Significant risk factors for intensive care unit-acquired weakness:A processing strategy based on repeated machine learning

BACKGROUND Intensive care unit-acquired weakness(ICU-AW)is a common complication that significantly impacts the patient's recovery process,even leading to adverse outcomes.Currently,there is a lack of effective preventive measures.AIM To identify significant risk factors for ICU-AW through iterative machine learning techniques and offer recommendations for its prevention and treatment.METHODS Patients were categorized into ICU-AW and non-ICU-AW groups on the 14th day post-ICU admission.Relevant data from the initial 14 d of ICU stay,such as age,comorbidities,sedative dosage,vasopressor dosage,duration of mechanical ventilation,length of ICU stay,and rehabilitation therapy,were gathered.The relationships between these variables and ICU-AW were examined.Utilizing iterative machine learning techniques,a multilayer perceptron neural network model was developed,and its predictive performance for ICU-AW was assessed using the receiver operating characteristic curve.RESULTS Within the ICU-AW group,age,duration of mechanical ventilation,lorazepam dosage,adrenaline dosage,and length of ICU stay were significantly higher than in the non-ICU-AW group.Additionally,sepsis,multiple organ dysfunction syndrome,hypoalbuminemia,acute heart failure,respiratory failure,acute kidney injury,anemia,stress-related gastrointestinal bleeding,shock,hypertension,coronary artery disease,malignant tumors,and rehabilitation therapy ratios were significantly higher in the ICU-AW group,demonstrating statistical significance.The most influential factors contributing to ICU-AW were identified as the length of ICU stay(100.0%)and the duration of mechanical ventilation(54.9%).The neural network model predicted ICU-AW with an area under the curve of 0.941,sensitivity of 92.2%,and specificity of 82.7%.CONCLUSION The main factors influencing ICU-AW are the length of ICU stay and the duration of mechanical ventilation.A primary preventive strategy,when feasible,involves minimizing both ICU stay and mechanical ventilation duration.

Intensive care unit-acquired weakness–preventive,and therapeutic aspects;future directions and special focus on lung transplantation

In this editorial,comments are made on an interesting article in the recent issue of the World Journal of Clinical Cases by Wang and Long.The authors describe the use of neural network model to identify risk factors for the development of intensive care unit(ICU)-acquired weakness.This condition has now become common with an increasing number of patients treated in ICUs and continues to be a source of morbidity and mortality.Despite identification of certain risk factors and corrective measures thereof,lacunae still exist in our understanding of this clinical entity.Numerous possible pathogenetic mechanisms at a molecular level have been described and these continue to be increasing.The amount of retrievable data for analysis from the ICU patients for study can be huge and enormous.Machine learning techniques to identify patterns in vast amounts of data are well known and may well provide pointers to bridge the knowledge gap in this condition.This editorial discusses the current knowledge of the condition including pathogenesis,diagnosis,risk factors,preventive measures,and therapy.Furthermore,it looks specifically at ICU acquired weakness in recipients of lung transplantation,because–unlike other solid organ transplants-muscular strength plays a vital role in the preservation and survival of the transplanted lung.Lungs differ from other solid organ transplants in that the proper function of the allograft is dependent on muscle function.Muscular weakness especially diaphragmatic weakness may lead to prolonged ventilation which has deleterious effects on the transplanted lung–ranging from ventilator associated pneumonia to bronchial anastomotic complications due to prolonged positive pressure on the anastomosis.

Advancing critical care recovery:The pivotal role of machine learning in early detection of intensive care unit-acquired weakness

This editorial explores the significant challenge of intensive care unit-acquiredweakness(ICU-AW),a prevalent condition affecting critically ill patients,characterizedby profound muscle weakness and complicating patient recovery.Highlightingthe paradox of modern medical advances,it emphasizes the urgent needfor early identification and intervention to mitigate ICU-AW's impact.Innovatively,the study by Wang et al is showcased for employing a multilayer perceptronneural network model,achieving high accuracy in predicting ICU-AWrisk.This advancement underscores the potential of neural network models inenhancing patient care but also calls for continued research to address limitationsand improve model applicability.The editorial advocates for the developmentand validation of sophisticated predictive tools,aiming for personalized carestrategies to reduce ICU-AW incidence and severity,ultimately improving patientoutcomes in critical care settings.

Unveiling significant risk factors for intensive care unit-acquired weakness:Advancing preventive care

In this editorial,we discuss an article titled,“Significant risk factors for intensive care unit-acquired weakness:A processing strategy based on repeated machine learning,”published in a recent issue of the World Journal of Clinical Cases.Intensive care unit-acquired weakness(ICU-AW)is a debilitating condition that affects critically ill patients,with significant implications for patient outcomes and their quality of life.This study explored the use of artificial intelligence and machine learning techniques to predict ICU-AW occurrence and identify key risk factors.Data from a cohort of 1063 adult intensive care unit(ICU)patients were analyzed,with a particular emphasis on variables such as duration of ICU stay,duration of mechanical ventilation,doses of sedatives and vasopressors,and underlying comorbidities.A multilayer perceptron neural network model was developed,which exhibited a remarkable impressive prediction accuracy of 86.2%on the training set and 85.5%on the test set.The study highlights the importance of early prediction and intervention in mitigating ICU-AW risk and improving patient outcomes.

Evaluating neuromuscular electrical stimulation for preventing and managing intensive care unit-acquired weakness:Current evidence and future directions

Intensive care unit-acquired weakness(ICU-AW)is a prevalent issue in critical care,leading to significant muscle atrophy and functional impairment.Aiming to address this,Neuromuscular Electrical Stimulation(NMES)has been explored as a therapy.This systematic review assesses NMES's safety and effectiveness in enhancing functional capacity and mobility in pre-and post-cardiac surgery patients.NMES was generally safe and feasible,with intervention sessions varying in frequency and duration.Improvements in muscle strength and 6-minute walking test distances were observed,particularly in preoperative settings,but postoperative benefits were inconsistent.NMES showed promise in preventing muscle loss and improving strength,although its impact on overall functional capacity remained uncertain.Challenges such as short ICU stays and body composition affecting NMES efficacy were noted.NMES also holds potential for other conditions like cerebral palsy and stroke.Further research is needed to optimize NMES protocols and better understand its full benefits in preventing ICU-AW and improving patient outcomes.

Predicting intensive care unit-acquired weakness:A multilayer perceptron neural network approach

In this editorial,we comment on the article by Wang and Long,published in a recent issue of the World Journal of Clinical Cases.The article addresses the challenge of predicting intensive care unit-acquired weakness(ICUAW),a neuromuscular disorder affecting critically ill patients,by employing a novel processing strategy based on repeated machine learning.The editorial presents a dataset comprising clinical,demographic,and laboratory variables from intensive care unit(ICU)patients and employs a multilayer perceptron neural network model to predict ICUAW.The authors also performed a feature importance analysis to identify the most relevant risk factors for ICUAW.This editorial contributes to the growing body of literature on predictive modeling in critical care,offering insights into the potential of machine learning approaches to improve patient outcomes and guide clinical decision-making in the ICU setting.

Machine learning insights on intensive care unit-acquired weakness

Intensive care unit-acquired weakness(ICU-AW)significantly hampers patient recovery and increases morbidity.With the absence of established preventive strategies,this study utilizes advanced machine learning methodologies to unearth key predictors of ICU-AW.Employing a sophisticated multilayer perceptron neural network,the research methodically assesses the predictive power for ICU-AW,pinpointing the length of ICU stay and duration of mechanical ventilation as pivotal risk factors.The findings advocate for minimizing these elements as a preventive approach,offering a novel perspective on combating ICU-AW.This research illuminates critical risk factors and lays the groundwork for future explorations into effective prevention and intervention strategies.

Intensive care unit-acquired weakness: Recent insights

Intensive care unit-acquired weakness(ICU-AW)is a common complication in critically ill patients and is associated with a variety of adverse outcomes.These include the need for prolonged mechanical ventilation and ICU stay;higher ICU,in-hospital,and 1-year mortality;and increased in-hospital costs.ICU-AW is associated with multiple risk factors including age,underlying disease,severity of illness,organ failure,sepsis,immobilization,receipt of mechanical ventilation,and other factors related to critical care.The pathological mechanism of ICUAW remains unclear and may be considerably varied.This review aimed to evaluate recent insights into ICU-AW from several aspects including risk factors,pathophysiology,diagnosis,and treatment strategies;this provides new perspectives for future research.

Intensive care unit-acquired weakness:Unveiling significant risk factors and preemptive strategies through machine learning

This editorial discusses an article recently published in the World Journal of Clinical Cases,focusing on risk factors associated with intensive care unit-acquired weak-ness(ICU-AW).ICU-AW is a serious neuromuscular complication seen in criti-cally ill patients,characterized by muscle dysfunction,weakness,and sensory impairments.Post-discharge,patients may encounter various obstacles impacting their quality of life.The pathogenesis involves intricate changes in muscle and nerve function,potentially leading to significant disabilities.Given its global significance,ICU-AW has become a key research area.The study identified critical risk factors using a multilayer perceptron neural network model,highlighting the impact of intensive care unit stay duration and mechanical ventilation duration on ICU-AW.Recommendations were provided for preventing ICU-AW,empha-sizing comprehensive interventions and risk factor mitigation.This editorial stresses the importance of external validation,cross-validation,and model tran-sparency to enhance model reliability.Moreover,the application of machine learning in clinical medicine has demonstrated clear benefits in improving disease understanding and treatment decisions.While machine learning presents oppor-tunities,challenges such as model reliability and data management necessitate thorough validation and ethical considerations.In conclusion,integrating ma-chine learning into healthcare offers significant potential and challenges.Enhan-cing data management,validating models,and upholding ethical standards are crucial for maximizing the benefits of machine learning in clinical practice.

Risk factors for intensive-care-unit-acquired weakness

Wang et al reported 1063 cases from the initial 14 d of intensive care unit(ICU)stay,and analyzed relevant data such as age,comorbidities,recent dosages,vapor pressure dosages,duration of mechanical ventilation,length of ICU stay,and rehabilitation therapy,which are closely related to ICU-acquired weakness(ICUAW).It is suggested that the length of ICU stay and the duration of mechanical ventilation are the main factors.ICU-AW is the most common neuromuscular injury in the ICU,which affects clinical progression and outcomes of patients.This manuscript helps to improve the early recognition of ICU-AW,thereby reducing mortality and improving prognosis.

Pioneering role of machine learning in unveiling intensive care unitacquired weakness

In the research published in the World Journal of Clinical Cases,Wang and Long conducted a quantitative analysis to delineate the risk factors for intensive care unit-acquired weakness(ICU-AW)utilizing advanced machine learning methodologies.The study employed a multilayer perceptron neural network to accurately predict the incidence of ICU-AW,focusing on critical variables such as ICU stay duration and mechanical ventilation.This research marks a significant advancement in applying machine learning to clinical diagnostics,offering a new paradigm for predictive medicine in critical care.It underscores the importance of integrating artificial intelligence technologies in clinical practice to enhance patient management strategies and calls for interdisciplinary collaboration to drive innovation in healthcare.

Increasing role of post-intensive care syndrome in quality of life of intensive care unit survivors

In this editorial we comment on the detrimental consequences that post-intensive care syndrome(PICS)has in the quality of life of intensive care unit(ICU)survivors,highlighting the importance of early onset of multidisciplinary rehabilitation from within the ICU.Although,the syndrome was identified and well described early in 2012,more awareness has been raised on the long-term PICS related health problems by the increased number of coronavirus disease 2019 ICU survivors.It is well outlined that the syndrome affects both the patient and the family and is described as the appearance or worsening of impairment in physical,cognitive,or mental health as consequence of critical illness.PICS was described in order:(1)To raise awareness among clinicians,researchers,even the society;(2)to highlight the need for a multilevel screening of these patients that starts from within the ICU and continues after discharge;(3)to present preventive strategies;and(4)to offer guidelines in terms of rehabilitation.An early multidisci-plinary approach is the key element form minimizing the incidence of PICS and its consequences in health related quality of life of both survivors and their families.

Intervention effect of neuromuscular electrical stimulation on ICU acquired weakness: A meta-analysis

Objective:The early use of neuromuscular electrical stimulation(NMES)to prevent intensive care unit-acquired weakness(ICU-AW)in critical patients is still a controversial topic.We conducted a systematic review to clarify the effectiveness of NMES in preventing ICU-AW.Methods:The Cochrane Library,PubMed,EMBASE,MEDUNE,Web of Science,Ovid,CNKI,Wanfang,VIP,China Biology Medicine disc(CBMdisc)and other databases were searched for randomized controlled trials on the influence of NMES on ICU-AW.The studies were selected according to the inclusion and exclusion criteria.After data and quality were evaluated,a meta-analysis was performed by RevMan 5.3 software.Results:A total of 11 randomized controlled trials with 576 patients were included.The meta-analysis results showed that NMES can improve muscle strength[MD=1.78,95%CI(0.44,3.12,P=0.009);shorten the mechanical ventilation(MV)time[SMD=-0.65,95%CI(-1.03,-0.27,P=0.001],ICU length of stay[MD=-3.41,95%CI(-4.58,-4.24),P<0.001],and total length of stay[MD=-3.97,95%CI(-6.89,-1.06,P=0.008];improve the ability of patients to perform activities of daily living[SMD=0.9,95%CI(0.45,1.35),P=0.001];and increase walking distance[MD=239.03,95%CI(179.22298.85),P<0.001].However,there is no evidence indicating that NMES can improve the functional status of ICU patients during hospitalization,promote the early awakening of patients or reduce mortality(P>0.05).Conclusion:Early implementation of the NMES intervention in ICU patients can prevent ICU-AW and improve their quality of life by enhancing their muscle strength and shortening the MV duration,length of stay in the ICU and total length of stay in the hospital.

肌肉超声回声联合血浆炎性因子对ICUAW诊断及预后评估的价值研究

目的:探讨重症监护病房(intensive care unit,ICU)获得性肌无力(ICU acquired weakness,ICUAW)患者肌肉超声回声与血浆炎性因子的相关性,以及其对ICUAW的诊断价值和预后的预测价值。方法:选择重庆市急救医疗中心ICU住院患者,分别在第1、3、7天使用床旁超声检测患者肌肉回声,获得的总体肌肉回声评分(global muscle echogenicity score,GEM),测定血清白细胞介素-6(interleukin-6,IL-6)和降钙素原(procalcitonin,PCT)浓度,采用医学研究理事会肌力评分法(medical research council scales,MRC-ss)评估肌肉力量。根据患者入ICU第7天MRC-ss评分将患者分为ICUAW组和非ICUAW组,分析比较2组患者GEM、IL-6、PCT的差异及各指标的相关性。利用受试者工作特征(receiver operator characteristic,ROC)曲线分析以上参数对ICUAW诊断效能,分析GEM、IL-6、PCT对ICUAW患者的预测预后价值。结果:ICUAW组第3天GEM、第7天IL-6浓度、GEM高于非ICUAW组(P<0.05)。GEM与第7天IL-6水平呈正相关(r=0.221),第7天GEM与MRC-ss评分呈负相关(r=-0.581)。ROC曲线分析显示,第7天GEM对ICUAW有诊断预测价值,ROC曲线下面积(area under the curve,AUC)为0.838,使用GEM、IL-6、PCT联合诊断,AUC=0.885(P<0.05)。ICUAW组Barthel指数评分(Barthel index,BI)低于非ICUAW组,ICUAW组中总体肌肉超声回声评分(global muscle echogenicity score,GEM)高的患者BI低于GEM低的患者(P<0.05)。结论:ICU住院患者GEM与IL-6、PCT浓度相关,其对ICUAW具有一定的诊断价值,并能够预测ICUAW患者的预后。

补中益气汤合小柴胡汤治疗机械通气重症监护室获得性衰弱患者的临床疗效观察

[目的]探讨补中益气汤合小柴胡汤治疗机械通气重症监护室获得性衰弱(ICU-AW)的疗效。[方法]选择2019年10月—2022年10月河北省沧州中西医结合医院收治的82例行机械通气治疗的重症监护室获得性衰弱(ICU-AW)患者,随机数字表法将患者分为两组,每组各41例。对照组给予常规治疗,观察组在对照组基础上给予补中益气汤合小柴胡汤治疗14 d。比较两组疗效、机械通气时间、ICU住院时间、下床活动时间、中医证候积分、衰弱、肌力状态、运动耐力、日常生活能力以及并发症和不良反应差异。[结果]观察组治疗总有效率高于对照组(95.12%vs.73.17%,P<0.05),机械通气时间、重症监护室(ICU)住院时间、下床活动时间短于对照组(P<0.01),6 min步行距离、Barthel指数(BI)指数高于对照组(P<0.05),Borg评分、呼吸机相关性肺炎发生率低于对照组(P<0.05)。两组治疗后体倦乏力、食欲不振、胁胀作痛、情志抑郁、面色萎黄积分、心血管健康研究指数(CHS)评分均较治疗前降低(P<0.01),医学研究委员会(MRC)评分较治疗前增高(P<0.01),观察组治疗后上述中医证候积分、CHS评分低于对照组(P<0.01),MRC评分高于对照组(P<0.01)。[结论]与常规治疗比较,补中益气汤合小柴胡汤更有助于改善衰弱和疲劳症状,提高运动耐力和日常生活能力,临床疗效更显著。

针刺联合物理康复治疗脓毒症相关性肌病的临床研究

目的:观察益气活血通络针刺法联合物理康复治疗脓毒症相关性肌无力(SIM)的临床疗效及作用机制。方法:选取佛山市中医院2021年1月~2023年10月收治的90例SIM患者为研究对象,随机分为对照组、物理康复组与观察组各30例。对照组给予常规治疗,如抗感染、营养支持、维持水电解质酸碱平衡等。物理康复治疗组在对照组治疗的基础上,予肢体物理康复治疗,30 min/次,2次/d。观察组在物理康复组治疗的基础上,予益气活血、化瘀通络法针刺治疗,疗程为7 d。比较三组患者治疗前后的肌肉力量评分(MRCs)、白细胞介素-6(IL-6)、股直肌横截面积(RFCSA)、急性生理与慢性健康评分(APACHEⅡ)和序贯器官衰竭评分(SOFA),统计三组患者ICU住院时间、总住院时间、28 d死亡率和第28天存活患者的日常生活活动能力评定(ADL评分)。结果:与治疗前比较,三组治疗后的IL-6均显著降低,差异有统计学意义(P<0.05),MRC评分显著提高,差异有统计学意义(P<0.05),对照组和物理康复组的RFCSA均显著减小,差异有统计学意义(P<0.05),而观察组减小的差异无统计学意义(P>0.05)。与对照组比较,观察组治疗后的IL-6显著降低,差异有统计学意义(P<0.05),观察组和物理康复组治疗后的RFCSA均明显增大,差异有统计学意义(P<0.05),观察组的MRC评分显著提高,差异有统计学意义(P<0.05)。与物理康复组比较,观察组治疗后的IL-6、RFCSA和MRC评分改善更明显,差异有统计学意义(P<0.05)。三组治疗后的APACHEⅡ评分和SOFA评分均较治疗前显著降低,差异有统计学意义(P<0.05),观察组治疗后的APACHEⅡ评分和SOFA评分均较对照组降低更显著,差异有统计学意义(P<0.05),而物理康复组与对照组、观察组比较均差异无统计学意义(P>0.05)。在ICU住院时间方面,物理康复组和观察组显著短于对照组,差异有统计学意义(P<0.05),而观察组和物理康复组差异无统计学意义(P>0.05);在总住院时间和28 d死亡率方面,三组比较差异无统计学意义(P>0.05)。存活患者第28天的ADL评分比较,观察组的ADL评分显著高于对照组与物理康复组(P<0.05),而物理康复组和对照组比较,差异无统计学意义(P>0.05)。结论:物理康复组可减少SIM患者的肌肉萎缩,而针刺联合物理康复治疗可有效降低SIM患者的炎性反应水平和减少肌肉萎缩,从而改善肌肉力量,缩短ICU住院时间,改善存活患者的生活质量。

ICU重症患者出现获得性衰弱的预测模型与验证

目的探讨重症监护室(ICU)内重症患者出现获得性衰弱的独立影响因素,构建预测模型并实施预测效果的验证。方法选择2017年1月至2022年12月期间睢县中医院ICU接诊治疗的患者368人的数据实施回顾性分析。采集发生ICU获得性衰弱患者的资料,进行单因素分析、多因素分析以及预测模型构建和预测效能分析。结果纳入本次调查的368名患者中,有189名患者判定为出现ICU获得性衰弱,发生率为51.36%。单因素分析结果显示,出现和未出现ICU获得性衰弱患者的入驻ICU时间长度,急性生理与慢性健康评分(APACHEⅡ)评分,使用神经肌肉阻滞剂情况,血乳酸最高值的数据差异有统计学意义(P<0.05)。多因素分析结果显示,入驻ICU时间长度,APACHEⅡ评分,使用神经肌肉阻滞剂情况,血乳酸最高值是患者发生ICU获得性衰弱的独立影响因素,差异有统计学意义(P<0.05)。依据多因素分析所筛选出来的变量构建列线图风险模型。C-index为0.713。利用Bootstrap自抽样法进行内部验证,重复自抽样1000次,获得校准曲线,平均绝对误差为0.043。利用logistic回归模型的独立影响因素以及P值预测概率对患者发生ICU获得性衰弱的情况进行受试者特征曲线(ROC)曲线的预测,约登指数分别为19.97%、32.92%、15.11%、37.30%、47.20%。结论ICU患者具有较高的获得性衰弱发生风险,若干因素均是该种病变出现的影响因素。利用这些影响因素构建的预测模型具有良好的预测效能,另外需要在工作中对这些影响因素进行监控,以便早期发现和干预。

三级医院ICU护士对ICU获得性衰弱评估及预防策略实践现状的调查研究

目的调查三级医院ICU护士对ICU获得性衰弱(intensive care unit acquired weakness,ICU-AW)评估及预防策略实践现状,并分析影响因素。方法采用便利抽样法,于2022年11月—12月选取北京市、辽宁省、河北省28所三级医院的397名护士为调查对象,采用自行设计的问卷进行调查。结果ICU-AW评估主要由医生完成(55.42%),肌力评估是首选方法(65.49%)。84.13%护士反映临床未有ICU-AW相关的标准化策略或流程,主要预防措施是镇痛镇静(65.24%)、早期活动(62.47%),活动形式主要是呼吸功能指导(33.00%)、床上被动训练(33.25%)。护士ICU-AW评估与预防策略认知得分为(20.74±8.03)分,态度得分(26.68±4.19)分,实践得分(29.79±5.40)分。年龄、工作年限、学历、医院地区分布是护士对ICU-AW评估与预防措施实践的影响因素(P<0.05)。结论目前护士对ICU-AW认知水平不足,ICU-AW评估方式受限,缺乏标准化干预流程,人力资源不足。建议加强ICU-AW教育培训,完善资源配置,构建标准化的评估和实践流程,促进ICU-AW评估与预防实践的临床开展。

首次早期肠内营养患者发生ICU获得性衰弱的影响因素研究

目的探讨首次早期肠内营养的患者发生ICU获得性衰弱(ICU-AW)的影响因素。方法对2021年1月至2022年12月期间在河南省人民医院急诊重症监护病房(EICU)进行首次早期肠内营养治疗的212例危重患者进行回顾性研究,根据早期肠内营养治疗期间是否发生ICU-AW分为ICU-AW组(n=76例)和非ICU-AW组(n=136例),记录两组患者的一般资料、早期肠内营养启动时间、热量-蛋白供应量及肠内营养第7天时腹内压值,分析腹内压和ICU-AW的关系,同时探讨发生ICU-AW的影响因素。结果两组患者在年龄、机械通气、急性生理与慢性健康(APACHEⅡ)评分、血糖、进行肾脏替代治疗、使用皮质类固醇药物、平均每日热卡量、平均每日蛋白量、肠内营养不耐受、肠内营养治疗第7天时腹内压等方面,差异有统计学意义(P<0.05);其中ICU-AW组患者肠内营养第7天时的腹内压为(16.42±1.52)cmH2O均为高于非ICU-AW组(12.88±2.19)cmH2O,差异有统计学意义(P<0.05);logistic回归分析显示:发生ICU-AW的影响因素为年龄大、APACHEⅡ评分高、机械通气、使用皮质类固醇药物、平均每日热卡量及蛋白量低、发生肠内营养不耐受、肠内营养治疗第7天时腹内压高。结论年龄大、APACHEⅡ评分高、机械通气、使用皮质类固醇药物、平均每日热卡量及蛋白量低、平均每日热卡量及蛋白量低、发生肠内营养不耐受、肠内营养治疗第7天时腹内压高是首次早期肠内营养治疗患者发生ICU-AW的危险因素,应给予有针对性的早期干预。

机械通气患者衰弱风险预测模型的系统评价

目的 系统评价机械通气患者衰弱风险预测模型。方法 检索PubMed、Web of Science、Embase、Cochrane Library、知网、万方和维普数据库,搜集关于机械通气患者衰弱风险预测模型的研究,检索时限为建库至2023年12月。由2名研究者独立筛选文献、提取资料并评价纳入文献的偏倚风险和适用性。结果 共纳入16篇文献。纳入模型的受试者工作特征曲线下面积为0.710~0.926。偏倚风险评估显示模型均存在高偏倚风险,适用性较好,出现频次前5个预测因子依次为机械通气时间、年龄、急性生理与慢性健康评估II评分、血乳酸水平和多器官功能障碍。6个验证模型的合并曲线下面积(Area Under Curve, AUC)值为0.800(95%CI:0.740-0.850),表明具有良好的区分度。结论 机械通气患者衰弱风险预测模型整体预测性能较好,但在数据来源、构建设计和统计分析方面有待进一步优化。未来应对现有模型开展外部验证或开发性能优良的高质量预测模型。