Automatic medical encoding with SNOMED categories
2008

Automatic Medical Encoding with SNOMED Categories

Sample size: 1000 publication Evidence: moderate

Author Information

Author(s): Ruch Patrick, Gobeill Julien, Lovis Christian, Geissbühler Antoine

Primary Institution: Medical Informatics Service, University and University Hospitals of Geneva, Geneva, Switzerland

Hypothesis

Can a new tool improve the encoding of medical episodes using SNOMED CT terminology?

Conclusion

The hybrid system shows improved precision in categorizing medical texts with SNOMED CT compared to existing terminologies.

Supporting Evidence

  • The hybrid system achieved a top precision of over 80%.
  • Manual evaluations indicated that SNOMED CT could improve upon existing medical terminologies like MeSH.

Takeaway

This study created a tool that helps doctors quickly label medical records using a special coding system called SNOMED.

Methodology

The study used a hybrid system combining a regular expression classifier and a vector-space classifier to categorize medical texts.

Limitations

Further studies are needed to evaluate the tool's effectiveness in real clinical settings.

Statistical Information

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1186/1472-6947-8-S1-S6

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication