Use of a Large Language Model to Identify and Classify Injuries With Free-Text Emergency Department Data

Giulia Lorenzoni; Dario Gregori; Silvia Bressan; Honoria Ocagli; Danila Azzolina; Liviana Da Dalt; Paola Berchialla

doi:10.1001/jamanetworkopen.2024.13208

Use of a Large Language Model to Identify and Classify Injuries With Free-Text Emergency Department Data

JAMA Netw Open. 2024 May 1;7(5):e2413208. doi: 10.1001/jamanetworkopen.2024.13208.

Authors

Giulia Lorenzoni¹, Dario Gregori¹, Silvia Bressan², Honoria Ocagli¹, Danila Azzolina³, Liviana Da Dalt², Paola Berchialla⁴

Affiliations

¹ Unit of Biostatistics, Epidemiology and Public Health, Department of Cardiac, Thoracic, Vascular Sciences and Public Health, University of Padova, Padova, Italy.
² Division of Pediatric Emergency Medicine, Department of Women's and Children's Health, University of Padova, Padova, Italy.
³ Department of Environmental and Preventive Science, University of Ferrara, Ferrara, Italy.
⁴ Centre for Biostatistics, Epidemiology and Public Health, Department of Clinical and Biological Sciences, University of Turin, Turin, Italy.

No abstract available

Plain language summary

This cross-sectional study assesses the accuracy, sensitivity, and specificity of a large language model used to process unstructured, non-English emergency department (ED) data in medical records.

MeSH terms

Adult
Emergency Service, Hospital* / statistics & numerical data
Female
Humans
Male
Natural Language Processing
Wounds and Injuries* / classification
Wounds and Injuries* / epidemiology