Manoj V Maddali1, Matthew Churpek2, Tai Pham3, Emanuele Rezoagli4, Hanjing Zhuo5, Wendi Zhao6, June He7, Kevin L Delucchi8, Chunxue Wang9, Nancy Wickersham9, J Brennan McNeil9, Alejandra Jauregui5, Serena Ke5, Kathryn Vessel5, Antonio Gomez10, Carolyn M Hendrickson10, Kirsten N Kangelaris6, Aartik Sarma11, Aleksandra Leligdowicz12, Kathleen D Liu13, Michael A Matthay14, Lorraine B Ware15, John G Laffey16, Giacomo Bellani17, Carolyn S Calfee18, Pratik Sinha19. 1. Division of Pulmonary, Allergy, and Critical Care Medicine, Department of Medicine, Stanford University, Stanford, CA, USA; Division of Hospital Medicine, University of California, San Francisco, San Francisco, CA, USA. 2. Division of Allergy, Pulmonary, and Critical Care, Department of Medicine, University of Wisconsin-Madison, Madison, WI, USA. 3. Service de Médecine Intensive-Réanimation, AP-HP, Hôpital de Bicêtre, DMU 4 CORREVE Maladies du Cœur et des Vaisseaux, FHU Sepsis, Groupe de Recherche Clinique CARMAS, Le Kremlin-Bicêtre, France; Université Paris-Saclay, UVSQ, Université Paris-Sud, Inserm U1018, Equipe d'Epidémiologie Respiratoire Intégrative, CESP, 94807, Villejuif, France. 4. Department of Medicine and Surgery, University of Milano-Bicocca, Monza, Italy. 5. Division of Pulmonary, Critical Care, Allergy and Sleep Medicine, University of California, San Francisco, San Francisco, CA, USA; Department of Medicine, Cardiovascular Research Institute, University of California, San Francisco, San Francisco, CA, USA. 6. Division of Hospital Medicine, University of California, San Francisco, San Francisco, CA, USA. 7. Division of Clinical and Translational Research, Washington University School of Medicine, St Louis, MO, USA. 8. Department of Psychiatry, University of California, San Francisco, San Francisco, CA, USA. 9. Division of Allergy, Pulmonary, and Critical Care Medicine, Department of Medicine, Vanderbilt University Medical Center, Nashville, TN, USA. 10. Division of Pulmonary, Critical Care, Allergy and Sleep Medicine, University of California, San Francisco, San Francisco, CA, USA; Division of Allergy, Pulmonary, and Critical Care Medicine, Department of Medicine, Zuckerberg San Francisco General Hospital and Trauma Center, San Francisco, CA, USA. 11. Division of Pulmonary, Critical Care, Allergy and Sleep Medicine, University of California, San Francisco, San Francisco, CA, USA. 12. Division of Pulmonary, Critical Care, Allergy and Sleep Medicine, University of California, San Francisco, San Francisco, CA, USA; Interdepartmental Division of Critical Care Medicine, University of Toronto, Toronto, ON, Canada. 13. Division of Nephrology, University of California, San Francisco, San Francisco, CA, USA; Department of Medicine, Cardiovascular Research Institute, University of California, San Francisco, San Francisco, CA, USA; Department of Psychiatry, University of California, San Francisco, San Francisco, CA, USA. 14. Division of Pulmonary, Critical Care, Allergy and Sleep Medicine, University of California, San Francisco, San Francisco, CA, USA; Department of Medicine, Cardiovascular Research Institute, University of California, San Francisco, San Francisco, CA, USA; Department of Anesthesia, University of California, San Francisco, San Francisco, CA, USA. 15. Division of Allergy, Pulmonary, and Critical Care Medicine, Department of Medicine, Vanderbilt University Medical Center, Nashville, TN, USA; Department of Pathology, Microbiology and Immunology, Vanderbilt University Medical Center, Nashville, TN, USA. 16. School of Medicine, Regenerative Medicine Institute at CÚRAM Centre for Research in Medical Devices, National University of Ireland Galway, Galway, Ireland; Anaesthesia and Intensive Care Medicine, Galway University Hospitals, Galway, Ireland. 17. Department of Medicine and Surgery, University of Milano-Bicocca, Monza, Italy; Department of Anesthesia and Intensive Care Medicine, ASST Monza-Ospedale San Gerardo, Monza, Italy. 18. Division of Pulmonary, Critical Care, Allergy and Sleep Medicine, University of California, San Francisco, San Francisco, CA, USA; Department of Anesthesia, University of California, San Francisco, San Francisco, CA, USA. 19. Division of Clinical and Translational Research, Washington University School of Medicine, St Louis, MO, USA; Department of Anesthesia, Division of Critical Care, Washington University, St Louis, MO, USA. Electronic address: p.sinha@wustl.edu.
Abstract
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.
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.
Authors: Katie R Famous; Kevin Delucchi; Lorraine B Ware; Kirsten N Kangelaris; Kathleen D Liu; B Taylor Thompson; Carolyn S Calfee Journal: Am J Respir Crit Care Med Date: 2017-02-01 Impact factor: 21.405
Authors: Carolyn S Calfee; Kevin L Delucchi; Pratik Sinha; Michael A Matthay; Jonathan Hackett; Manu Shankar-Hari; Cliona McDowell; John G Laffey; Cecilia M O'Kane; Daniel F McAuley Journal: Lancet Respir Med Date: 2018-08-02 Impact factor: 30.700
Authors: Roy G Brower; Paul N Lanken; Neil MacIntyre; Michael A Matthay; Alan Morris; Marek Ancukiewicz; David Schoenfeld; B Taylor Thompson Journal: N Engl J Med Date: 2004-07-22 Impact factor: 91.245
Authors: Carolyn S Calfee; Mark D Eisner; Lorraine B Ware; B Taylor Thompson; Polly E Parsons; Arthur P Wheeler; Anna Korpak; Michael A Matthay Journal: Crit Care Med Date: 2007-10 Impact factor: 7.598
Authors: Pratik Sinha; Kevin L Delucchi; Yue Chen; Hanjing Zhuo; Jason Abbott; Chunxue Wang; Nancy Wickersham; J Brennan McNeil; Alejandra Jauregui; Serena Ke; Kathryn Vessel; Antonio Gomez; Carolyn M Hendrickson; Kirsten N Kangelaris; Aartik Sarma; Aleksandra Leligdowicz; Kathleen D Liu; Michael A Matthay; Lorraine B Ware; Carolyn S Calfee Journal: Thorax Date: 2021-07-12 Impact factor: 9.139
Authors: Michael A Matthay; Yaseen M Arabi; Emily R Siegel; Lorraine B Ware; Lieuwe D J Bos; Pratik Sinha; Jeremy R Beitler; Katherine D Wick; Martha A Q Curley; Jean-Michel Constantin; Joseph E Levitt; Carolyn S Calfee Journal: Intensive Care Med Date: 2020-11-18 Impact factor: 17.440
Authors: Lorenzo Berra; Emanuele Rezoagli; Davide Signori; Aurora Magliocca; Kei Hayashida; Jan A Graw; Rajeev Malhotra; Giacomo Bellani Journal: Intensive Care Med Exp Date: 2022-06-27
Authors: Suvi T Vaara; Pavan K Bhatraju; Natalja L Stanski; Blaithin A McMahon; Kathleen Liu; Michael Joannidis; Sean M Bagshaw Journal: Crit Care Date: 2022-08-19 Impact factor: 19.334