Evaluating Guideline-Adherent Antibiotic Use for Skin Infections Using Natural Language Processing
The NLP model demonstrated that automated analysis of clinical narratives for determining guideline adherence is feasible. Despite missing data in narratives, the model's high performance suggests potential for broader application. Given the rise in antibiotic-resistant infections and the role of judicious antibiotic use, developing automated systems through NLP can significantly contribute to health care delivery and patient safety. The methodology of this study provides a feasible, sustainable path for similar applications in the emergency setting.
Authors
- Amir A. Kimia (ORCID: https://orcid.org/0000-0002-1529-4246)
- Albert Lai (ORCID: https://orcid.org/0000-0002-7265-2986)
- Stephanie A. Fritz (ORCID: https://orcid.org/0000-0002-8602-5879)
- Assaf Landschaft (ORCID: https://orcid.org/0009-0004-1698-1496)
- Rakesh D. Mistry (ORCID: https://orcid.org/0000-0002-7873-5651)
- Jason G. Newland
- Fahd A. Ahmad
- James R. Rudloff
Institutions
- Hartford Hospital (US)
- Harvard University (US)
- Washington University in St. Louis (US)
- Yale University (US)
- Connecticut Children's Medical Center (US)
Publication Details
- Journal
- Pediatric Emergency Care
- Published
- 2026-02-27
- DOI
- https://doi.org/10.1097/pec.0000000000003576
- Primary Topic
- Antimicrobial Resistance in Staphylococcus
- Type
- article
- Field-Weighted Citation Impact
- 0.00