Journal of Clinical Anesthesia最新文献

{"title":"Assessing the accuracy of ChatGPT in interpreting blood gas analysis results ChatGPT-4 in blood gas analysis","authors":"Engin İhsan Turan ,&nbsp;Abdurrahman Engin Baydemir ,&nbsp;Anıl Berkay Balıtatlı ,&nbsp;Ayça Sultan Şahin","doi":"10.1016/j.jclinane.2025.111787","DOIUrl":"10.1016/j.jclinane.2025.111787","url":null,"abstract":"<div><h3>Background</h3><div>Arterial blood gas (ABG) analysis is a critical component of patient management in intensive care units (ICUs), operating rooms, and general wards, providing essential information on acid-base balance, oxygenation, and metabolic status. Interpretation requires a high level of expertise, potentially leading to variability in accuracy. This study explores the feasibility and accuracy of ChatGPT-4, an AI-based model, in interpreting ABG results compared to experienced anesthesiologists.</div></div><div><h3>Methods</h3><div>This prospective observational study, approved by the institutional ethics board, included 400 ABG samples from ICU patients, anonymized and assessed by ChatGPT-4. The model analyzed parameters including acid-base status, oxygenation, hemoglobin levels, and metabolic markers, and provided both diagnostic and treatment recommendations. Two anesthesiologists, trained in ABG interpretation, independently evaluated the model's predictions to determine accuracy in potential diagnoses and treatment.</div></div><div><h3>Results</h3><div>ChatGPT-4 achieved high accuracy across most ABG parameters, with 100 % accuracy for pH, oxygenation, sodium, and chloride. Hemoglobin accuracy was 92.5 %, while bilirubin interpretation showed limitations at 72.5 %. In several cases, the model recommended unnecessary bicarbonate treatment, suggesting an area for improvement in clinical judgment for acid-base balance management. The model's overall performance was statistically significant across most parameters (<em>p</em> &lt; 0.05).</div></div><div><h3>Discussion</h3><div>ChatGPT-4 demonstrated potential as a supplementary tool for ABG interpretation in high-demand clinical settings, supporting rapid, reliable decision-making. However, the model's limitations in interpreting complex metabolic markers highlight the need for clinician oversight. Future refinements should focus on enhancing AI training for nuanced metabolic interpretation, particularly for markers like bilirubin, to ensure safe and effective application across diverse clinical contexts.</div></div>","PeriodicalId":15506,"journal":{"name":"Journal of Clinical Anesthesia","volume":"102 ","pages":"Article 111787"},"PeriodicalIF":5.0,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143454002","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Editorial: The global need for standardized education in airway management.","authors":"Gregor Massoth, Maria Wittmann","doi":"10.1016/j.jclinane.2025.111781","DOIUrl":"https://doi.org/10.1016/j.jclinane.2025.111781","url":null,"abstract":"","PeriodicalId":15506,"journal":{"name":"Journal of Clinical Anesthesia","volume":" ","pages":"111781"},"PeriodicalIF":5.0,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143476636","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The expanding role of critical care anesthesiologists outside the ICU.","authors":"Siddharth Dave, Brigid Flynn, Kunal Karamchandani","doi":"10.1016/j.jclinane.2025.111779","DOIUrl":"https://doi.org/10.1016/j.jclinane.2025.111779","url":null,"abstract":"","PeriodicalId":15506,"journal":{"name":"Journal of Clinical Anesthesia","volume":" ","pages":"111779"},"PeriodicalIF":5.0,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143472533","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A closer look at a decade of industry payments to anesthesiologists","authors":"Caitlin Sebastian BS ,&nbsp;Catherine Cha MD ,&nbsp;Brittany N. Burton MD, MHS, MAS","doi":"10.1016/j.jclinane.2025.111775","DOIUrl":"10.1016/j.jclinane.2025.111775","url":null,"abstract":"","PeriodicalId":15506,"journal":{"name":"Journal of Clinical Anesthesia","volume":"102 ","pages":"Article 111775"},"PeriodicalIF":5.0,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143445705","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Machine learning or traditional statistical methods for predictive modelling in perioperative medicine: A narrative review","authors":"Jason Mann ,&nbsp;Mathew Lyons ,&nbsp;John O'Rourke ,&nbsp;Simon Davies","doi":"10.1016/j.jclinane.2025.111782","DOIUrl":"10.1016/j.jclinane.2025.111782","url":null,"abstract":"<div><div>Prediction of outcomes in perioperative medicine is key to decision-making and various prediction models have been created to help quantify and communicate those risks to both patients and clinicians. Increasingly, machine learning (ML) is being favoured over more traditional techniques to improve prediction of outcomes, however, the studies are of varying quality. It is also not known whether any increase in predictive performance using ML algorithms transpires into a clinically meaningful benefit. This coupled with the difficulty in interrogating ML algorithms is a potential cause of concern within the medical community. In this review, we provide a concise appraisal of studies which develop perioperative predictive ML models and compare predictive performance to traditional statistical models.</div><div>The search strategy, title and abstract screening, and full-text reviews produced 37 studies for data extraction. Initially designed as a systematic review but due to the heterogeneity of the population and outcomes, was written in the narrative.</div><div>Perioperative ML and traditional predictive models continue to be developed and published across a range of populations. This review highlights several studies which show that ML can enhance perioperative prediction models, although this is not universal, and performance for both methods remain context dependent. By focusing on relevant patient-centred outcomes, model interpretability, external validation, and maintaining high standards of reporting and methodological transparency, researchers can develop ML models alongside traditional methods to enhance clinical decision-making and improve patient care.</div></div>","PeriodicalId":15506,"journal":{"name":"Journal of Clinical Anesthesia","volume":"102 ","pages":"Article 111782"},"PeriodicalIF":5.0,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143436469","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Preoperative LDL-C and major cardiovascular and cerebrovascular events after non-cardiac surgery","authors":"David Rehe MD, MBA ,&nbsp;Varun Subashchandran MD ,&nbsp;Yan Zhang MPH ,&nbsp;Germaine Cuff PhD ,&nbsp;Mitchell Lee MD ,&nbsp;Jeffrey S. Berger MD, MS ,&nbsp;Nathaniel R. Smilowitz MD, MS","doi":"10.1016/j.jclinane.2025.111783","DOIUrl":"10.1016/j.jclinane.2025.111783","url":null,"abstract":"<div><h3>Study objective</h3><div>To determine whether preoperative LDL-C concentration affects the risk of perioperative major adverse cardiovascular or cerebrovascular events (MACCE) after noncardiac surgery.</div></div><div><h3>Design</h3><div>Single center retrospective cohort study.</div></div><div><h3>Setting</h3><div>Hospital (including medical and surgical floor, intensive care unit) and patient disposition location (including the patient's home or any other receiving facility).</div></div><div><h3>Patients</h3><div>43,348 non-cardiac surgeries at NYU Langone Health between January 2016 and September 2020.</div></div><div><h3>Interventions</h3><div>Patients were grouped based on preoperative LDL-C.</div></div><div><h3>Measurements</h3><div>Complete serum lipid panel obtained within one year prior to the date of noncardiac surgery and rate of perioperative MACCE, defined as a composite of in-hospital non-fatal myocardial infarction, in-hospital acute ischemic stroke, myocardial injury after noncardiac surgery, and death from any cause within 30 days of surgery.</div></div><div><h3>Main results</h3><div>Perioperative MACCE occurred in 1093 patients (2.5 %) overall. After multivariable adjustment, odds of MACCE were significantly lower in patients with higher (≥100 mg/dL) versus lower (&lt;100 mg/dL) LDL-C (adjusted odds ratio [aOR] 0.783, 95 % CI, 0.660–0.926]).</div></div><div><h3>Conclusions</h3><div>In a large cohort of patients undergoing non-cardiac surgery at a major academic health system in New York City, lower LDL-C concentrations were not associated with a lower incidence of perioperative MACCE. Further investigation into modifiable perioperative cardiovascular risk factors is needed to improve perioperative outcomes.</div></div>","PeriodicalId":15506,"journal":{"name":"Journal of Clinical Anesthesia","volume":"102 ","pages":"Article 111783"},"PeriodicalIF":5.0,"publicationDate":"2025-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143421755","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The rise of Zyn: Implications for anesthesiology and perioperative management","authors":"Jamie Kim BS ,&nbsp;Kazi Maisha BS ,&nbsp;Rogelio Perez BS ,&nbsp;Robert White MD, MS ,&nbsp;Rohan Jotwani MD, MBA","doi":"10.1016/j.jclinane.2025.111780","DOIUrl":"10.1016/j.jclinane.2025.111780","url":null,"abstract":"","PeriodicalId":15506,"journal":{"name":"Journal of Clinical Anesthesia","volume":"102 ","pages":"Article 111780"},"PeriodicalIF":5.0,"publicationDate":"2025-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143421756","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Impact of intraoperative anesthesia handover on major adverse cardiovascular events after thoracic surgery: A propensity-score matched retrospective cohort study","authors":"Xiao-Ling Zhang ,&nbsp;Yan Zhou ,&nbsp;Mo Li ,&nbsp;Jia-Hui Ma ,&nbsp;Lin Liu ,&nbsp;Dong-Xin Wang","doi":"10.1016/j.jclinane.2025.111778","DOIUrl":"10.1016/j.jclinane.2025.111778","url":null,"abstract":"<div><h3>Study objective</h3><div>Handover of anesthesia care is often required in busy clinical settings. Herein, we investigated whether intraoperative anesthesia handover was associated with an increased risk of major adverse cardiovascular events (MACEs) after thoracic surgery.</div></div><div><h3>Design</h3><div>A retrospective cohort study.</div></div><div><h3>Setting</h3><div>A tertiary hospital.</div></div><div><h3>Patients</h3><div>Adult patients who underwent elective thoracic surgery.</div></div><div><h3>Exposures</h3><div>A complete handover of intraoperative anesthesia care was defined when the outgoing anesthesiologist transferred patient care to the incoming anesthesiologist and no longer returned.</div></div><div><h3>Measurements</h3><div>Our primary endpoint was a composite of MACEs, including acute myocardial infarction, new-onset congestive heart failure, non-fatal cardiac arrest, and cardiac death, that occurred within 7 days after surgery. The impact of complete anesthesia handover on postoperative MACEs was analyzed using propensity score matching.</div></div><div><h3>Main results</h3><div>Of 6962 patients (mean age 59.7 years; 57.4 % female) included in the analysis, 2319 (33.3 %) surgeries were conducted with anesthesia handover whereas 4643 (66.7 %) were conducted without. After propensity score matching, 2165 (50.0 %) surgeries were conducted with anesthesia handover whereas the other half were conducted without. Patients with anesthesia handover developed more MACEs when compared with those without (10.4 % [225/2165] vs. 8.4 % [181/2165]; relative risk 1.24, 95 % CI 1.03 to 1.50, <em>P</em> = 0.022). Specifically, myocardial infarction was more common in patients with anesthesia handover than in those without (9.2 % [199/2165] vs. 7.4 % [160/2165]; relative risk 1.24, 95 % CI 1.02 to 1.52, <em>P</em> = 0.032).</div></div><div><h3>Conclusions</h3><div>For adult patients undergoing thoracic surgery, a complete handover of intraoperative anesthesia care was associated with an increased risk of MACEs after surgery.</div></div>","PeriodicalId":15506,"journal":{"name":"Journal of Clinical Anesthesia","volume":"102 ","pages":"Article 111778"},"PeriodicalIF":5.0,"publicationDate":"2025-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143421723","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Perioperative goal-directed therapy with artificial intelligence to reduce the incidence of intraoperative hypotension and renal failure in patients undergoing lung surgery: A pilot study","authors":"Marit Habicher MD ,&nbsp;Sara Marie Denn MD ,&nbsp;Emmanuel Schneck MD ,&nbsp;Amir Ali Akbari MD ,&nbsp;Götz Schmidt MD ,&nbsp;Melanie Markmann PhD ,&nbsp;Ibrahim Alkoudmani MD ,&nbsp;Christian Koch MD ,&nbsp;Michael Sander MD","doi":"10.1016/j.jclinane.2025.111777","DOIUrl":"10.1016/j.jclinane.2025.111777","url":null,"abstract":"<div><h3>Study objective</h3><div>The aim of this study was to investigate whether goal-directed treatment using artificial intelligence, compared to standard care, can reduce the frequency, duration, and severity of intraoperative hypotension in patients undergoing single lung ventilation, with a potential reduction of postoperative acute kidney injury (AKI).</div></div><div><h3>Design</h3><div>single center, single-blinded randomized controlled trial.</div></div><div><h3>Setting</h3><div>University hospital operating room.</div></div><div><h3>Patients</h3><div>150 patients undergoing lung surgery with single lung ventilation were included.</div></div><div><h3>Interventions</h3><div>Patients were randomly assigned to two groups: the Intervention group, where a goal-directed therapy based on the Hypotension Prediction Index (HPI) was implemented; the Control group, without a specific hemodynamic protocol.</div></div><div><h3>Measurements</h3><div>The primary outcome measures include the frequency, duration of intraoperative hypotension, furthermore the Area under MAP 65 and the time-weighted average (TWA) of MAP of 65. Other outcome parameters are the incidence of AKI and myocardial injury after non-cardiac surgery (MINS).</div></div><div><h3>Main results</h3><div>The number of hypotensive episodes was lower in the intervention group compared to the control group (0 [0–1] vs. 1 [0–2]; <em>p</em> = 0.01), the duration of hypotension was shorter in the intervention group (0 min [0–3.17] vs. 2.33 min [0–7.42]; p = 0.01). The area under the MAP of 65 (0 mmHg * min [0−12] vs. 10.67 mmHg * min [0–44.16]; <em>p</em> &lt; 0.01) and the TWA of MAP of 65 (0 mmHg [0–0.08] vs. 0.07 mmHg [0–0.25]; p &lt; 0.01) were lower in the intervention group.</div><div>The incidence of postoperative AKI showed no differences between the groups (6.7 % vs.4.2 %; <em>p</em> = 0.72). There was a trend to lower incidence of MINS in the intervention group (17.1 % vs. 31.8 %; <em>p</em> = 0.07). A tendency towards reduced postoperative infection was seen in the intervention group (16.0 % vs. 26.8 %; <em>p</em> = 0.16).</div></div><div><h3>Conclusions</h3><div>The implementation of a treatment algorithm based on HPI allowed us to decrease the duration and severity of hypotension in patients undergoing lung surgery. It did not result in a significant reduction in the incidence of AKI, however we observed a tendency towards lower incidence of MINS in the intervention group, along with a slight reduction in postoperative infections.</div></div>","PeriodicalId":15506,"journal":{"name":"Journal of Clinical Anesthesia","volume":"102 ","pages":"Article 111777"},"PeriodicalIF":5.0,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143402797","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Functional MRI-based machine learning strategy for prediction of postoperative delirium in cardiac surgery patients: A secondary analysis of a prospective observational study","authors":"Mei-Yan Zhou ,&nbsp;Yi-Bing Shi ,&nbsp;Sheng-Jie Bai ,&nbsp;Yao Lu ,&nbsp;Yan Zhang ,&nbsp;Wei Zhang ,&nbsp;Wei Wang ,&nbsp;Yang-Zi Zhu ,&nbsp;Jun-Li Cao ,&nbsp;Li-Wei Wang","doi":"10.1016/j.jclinane.2025.111771","DOIUrl":"10.1016/j.jclinane.2025.111771","url":null,"abstract":"<div><h3>Study objective</h3><div>Delirium is a common complication after cardiac surgery and is associated with poor prognosis. An effective delirium prediction model could identify high-risk patients who might benefit from targeted prevention strategies. We introduce machine learning models that employ resting-state functional MRI datasets obtained before surgery to predict postoperative delirium.</div></div><div><h3>Design</h3><div>A secondary analysis of a prospective observational study.</div></div><div><h3>Setting</h3><div>The study was conducted at one tertiary hospital in China.</div></div><div><h3>Patients</h3><div>The study involved 103 patients who underwent preoperative functional MRI scan and cardiac valve replacement.</div></div><div><h3>Interventions</h3><div>None.</div></div><div><h3>Measurements</h3><div>Delirium was assessed twice daily for the first seven postoperative days using the Confusion Assessment Method. We used three whole-brain functional connectivity (FC) measures (parcel-wise connectivity matrix, mean FC and degree of FC) and trained three machine models, namely, random forest, logistic regression, and linear support vector machine, to distinguish delirium patients from patients without delirium. The top performing model was selected for further training with functional MRI datasets and clinical variables.</div></div><div><h3>Main results</h3><div>This study included 103 participants. A total of 29 participants (28.2 %) met postoperative delirium criteria. Based solely on functional MRI datasets, the random forest model trained using the degree of FC achieved the highest accuracy (0.864), precision (0.887), specificity (0.894), F1 score (0.859) and area under the curve (0.924), and this model was further optimized for accuracy (0.879), sensitivity (0.909), F1 score (0.882) and area under the curve (0.928) by fusing clinical variables. The most discriminative nodes for predicting postoperative delirium were located in the default, cingulo-opercular, and frontoparietal networks.</div></div><div><h3>Conclusions</h3><div>This study found that the random forest model using preoperative functional MRI data and clinical variables was accurate in identifying patients at high risk of developing delirium after cardiac surgery.</div></div>","PeriodicalId":15506,"journal":{"name":"Journal of Clinical Anesthesia","volume":"102 ","pages":"Article 111771"},"PeriodicalIF":5.0,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143402796","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}