Agentic AI-Generated vs. Clinician-Authored Hospital Course Narratives for Cardiology Hospitalizations: A Blinded Physician Evaluation
Circulation: Population Health and Outcomes · 06.11.2026
DOI: 10.1161/circoutcomes.126.014472 ↗Kurz gefasst
Fachartikel in der Zeitschrift Circulation: Population Health and Outcomes, online erschienen am 06.11.2026. Verfasst von Eunjung Lee und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MN.
Abstract (Originalsprache)
Background
Discharge summaries are essential for safe transitions of care, but writing the hospital course narrative is time intensive. Large language models can generate plausible clinical narratives, yet prior approaches often rely on static inputs and remain vulnerable to omissions and factual inconsistencies.
Methods
We developed an electronic health record (EHR)-integrated agentic artificial intelligence (AI) system that uses Gemini 2.5 Pro and Model Context Protocol tools to retrieve clinical notes, diagnostic reports, diagnoses, medications, and appointments on demand. In this retrospective, blinded, paired study, 50 inpatient cardiology encounters were randomly selected from admissions July 13 to 27, 2024, at Mayo Clinic, Rochester, Minnesota. Five physicians rated AI-generated and clinician-authored hospital course narratives for each encounter (250 ratings) on 0-to-10 scales for overall quality, clarity, completeness, accuracy, and readability and indicated a preference. The primary outcome was the paired difference in overall quality (linear mixed-effects model with crossed random intercepts for encounter and reviewer). Secondary domains were analyzed similarly with Bonferroni adjustment, and preference with a crossed random-effects logistic model.
Results
Clinician-authored narratives were preferred in 132 ratings (52.8%) and AI-generated narratives in 118 (47.2%) (odds ratio for clinician-authored preference, 1.12; 95% CI, 0.71 to 1.78). Overall quality did not differ significantly (mean, 7.27 AI-generated versus 7.42 clinician-authored; difference, -0.15; 95% CI, -0.86 to 0.56; p=0.627). AI-generated narratives were rated higher for clarity (0.36; 95% CI, 0.07 to 0.65) and readability (0.72; 95% CI, 0.20 to 1.24) but lower for completeness (-0.84; 95% CI, -1.36 to -0.32) and accuracy (-0.35; 95% CI, -0.66 to -0.05). After Bonferroni correction, only lower completeness remained significant (adjusted p=0.012).
Conclusions
Hospital course narratives generated by the EHR-integrated agentic AI system did not differ significantly from clinician-authored narratives in physician-rated overall quality or preference. Lower completeness supports continued clinician review before use in the medical record.
Autor:innen und Institutionen
- Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MN.
ORCID-Profile: Eunjung Lee, David M Harmon, Jason M Holmes, Alexandra E Allman, Stephanie A Saey, Reid P Schlesinger, Iuri Ferreira Felix, Paul A Friedman, Zachi I Attia
Zitieren
APA
Lee, E., Harmon, D. M., Holmes, J. M., Allman, A. E., Saey, S. A., Schlesinger, R. P., Ferreira Felix, I., Friedman, P. A., & Attia, Z. I. (2026). Agentic AI-Generated vs. Clinician-Authored Hospital Course Narratives for Cardiology Hospitalizations: A Blinded Physician Evaluation. Circulation: Population Health and Outcomes. https://doi.org/10.1161/circoutcomes.126.014472
Vancouver
Lee E, Harmon DM, Holmes JM, Allman AE, Saey SA, Schlesinger RP, et al. Agentic AI-Generated vs. Clinician-Authored Hospital Course Narratives for Cardiology Hospitalizations: A Blinded Physician Evaluation. Circulation: Population Health and Outcomes. 2026. doi:10.1161/circoutcomes.126.014472
BibTeX
@article{Lee2026,
author = {Lee, Eunjung and Harmon, David M and Holmes, Jason M and Allman, Alexandra E and Saey, Stephanie A and Schlesinger, Reid P and Ferreira Felix, Iuri and Friedman, Paul A and Attia, Zachi I},
title = {Agentic AI-Generated vs. Clinician-Authored Hospital Course Narratives for Cardiology Hospitalizations: A Blinded Physician Evaluation},
journal = {Circulation: Population Health and Outcomes},
year = {2026},
doi = {10.1161/circoutcomes.126.014472}
}
EUVIMED