• Jesús Villar, Jesús M González-Martín, Jerónimo Hernández-González, Miguel A Armengol, Cristina Fernández, Carmen Martín-Rodríguez, Fernando Mosteiro, Domingo Martínez, Jesús Sánchez-Ballesteros, Carlos Ferrando, Ana M Domínguez-Berrot, José M Añón, Laura Parra, Raquel Montiel, Rosario Solano, Denis Robaglia, Pedro Rodríguez-Suárez, Estrella Gómez-Bentolila, Rosa L Fernández, Tamas Szakmany, Ewout W Steyerberg, Arthur S Slutsky, and Predicting Outcome and STratifiCation of severity in ARDS (POSTCARDS) Network.
• CIBER de Enfermedades Respiratorias, Instituto de Salud Carlos III, Madrid, Spain.
• Crit. Care Med. 2023 Dec 1; 51 (12): 163816491638-1649.

ObjectivesTo 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).DesignA development, testing, and external validation study using clinical data from four prospective, multicenter, observational cohorts.SettingA network of multidisciplinary ICUs.PatientsA total of 1,303 patients with moderate-to-severe ARDS managed with lung-protective ventilation.InterventionsNone.Measurements And Main ResultsWe 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, Pa o2 /F io2 , 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).ConclusionsBoth 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.

29 keywords...

hide…