TY - JOUR
T1 - Validation and utility of ARDS subphenotypes identified by machine-learning models using clinical data
T2 - an observational, multicohort, retrospective analysis
AU - LUNG SAFE Investigators and the ESICM Trials Group
AU - Maddali, Manoj V.
AU - Churpek, Matthew
AU - Pham, Tai
AU - Rezoagli, Emanuele
AU - Zhuo, Hanjing
AU - Zhao, Wendi
AU - He, June
AU - Delucchi, Kevin L.
AU - Wang, Chunxue
AU - Wickersham, Nancy
AU - McNeil, J. Brennan
AU - Jauregui, Alejandra
AU - Ke, Serena
AU - Vessel, Kathryn
AU - Gomez, Antonio
AU - Hendrickson, Carolyn M.
AU - Kangelaris, Kirsten N.
AU - Sarma, Aartik
AU - Leligdowicz, Aleksandra
AU - Liu, Kathleen D.
AU - Matthay, Michael A.
AU - Ware, Lorraine B.
AU - Laffey, John G.
AU - Bellani, Giacomo
AU - Calfee, Carolyn S.
AU - Sinha, Pratik
AU - Rios, Fernando
AU - Van Haren, Frank
AU - Sottiaux, T.
AU - Lora, Fredy S.
AU - Azevedo, Luciano C.
AU - Depuydt, P.
AU - Fan, Eddy
AU - Bugedo, Guillermo
AU - Qiu, Haibo
AU - Gonzalez, Marcos
AU - Silesky, Juan
AU - Cerny, Vladimir
AU - Nielsen, Jonas
AU - Jibaja, Manuel
AU - Pham, Tài
AU - Wrigge, Hermann
AU - Matamis, Dimitrios
AU - Ranero, Jorge Luis
AU - Hashemian, S. M.
AU - Amin, Pravin
AU - Clarkson, Kevin
AU - Kurahashi, Kiyoyasu
AU - Villagomez, Asisclo
AU - Zeggwagh, Amine Ali
N1 - Publisher Copyright:
© 2022 Elsevier Ltd
PY - 2022/4
Y1 - 2022/4
N2 - Background: Two acute respiratory distress syndrome (ARDS) subphenotypes (hyperinflammatory and hypoinflammatory) with distinct clinical and biological features and differential treatment responses have been identified using latent class analysis (LCA) in seven individual cohorts. To facilitate bedside identification of subphenotypes, clinical classifier models using readily available clinical variables have been described in four randomised controlled trials. We aimed to assess the performance of these models in observational cohorts of ARDS. Methods: In this observational, multicohort, retrospective study, we validated two machine-learning clinical classifier models for assigning ARDS subphenotypes in two observational cohorts of patients with ARDS: Early Assessment of Renal and Lung Injury (EARLI; n=335) and Validating Acute Lung Injury Markers for Diagnosis (VALID; n=452), with LCA-derived subphenotypes as the gold standard. The primary model comprised only vital signs and laboratory variables, and the secondary model comprised all predictors in the primary model, with the addition of ventilatory variables and demographics. Model performance was assessed by calculating the area under the receiver operating characteristic curve (AUC) and calibration plots, and assigning subphenotypes using a probability cutoff value of 0·5 to determine sensitivity, specificity, and accuracy of the assignments. We also assessed the performance of the primary model in EARLI using data automatically extracted from an electronic health record (EHR; EHR-derived EARLI cohort). In Large Observational Study to Understand the Global Impact of Severe Acute Respiratory Failure (LUNG SAFE; n=2813), a multinational, observational ARDS cohort, we applied a custom classifier model (with fewer variables than the primary model) to determine the prognostic value of the subphenotypes and tested their interaction with the positive end-expiratory pressure (PEEP) strategy, with 90-day mortality as the dependent variable. Findings: The primary clinical classifier model had an area under receiver operating characteristic curve (AUC) of 0·92 (95% CI 0·90–0·95) in EARLI and 0·88 (0·84–0·91) in VALID. Performance of the primary model was similar when using exclusively EHR-derived predictors compared with manually curated predictors (AUC=0·88 [95% CI 0·81–0·94] vs 0·92 [0·88–0·97]). In LUNG SAFE, 90-day mortality was higher in patients assigned the hyperinflammatory subphenotype than in those with the hypoinflammatory phenotype (414 [57%] of 725 vs 694 [33%] of 2088; p<0·0001). There was a significant treatment interaction with PEEP strategy and ARDS subphenotype (p=0·041), with lower 90-day mortality in the high PEEP group of patients with the hyperinflammatory subphenotype (hyperinflammatory subphenotype: 169 [54%] of 313 patients in the high PEEP group vs 127 [62%] of 205 patients in the low PEEP group; hypoinflammatory subphenotype: 231 [34%] of 675 patients in the high PEEP group vs 233 [32%] of 734 patients in the low PEEP group). Interpretation: Classifier models using clinical variables alone can accurately assign ARDS subphenotypes in observational cohorts. Application of these models can provide valuable prognostic information and could inform management strategies for personalised treatment, including application of PEEP, once prospectively validated. Funding: US National Institutes of Health and European Society of Intensive Care Medicine.
AB - Background: Two acute respiratory distress syndrome (ARDS) subphenotypes (hyperinflammatory and hypoinflammatory) with distinct clinical and biological features and differential treatment responses have been identified using latent class analysis (LCA) in seven individual cohorts. To facilitate bedside identification of subphenotypes, clinical classifier models using readily available clinical variables have been described in four randomised controlled trials. We aimed to assess the performance of these models in observational cohorts of ARDS. Methods: In this observational, multicohort, retrospective study, we validated two machine-learning clinical classifier models for assigning ARDS subphenotypes in two observational cohorts of patients with ARDS: Early Assessment of Renal and Lung Injury (EARLI; n=335) and Validating Acute Lung Injury Markers for Diagnosis (VALID; n=452), with LCA-derived subphenotypes as the gold standard. The primary model comprised only vital signs and laboratory variables, and the secondary model comprised all predictors in the primary model, with the addition of ventilatory variables and demographics. Model performance was assessed by calculating the area under the receiver operating characteristic curve (AUC) and calibration plots, and assigning subphenotypes using a probability cutoff value of 0·5 to determine sensitivity, specificity, and accuracy of the assignments. We also assessed the performance of the primary model in EARLI using data automatically extracted from an electronic health record (EHR; EHR-derived EARLI cohort). In Large Observational Study to Understand the Global Impact of Severe Acute Respiratory Failure (LUNG SAFE; n=2813), a multinational, observational ARDS cohort, we applied a custom classifier model (with fewer variables than the primary model) to determine the prognostic value of the subphenotypes and tested their interaction with the positive end-expiratory pressure (PEEP) strategy, with 90-day mortality as the dependent variable. Findings: The primary clinical classifier model had an area under receiver operating characteristic curve (AUC) of 0·92 (95% CI 0·90–0·95) in EARLI and 0·88 (0·84–0·91) in VALID. Performance of the primary model was similar when using exclusively EHR-derived predictors compared with manually curated predictors (AUC=0·88 [95% CI 0·81–0·94] vs 0·92 [0·88–0·97]). In LUNG SAFE, 90-day mortality was higher in patients assigned the hyperinflammatory subphenotype than in those with the hypoinflammatory phenotype (414 [57%] of 725 vs 694 [33%] of 2088; p<0·0001). There was a significant treatment interaction with PEEP strategy and ARDS subphenotype (p=0·041), with lower 90-day mortality in the high PEEP group of patients with the hyperinflammatory subphenotype (hyperinflammatory subphenotype: 169 [54%] of 313 patients in the high PEEP group vs 127 [62%] of 205 patients in the low PEEP group; hypoinflammatory subphenotype: 231 [34%] of 675 patients in the high PEEP group vs 233 [32%] of 734 patients in the low PEEP group). Interpretation: Classifier models using clinical variables alone can accurately assign ARDS subphenotypes in observational cohorts. Application of these models can provide valuable prognostic information and could inform management strategies for personalised treatment, including application of PEEP, once prospectively validated. Funding: US National Institutes of Health and European Society of Intensive Care Medicine.
UR - http://www.scopus.com/inward/record.url?scp=85124466107&partnerID=8YFLogxK
U2 - 10.1016/S2213-2600(21)00461-6
DO - 10.1016/S2213-2600(21)00461-6
M3 - Artículo en revista científica indexada
C2 - 35026177
AN - SCOPUS:85124466107
SN - 2213-2600
VL - 10
SP - 367
EP - 377
JO - The Lancet Respiratory Medicine
JF - The Lancet Respiratory Medicine
IS - 4
ER -