为了评估机器学习方法在建立多变量模型，用于早期预测急性呼吸窘迫综合征（ARDS）患者住院期间ICU死亡的价值。通过使用来自四个前瞻性、多中心、观察性队列的临床数据，进行开发、测试和外部验证研究。多学科ICU网络。共有1,303例中重度ARDS患者采用肺保护性通气进行管理。没有。我们在1,000例ARDS患者中开发和测试了预测模型。我们采用了遗传算法、随机森林和极端梯度增强机器学习技术进行变量筛选后进行了逻辑回归分析。潜在的预测因子包括人口统计学信息、合并症、通气和氧合指标，以及肺外器官衰竭。风险模型鉴定了一些重要的ICU死亡预后因素，包括年龄、癌症、免疫抑制、Pao2/Fio2、吸气平台压力和肺外器官衰竭的数量。这些特征包含了在预测ICU死亡方面最初24小时内的大部分预测信息。机器学习方法的性能与逻辑回归类似（受试者工作特征曲线下面积[AUC]为0.87，95% CI为0.82-0.91）。对303例ARDS患者的独立队列进行外部验证，证实该模型的性能与逻辑回归模型相似（AUC为0.91，95% CI为0.87-0.94）。无论是机器学习还是传统方法，都可以用于预测中重度ARDS患者的ICU死亡。还需要进一步研究，以确定超出临床决定因素（如人口统计学信息、合并症、肺力学、氧合和肺外器官衰竭）的严重程度标志，以指导患者管理。© 2023年，由重症医学学会和Wolters Kluwer Health, Inc.保留所有权利。

To assess the value of machine learning approaches in the development of a multivariable model for early prediction of ICU death in patients with acute respiratory distress syndrome (ARDS).A development, testing, and external validation study using clinical data from four prospective, multicenter, observational cohorts.A network of multidisciplinary ICUs.A total of 1,303 patients with moderate-to-severe ARDS managed with lung-protective ventilation.None.We developed and tested prediction models in 1,000 ARDS patients. We performed logistic regression analysis following variable selection by a genetic algorithm, random forest and extreme gradient boosting machine learning techniques. Potential predictors included demographics, comorbidities, ventilatory and oxygenation descriptors, and extrapulmonary organ failures. Risk modeling identified some major prognostic factors for ICU mortality, including age, cancer, immunosuppression, Pao2/Fio2, inspiratory plateau pressure, and number of extrapulmonary organ failures. Together, these characteristics contained most of the prognostic information in the first 24 hours to predict ICU mortality. Performance with machine learning methods was similar to logistic regression (area under the receiver operating characteristic curve [AUC], 0.87; 95% CI, 0.82-0.91). External validation in an independent cohort of 303 ARDS patients confirmed that the performance of the model was similar to a logistic regression model (AUC, 0.91; 95% CI, 0.87-0.94).Both machine learning and traditional methods lead to promising models to predict ICU death in moderate/severe ARDS patients. More research is needed to identify markers for severity beyond clinical determinants, such as demographics, comorbidities, lung mechanics, oxygenation, and extrapulmonary organ failure to guide patient management.Copyright © 2023 by the Society of Critical Care Medicine and Wolters Kluwer Health, Inc. All Rights Reserved.