Critical Care Medicine最新文献

{"title":"Long-Lasting Mental Disorders in Caregivers of ICU Sepsis Survivors and Their Association With Patients' Post-Intensive Care Syndrome: A Prospective Multicenter Cohort Study.","authors":"Kasumi Shirasaki, Keibun Liu, Akira Kawauchi, Shutaro Isokawa, Kensuke Nakamura, Hidehiko Nakano, Maiko Motoki, Hiroshi Kamijo, Ayaka Matsuoka, Kenzo Ishii, Yasunari Morita, Takashi Hongo, Nobutake Shimojo, Yukiko Tanaka, Manabu Hanazawa, Tomohiro Hamagami, Kenji Oike, Daisuke Kasugai, Yutaka Sakuda, Yuhei Irie, Masakazu Nitta, Kazuki Akieda, Daigo Shimakura, Hajime Katsukawa, Toru Kotani, David McWilliams, Peter Nydahl, Stefan J Schaller, Masaki Okajima, Norio Otani, Takayuki Ogura","doi":"10.1097/CCM.0000000000007378","DOIUrl":"https://doi.org/10.1097/CCM.0000000000007378","url":null,"abstract":"<p><strong>Objectives: </strong>To investigate the prevalence of long-term mental disorders in caregivers of ICU sepsis survivors and examine associations with post-intensive care syndrome (PICS) in patients.</p><p><strong>Design: </strong>Prospective observational study.</p><p><strong>Setting: </strong>Twenty-one mixed ICUs.</p><p><strong>Patients: </strong>Caregivers (the next of kin) of the patients diagnosed with sepsis between November 2020 and April 2022.</p><p><strong>Interventions: </strong>None.</p><p><strong>Measurements and main results: </strong>Caregivers and patients were assessed at 3, 6, and 12 months after hospital discharge by telephone and mail. The primary outcome was caregiver mental disorders (mental post-intensive care syndrome-family [PICS-F]). Mixed-effects logistic regression analyses were performed to evaluate the association between caregiver PICS-F and patient PICS. Ninety-four caregiver-patient dyads were analyzed. Caregivers were a median of 67 years old (55-79 yr old), 31 (33.0%) were male, and 41 (43.6%) were spouses. Patients were a median of 74 years old (69-82 yr old), and 54 (57.4%) were male. The prevalence of mental PICS-F did not decrease from 3 to 12 months (43% vs. 42%, respectively), whereas the presence of PICS symptoms in patients decreased from 82% to 62%. In mixed-effects logistic regression, the presence of PICS symptoms in patients was significantly associated with PICS-F (adjusted odds ratio, 3.00; 95% CI, 1.54-5.88; p < 0.01). Among the individual patient PICS domains, only mental PICS was significantly associated with PICS-F (3.71; 2.03-6.77; p < 0.01), whereas physical and cognitive impairments in patients were not.</p><p><strong>Conclusions: </strong>The prevalence of mental PICS-F in caregivers of ICU sepsis survivors was frequent and long-lasting over the first year after hospital discharge. Since it was most strongly associated with patients' mental disorders rather than physical or cognitive impairments, the mental PICS domain in patients may be an important indicator of PICS-F and should be considered in future studies.</p>","PeriodicalId":10765,"journal":{"name":"Critical Care Medicine","volume":" ","pages":""},"PeriodicalIF":7.5,"publicationDate":"2026-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149179768","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Pediatric Cardiopulmonary Resuscitation Ventilation Rates and Outcomes.","authors":"Lindsay N Shepard, Stuart H Friess, Ron W Reeder, Dieter Bender, Robert A Berg, Kathryn Graham, Kathleen L Meert, Peter M Mourani, Robert Murray, Vinay M Nadkarni, C Nataraj, Chella A Palmer, Elizabeth Patterson, Neeraj Srivastava, Heather A Wolfe, Andrew R Yates, Ryan W Morgan, Robert M Sutton","doi":"10.1097/CCM.0000000000007381","DOIUrl":"https://doi.org/10.1097/CCM.0000000000007381","url":null,"abstract":"<p><strong>Objectives: </strong>Evaluate the association between cardiopulmonary resuscitation (CPR) ventilation rates and survival to hospital discharge, and identify novel ventilation targets.</p><p><strong>Design: </strong>Multicenter prospective ancillary observational cohort study of the ICU-RESUS trial (NCT02837497).</p><p><strong>Setting: </strong>A total of 18 ICUs from 10 U.S. clinical sites from October 2016 to March 2021.</p><p><strong>Patients: </strong>Hospitalized children (≤ 18 yr) with endotracheal or tracheostomy tubes and evaluable intra-arrest end-tidal carbon dioxide data to calculate ventilation rate.</p><p><strong>Interventions: </strong>None.</p><p><strong>Measurements and main results: </strong>Among 234 included events, 86 events (36.8%) had guideline-recommended (20-30 beats per min [bpm]) average ventilation rates during CPR. The association between guideline-recommended CPR ventilation rate and survival to hospital discharge was evaluated with Poisson regression using generalized estimating equations, controlling for a priori covariables (initial pulse status, immediate cause of arrest). We found no association between guideline-recommended ventilation rates and survival to hospital discharge (adjusted relative risk [aRR], 0.95; 95% CI, 0.75-1.21; p = 0.68). In exploratory analyses, novel age-stratified ventilation rates were identified using natural cubic splines and subsequently evaluated in multivariable models. We identified potential thresholds (< 8 yr, ≥ 26 bpm; ≥ 8 yr, < 26 bpm). For children younger than 8 years, average CPR ventilation rate greater than or equal to 26 bpm was associated with improved survival to hospital discharge compared with less than 26 bpm (aRR, 1.32; 95% CI, 1.00-1.73; p = 0.048).</p><p><strong>Conclusions: </strong>CPR ventilation rates in the currently recommended range (20-30 bpm) were not associated with survival in children with in-hospital cardiac arrest. In exploratory analyses in children younger than 8 years, higher ventilation rates (≥ 26 bpm) were associated with improved survival and warrant confirmation in future studies.</p>","PeriodicalId":10765,"journal":{"name":"Critical Care Medicine","volume":" ","pages":""},"PeriodicalIF":7.5,"publicationDate":"2026-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149179858","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"New Insights Into U.S. Pediatric Critical Care Epidemiology.","authors":"Christine Wang, Christopher M Horvat","doi":"10.1097/CCM.0000000000007396","DOIUrl":"https://doi.org/10.1097/CCM.0000000000007396","url":null,"abstract":"","PeriodicalId":10765,"journal":{"name":"Critical Care Medicine","volume":" ","pages":""},"PeriodicalIF":7.5,"publicationDate":"2026-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149179727","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Easiest Decision in the Room: Continuous Renal Replacement Therapy in Cirrhosis.","authors":"Rahul Nanchal","doi":"10.1097/CCM.0000000000007397","DOIUrl":"https://doi.org/10.1097/CCM.0000000000007397","url":null,"abstract":"","PeriodicalId":10765,"journal":{"name":"Critical Care Medicine","volume":" ","pages":""},"PeriodicalIF":7.5,"publicationDate":"2026-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149179868","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Race and Ethnicity Are Associated With Physical Impairment Among ICU Survivors","authors":"Megan A. Watson,Mikita Fuchita,Ellen L. Burnham,Sarah E. Jolley","doi":"10.1097/ccm.0000000000007373","DOIUrl":"https://doi.org/10.1097/ccm.0000000000007373","url":null,"abstract":"Objectives: To evaluate whether race and ethnicity are associated with increased odds of physical impairment among post-ICU survivors and to assess how impairment influences healthcare utilization after hospital discharge. Design: This was a retrospective cohort study. Setting: The study was conducted at an academic medical center. Patients: We included 4370 adult ICU survivors who experienced shock, respiratory failure, or received extracorporeal membrane oxygenation. Interventions: None. Measurements and Main Results: The primary exposure was self-reported race and ethnicity. The primary outcome was impairment at hospital discharge, defined using the International Classification of Diseases , 10th Revision codes and/or a Johns Hopkins Highest Level of Mobility score of less than or equal to 5. Multivariable logistic regression was used to assess associations with impairment, and Fine-Gray models evaluated post-discharge healthcare utilization. Impairment was identified in 31% of ICU survivors. Non-Hispanic Black race was associated with increased odds of any impairment (adjusted odds ratio [aOR], 1.34; 95% CI, 1.04–1.72), and Hispanic ethnicity was associated with increased odds of new impairment (aOR, 1.42; 95% CI, 1.05–1.91), compared with non-Hispanic White-identifying survivors. Among those with impairment, both non-Hispanic Black and Hispanic individuals had increased risk of healthcare utilization within 1 year. Conclusions: Non-Hispanic Black race and Hispanic ethnicity are associated with increased odds of post-ICU physical impairment and subsequent healthcare utilization. These findings highlight the need to understand root causes better and explore targeted interventions to reduce disparities among ICU survivors.","PeriodicalId":10765,"journal":{"name":"Critical Care Medicine","volume":"15 1","pages":""},"PeriodicalIF":8.8,"publicationDate":"2026-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149088211","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Derivation and Validation of Operational Definitions From Claims Data for Identifying Cardiogenic Shock","authors":"Ki Hong Choi,Ji Hyun Cha,Hyeon-Cheol Gwon,Yeonkyeong Han,Danbee Kang,Jeong Hoon Yang","doi":"10.1097/ccm.0000000000007380","DOIUrl":"https://doi.org/10.1097/ccm.0000000000007380","url":null,"abstract":"Objectives: To derive and validate a claims-based operational definition for cardiogenic shock (CS) using administrative data against clinically adjudicated reference standards. Design: Diagnostic accuracy study. Setting: Two independent clinical cohorts, a single-center cardiac ICU (CICU) registry and a multicenter CS registry (REtrospective and prospective observational Study to investigate Clinical oUtcomes and Efficacy of left ventricular assist device for Korean patients with cardiogenic shock [RESCUE]), and a nationwide administrative database from the Korean National Health Insurance Service. Patients: A total of 10,156 patients from the CICU registry and 1,247 patients from the RESCUE registry. For population-level application, 207,419 patients were identified from the national claims database. Interventions: None. Measurements and Main Results: A claims-based algorithm defined CS using the International Classification of Diseases , 10th Revision code R57.0 or cardiac disease codes combined with treatment-based criteria reflecting hemodynamic support, including mechanical circulatory support or vasoactive therapy. In the CICU cohort, the algorithm demonstrated a sensitivity of 0.89 and specificity of 0.90, with an overall accuracy of 0.90. In the RESCUE cohort, sensitivity was 0.95. When applied to the nationwide database, 207,419 patients with CS were identified. The cumulative mortality rates were 37.9% at 12 months, 49.9% at 5 years, and 61.7% at 10 years. Conclusions: A claims-based definition combining diagnostic codes with treatment-based criteria demonstrated high diagnostic performance for identifying CS. This approach enables reliable large-scale epidemiologic studies and long-term outcome assessments using administrative data and may facilitate system-level evaluation of critical care delivery in patients with CS.","PeriodicalId":10765,"journal":{"name":"Critical Care Medicine","volume":"480 1","pages":""},"PeriodicalIF":8.8,"publicationDate":"2026-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149088215","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Telemedicine Critical Care Billing For Hospitalized Medicare Fee-For-Service Beneficiaries, 2018-2024.","authors":"Uchenna R Ofoma, Jonah M Graves, R J Waken, Anne M Drewry, Sanjay Subramanian, Benjamin Scott, Chiedozie Udeh, Vitaly Herasevich, Karen E Joynt Maddox","doi":"10.1097/CCM.0000000000007301","DOIUrl":"10.1097/CCM.0000000000007301","url":null,"abstract":"<p><strong>Objectives: </strong>Expanded coverage for telehealth during the COVID-19 pandemic allowed providers to bill for telemedicine services that were previously not reimbursable, including telemedicine critical care (TCC) services for critically ill patients. We aimed to characterize TCC billing practices among Medicare beneficiaries before, during, and after the COVID-19 pandemic.</p><p><strong>Design, setting, and patients: </strong>This was a serial cross-sectional study of adult Medicare Fee-For-Service beneficiaries with at least one bill for critical care at acute care hospitals from January 2018 to September 2024. TCC billing was identified using provider billing codes; multivariate regression models were used to determine characteristics associated with receipt of TCC. Key outcomes were patient-, provider-, and hospital-level characteristics associated with TCC billing.</p><p><strong>Interventions: </strong>None.</p><p><strong>Measurements and main results: </strong>Billing for TCC increased from 0.002% of critical care bills pre-pandemic to 0.01% of critical care bills during and after the pandemic. Patients billed for TCC were disproportionately likely to have COVID-19 but were otherwise relatively similar to critically ill patients not billed for TCC. Internal medicine/critical care providers accounted for the highest proportion of pandemic TCC bills (46.0%). TCC billing occurred more often at minor teaching hospitals (adjusted odds ratio [aOR], 1.21; 95% CI, 1.03-1.43) and at safety-net hospitals (aOR, 1.33; 95% CI, 1.04-1.70). TCC billing was less likely at small-sized hospitals (aOR, 0.39; 95% CI 0.26-0.58) and medium-sized hospitals (aOR, 0.67; 95% CI, 0.47-0.95), government-owned hospitals (aOR, 0.70; 95% CI, 0.57-0.86), for-profit hospitals (aOR, 0.58; 95% CI, 0.48-0.71), rural hospitals (aOR, 0.70; 95% CI, 0.55-0.89), and critical access hospitals (aOR, 0.59; 95% CI, 0.47-0.73).</p><p><strong>Conclusions: </strong>Billing for TCC among hospitalized critically ill Medicare beneficiaries increased during the pandemic but remained low as a proportion of all critical care bills. There was variability in utilization across subspecialties and lesser utilization at rural and critical access hospitals. Further studies are needed to characterize the clinical and economic consequences of this shift.</p>","PeriodicalId":10765,"journal":{"name":"Critical Care Medicine","volume":" ","pages":"2543-2554"},"PeriodicalIF":7.5,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148683664","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The authors reply.","authors":"Marianne E Nellis, Oliver Karam","doi":"10.1097/CCM.0000000000007302","DOIUrl":"https://doi.org/10.1097/CCM.0000000000007302","url":null,"abstract":"","PeriodicalId":10765,"journal":{"name":"Critical Care Medicine","volume":"54 10","pages":"2791-2792"},"PeriodicalIF":7.5,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149105392","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Lidocaine Versus Amiodarone in Patients With Shockable Out-of-Hospital Cardiac Arrest: A Target Trial Emulation.","authors":"Georg Gelbenegger, Sheldon Cheskes, Ian R Drennan, Steve Lin, Bernd Jilma, Markus Zeitlinger, Damon C Scales, Anselm Jorda","doi":"10.1097/CCM.0000000000007265","DOIUrl":"10.1097/CCM.0000000000007265","url":null,"abstract":"<p><strong>Objectives: </strong>Amiodarone or lidocaine are recommended for the treatment of shockable out-of-hospital cardiac arrest (OHCA). Previous comparisons between the two antiarrhythmic drugs were inconclusive.</p><p><strong>Design: </strong>This analysis included data from the Resuscitation Outcomes Consortium Cardiac Epidemiologic Registry 3 (2011-2015). A target trial framework was used to overcome confounding inherent in observational comparisons.</p><p><strong>Setting: </strong>Data from patients with OHCA were prospectively collected by emergency medical services (EMS) at multiple North American sites.</p><p><strong>Patients: </strong>Adults with nontraumatic OHCA and an initial shockable rhythm who received at least three defibrillation attempts were included. Time zero was defined as first antiarrhythmic drug administration, at which eligibility criteria had to be met.</p><p><strong>Interventions: </strong>Two antiarrhythmic treatment strategies were compared: lidocaine vs. amiodarone.</p><p><strong>Measurements and main results: </strong>The primary outcome was survival to hospital discharge. The key secondary outcome was favorable neurologic outcome at discharge (modified Rankin scale score of 3 or less). Group differences were adjusted using inverse probability weighting (key covariates: age, sex, location of OHCA, witness status, bystander resuscitation, automated external defibrillator shock, elapsed time from call to advanced life support arrival/first EMS shock/advanced airway, intraosseous access) and a multiple logistic regression model. Of 2451 patients included, 987 received lidocaine and 1464 received amiodarone. The adjusted percentage point difference in survival to hospital discharge was 2.8% favoring lidocaine (95% CI, -0.6 to 6.2); the estimated survival probabilities were 26.2% (275/987) with lidocaine and 23.5% (329/1464) with amiodarone. No difference was observed in the estimated probability of favorable neurologic outcome at discharge between the lidocaine group (17.7%) and the amiodarone group (16.2%) (adjusted difference, 1.5%; 95% CI, -1.5 to 4.5).</p><p><strong>Conclusions: </strong>No statistically significant difference in survival or favorable neurologic outcome was observed between lidocaine and amiodarone; however, the wide CIs cannot exclude a clinically meaningful benefit for lidocaine. These findings are consistent with randomized controlled trials, but residual confounding cannot be excluded.</p>","PeriodicalId":10765,"journal":{"name":"Critical Care Medicine","volume":" ","pages":"2579-2589"},"PeriodicalIF":7.5,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13632812/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148454870","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ICU Open-Access Databases for Artificial Intelligence in Sepsis: Balancing Innovation With Data Quality Challenges.","authors":"Joanne Jegou, Ioana Manolescu, Stéphane Ruckly, Jean-François Timsit, Michael Thy","doi":"10.1097/CCM.0000000000007319","DOIUrl":"10.1097/CCM.0000000000007319","url":null,"abstract":"<p><strong>Objectives: </strong>To evaluate the suitability of three major open-access ICU databases (Medical Information Mart for Intensive Care IV [MIMIC-IV], eICU Collaborative Research Database [eICU-CRD], and Amsterdam University Medical Center Database [AmsterdamUMCdb]) for artificial intelligence (AI)-based sepsis research, with a focus on data completeness, internal consistency, terminological standardization, and structural redundancy affecting clinical interpretability and reproducibility.</p><p><strong>Design: </strong>A descriptive comparative design was employed to evaluate data completeness, terminological consistency, structural integrity, and clinical usability, with emphasis on sepsis-related variables such as antimicrobial administration, hemodynamic support, and mortality indicators.</p><p><strong>Setting: </strong>Open-access ICU electronic health record databases including MIMIC-IV (2008-2019), eICU-CRD (2014-2015), and AmsterdamUMCdb (2003-2016), accessed under credentialed use agreements. Documentation, schema, and metadata were reviewed in parallel to primary datasets.</p><p><strong>Interventions: </strong>Structured queries and descriptive analyses were performed to quantify missing values, distinct diagnosis strings, medication administration completeness, and redundancy of mortality markers. Manual semantic inspection of terminology, units, and coding ( International Classification of Diseases , 9th revision/10th revision) was applied to evaluate inconsistency and typographical variability. Comparisons were made across key clinical dimensions including diagnosis, mortality, microbiology, and antibiotic administration.</p><p><strong>Measurements and main results: </strong>Marked heterogeneity and data quality limitations were identified. MIMIC-IV demonstrated extensive missingness in medication route (49%) and dose (58%), 99.9% missing fields in microbiology quantity, and diagnosis redundancy with 17,557 unique strings and 174 near-duplicate variants. eICU-CRD exhibited 1.9% admissions lacking diagnosis and discordance between ICU and hospital mortality in 7,319 stays. AmsterdamUMCdb showed fewer structural inconsistencies but limited demographics and the highest proportion of admissions without diagnosis (61.4%), complicated by mixed English-Dutch terminology. All three databases lacked reliable sepsis diagnosis timestamps, constraining analysis of early intervention.</p><p><strong>Conclusions: </strong>Although widely used and valuable for sepsis research, open-access ICU databases exhibit substantial missingness, redundancy, semantic variability, and demographic imbalance. These limitations require rigorous preprocessing and highlight the need for standardized data collection to improve the validity and generalizability of AI-driven sepsis studies.</p>","PeriodicalId":10765,"journal":{"name":"Critical Care Medicine","volume":" ","pages":"2686-2696"},"PeriodicalIF":7.5,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148808285","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}