Eligibility for eCPR Warming in Hypothermic Cardiac Arrest: Lack of Guidelines and the Current Constraints of Artificial Intelligence in Clinical Decision‐Making
Artificial Organs · 2025
DOI: 10.1111/aor.14993 ↗Kurz gefasst
Leitlinie in der Zeitschrift Artificial Organs, 2025. Verfasst von Michał P Pluta und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Acute Medicine, Medical University of Silesia, Zabrze, Poland. Hauptthemen laut MEDLINE: Artificial Intelligence, Heart Arrest, Clinical Decision-Making, Cardiopulmonary Resuscitation. Die Arbeit nennt 21 Literaturangaben.
Abstract (Originalsprache)
Aim of the Study Artificial intelligence (AI) such as large language models (LLMs) tools are potential sources of information on hypothermic cardiac arrest (HCA). The aim of our study was to determine whether, for patients with HCA, LLMs provide information consistent with expert consensus on criteria that would usually contraindicate extracorporeal cardiopulmonary resuscitation (eCRP) in patients with normothermic cardiac arrest (NCA), but not HCA.
Methods
Based on Extracorporeal Life Support Organization guidelines, selected factors were identified that may be contraindications to eCPR in NCA but not in HCA. Four questions were created and entered into AI software (GPT‐3.5 turbo, GPT‐4o, GPT‐4o‐mini, Claude 3.5 Sonnet, Claude 3 Haiku, Mistral Large, Mistral Small, Gemini Pro and Gemini Flash). The responses obtained and citations returned were assessed by an international panel of experts for consistency with current knowledge.
Results
Complete agreement of responses with expert consensus was obtained for 5/10 AI tools. In total, all AI tools presented 101 items in the literature. No reference was rated as “correct”; 45 citations (45%) “existed but did not answer the question”; and 56 citations (55%) were considered “hallucinatory”.
Conclusion
Use of artificial intelligence in decision‐making for extracorporeal cardiopulmonary resuscitation in patients with hypothermic cardiac arrest risks unjustifiably withdrawing treatment from patients who have a chance of survival with a good neurological outcome. Large language models should not be used as the only tool for decision‐making.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Acute Medicine, Medical University of Silesia, Zabrze, Poland.
- Department of Anaesthesiology and Intensive Care, Medical University of Silesia, Katowice, Poland.
- Doctoral School, Medical University of Lublin, Poland.
- Department of Emergency Medicine, Lausanne University Hospital, Lausanne, Switzerland.
- Department of Cardiac Surgery, Upper-Silesian Heart Center, Katowice, Poland.
- Mountain Medicine Laboratory, Jagiellonian University Medical College, Krakow, Poland.
ORCID-Profile: Michał P Pluta
Zitieren
APA
Pluta, M. P., Darocha, T., Pasternak, M., Pasquier, M., Mendrala, K., Gocoł, R., & Kosiński, S. (2025). Eligibility for eCPR Warming in Hypothermic Cardiac Arrest: Lack of Guidelines and the Current Constraints of Artificial Intelligence in Clinical Decision‐Making. Artificial Organs. https://doi.org/10.1111/aor.14993
Vancouver
Pluta MP, Darocha T, Pasternak M, Pasquier M, Mendrala K, Gocoł R, et al. Eligibility for eCPR Warming in Hypothermic Cardiac Arrest: Lack of Guidelines and the Current Constraints of Artificial Intelligence in Clinical Decision‐Making. Artificial Organs. 2025. doi:10.1111/aor.14993
BibTeX
@article{Pluta2025,
author = {Pluta, Michał P and Darocha, Tomasz and Pasternak, Michał and Pasquier, Mathieu and Mendrala, Konrad and Gocoł, Radosław and Kosiński, Sylweriusz},
title = {Eligibility for eCPR Warming in Hypothermic Cardiac Arrest: Lack of Guidelines and the Current Constraints of Artificial Intelligence in Clinical Decision‐Making},
journal = {Artificial Organs},
year = {2025},
doi = {10.1111/aor.14993}
}
EUVIMED