Journal of intensive medicine最新文献_第5页

Title Page 标题页

Journal of intensive medicine

Pub Date : 2025-07-01 DOI: 10.1016/S2667-100X(25)00042-8

引用次数: 0

Deep learning integration of chest computed tomography and plasma proteomics to identify novel aspects of severe COVID-19 pneumonia 深度学习整合胸部计算机断层扫描和血浆蛋白质组学，以识别COVID-19重症肺炎的新方面

Journal of intensive medicine

Pub Date : 2025-07-01 Epub Date: 2024-12-16 DOI: 10.1016/j.jointm.2024.11.001

Yucai Hong , Lin Chen , Yang Yu , Ziyue Zhao , Ronghua Wu , Rui Gong , Yandong Cheng , Lingmin Yuan , Shaojun Zheng , Cheng Zheng , Ronghai Lin , Jianping Chen , Kangwei Sun , Ping Xu , Li Ye , Chaoting Han , Xihao Zhou , Yaqing Liu , Jianhua Yu , Yaqin Zheng , Zhongheng Zhang

Background

Heterogeneity is a critical characteristic of severe coronavirus disease 2019 (COVID-19) pneumonia. Integrating chest computed tomography (CT) imaging and plasma proteomics holds the potential to elucidate Image-Expression Axes (IEAs) that can effectively address this disease heterogeneity.

Methods

A cohort of subjects diagnosed with severe COVID-19 pneumonia at 12 participating hospitals between December 2022 and March 2023 was prospectively screened for eligibility. Context-aware self-supervised representation learning (CSRL) was employed to extract intricate features from CT images. Quantification of plasma proteins was achieved using the Olink® inflammation panel. A deep learning model was meticulously trained, with CSRL features serving as input and the proteomic data as the target. This trained model facilitated the construction of IEAs, offering a representation of the underlying disease heterogeneity. The potential of these IEAs for prognostic and predictive enrichment was subsequently explored via conventional regression models.

Results

The study cohort comprised 1979 eligible patients, who were stratified into a training set of 630 individuals and a testing set of 1349 individuals. Three distinct IEAs were identified: IEA1 was correlated with shock conditions, IEA2 was associated with the systemic inflammatory response syndrome (SIRS), and IEA3 was reflective of the coagulation profile. Notably, IEA1 (odds ratio [OR]= 0.52, 95 % confidence interval [CI]: 0.40 to 0.67, P < 0.001) and IEA2 (OR=0.74, 95 % CI: 0.62 to 0.90, P=0.002) exhibited significant associations with the risk of mortality. Intriguingly, patients characterized by lower IEA1 values (<-2, indicative of more severe shock) demonstrated a reduced mortality risk when administered with steroids. Conversely, patients with higher IEA2 values seemed to benefit from a judicious approach to fluid infusion.

Conclusions

Our comprehensive approach, seamlessly integrating advanced deep learning techniques, proteomic profiling, and clinical data, has unraveled intricate interdependencies between IEAs, protein abundance patterns, therapeutic interventions, and ultimate patient outcomes in the context of severe COVID-19 pneumonia. These discoveries make a significant contribution to the rapidly advancing field of precision medicine, paving the way for tailored therapeutic strategies that can significantly impact patient care.

异质性是2019年严重冠状病毒病（COVID-19）肺炎的关键特征。整合胸部计算机断层扫描（CT）成像和血浆蛋白质组学具有阐明图像表达轴（IEAs）的潜力，可以有效地解决这种疾病的异质性。方法前瞻性筛选2022年12月至2023年3月期间在12家参与医院诊断为COVID-19重症肺炎的受试者。采用上下文感知自监督表示学习（CSRL）从CT图像中提取复杂特征。使用Olink®炎症面板实现血浆蛋白定量。以CSRL特征作为输入，以蛋白质组学数据为目标，精心训练深度学习模型。这个经过训练的模型促进了IEAs的构建，提供了潜在疾病异质性的表示。随后通过传统回归模型探索了这些IEAs在预测和预测富集方面的潜力。结果研究队列包括1979名符合条件的患者，他们被分为630名训练组和1349名测试组。确定了三种不同的iea: IEA1与休克状况相关，IEA2与全身炎症反应综合征（SIRS）相关，IEA3反映凝血状况。值得注意的是，IEA1(优势比[OR]= 0.52, 95 %置信区间[CI]: 0.40至0.67,P <；0.001)和IEA2 （OR=0.74, 95 % CI: 0.62 ~ 0.90， P=0.002）与死亡风险显著相关。有趣的是，IEA1值较低（<-2，表明休克更严重）的患者在服用类固醇后死亡风险降低。相反，较高IEA2值的患者似乎受益于明智的输液方法。我们的综合方法无缝整合了先进的深度学习技术、蛋白质组学分析和临床数据，揭示了COVID-19重症肺炎背景下IEAs、蛋白质丰度模式、治疗干预和最终患者结局之间复杂的相互依赖关系。这些发现为快速发展的精准医学领域做出了重大贡献，为定制治疗策略铺平了道路，可以显著影响患者护理。

{"title":"Deep learning integration of chest computed tomography and plasma proteomics to identify novel aspects of severe COVID-19 pneumonia","authors":"Yucai Hong , Lin Chen , Yang Yu , Ziyue Zhao , Ronghua Wu , Rui Gong , Yandong Cheng , Lingmin Yuan , Shaojun Zheng , Cheng Zheng , Ronghai Lin , Jianping Chen , Kangwei Sun , Ping Xu , Li Ye , Chaoting Han , Xihao Zhou , Yaqing Liu , Jianhua Yu , Yaqin Zheng , Zhongheng Zhang","doi":"10.1016/j.jointm.2024.11.001","DOIUrl":"10.1016/j.jointm.2024.11.001","url":null,"abstract":"<div><h3>Background</h3><div>Heterogeneity is a critical characteristic of severe coronavirus disease 2019 (COVID-19) pneumonia. Integrating chest computed tomography (CT) imaging and plasma proteomics holds the potential to elucidate Image-Expression Axes (IEAs) that can effectively address this disease heterogeneity.</div></div><div><h3>Methods</h3><div>A cohort of subjects diagnosed with severe COVID-19 pneumonia at 12 participating hospitals between December 2022 and March 2023 was prospectively screened for eligibility. Context-aware self-supervised representation learning (CSRL) was employed to extract intricate features from CT images. Quantification of plasma proteins was achieved using the Olink® inflammation panel. A deep learning model was meticulously trained, with CSRL features serving as input and the proteomic data as the target. This trained model facilitated the construction of IEAs, offering a representation of the underlying disease heterogeneity. The potential of these IEAs for prognostic and predictive enrichment was subsequently explored via conventional regression models.</div></div><div><h3>Results</h3><div>The study cohort comprised 1979 eligible patients, who were stratified into a training set of 630 individuals and a testing set of 1349 individuals. Three distinct IEAs were identified: IEA1 was correlated with shock conditions, IEA2 was associated with the systemic inflammatory response syndrome (SIRS), and IEA3 was reflective of the coagulation profile. Notably, IEA1 (odds ratio [OR]= 0.52, 95 % confidence interval [CI]: 0.40 to 0.67, <em>P</em> < 0.001) and IEA2 (OR=0.74, 95 % CI: 0.62 to 0.90, <em>P</em>=0.002) exhibited significant associations with the risk of mortality. Intriguingly, patients characterized by lower IEA1 values (<-2, indicative of more severe shock) demonstrated a reduced mortality risk when administered with steroids. Conversely, patients with higher IEA2 values seemed to benefit from a judicious approach to fluid infusion.</div></div><div><h3>Conclusions</h3><div>Our comprehensive approach, seamlessly integrating advanced deep learning techniques, proteomic profiling, and clinical data, has unraveled intricate interdependencies between IEAs, protein abundance patterns, therapeutic interventions, and ultimate patient outcomes in the context of severe COVID-19 pneumonia. These discoveries make a significant contribution to the rapidly advancing field of precision medicine, paving the way for tailored therapeutic strategies that can significantly impact patient care.</div></div>","PeriodicalId":73799,"journal":{"name":"Journal of intensive medicine","volume":"5 3","pages":"Pages 252-261"},"PeriodicalIF":0.0,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144522360","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The glyoxalase system: A new target for inflammatory diseases 乙二醛酶系统：炎症性疾病的新靶点

Journal of intensive medicine

Pub Date : 2025-07-01 Epub Date: 2025-04-11 DOI: 10.1016/j.jointm.2025.03.002

Yingyi Yang , Rui Kang , Huiting Zhou , Daolin Tang

引用次数: 0

Anemia as a potent marker of in-hospital mortality in patients admitted to the cardiac intensive care unit: Data from the Critical Care Cardiology Trials Network (CCCTN) Registry 贫血是心脏重症监护病房入院患者住院死亡率的一个有效标志：来自重症监护心脏病学试验网络（CCCTN）注册的数据

Journal of intensive medicine

Pub Date : 2025-07-01 Epub Date: 2025-01-24 DOI: 10.1016/j.jointm.2024.12.006

Christine Chow , Rasheed Durowoju , Carlos Alviar , Gregory W Barsness , Howard A Cooper , Lori B Daniels , Xuan Ding , Shahab Ghafghazi , Umesh Gidwani , Michael Goldfarb , Dustin Hillerson , Jason N Katz , Paul Marano , Jeong-Gun Park , Matthew Pierce , Scott W Rose , Robert O Roswell , Sean van Diepen , Anjali Wagle , Erin A Bohula , Younghoon Kwon

Background

Anemia is common in critically ill patients and is associated with poor outcomes. We investigated the prevalence of anemia and its association with in-hospital outcomes among patients admitted to cardiac intensive care units (CICUs) and subgroups within this population.

Methods

The Critical Care Cardiology Trials Network (CCCTN) is a multicenter network of tertiary CICUs in North America. CICU admissions with available baseline hemoglobin (Hgb) between 2017 and 2023 were included in this analysis. Patients were stratified by Hgb levels (Hgb <8 g/dL, 8 g/dL ≤ Hgb <10 g/dL, 10 g/dL ≤ Hgb <12 g/dL, 12 g/dL ≤ Hgb <14 g/dL, and ≥14 g/dL). The ≥14 g/dL group was used for reference. The association of Hgb level and in-hospital mortality was examined by multivariable logistic regression.

Results

Among 28,585 patient admissions (median age 67 years, 36.7 % female), the median Hgb was 12.1 g/dL (interquartile range: 10.1–13.9), with 48.3 % of patients who meet criteria for anemia (Hgb <12 g/dL). The adjusted relative odds of in-hospital mortality was highest for patients with Hgb <8 g/dL (1.60, 95 % confidence interval [CI]: 1.35 to 1.89, P < 0.0001), followed by patients with 8 g/dL≤ Hgb <10 g/dL (adjusted relative odds =1.51, 95 % CI: 1.32 to 1.73, P < 0.0001), and patients with Hgb 10 g/dL≤ Hgb<12 g/dL (adjusted relative odds=1.24, 95 % CI: 1.09 to 1.41, P=0.0012). This association was present among those with non-acute coronary syndrome (ACS) cardiogenic shock (n=4255) and those with non-cardiogenic shock ACS (n=7194).

Conclusions

Anemia was present in nearly half of patients admitted to CICUs. Lower admission Hgb is independently associated with higher in-hospital mortality in a graded relationship among patients with cardiac critical illness.

背景：贫血在危重患者中很常见，并与不良预后相关。我们调查了心脏重症监护病房（CICUs）住院患者及其亚组中贫血的患病率及其与住院预后的关系。方法重症监护心脏病学试验网络（CCCTN）是北美三级重症监护中心的多中心网络。该分析纳入了2017年至2023年期间可用基线血红蛋白（Hgb）的CICU入院患者。患者按Hgb水平分层（Hgb <、8g /dL、8g /dL≤Hgb <、10g /dL、10g /dL≤Hgb <、12g /dL、12g /dL≤Hgb <、14g /dL、≥14g /dL）。≥14 g/dL组为参考。采用多变量logistic回归检验Hgb水平与住院死亡率的关系。结果28,585例入院患者（中位年龄67岁，36.7% %女性）中位Hgb为12.1 g/dL（四分位数范围：10.1-13.9），48.3% %的患者符合贫血标准（Hgb <12 g/dL）。Hgb <；8 g/dL患者的调整后住院死亡率相对赔率最高(1.60,95 %置信区间[CI]: 1.35 ~ 1.89, P <；0.0001)，其次是8 g/dL≤Hgb <；10 g/dL(校正相对优势=1.51,95 % CI: 1.32 ~ 1.73, P <；0.0001)， hgb10g /dL≤hgb12g /dL患者（校正相对优势=1.24,95 % CI: 1.09 ~ 1.41， P=0.0012）。在非急性冠脉综合征（ACS）心源性休克（n=4255）和非心源性休克ACS （n=7194）患者中存在这种关联。结论近半数住院患者存在贫血。在心脏危重症患者中，较低的入院Hgb与较高的住院死亡率呈分级关系独立相关。

{"title":"Anemia as a potent marker of in-hospital mortality in patients admitted to the cardiac intensive care unit: Data from the Critical Care Cardiology Trials Network (CCCTN) Registry","authors":"Christine Chow , Rasheed Durowoju , Carlos Alviar , Gregory W Barsness , Howard A Cooper , Lori B Daniels , Xuan Ding , Shahab Ghafghazi , Umesh Gidwani , Michael Goldfarb , Dustin Hillerson , Jason N Katz , Paul Marano , Jeong-Gun Park , Matthew Pierce , Scott W Rose , Robert O Roswell , Sean van Diepen , Anjali Wagle , Erin A Bohula , Younghoon Kwon","doi":"10.1016/j.jointm.2024.12.006","DOIUrl":"10.1016/j.jointm.2024.12.006","url":null,"abstract":"<div><h3>Background</h3><div>Anemia is common in critically ill patients and is associated with poor outcomes. We investigated the prevalence of anemia and its association with in-hospital outcomes among patients admitted to cardiac intensive care units (CICUs) and subgroups within this population.</div></div><div><h3>Methods</h3><div>The Critical Care Cardiology Trials Network (CCCTN) is a multicenter network of tertiary CICUs in North America. CICU admissions with available baseline hemoglobin (Hgb) between 2017 and 2023 were included in this analysis. Patients were stratified by Hgb levels (Hgb <8 g/dL, 8 g/dL ≤ Hgb <10 g/dL, 10 g/dL ≤ Hgb <12 g/dL, 12 g/dL ≤ Hgb <14 g/dL, and ≥14 g/dL). The ≥14 g/dL group was used for reference. The association of Hgb level and in-hospital mortality was examined by multivariable logistic regression.</div></div><div><h3>Results</h3><div>Among 28,585 patient admissions (median age 67 years, 36.7 % female), the median Hgb was 12.1 g/dL (interquartile range: 10.1–13.9), with 48.3 % of patients who meet criteria for anemia (Hgb <12 g/dL). The adjusted relative odds of in-hospital mortality was highest for patients with Hgb <8 g/dL (1.60, 95 % confidence interval [CI]: 1.35 to 1.89, <em>P</em> < 0.0001), followed by patients with 8 g/dL≤ Hgb <10 g/dL (adjusted relative odds =1.51, 95 % CI: 1.32 to 1.73, <em>P</em> < 0.0001), and patients with Hgb 10 g/dL≤ Hgb<12 g/dL (adjusted relative odds=1.24, 95 % CI: 1.09 to 1.41, <em>P</em>=0.0012). This association was present among those with non-acute coronary syndrome (ACS) cardiogenic shock (<em>n</em>=4255) and those with non-cardiogenic shock ACS (<em>n</em>=7194).</div></div><div><h3>Conclusions</h3><div>Anemia was present in nearly half of patients admitted to CICUs. Lower admission Hgb is independently associated with higher in-hospital mortality in a graded relationship among patients with cardiac critical illness.</div></div>","PeriodicalId":73799,"journal":{"name":"Journal of intensive medicine","volume":"5 3","pages":"Pages 262-268"},"PeriodicalIF":0.0,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144522361","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

CHA2DS2-VASc scores to predict left atrial/left atrial appendage abnormalities in patients with sepsis-induced atrial fibrillation: A preliminary investigation CHA2DS2-VASc评分预测脓毒症心房颤动患者左房/左房附件异常的初步研究

Journal of intensive medicine

Pub Date : 2025-07-01 Epub Date: 2025-02-11 DOI: 10.1016/j.jointm.2024.12.007

Vincent Labbé , Stephane Ederhy , David Legouis , Jérémie Joffre , Keyvan Razazi , Oumar Sy , Frank Chemouni , Armand Mekontso Dessap , Muriel Fartoukh , Ariel Cohen , FAST Study Group

引用次数: 0

Redefining sepsis management: The comprehensive impact of artificial intelligence 重新定义败血症管理：人工智能的全面影响

Journal of intensive medicine

Pub Date : 2025-04-01 Epub Date: 2024-09-30 DOI: 10.1016/j.jointm.2024.08.002

Jamie Ghossein , Brett N. Hryciw , Kwadwo Kyeremanteng

引用次数: 0

Preparing for future pandemics: Automated intensive care electronic health record data extraction to accelerate clinical insights 为未来的流行病做准备：自动化重症监护电子健康记录数据提取，以加速临床洞察

Journal of intensive medicine

Pub Date : 2025-04-01 Epub Date: 2024-11-30 DOI: 10.1016/j.jointm.2024.10.003

Lada Lijović , Harm Jan de Grooth , Patrick Thoral , Lieuwe Bos , Zheng Feng , Tomislav Radočaj , Paul Elbers

Background

Manual data abstraction from electronic health records (EHRs) for research on intensive care patients is time-intensive and challenging, especially during high-pressure periods such as pandemics. Automated data extraction is a potential alternative but may raise quality concerns. This study assessed the feasibility and credibility of automated data extraction during the coronavirus disease 2019 (COVID-19) pandemic.

Methods

We retrieved routinely collected data from the COVID-Predict Dutch Data Warehouse, a multicenter database containing the following data on intensive care patients with COVID-19: demographic, medication, laboratory results, and data from monitoring and life support devices. These data were sourced from EHRs using automated data extraction. We used these data to determine indices of wasted ventilation and their prognostic value and compared our findings to a previously published original study that relied on manual data abstraction largely from the same hospitals.

Results

Using automatically extracted data, we replicated the original study. Among 1515 patients intubated for over 2 days, Harris–Benedict (HB) estimates of dead space fraction increased over time and were higher in non-survivors at each time point: at the start of ventilation (0.70±0.13 vs. 0.67±0.15, P <0.001), day 1 (0.74±0.10 vs. 0.71±0.11, P<0.001), day 2 (0.77±0.09 vs. 0.73±0.11, P<0.001), and day 3 (0.78±0.09 vs. 0.74±0.10, P<0.001). Patients with HB dead space fraction above the median had an increased mortality rate of 13.5%, compared to 10.1% in those with values below the median (P<0.005). Ventilatory ratio showed similar trends, with mortality increasing from 10.8% to 12.9% (P=0.040). Conversely, the end-tidal-to-arterial partial pressure of carbon dioxide (PaCO₂) ratio was inversely related to mortality, with a lower 28-day mortality in the higher than median group (8.5% vs. 15.1%, P<0.001). After adjusting for base risk, impaired ventilation markers showed no significant association with 28-day mortality.

Conclusion

Manual data abstraction from EHRs may be unnecessary for reliable research on intensive care patients, highlighting the feasibility and credibility of automated data extraction as a trustworthy and scalable solution to accelerate clinical insights, especially during future pandemics.

从电子健康记录（EHRs）中手动提取数据用于重症监护患者的研究是一项耗时且具有挑战性的工作，特别是在流行病等高压时期。自动数据提取是一个潜在的替代方案，但可能会引起质量问题。本研究评估了2019冠状病毒病（COVID-19）大流行期间自动数据提取的可行性和可信度。方法我们从COVID-Predict荷兰数据仓库（一个多中心数据库）中检索常规收集的数据，该数据库包含以下COVID-19重症监护患者的数据：人口统计学、药物、实验室结果以及监测和生命支持设备的数据。这些数据来自使用自动数据提取的电子病历。我们使用这些数据来确定浪费通气的指标及其预后价值，并将我们的发现与先前发表的一项原始研究进行比较，该研究主要依赖于来自同一家医院的人工数据提取。结果使用自动提取的数据，我们重复了原始研究。在1515例插管超过2天的患者中，哈里斯-本尼迪克特（HB）估计的死亡空间分数随着时间的推移而增加，在每个时间点，非幸存者的死亡空间分数更高：通气开始时（0.70±0.13比0.67±0.15,P<0.001），第1天（0.74±0.10比0.71±0.11,P<0.001），第2天（0.77±0.09比0.73±0.11,P<0.001），第3天（0.78±0.09比0.74±0.10,P<0.001）。HB死亡空间分数高于中位数的患者死亡率增加13.5%，而低于中位数的患者死亡率增加10.1% （P<0.005）。通气量变化趋势相似，死亡率由10.8%上升至12.9% （P=0.040）。相反，尾潮-动脉二氧化碳分压（PaCO₂）比与死亡率呈负相关，高中位数组28天死亡率较低（8.5%比15.1%,P<0.001）。在调整基础风险后，通气指标受损与28天死亡率无显著关联。结论从电子病历中手动提取数据对于重症监护患者的可靠研究可能是不必要的，这突出了自动化数据提取作为一种值得信赖和可扩展的解决方案的可行性和可信度，以加速临床洞察，特别是在未来的大流行期间。

{"title":"Preparing for future pandemics: Automated intensive care electronic health record data extraction to accelerate clinical insights","authors":"Lada Lijović , Harm Jan de Grooth , Patrick Thoral , Lieuwe Bos , Zheng Feng , Tomislav Radočaj , Paul Elbers","doi":"10.1016/j.jointm.2024.10.003","DOIUrl":"10.1016/j.jointm.2024.10.003","url":null,"abstract":"<div><h3>Background</h3><div>Manual data abstraction from electronic health records (EHRs) for research on intensive care patients is time-intensive and challenging, especially during high-pressure periods such as pandemics. Automated data extraction is a potential alternative but may raise quality concerns. This study assessed the feasibility and credibility of automated data extraction during the coronavirus disease 2019 (COVID-19) pandemic.</div></div><div><h3>Methods</h3><div>We retrieved routinely collected data from the COVID-Predict Dutch Data Warehouse, a multicenter database containing the following data on intensive care patients with COVID-19: demographic, medication, laboratory results, and data from monitoring and life support devices. These data were sourced from EHRs using automated data extraction. We used these data to determine indices of wasted ventilation and their prognostic value and compared our findings to a previously published original study that relied on manual data abstraction largely from the same hospitals.</div></div><div><h3>Results</h3><div>Using automatically extracted data, we replicated the original study. Among 1515 patients intubated for over 2 days, Harris–Benedict (HB) estimates of dead space fraction increased over time and were higher in non-survivors at each time point: at the start of ventilation (0.70±0.13 <em>vs</em>. 0.67±0.15, <em>P</em> <0.001), day 1 (0.74±0.10 <em>vs</em>. 0.71±0.11, <em>P</em><0.001), day 2 (0.77±0.09 <em>vs</em>. 0.73±0.11, <em>P</em><0.001), and day 3 (0.78±0.09 <em>vs</em>. 0.74±0.10, <em>P</em><0.001). Patients with HB dead space fraction above the median had an increased mortality rate of 13.5%, compared to 10.1% in those with values below the median (<em>P</em><0.005). Ventilatory ratio showed similar trends, with mortality increasing from 10.8% to 12.9% (<em>P</em>=0.040). Conversely, the end-tidal-to-arterial partial pressure of carbon dioxide (PaCO₂) ratio was inversely related to mortality, with a lower 28-day mortality in the higher than median group (8.5% <em>vs</em>. 15.1%, <em>P</em><0.001). After adjusting for base risk, impaired ventilation markers showed no significant association with 28-day mortality.</div></div><div><h3>Conclusion</h3><div>Manual data abstraction from EHRs may be unnecessary for reliable research on intensive care patients, highlighting the feasibility and credibility of automated data extraction as a trustworthy and scalable solution to accelerate clinical insights, especially during future pandemics.</div></div>","PeriodicalId":73799,"journal":{"name":"Journal of intensive medicine","volume":"5 2","pages":"Pages 167-175"},"PeriodicalIF":0.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143724777","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Predicting multiple organ dysfunction syndrome in trauma-induced sepsis: Nomogram and machine learning approaches 预测创伤性败血症中的多器官功能障碍综合征：Nomogram和machine learning方法

Journal of intensive medicine

Pub Date : 2025-04-01 Epub Date: 2025-02-08 DOI: 10.1016/j.jointm.2024.12.008

Jinyu Peng , Yun Li , Chao Liu , Zhi Mao , Hongjun Kang , Feihu Zhou

Background

Multiple organ dysfunction syndrome (MODS) is a critical complication in trauma-induced sepsis patients and is associated with a high mortality rate. This study aimed to develop and validate predictive models for MODS in this patient population using a nomogram and machine learning approaches.

Methods

This retrospective cohort study utilized data from the Medical Information Mart for Intensive Care-IV 2.2 database, focusing on trauma patients diagnosed with sepsis within the first day of intensive care unit (ICU) admission. Predictive variables were extracted from the initial 24 h of ICU data. The dataset (2008–2019) was divided into a training set (2008–2016) and a temporal validation set (2017–2019). Feature selection was conducted using the Boruta algorithm. Predictive models were developed and validated using a nomogram and various machine learning techniques. Model performance was evaluated based on discrimination, calibration, and decision curve analysis.

Results

Among 1295 trauma patients with sepsis, 349 (26.95%) developed MODS. The 28-day mortality rates were 11.21% for non-MODS patients and 23.82% for MODS patients. Key predictors of MODS included the simplified acute physiology score II score, use of mechanical ventilation, and vasopressor administration. In temporal validation, all models significantly outperformed traditional scoring systems (all P <0.05). The nomogram achieved an area under the curve (AUC) of 0.757 (95% confidence interval [CI]: 0.700 to 0.814), while the random forest model demonstrated the highest performance with an AUC of 0.769 (95% CI: 0.712 to 0.826). Calibration plots showed excellent agreement between predicted and observed probabilities, and decision curve analysis indicated a consistently higher net benefit for the newly developed models.

Conclusion

The nomogram and machine learning models provide enhanced predictive accuracy for MODS in trauma-induced sepsis patients compared to traditional scoring systems. These tools, accessible via web-based applications, have the potential to improve early risk stratification and guide clinical decision-making, ultimately enhancing outcomes for trauma patients. Further external validation is recommended to confirm their generalizability.

背景：多器官功能障碍综合征（MODS）是创伤性脓毒症患者的重要并发症，死亡率高。本研究旨在利用nomogram和机器学习方法开发并验证该患者群体MODS的预测模型。方法本回顾性队列研究利用重症监护医学信息市场- iv - 2.2数据库的数据，重点研究重症监护病房（ICU）入院第一天诊断为败血症的创伤患者。从ICU的最初24小时数据中提取预测变量。数据集（2008-2019）分为训练集（2008-2016）和时间验证集（2017-2019）。采用Boruta算法进行特征选择。使用nomogram和各种机器学习技术开发并验证了预测模型。基于判别、校准和决策曲线分析对模型性能进行评估。结果1295例创伤脓毒症患者中，349例（26.95%）发生MODS。非MODS患者28天死亡率为11.21%，MODS患者为23.82%。MODS的主要预测因素包括简化急性生理评分、机械通气的使用和血管加压药的使用。在时间验证中，所有模型都显著优于传统评分系统（均P <；0.05）。模态图的曲线下面积（AUC）为0.757(95%可信区间[CI]: 0.700至0.814)，而随机森林模型的AUC为0.769 (95% CI: 0.712至0.826)，表现出最高的性能。校正图显示预测概率和观测概率非常吻合，决策曲线分析表明新开发模型的净效益始终较高。结论与传统评分系统相比，nomogram和machine learning模型可提高创伤性败血症患者MODS的预测准确性。这些工具可通过基于网络的应用程序访问，具有改善早期风险分层和指导临床决策的潜力，最终提高创伤患者的预后。建议进一步进行外部验证以确认其通用性。

{"title":"Predicting multiple organ dysfunction syndrome in trauma-induced sepsis: Nomogram and machine learning approaches","authors":"Jinyu Peng , Yun Li , Chao Liu , Zhi Mao , Hongjun Kang , Feihu Zhou","doi":"10.1016/j.jointm.2024.12.008","DOIUrl":"10.1016/j.jointm.2024.12.008","url":null,"abstract":"<div><h3>Background</h3><div>Multiple organ dysfunction syndrome (MODS) is a critical complication in trauma-induced sepsis patients and is associated with a high mortality rate. This study aimed to develop and validate predictive models for MODS in this patient population using a nomogram and machine learning approaches.</div></div><div><h3>Methods</h3><div>This retrospective cohort study utilized data from the Medical Information Mart for Intensive Care-IV 2.2 database, focusing on trauma patients diagnosed with sepsis within the first day of intensive care unit (ICU) admission. Predictive variables were extracted from the initial 24 h of ICU data. The dataset (2008–2019) was divided into a training set (2008–2016) and a temporal validation set (2017–2019). Feature selection was conducted using the Boruta algorithm. Predictive models were developed and validated using a nomogram and various machine learning techniques. Model performance was evaluated based on discrimination, calibration, and decision curve analysis.</div></div><div><h3>Results</h3><div>Among 1295 trauma patients with sepsis, 349 (26.95%) developed MODS. The 28-day mortality rates were 11.21% for non-MODS patients and 23.82% for MODS patients. Key predictors of MODS included the simplified acute physiology score II score, use of mechanical ventilation, and vasopressor administration. In temporal validation, all models significantly outperformed traditional scoring systems (all <em>P</em> <0.05). The nomogram achieved an area under the curve (AUC) of 0.757 (95% confidence interval [CI]: 0.700 to 0.814), while the random forest model demonstrated the highest performance with an AUC of 0.769 (95% CI: 0.712 to 0.826). Calibration plots showed excellent agreement between predicted and observed probabilities, and decision curve analysis indicated a consistently higher net benefit for the newly developed models.</div></div><div><h3>Conclusion</h3><div>The nomogram and machine learning models provide enhanced predictive accuracy for MODS in trauma-induced sepsis patients compared to traditional scoring systems. These tools, accessible via web-based applications, have the potential to improve early risk stratification and guide clinical decision-making, ultimately enhancing outcomes for trauma patients. Further external validation is recommended to confirm their generalizability.</div></div>","PeriodicalId":73799,"journal":{"name":"Journal of intensive medicine","volume":"5 2","pages":"Pages 193-201"},"PeriodicalIF":0.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143724780","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Is it beneficial to allow the patient's family to attend cardiac resuscitation: Different cultural perspectives? A scoping review 允许患者家属参加心脏复苏是否有益：不同的文化视角？范围审查

Journal of intensive medicine

Pub Date : 2025-04-01 Epub Date: 2024-12-18 DOI: 10.1016/j.jointm.2024.11.002

Hasan Abualruz , Mohammad A. Abu Sabra , Elham H. Othman , Malakeh Z. Malak , Saleh Al Omar , Reema R. Safadi , Salah M. AbuRuz , Khaled Suleiman

Background

Family presence during resuscitation (FPDR) is a controversial issue that remains unresolved in contemporary practice. Although there are many research studies on FPDR and several published statements and guidelines supporting FPDR by international organizations, no conclusive position guides clinicians in making a decision. A scoping review was conducted to discuss the different healthcare professionals (HCPs) and cultural perspectives toward family presence during CPR is conducted.

Methods

Using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews (PRISMA-ScR) guidelines, we screened 797 studies published between 2000 and 2022 from the databases including Springer Link, MEDLINE, Pro-Quest Central, CINAHL Plus, and Google Scholar. All articles were filtered using inclusion criteria to eliminate redundant, irrelevant, and unnecessary content.

Results

A total of 34 studies that fulfill the eligibility criteria reported that there are multiple perspectives from HCPs and families about FPDR. HCPs felt that their performance had improved during resuscitation and received family support in breaking the bad news of death. Family relatives who attended cardiopulmonary resuscitation (CPR) had less stress, less anxiety, more positive grieving behavior, and enhanced family members’ decision-making. Contrastingly, some HCPs were against FPDR because they were concerned about the family's misinterpretation of resuscitation activities, psychological trauma to the family members, increased stress levels among staff, and worry about an unexpected response from the distressed family.

Conclusions

It is important to consider the culture and awareness of families when deciding on FPDR. It is the responsibility of HCPs to assess family members’ willingness and the benefits they attain from attending CPR. The decision should be based on the given situation, cultural context and beliefs, and current policy to guide practice.

家庭在复苏中的存在（FPDR）是一个有争议的问题，在当代实践中仍未得到解决。尽管有许多关于FPDR的研究和一些国际组织发表的支持FPDR的声明和指南，但没有结论性的立场指导临床医生做出决定。进行了一项范围审查，以讨论不同的医疗保健专业人员（HCPs）和文化观点，在心肺复苏术期间的家庭存在。方法采用系统评价首选报告项目和荟萃分析扩展范围评价（PRISMA-ScR）指南，从施普林格Link、MEDLINE、Pro-Quest Central、CINAHL Plus和谷歌Scholar等数据库中筛选2000年至2022年发表的797项研究。使用纳入标准对所有文章进行筛选，以消除冗余、不相关和不必要的内容。结果共有34项符合资格标准的研究报告了来自医护人员和家庭对FPDR的多种观点。医护人员认为他们在复苏期间的表现有所改善，在宣布死亡的坏消息时得到了家人的支持。接受心肺复苏术（CPR）的家属压力更小，焦虑更少，更积极的悲伤行为，并提高了家庭成员的决策能力。相反，一些医护人员反对FPDR，因为他们担心家庭对复苏活动的误解，对家庭成员的心理创伤，工作人员的压力水平增加，以及担心痛苦家庭的意外反应。结论在决定是否采用FPDR时，应考虑家庭的文化和意识。医务人员有责任评估家庭成员参加心肺复苏术的意愿和益处。这一决定应该基于特定的情况、文化背景和信仰，以及当前的政策来指导实践。

{"title":"Is it beneficial to allow the patient's family to attend cardiac resuscitation: Different cultural perspectives? A scoping review","authors":"Hasan Abualruz , Mohammad A. Abu Sabra , Elham H. Othman , Malakeh Z. Malak , Saleh Al Omar , Reema R. Safadi , Salah M. AbuRuz , Khaled Suleiman","doi":"10.1016/j.jointm.2024.11.002","DOIUrl":"10.1016/j.jointm.2024.11.002","url":null,"abstract":"<div><h3>Background</h3><div>Family presence during resuscitation (FPDR) is a controversial issue that remains unresolved in contemporary practice. Although there are many research studies on FPDR and several published statements and guidelines supporting FPDR by international organizations, no conclusive position guides clinicians in making a decision. A scoping review was conducted to discuss the different healthcare professionals (HCPs) and cultural perspectives toward family presence during CPR is conducted.</div></div><div><h3>Methods</h3><div>Using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews (PRISMA-ScR) guidelines, we screened 797 studies published between 2000 and 2022 from the databases including Springer Link, MEDLINE, Pro-Quest Central, CINAHL Plus, and Google Scholar. All articles were filtered using inclusion criteria to eliminate redundant, irrelevant, and unnecessary content.</div></div><div><h3>Results</h3><div>A total of 34 studies that fulfill the eligibility criteria reported that there are multiple perspectives from HCPs and families about FPDR. HCPs felt that their performance had improved during resuscitation and received family support in breaking the bad news of death. Family relatives who attended cardiopulmonary resuscitation (CPR) had less stress, less anxiety, more positive grieving behavior, and enhanced family members’ decision-making. Contrastingly, some HCPs were against FPDR because they were concerned about the family's misinterpretation of resuscitation activities, psychological trauma to the family members, increased stress levels among staff, and worry about an unexpected response from the distressed family.</div></div><div><h3>Conclusions</h3><div>It is important to consider the culture and awareness of families when deciding on FPDR. It is the responsibility of HCPs to assess family members’ willingness and the benefits they attain from attending CPR. The decision should be based on the given situation, cultural context and beliefs, and current policy to guide practice.</div></div>","PeriodicalId":73799,"journal":{"name":"Journal of intensive medicine","volume":"5 2","pages":"Pages 202-210"},"PeriodicalIF":0.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143724781","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Physiological effects and clinical evidence of high-flow nasal cannula during acute exacerbation in COPD patients: A narrative review 高流量鼻插管在慢性阻塞性肺病患者急性加重期的生理效应和临床证据：一项叙述性综述

Journal of intensive medicine

Pub Date : 2025-04-01 Epub Date: 2024-12-19 DOI: 10.1016/j.jointm.2024.10.005

Nicolás Colaianni-Alfonso , Federico Herrera , Diego Flores , Cristian Deana , Mina Vapireva , Daniele Guerino Biasucci , Salvatore Maurizio Maggiore , Luigi Vetrugno

Chronic obstructive pulmonary disease (COPD) is one of the leading causes of death worldwide. During severe exacerbations, COPD patients may develop acute respiratory failure (ARF), often necessitating hospital admission due to impaired gas exchange. In COPD patients, the diaphragm is subjected to an increased workload resulting from airflow limitations and geometric changes in the thorax due to pulmonary hyperinflation. Noninvasive ventilation (NIV) plays a crucial role in managing type II ARF by improving alveolar ventilation, reducing the work of breathing, minimizing the need for endotracheal intubation (ETI), and decreasing both hospital stays and mortality rates. Studies have shown that approximately 64% of patients with acute exacerbation of COPD (AECOPD) may fail NIV, primarily due to worsening respiratory function, interface intolerance, cardiovascular instability, or neurological deterioration. For patients intolerant to NIV, a trial with a high-flow nasal cannula (HFNC) is recommended. Recently, HFNC has gained popularity as a novel respiratory support system and is increasingly used in routine clinical practice for AECOPD patients. It delivers warmed, humidified, and oxygen-enriched air through a nasal cannula at flow rates of up to 60 L/min. This narrative review aims to describe the physiological effects of HFNC in the COPD population and provide an updated overview of HFNC's role in AECOPD patients requiring hospitalization.

慢性阻塞性肺疾病（COPD）是世界范围内导致死亡的主要原因之一。在严重恶化期间，COPD患者可能会出现急性呼吸衰竭（ARF），通常由于气体交换受损而需要住院。在慢性阻塞性肺病患者中，由于气流限制和肺部恶性膨胀导致的胸腔几何变化，隔膜承受的工作量增加。无创通气（NIV）通过改善肺泡通气，减少呼吸功，最大限度地减少气管插管（ETI）的需要，减少住院时间和死亡率，在治疗II型ARF中起着至关重要的作用。研究表明，大约64%的慢性阻塞性肺病急性加重（AECOPD）患者可能无法进行NIV，主要原因是呼吸功能恶化、界面不耐受、心血管不稳定或神经系统恶化。对于不耐受NIV的患者，建议进行高流量鼻插管（HFNC）试验。近年来，HFNC作为一种新型的呼吸支持系统越来越受到人们的欢迎，并越来越多地用于AECOPD患者的常规临床实践。它通过鼻插管以高达60升/分钟的流速输送温暖、湿润和富氧的空气。这篇叙述性综述旨在描述HFNC在COPD人群中的生理作用，并提供HFNC在需要住院治疗的AECOPD患者中的作用的最新概述。

{"title":"Physiological effects and clinical evidence of high-flow nasal cannula during acute exacerbation in COPD patients: A narrative review","authors":"Nicolás Colaianni-Alfonso , Federico Herrera , Diego Flores , Cristian Deana , Mina Vapireva , Daniele Guerino Biasucci , Salvatore Maurizio Maggiore , Luigi Vetrugno","doi":"10.1016/j.jointm.2024.10.005","DOIUrl":"10.1016/j.jointm.2024.10.005","url":null,"abstract":"<div><div>Chronic obstructive pulmonary disease (COPD) is one of the leading causes of death worldwide. During severe exacerbations, COPD patients may develop acute respiratory failure (ARF), often necessitating hospital admission due to impaired gas exchange. In COPD patients, the diaphragm is subjected to an increased workload resulting from airflow limitations and geometric changes in the thorax due to pulmonary hyperinflation. Noninvasive ventilation (NIV) plays a crucial role in managing type II ARF by improving alveolar ventilation, reducing the work of breathing, minimizing the need for endotracheal intubation (ETI), and decreasing both hospital stays and mortality rates. Studies have shown that approximately 64% of patients with acute exacerbation of COPD (AECOPD) may fail NIV, primarily due to worsening respiratory function, interface intolerance, cardiovascular instability, or neurological deterioration. For patients intolerant to NIV, a trial with a high-flow nasal cannula (HFNC) is recommended. Recently, HFNC has gained popularity as a novel respiratory support system and is increasingly used in routine clinical practice for AECOPD patients. It delivers warmed, humidified, and oxygen-enriched air through a nasal cannula at flow rates of up to 60 L/min. This narrative review aims to describe the physiological effects of HFNC in the COPD population and provide an updated overview of HFNC's role in AECOPD patients requiring hospitalization.</div></div>","PeriodicalId":73799,"journal":{"name":"Journal of intensive medicine","volume":"5 2","pages":"Pages 127-133"},"PeriodicalIF":0.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143724787","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0