SHOCK最新文献

{"title":"SHOCK SYNOPSIS MARCH 2025.","authors":"Stefanie Flohe","doi":"10.1097/SHK.0000000000002560","DOIUrl":"https://doi.org/10.1097/SHK.0000000000002560","url":null,"abstract":"","PeriodicalId":21667,"journal":{"name":"SHOCK","volume":"63 3","pages":"339-341"},"PeriodicalIF":2.7,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143524319","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"THE USE OF OLD WORLD PRIMATES (RHESUS MACAQUES) AS A PRECLINICAL MODEL FOR EVALUATION OF HUMAN-DERIVED BLOOD PRODUCTS IN TRAUMATIC SHOCK RESUSCITATION.","authors":"Clifford G Morgan, Leslie E Neidert, Kassandra M Ozuna, Melissa N Romero, Jacob J Glaser, Anthony E Pusateri, Michael M Tiller, Sylvain Cardin","doi":"10.1097/SHK.0000000000002522","DOIUrl":"10.1097/SHK.0000000000002522","url":null,"abstract":"","PeriodicalId":21667,"journal":{"name":"SHOCK","volume":" ","pages":"495-498"},"PeriodicalIF":2.7,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142771477","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cell Free DNA-Based Prediction of Prognosis for Patients on Veno-Arterial Extracorporeal Membrane Oxygenation.","authors":"Jin Li, ChengLong Li, Liangshan Wang, Xiaomeng Wang, Bo Xu, Chunjing Jiang, Meng Xin, Dong Guo, Jing Chen, Zhongtao Du, Hong Wang, Xing Hao, Xiaotong Hou","doi":"10.1097/SHK.0000000000002569","DOIUrl":"https://doi.org/10.1097/SHK.0000000000002569","url":null,"abstract":"<p><strong>Introduction: </strong>Elevated cell-free DNA (cfDNA) was observed in patients receiving venoarterial (VA) extracorporeal membrane oxygenation (ECMO), but the clinical relevance of cfDNA is still not clear. We aimed to establish an predictive model based on the cfDNA to predict the prognosis for patients on ECMO, and reveal the values of cfDNA for complications of limb ischemia and bleeding/thromboembolic events.</p><p><strong>Methods: </strong>Single-center, retrospective evaluation of patients with ECMO support from 2018 through 2023. The derivation cohort included 133 adults diagnosed with cardiogenic shock who received VA-ECMO for circulatory support. We developed three independent features and combined them with a logistic model to predict mortality. Predictive performance was assessed through Bootstrap analysis and validated by another cohort of 27 patients. The values of cfDNA for complications were analysised by restricted cubic spline (RCS) analysis, receiver-operating characteristic curves (ROC) and multivariate regression analyses.</p><p><strong>Results: </strong>A total of 133 adults who underwent VA-ECMO for refractory cardiogenic shock were entered into the derivation cohort. The logistic model, consisted of cfDNA, the worst mean arterial pressure (MAP) before ECMO and the worst lactate within 24 h of VA-ECMO implantation was predictive and performed similarly for validation cohorts (AUROC:0.768 vs 0.747). RCS analysis revealed a positive linear relationship for the risk of limb ischemia (linear, P = 0.006; AUROC of 0.75 [95% CI, 0.656-0.848]), a U-shaped trend for bleeding events (nonlinear, P = 0.214), and a negative trend for thrombotic events (linear, P = 0.552).</p><p><strong>Conclusions: </strong>In addition to MAP and lactate levels, elevated cfDNA levels within 48 h of ECMO support were highly associated with mortality for patients. Additionally, cfDNA is predictive of limb ischemia.</p>","PeriodicalId":21667,"journal":{"name":"SHOCK","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143516710","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Low-volume Resuscitation with VS-101, a Next-Generation PEGylated HBOC, Improves Survival after Severe Hemorrhagic Shock in Rats.","authors":"William H Nugent, Kim D Vandegriff, Ashok Malavalli, Forest R Sheppard, Bjorn K Song","doi":"10.1097/SHK.0000000000002570","DOIUrl":"https://doi.org/10.1097/SHK.0000000000002570","url":null,"abstract":"<p><strong>Abstract: </strong>Over 30% of trauma-related deaths are from massive hemorrhage with 90% of potentially preventable battlefield deaths occurring pre-hospital. Immediate resuscitation with whole blood is ideal but often limited to hospital and medical treatment facilities. Shelf-stable hemoglobin-based oxygen carriers (HBOCs) are designed to relieve the hypoperfusion and hypoxia of shock during the critical pre-hospital period. A new PEGylated human HBOC product, VS-101, with high oxygen affinity and hyperoncotic pressure, has been designed for hypovolemic resuscitation protocols at the point of injury. Thirty-six Sprague-Dawley rats underwent a severe, pressure-guided 45% total blood volume (TBV) hemorrhage. Shocked animals were randomly assigned to receive 20% TBV Lactated Ringers' (LRS), Plasma, Blood, or VS-101. Cardiovascular parameters, arterial blood gases, 8-hr survival, arteriolar diameters, and oxygenation of the spinotrapezius microvasculature were measured. Even compared with whole blood, VS-101 was the only group with survivors (67%) at the end of the 8-hr observation period. Mean survival times were 49, 95, 197, and 426 min for LRS, Plasma, Blood, and VS-101 (p < 0.05 vs all), respectively. VS-101 produced the highest spinotrapezius interstitial oxygenation and recovery of MAP with no evidence of hypertension or arteriolar vasoconstriction. Hypovolemic resuscitation with VS-101 was effective in stabilizing hemorrhagic shock in a simulated pre-hospital setting, which was associated with its combination of high oncotic pressure and oxygen carrying constituent. The lack of arteriolar vasoconstriction and hypertension suggests VS-101 is poised to pass critical safety and efficacy checkpoints for treatment of severe hemorrhage.</p>","PeriodicalId":21667,"journal":{"name":"SHOCK","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143515706","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Ten-Year Trends in How Early-Stage Sepsis Start-Ups Receive Investment.","authors":"John G Younger, Jacob Jordan, Shintaro Kaido","doi":"10.1097/SHK.0000000000002573","DOIUrl":"https://doi.org/10.1097/SHK.0000000000002573","url":null,"abstract":"<p><strong>Abstract: </strong>Often initiated with small governmental or philanthropic grants, nearly all improvements in the detection and care of sepsis require many years and many millions of dollars of financing before becoming generally clinically available. As early-stage healthcare investors are free to pursue a wide variety of new enterprises, innovations in sepsis care must compete in the early investment marketplace by offering both a path to clinical benefit and a path to commercial viability upon commercialization. In this note, we consider the investment environment for sepsis-related technologies including pharmaceuticals and biologicals, diagnostic and therapeutic devices, and health care information technologies and place a decade of investment trends into a broader economic context. Our hope is to better familiarize basic, translational, and clinical scientists with greater insight into how their inventions will be supported as they make their way to the bedside.</p>","PeriodicalId":21667,"journal":{"name":"SHOCK","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143515707","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Machine Learning and Shock Indices-Derived Score for Predicting Contrast-Induced Nephropathy in ACS Patients.","authors":"Yunus Emre Yavuz, Sefa Tatar, Hakan Akıllı, Muzaffer Aslan, Abdullah İçli","doi":"10.1097/SHK.0000000000002567","DOIUrl":"https://doi.org/10.1097/SHK.0000000000002567","url":null,"abstract":"<p><strong>Background: </strong>Contrast-induced nephropathy (CIN) is a serious complication following acute coronary syndrome (ACS), leading to increased morbidity and mortality. Machine learning (ML), combined with parameters such as shock indices, can potentially improve CIN risk prediction by analyzing complex variable interactions and creating accessible, clinically applicable models.</p><p><strong>Methods: </strong>This retrospective case-control study included 719 ACS patients who underwent percutaneous coronary intervention (PCI). Patients were divided into two groups (CIN and non-CIN), and clinical, procedural, and hemodynamic parameters, including shock indices, were analyzed using machine learning algorithms. A new predictive model, CIN-Predict 5, was developed using the Gradient Boosting Machine (GBM) algorithm, incorporating clinically relevant and statistically significant variables. Correlations between model predictions and secondary outcomes, including in-hospital mortality and hospitalization duration, were evaluated.</p><p><strong>Results: </strong>Among the variables used in the GBM algorithm, the Modified Shock Index emerged as the most significant predictor, with an importance score of 0.25. The CIN-Predict 5 model achieved an AUC of 0.87, outperforming the Mehran Risk Score (AUC = 0.75) for predicting CIN. The secondary outcomes showed that CIN-Predict 5 correlated significantly with in hospital mortality (r = 0.16, p < 0.001) and hospitalization duration (r = 0.20, p < 0.001).</p><p><strong>Conclusions: </strong>The GBM-based model we developed, utilizing shock indices and derived through ML, provides a practical tool for early identification of high-risk CIN patients post-ACS, enabling timely preventive strategies and improving clinical decision-making.</p>","PeriodicalId":21667,"journal":{"name":"SHOCK","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143450086","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Plasma Utilization Exacerbates Renal Cortex Inflammation in a Rodent Model of Hemorrhagic Shock and Resuscitation.","authors":"William B Risinger, Paul J Matheson, Marisa E Franklin, Victoria R Hammond, Jaganathan Lakshmanan, Sathnur Pushpakumar, Yan Li, Emily E Volk, Brian G Harbrecht, Jason W Smith","doi":"10.1097/SHK.0000000000002563","DOIUrl":"https://doi.org/10.1097/SHK.0000000000002563","url":null,"abstract":"<p><strong>Background and hypothesis: </strong>Resuscitation strategies incorporating fresh frozen plasma have become the standard of care in the management of traumatic hemorrhagic shock. While plasma resuscitation has been shown to augment the circulation and reduce inflammation within the splanchnic and pulmonary circulation, its global effect on the kidney remains unknown. We hypothesized that plasma would improve intra-renal blood flow and reduce parenchymal inflammation when compared to resuscitation with lactated ringer's.</p><p><strong>Methods: </strong>Animals were randomized into four groups (n = 8): a) baseline, b) hemorrhagic shock alone, c) lactated ringer's resuscitation, and d) fresh frozen plasma resuscitation. Multiplex immunoassays were used to evaluate cytokine and chemokine signaling within the renal cortex and immunohistochemistry was used to identify leukocyte infiltration. Doppler ultrasonography was used to evaluate changes in blood flow and maximum kidney diameter during hemorrhagic shock and resuscitation.</p><p><strong>Results: </strong>While no difference in resistive index (surrogate for blood flow) within the renal artery or parenchymal vessels was observed between resuscitation strategies, plasma resulted in increased transverse kidney diameter. Plasma administration promoted cytokine/chemokine signaling, resulting in increased infiltration of leukocytes within the renal cortex when compared to lactated ringer's.</p><p><strong>Conclusion: </strong>Although the clinical benefits of plasma resuscitation mandate its utilization, our current findings highlight the complexities of plasma resuscitation. While the increase in renal diameter may be related to augmentation of the microcirculation, plasma resuscitation did not enhance macro-circulatory blood flow. Furthermore, plasma resuscitation appears to exacerbate inflammation within the renal cortex after hemorrhage. The downstream physiologic implications of plasma-induced inflammation warrant further exploration.</p>","PeriodicalId":21667,"journal":{"name":"SHOCK","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143450088","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Adjunctive Vasopressors and Short-Term Mortality in Adults with Septic Shock: A Systematic Review and Meta-Analysis.","authors":"Seth R Bauer, Patrick M Wieruszewski, Brittany D Bissell Turpin, Siddharth Dugar, Gretchen L Sacha, Ryota Sato, Matthew T Siuba, Mary Schleicher, Vidula Vachharajani, Yngve Falck-Ytter, Rebecca L Morgan","doi":"10.1097/SHK.0000000000002558","DOIUrl":"10.1097/SHK.0000000000002558","url":null,"abstract":"<p><strong>Background: </strong>Adjunctive vasopressors are added to norepinephrine in one-third of adults with septic shock in the United States. However, effectiveness of this approach is unclear, and treatment recommendations are based on indirect evidence. We sought to synthesize the direct evidence for adjunctive vasopressor administration in adults with septic shock.</p><p><strong>Methods: </strong>We searched MEDLINE, Embase, and Cochrane Central Register of Controlled Trials from inception to June 7, 2023. We included randomized clinical trials of adults with septic shock comparing adjunctive treatment with a vasopressin analogue, angiotensin II, methylene blue, hydroxocobalamin, or catecholamine analogue to standard care vasopressors. The primary outcome was short-term mortality (at or before 28-30 days or intensive care discharge). Secondary outcomes included kidney replacement therapy, digital/peripheral ischemia, and venous thromboembolism. Random-effects meta-analyses were conducted to derive risk ratios (RRs) and 95% CIs. The certainty of the evidence was assessed using Grading of Recommendations Assessment, Development, and Evaluation.</p><p><strong>Results: </strong>Of 6763 records, 17 trials (3813 participants) were included. Compared with standard care, adjunctive vasopressor administration may reduce short-term mortality risk (RR, 0.92 [95% CI, 0.85 to 1.00], low certainty, 17 trials [18 participants]) and likely reduces kidney replacement therapy receipt (RR, 0.92 [95% CI, 0.84 to 1.01], moderate certainty, 8 trials [2408 participants]). Adjunctive vasopressor treatment may increase risk of digital/peripheral ischemia (RR, 2.44 [95% CI, 1.17 to 5.10], low certainty, 9 trials [2981 participants]) and venous thromboembolism (RR, 16.48 [95% CI, 0.96 to 283.17], low certainty, 1 trial [321 participants]). There was some evidence that the pooled estimate for short-term mortality was different (interaction P = 0.13) for trials adjudicated as low risk of bias (RR, 0.95 [95% CI, 0.87 to 1.05]) compared with trials adjudicated as some concerns or high risk of bias (RR, 0.82 [95% CI, 0.69 to 0.97]). The findings were robust to multiple sensitivity and subgroup analyses.</p><p><strong>Conclusions: </strong>In adults with septic shock, adjunctive vasopressors may lower short-term death risk and likely lower kidney replacement therapy risk, but may increase risk of adverse effects. In the United States, adjunctive vasopressor use prevalence in septic shock is disconnected from the low evidence certainty for a favorable mortality-to-risk profile.</p><p><strong>Registration: </strong>PROSPERO CRD42023427984.</p>","PeriodicalId":21667,"journal":{"name":"SHOCK","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143449812","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluation of Prognostic Risk Models Based on Age and Comorbidity in Septic Patients: Insights from Machine Learning and Traditional Methods in a Large-Scale, Multicenter, Retrospective Study.","authors":"Guoxiang Liu, Zhaoming Shang, Ning Ning, Juan Li, Wenwu Sun, Yiwen Fan, Yiran Guo, Jiawei Ye, Wenzhen Zhou, Junwei Qian, Chaoping Ma, Jiyuan Zhang, Xiaofei Jiang, Changqin Zhu, Enqiang Mao, Mingquan Chen, Chengjin Gao","doi":"10.1097/SHK.0000000000002562","DOIUrl":"https://doi.org/10.1097/SHK.0000000000002562","url":null,"abstract":"<p><strong>Background: </strong>Age and comorbidity significantly impact the prognosis of septic patients and inform treatment decisions. To provide clinicians with effective tools for identifying high-risk patients, this study assesses the predictive value of the age-adjusted Charlson Comorbidity Index (ACCI) and its simplified version, the quick ACCI (qACCI), for mortality in septic patients.</p><p><strong>Methods: </strong>This retrospective study included septic patients from four Chinese medical centers. The internal validation cohort comprised patients from Xinhua Hospital, Ruijin Hospital, and Huashan Hospital, while participants from Renji Hospital served as the external validation cohort. Machine learning models identified ACCI's feature importance. Restricted cubic spline regression and subgroup analysis assess the correlation between ACCI and mortality risk. The qACCI, derived from the ACCI components, was also evaluated for predictive reliability.</p><p><strong>Results: </strong>A total of 3,287 septic patients were included: 2,974 in the internal cohort (mean age 67.96 years; 37.5% male) and 313 in the external cohort (mean age 67.90 years; 48.2% male). Machine learning models identified ACCI as a key predictor of in-hospital mortality. A linear correlation was confirmed between ACCI and risks of in-hospital, 30-day, and ICU mortality. Sensitivity analysis revealed consistent results across subgroups, demonstrating significantly higher mortality risks in the moderate- (HR 2.18, 95% CI 1.77-2.70) and high-ACCI (HR 3.72, 95% CI 2.99-4.65) groups compared to the low-ACCI group (HR 1, Reference). The ACCI achieved an AUC of 0.788 for in-hospital mortality, outperforming the SOFA in gastrointestinal (0.831 vs. 0.794) and central nervous system infections (0.803 vs. 0.739). The qACCI showed moderate predictive performance in both the internal (AUC, 0.734) and external (AUC, 0.758) cohorts.</p><p><strong>Conclusions: </strong>As composite indicators of age and comorbidity, ACCI and qACCI provide valuable and reliable tools for clinicians to identify high-risk patients early.</p>","PeriodicalId":21667,"journal":{"name":"SHOCK","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143449976","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predicting Chronic Critical Illness in Bone Trauma Patients: An AI-Based Approach for ICU Healthcare Providers.","authors":"Shengjie Wang, Tao Liu, Ze Long, Yong Qin, Baisheng Sun, Zhencan Han, Xianlong Zhang, Li Li, Mingxing Lei","doi":"10.1097/SHK.0000000000002549","DOIUrl":"https://doi.org/10.1097/SHK.0000000000002549","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Chronic critical illness (CCI) is a serious condition characterized by a prolonged course of illness, resulting in elevated morbidity and mortality. CCI presents significant challenges for healthcare providers in intensive care units (ICUs), particularly among patients with bone trauma. Accurate prediction of CCI in this patient population is essential for effective management and intervention. This study aims to develop a web-based artificial intelligence (AI) application designed to predict CCI in ICU patients suffering from bone trauma.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;A cohort of 1049 patients were included in the study, with 775 patients from the Medical Information Mart for Intensive Care III (MIMIC-III) database and 274 patients from two tertiary hospitals. Five machine learning techniques and logistic regression were employed to develop the models, using 80% of the MIMIC-III cohort. The models' internal effectiveness was evaluated using the remaining 20% of the cohort, and external validation was performed on the 274 prospective patients. Eleven evaluation metrics were used to develop a scoring system for comprehensive performance evaluation.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Among all the models evaluated, the eXGBoosting Machine (eXGBM) model demonstrated the highest performance in internal validation, with an area under the curve (AUC) value of 0.979 (95%CI: 0.970-0.991). It outperformed the Random Forest (RF) model, which had an AUC of 0.957 (95%CI: 0.941-0.967), and the Support Vector Machine (SVM) model, which achieved an AUC of 0.911 (95%CI: 0.878-0.928). The Logistic Regression (LR) model had a relatively lower AUC of 0.753 (95%CI: 0.714-0.793). In terms of various evaluation metrics, including accuracy (0.925), precision (0.906), recall (0.947), specificity (0.902), F1 score (0.926), Brier score (0.056), and Log loss (0.197), the eXGBM model consistently outperformed the other models. Additionally, based on the scoring system, the eXGBM model achieved the highest prediction score of 60, followed by the RF model with a score of 52 and the K-Nearest Neighbor (KNN) model with a score of 39. External validation of the eXGBM model resulted in an AUC of 0.887 (95%CI: 0.863-0.917), confirming its robust performance and generalizability. A user-friendly web-based AI application based on the eXGBM model was successfully developed and was freely accessible at the Internet.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;The development of a web-based AI application utilizing the eXGBM model demonstrates a promising advancement in the prediction of CCI among ICU patients. With favorable performance in both internal and external validation, the AI application not only achieved high accuracy and reliability but also provided a user-friendly tool for clinicians. This application has the potential to enhance patient management and care by facilitating timely interventions for at-risk patients. Future research should focus on fu","PeriodicalId":21667,"journal":{"name":"SHOCK","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143450090","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}