AI-Automated Risk Operative Stratification for Severe Aortic Stenosis: A Proof-of-Concept Study
Journal of Clinical Medicine · 22.11.2025 · 14 (23) · 8304
DOI: 10.3390/jcm14238304 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Clinical Medicine, online erschienen am 22.11.2025. Verfasst von Dorian Garin und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Cardiology, University and Hospital Fribourg, 1708 Fribourg, Switzerland. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fond Scientifique Cardiovasculaire.
Abstract (Originalsprache)
Background
Accurate operative risk stratification is essential for treatment selection in severe aortic stenosis. We developed an automated workflow using large language models (LLMs) to replicate Heart Team risk assessment.
Methods
We retrospectively analyzed 231 consecutive patients with severe aortic stenosis evaluated by multidisciplinary Heart Teams (January 2022–December 2024). An automated system using GPT-4o was developed, comprising the following: (1) structured data extraction from clinical dossiers; (2) EuroSCORE II calculation via two methods (algorithmic vs. LLM-based); (3) clinical vignette generation; and (4) risk stratification comparing EuroSCORE-based thresholds versus guideline-integrated LLM approaches with/without EuroSCORE values. The primary endpoint was the risk stratification accuracy of each method compared to Heart Team decisions.
Results
Mean age was 79.5 ± 7.7 years, with 58.4% female. The automated workflow processed patients in 32.6 ± 6.4 s. The LLM-calculated EuroSCORE II showed a lower mean difference from Heart Team values (−1.42%, 95% CI −2.32 to −0.53) versus algorithmic calculation (−1.88%, 95% CI −2.38 to −1.38). For risk stratification, the guideline-integrated LLM without EuroSCORE achieved the highest accuracy (90.0%) and AUC (0.93), outperforming both the EuroSCORE-based (accuracy 50.2% for high-risk, AUC 0.63) and guideline-integrated LLM with EuroSCORE approaches (accuracy 82.4%, AUC 0.76). However, systematic hallucinations occurred for cardiovascular risk factors when data were missing.
Conclusions
LLMs accurately calculated EuroSCORE II and achieved 90% concordance with multidisciplinary Heart Team decisions. However, hallucinations, reproducibility concerns, and the absence of clinical outcome validation preclude direct clinical application.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Cardiology, University and Hospital Fribourg, 1708 Fribourg, Switzerland.
- Department of Cardiology, Geneva University Hospitals, 1206 Geneve, Switzerland.
ORCID-Profile: Dorian Garin, Ioannis Skalidis, Philippe Di Cicco, Charlie Ferry, Stéphane Cook
Förderung
- Fond Scientifique Cardiovasculaire
Zitieren
APA
Garin, D., Arroyo, D., Skalidis, I., Di Cicco, P., Ferry, C., Bennar, W., Puricel, S., Meier, P., Togni, M., & Cook, S. (2025). AI-Automated Risk Operative Stratification for Severe Aortic Stenosis: A Proof-of-Concept Study. Journal of Clinical Medicine, 14(23), 8304. https://doi.org/10.3390/jcm14238304
Vancouver
Garin D, Arroyo D, Skalidis I, Di Cicco P, Ferry C, Bennar W, et al. AI-Automated Risk Operative Stratification for Severe Aortic Stenosis: A Proof-of-Concept Study. Journal of Clinical Medicine. 2025;14(23):8304. doi:10.3390/jcm14238304
BibTeX
@article{Garin2025,
author = {Garin, Dorian and Arroyo, Diego and Skalidis, Ioannis and Di Cicco, Philippe and Ferry, Charlie and Bennar, Wesley and Puricel, Serban and Meier, Pascal and Togni, Mario and Cook, Stéphane},
title = {AI-Automated Risk Operative Stratification for Severe Aortic Stenosis: A Proof-of-Concept Study},
journal = {Journal of Clinical Medicine},
year = {2025},
volume = {14},
number = {23},
pages = {8304},
doi = {10.3390/jcm14238304}
}
EUVIMED