Sustainable electronic trauma registry with NLP/ML-enhanced ICD-10 classification: 13-year insights from violence-heavy KwaZulu-Natal, South Africa
The ESR, enhanced by NLP/ML for nuanced ICD-10 classification, reveals KwaZulu-Natal's unique violence-dominated epidemiology as an illustrative example of its utility. Female and pediatric assault data require urgent prevention strategies. The ESR is a dependable tool for resource-constrained trauma services, informing public health priorities through reliable epidemiological surveillance.
Authors
- Howard Wain (ORCID: https://orcid.org/0000-0002-6693-0062)
- John Bruce (ORCID: https://orcid.org/0000-0001-8666-4104)
- Grant Laing (ORCID: https://orcid.org/0000-0001-8075-0386)
- Wanda Bekker (ORCID: https://orcid.org/0000-0003-0695-5994)
- Damian Clarke (ORCID: https://orcid.org/0000-0002-8467-1455)
- V Manchev
Institutions
- University of the Witwatersrand (ZA)
- University of KwaZulu-Natal (ZA)
Publication Details
- Journal
- Injury
- Published
- 2025-10-13
- DOI
- https://doi.org/10.1016/j.injury.2025.112799
- Primary Topic
- Trauma and Emergency Care Studies
- Type
- article
- Field-Weighted Citation Impact
- 0.00