Subphenotyping Prone Position Responders with Machine Learning

Overview

Journal Crit Care

Specialty Critical Care

Date 2025 Mar 15

PMID 40087660

Authors

Maxime Fosset

Dario von Wedel

Simone Redaelli

Daniel Talmor

Nicolas Molinari

Julie Josse

Elias N Baedorf-Kassis

Maximilian S Schaefer

Boris Jung

Affiliations

Soon will be listed here.

Abstract

Background: Acute respiratory distress syndrome (ARDS) is a heterogeneous condition with varying response to prone positioning. We aimed to identify subphenotypes of ARDS patients undergoing prone positioning using machine learning and assess their association with mortality and response to prone positioning.

Methods: In this retrospective observational study, we enrolled 353 mechanically ventilated ARDS patients who underwent at least one prone positioning cycle. Unsupervised machine learning was used to identify subphenotypes based on respiratory mechanics, oxygenation parameters, and demographic variables collected in supine position. The primary outcome was 28-day mortality. Secondary outcomes included response to prone positioning in terms of respiratory system compliance, driving pressure, PaO/FiO ratio, ventilatory ratio, and mechanical power.

Results: Three distinct subphenotypes were identified. Cluster 1 (22.9% of whole cohort) had a higher PaO/FiO ratio and lower Positive End-Expiratory Pressure (PEEP). Cluster 2 (51.3%) had a higher proportion of COVID-19 patients, lower driving pressure, higher PEEP, and higher respiratory system compliance. Cluster 3 (25.8%) had a lower pH, higher PaCO, and higher ventilatory ratio. Mortality differed significantly across clusters (p = 0.03), with Cluster 3 having the highest mortality (56%). There were no significant differences in the proportions of responders to prone positioning for any of the studied parameters. Transpulmonary pressure measurements in a subcohort did not improve subphenotype characterization.

Conclusions: Distinct ARDS subphenotypes with varying mortality were identified in patients undergoing prone positioning; however, predicting which patients benefited from this intervention based on available data was not possible. These findings underscore the need for continued efforts in phenotyping ARDS through multimodal data to better understand the heterogeneity of this population.

References

Bellani G, Laffey J, Pham T, Fan E, Brochard L, Esteban A . Epidemiology, Patterns of Care, and Mortality for Patients With Acute Respiratory Distress Syndrome in Intensive Care Units in 50 Countries. JAMA. 2016; 315(8):788-800. DOI: 10.1001/jama.2016.0291. View

Matthay M, Arabi Y, Arroliga A, Bernard G, Bersten A, Brochard L . A New Global Definition of Acute Respiratory Distress Syndrome. Am J Respir Crit Care Med. 2023; 209(1):37-47. PMC: 10870872. DOI: 10.1164/rccm.202303-0558WS. View

Thompson B, Chambers R, Liu K . Acute Respiratory Distress Syndrome. N Engl J Med. 2017; 377(6):562-572. DOI: 10.1056/NEJMra1608077. View

Grasselli G, Calfee C, Camporota L, Poole D, Amato M, Antonelli M . ESICM guidelines on acute respiratory distress syndrome: definition, phenotyping and respiratory support strategies. Intensive Care Med. 2023; 49(7):727-759. PMC: 10354163. DOI: 10.1007/s00134-023-07050-7. View

Reddy K, Calfee C, McAuley D . Acute Respiratory Distress Syndrome Subphenotypes beyond the Syndrome: A Step toward Treatable Traits?. Am J Respir Crit Care Med. 2021; 203(12):1449-1451. PMC: 8483225. DOI: 10.1164/rccm.202101-0218ED. View

Calfee C, Delucchi K, Parsons P, Thompson B, Ware L, Matthay M . Subphenotypes in acute respiratory distress syndrome: latent class analysis of data from two randomised controlled trials. Lancet Respir Med. 2014; 2(8):611-20. PMC: 4154544. DOI: 10.1016/S2213-2600(14)70097-9. View

Maddali M, Churpek M, Pham T, Rezoagli E, Zhuo H, Zhao W . Validation and utility of ARDS subphenotypes identified by machine-learning models using clinical data: an observational, multicohort, retrospective analysis. Lancet Respir Med. 2022; 10(4):367-377. PMC: 8976729. DOI: 10.1016/S2213-2600(21)00461-6. View

Famous K, Delucchi K, Ware L, Kangelaris K, Liu K, Thompson B . Acute Respiratory Distress Syndrome Subphenotypes Respond Differently to Randomized Fluid Management Strategy. Am J Respir Crit Care Med. 2016; 195(3):331-338. PMC: 5328179. DOI: 10.1164/rccm.201603-0645OC. View

Redaelli S, von Wedel D, Fosset M, Suleiman A, Chen G, Alingrin J . Inflammatory subphenotypes in patients at risk of ARDS: evidence from the LIPS-A trial. Intensive Care Med. 2023; 49(12):1499-1507. DOI: 10.1007/s00134-023-07244-z. View

10.

Guerin C, Reignier J, Richard J, Beuret P, Gacouin A, Boulain T . Prone positioning in severe acute respiratory distress syndrome. N Engl J Med. 2013; 368(23):2159-68. DOI: 10.1056/NEJMoa1214103. View

11.

Sud S, Fan E, Adhikari N, Friedrich J, Ferguson N, Combes A . Comparison of venovenous extracorporeal membrane oxygenation, prone position and supine mechanical ventilation for severely hypoxemic acute respiratory distress syndrome: a network meta-analysis. Intensive Care Med. 2024; 50(7):1021-1034. DOI: 10.1007/s00134-024-07492-7. View

12.

Matthay M, Arabi Y, Siegel E, Ware L, Bos L, Sinha P . Phenotypes and personalized medicine in the acute respiratory distress syndrome. Intensive Care Med. 2020; 46(12):2136-2152. PMC: 7673253. DOI: 10.1007/s00134-020-06296-9. View

13.

Guerin C, Albert R, Beitler J, Gattinoni L, Jaber S, Marini J . Prone position in ARDS patients: why, when, how and for whom. Intensive Care Med. 2020; 46(12):2385-2396. PMC: 7652705. DOI: 10.1007/s00134-020-06306-w. View

14.

Constantin J, Jabaudon M, Lefrant J, Jaber S, Quenot J, Langeron O . Personalised mechanical ventilation tailored to lung morphology versus low positive end-expiratory pressure for patients with acute respiratory distress syndrome in France (the LIVE study): a multicentre, single-blind, randomised controlled trial. Lancet Respir Med. 2019; 7(10):870-880. DOI: 10.1016/S2213-2600(19)30138-9. View

15.

Papazian L, Munshi L, Guerin C . Prone position in mechanically ventilated patients. Intensive Care Med. 2022; 48(8):1062-1065. PMC: 9160174. DOI: 10.1007/s00134-022-06731-z. View

16.

Haddam M, Zieleskiewicz L, Perbet S, Baldovini A, Guervilly C, Arbelot C . Lung ultrasonography for assessment of oxygenation response to prone position ventilation in ARDS. Intensive Care Med. 2016; 42(10):1546-1556. DOI: 10.1007/s00134-016-4411-7. View

17.

Dam T, Roggeveen L, van Diggelen F, Fleuren L, Jagesar A, Otten M . Predicting responders to prone positioning in mechanically ventilated patients with COVID-19 using machine learning. Ann Intensive Care. 2022; 12(1):99. PMC: 9583049. DOI: 10.1186/s13613-022-01070-0. View

18.

Hannon D, Syed J, McNicholas B, Madden M, Laffey J . The development of a C5.0 machine learning model in a limited data set to predict early mortality in patients with ARDS undergoing an initial session of prone positioning. Intensive Care Med Exp. 2024; 12(1):103. PMC: 11564488. DOI: 10.1186/s40635-024-00682-z. View

19.

Sarge T, Baedorf-Kassis E, Banner-Goodspeed V, Novack V, Loring S, Gong M . Effect of Esophageal Pressure-guided Positive End-Expiratory Pressure on Survival from Acute Respiratory Distress Syndrome: A Risk-based and Mechanistic Reanalysis of the EPVent-2 Trial. Am J Respir Crit Care Med. 2021; 204(10):1153-1163. PMC: 8759303. DOI: 10.1164/rccm.202009-3539OC. View

20.

Goligher E, Telias I, Sahetya S, Baedorf-Kassis E, Patel B, Yehya N . Physiology Is Vital to Precision Medicine in Acute Respiratory Distress Syndrome and Sepsis. Am J Respir Crit Care Med. 2022; 206(1):14-16. PMC: 9954327. DOI: 10.1164/rccm.202202-0230ED. View