Journal article
Generative AI in Admission Notes and Diagnostic Completeness: A Pilot Study
Applied clinical informatics, Vol.17(03), pp.392-399
05/2026
DOI: 10.1055/a-2876-0998
PMID: 42150573
Abstract
Background Admission history and physical (H&P) notes influence inpatient documentation, risk adjustment, and reimbursement. In high-acuity settings, time constraints and fragmented chart data contribute to under-documentation of comorbidities. Generative AI systems that draft admission notes from existing electronic health record data may improve documentation completeness, but real-world inpatient performance remains insufficiently characterized. Objective To evaluate whether AI-generated admission notes identify documentation-relevant diagnoses supported by the medical record but not explicitly captured in provider-authored admission notes. Methods In this single-center retrospective pilot study, we reviewed 22 matched pairs of AI-generated and provider-authored admission H&P notes at a large academic medical center. We assessed principal diagnosis concordance and identified net-new secondary diagnoses. Secondary diagnoses identified by the AI but absent from provider-authored notes were adjudicated by a Clinical Documentation Improvement (CDI) team using standard institutional criteria. Results AI-generated notes aligned with the provider-authored principal diagnosis in 91% of cases (20/22). The CDI team adjudicated 104 AI-identified secondary diagnoses, of which 97% (101/104) were supported for documentation. Ninety-four diagnoses were net-new, quality-relevant conditions not documented in provider-authored notes (median 4.5 per admission). Net-new diagnoses varied across provider types-advanced practice providers (median 6), residents (5), and staff physicians (3)-without statistically significant differences (p = 0.36). Discussion Despite its modest sample size, this pilot demonstrated that AI-generated drafts achieved high principal diagnosis concordance and identified additional CDI-supported diagnoses, though narrative quality and factual accuracy were not evaluated. These patterns suggest a potential role for AI in supporting inpatient documentation completeness. Conclusion These findings highlight the potential of generative AI to surface documentation-relevant information at admission and underscore the importance of human oversight in AI-assisted documentation workflows. Larger multi-center studies are needed to assess generalizability and safety.
Details
- Title: Subtitle
- Generative AI in Admission Notes and Diagnostic Completeness: A Pilot Study
- Creators
- Alfredo Camargo Rodrigues - University of Iowa Health Care, Health Care Information Systems / Department of Anesthesia, Iowa, United States, Iowa CityJason Misurac - University of IowaLindsey A Knake - University of IowaKevin Barker - University of Iowa Health CareJames M Blum - University of Iowa
- Resource Type
- Journal article
- Publication Details
- Applied clinical informatics, Vol.17(03), pp.392-399
- DOI
- 10.1055/a-2876-0998
- PMID
- 42150573
- NLM abbreviation
- Appl Clin Inform
- ISSN
- 1869-0327
- eISSN
- 1869-0327
- Publisher
- Thieme
- Language
- English
- Electronic publication date
- 05/18/2026
- Date published
- 05/2026
- Academic Unit
- Nephrology, Dialysis and Transplantation; Stead Family Department of Pediatrics; Anesthesia; Neonatology
- Record Identifier
- 9985164728702771
Metrics
3 Record Views