AI-Driven Injury Reporting in Pediatric Emergency Departments

Can natural language processing (NLP) models automate detecting injury cases in emergency department patient medical records to improve the efficiency of injury reporting and surveillance programs?In this prognostic study of 217 173 emergency department visits at The Hospital for Sick Children, NLP models identified 90% of injury cases and reduced manual medical record review from 100% of patient medical records to only 17%, representing an 83% reduction.These findings suggest natural language processing models can effectively automate injury case detection in emergency department patient medical records, substantially improving the efficiency of injury surveillance reporting.

Corresponding Author: Devin Singh, MBBS, MSc, Department of Computer Science, Temerty Centre for AI Research and Education (T-CAIREM), University of Toronto, 555 University Ave, Toronto, ON M5G 1X8, Canada (devin.singh@sickkids.ca).

Link to the article in your story

We encourage you to link out to this article in your story using the link below. It includes an access token that will give free access to the article for your readers up to one year after publication. (The link will be live after the article publishes and embargo is lifted.)

Please see the article for additional information, including full author list, author contributions and affiliations, conflict of interest and financial disclosures, and funding and support.

Need more information? Contact us.