misclassification Errors

Actual Predicted Structural N (% Total) Neurological N (% Total) Vascular N (% Total)
abnormal normal 30 (25.9) 15 (20.5) 23 (18.9)
abnormal not assessed 13 (11.2) 13 (17.8) 29 (23.8)
normal abnormal 29 (25.0) 24 (32.9) 23 (18.9)
normal not assessed 10 (8.6) 8 (10.9) 19 (15.6)
not assessed abnormal 24 (20.7) 7 (9.6) 17 (13.9)
not assessed normal 10 (9.0) 6 (8.3) 11 (9.0)
Total classification errors 116 73 122

This Article

  1. Abstract
  2. Full text
  3. PDF

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.