Eligibility for eCPR Warming in Hypothermic Cardiac Arrest: Lack of Guidelines and the Current Constraints of Artificial Intelligence in Clinical Decision-Making.

IF 2.2 3区医学 Q3 ENGINEERING, BIOMEDICAL

Artificial organs Pub Date : 2025-03-13 DOI:10.1111/aor.14993

Michał P Pluta, Tomasz Darocha, Michał Pasternak, Mathieu Pasquier, Konrad Mendrala, Radosław Gocoł, Sylweriusz Kosiński

{"title":"Eligibility for eCPR Warming in Hypothermic Cardiac Arrest: Lack of Guidelines and the Current Constraints of Artificial Intelligence in Clinical Decision-Making.","authors":"Michał P Pluta, Tomasz Darocha, Michał Pasternak, Mathieu Pasquier, Konrad Mendrala, Radosław Gocoł, Sylweriusz Kosiński","doi":"10.1111/aor.14993","DOIUrl":null,"url":null,"abstract":"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.","PeriodicalId":8450,"journal":{"name":"Artificial organs","volume":" ","pages":""},"PeriodicalIF":2.2000,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Artificial organs","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1111/aor.14993","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, BIOMEDICAL","Score":null,"Total":0}

引用次数: 0

Abstract

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.

查看原文本刊更多论文

求助全文

约1分钟内获得全文求助全文

来源期刊

Artificial organs 工程技术-工程：生物医学

CiteScore

4.30

自引率

12.50%

发文量

303

审稿时长

4-8 weeks

期刊介绍： Artificial Organs is the official peer reviewed journal of The International Federation for Artificial Organs (Members of the Federation are: The American Society for Artificial Internal Organs, The European Society for Artificial Organs, and The Japanese Society for Artificial Organs), The International Faculty for Artificial Organs, the International Society for Rotary Blood Pumps, The International Society for Pediatric Mechanical Cardiopulmonary Support, and the Vienna International Workshop on Functional Electrical Stimulation. Artificial Organs publishes original research articles dealing with developments in artificial organs applications and treatment modalities and their clinical applications worldwide. Membership in the Societies listed above is not a prerequisite for publication. Articles are published without charge to the author except for color figures and excess page charges as noted.