Supervised Machine Learning Model to Predict Mortality in Patients Undergoing Venovenous Extracorporeal Membrane Oxygenation from a Nationwide Multicentre Registry

Overview

Journal BMJ Open Respir Res

Date 2023 Dec 28

PMID 38154913

Authors

Haeun Lee

Myung Jin Song

Young-Jae Cho

Dong Jung Kim

Sang-Bum Hong

Se Young Jung

Sung Yoon Lim

Affiliations

Soon will be listed here.

Abstract

Background: Existing models have performed poorly when predicting mortality for patients undergoing venovenous extracorporeal membrane oxygenation (VV-ECMO). This study aimed to develop and validate a machine learning (ML)-based prediction model to predict 90-day mortality in patients undergoing VV-ECMO.

Methods: This study included 368 patients with acute respiratory failure undergoing VV-ECMO from 16 tertiary hospitals across South Korea between 2012 and 2015. The primary outcome was the 90-day mortality after ECMO initiation. The inputs included all available features (n=51) and those from the electronic health record (EHR) systems without preprocessing (n=40). The discriminatory strengths of ML models were evaluated in both internal and external validation sets. The models were compared with conventional models, such as respiratory ECMO survival prediction (RESP) and predicting death for severe acute respiratory distress syndrome on VV-ECMO (PRESERVE).

Results: Extreme gradient boosting (XGB) (areas under the receiver operating characteristic curve, AUROC 0.82, 95% CI (0.73 to 0.89)) and light gradient boosting (AUROC 0.81 (95% CI 0.71 to 0.88)) models achieved the highest performance using EHR's and all other available features. The developed models had higher AUROCs (95% CI 0.76 to 0.82) than those of RESP (AUROC 0.66 (95% CI 0.56 to 0.76)) and PRESERVE (AUROC 0.71 (95% CI 0.61 to 0.81)). Additionally, we achieved an AUROC (0.75) for 90-day mortality in external validation in the case of the XGB model, which was higher than that of RESP (0.70) and PRESERVE (0.67) in the same validation dataset.

Conclusions: ML prediction models outperformed previous mortality risk models. This model may be used to identify patients who are unlikely to benefit from VV-ECMO therapy during patient selection.

References

Schmidt M, Zogheib E, Roze H, Repesse X, Lebreton G, Luyt C . The PRESERVE mortality risk score and analysis of long-term outcomes after extracorporeal membrane oxygenation for severe acute respiratory distress syndrome. Intensive Care Med. 2013; 39(10):1704-13. PMC: 7094902. DOI: 10.1007/s00134-013-3037-2. View

Enger T, Philipp A, Videm V, Lubnow M, Wahba A, Fischer M . Prediction of mortality in adult patients with severe acute lung failure receiving veno-venous extracorporeal membrane oxygenation: a prospective observational study. Crit Care. 2014; 18(2):R67. PMC: 4057201. DOI: 10.1186/cc13824. View

Harnisch L, Moerer O . Contraindications to the Initiation of Veno-Venous ECMO for Severe Acute Respiratory Failure in Adults: A Systematic Review and Practical Approach Based on the Current Literature. Membranes (Basel). 2021; 11(8). PMC: 8400963. DOI: 10.3390/membranes11080584. View

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

Combes A, Hajage D, Capellier G, Demoule A, Lavoue S, Guervilly C . Extracorporeal Membrane Oxygenation for Severe Acute Respiratory Distress Syndrome. N Engl J Med. 2018; 378(21):1965-1975. DOI: 10.1056/NEJMoa1800385. View

Tabatabai A, Ghneim M, Kaczorowski D, Shah A, Dave S, Haase D . Mortality Risk Assessment in COVID-19 Venovenous Extracorporeal Membrane Oxygenation. Ann Thorac Surg. 2021; 112(6):1983-1989. PMC: 7825896. DOI: 10.1016/j.athoracsur.2020.12.050. View

Li X, Hu M, Zheng R, Wang Y, Kang H, Jiang L . Delayed Initiation of ECMO Is Associated With Poor Outcomes in Patients With Severe COVID-19: A Multicenter Retrospective Cohort Study. Front Med (Lausanne). 2021; 8:716086. PMC: 8481658. DOI: 10.3389/fmed.2021.716086. View

Yoon J, Pinsky M, Clermont G . Artificial Intelligence in Critical Care Medicine. Crit Care. 2022; 26(1):75. PMC: 8951650. DOI: 10.1186/s13054-022-03915-3. View

Shaefi S, Brenner S, Gupta S, OGara B, Krajewski M, Charytan D . Extracorporeal membrane oxygenation in patients with severe respiratory failure from COVID-19. Intensive Care Med. 2021; 47(2):208-221. PMC: 7851810. DOI: 10.1007/s00134-020-06331-9. View

10.

Tonna J, Abrams D, Brodie D, Greenwood J, Rubio Mateo-Sidron J, Usman A . Management of Adult Patients Supported with Venovenous Extracorporeal Membrane Oxygenation (VV ECMO): Guideline from the Extracorporeal Life Support Organization (ELSO). ASAIO J. 2021; 67(6):601-610. PMC: 8315725. DOI: 10.1097/MAT.0000000000001432. View

11.

Baek M, Chung C, Kim H, Cho W, Cho Y, Park S . Age is major factor for predicting survival in patients with acute respiratory failure on extracorporeal membrane oxygenation: a Korean multicenter study. J Thorac Dis. 2018; 10(3):1406-1417. PMC: 5906318. DOI: 10.21037/jtd.2018.03.71. View

12.

Badulak J, Antonini M, Stead C, Shekerdemian L, Raman L, Paden M . Extracorporeal Membrane Oxygenation for COVID-19: Updated 2021 Guidelines from the Extracorporeal Life Support Organization. ASAIO J. 2021; 67(5):485-495. PMC: 8078022. DOI: 10.1097/MAT.0000000000001422. View

13.

Nielsen A, Thorsen-Meyer H, Belling K, Nielsen A, Thomas C, Chmura P . Survival prediction in intensive-care units based on aggregation of long-term disease history and acute physiology: a retrospective study of the Danish National Patient Registry and electronic patient records. Lancet Digit Health. 2020; 1(2):e78-e89. DOI: 10.1016/S2589-7500(19)30024-X. View

14.

Thompson B, Chambers R, Liu K . Acute Respiratory Distress Syndrome. N Engl J Med. 2017; 377(19):1904-1905. DOI: 10.1056/NEJMc1711824. View

15.

Kang M, Kim J, Kim D, Oh K, Joo K, Kim Y . Machine learning algorithm to predict mortality in patients undergoing continuous renal replacement therapy. Crit Care. 2020; 24(1):42. PMC: 7006166. DOI: 10.1186/s13054-020-2752-7. View

16.

MacLaren G . When to initiate ECMO with low likelihood of success. Crit Care. 2018; 22(1):217. PMC: 6145325. DOI: 10.1186/s13054-018-2162-2. View

17.

Schmidt M, Bailey M, Sheldrake J, Hodgson C, Aubron C, Rycus P . Predicting survival after extracorporeal membrane oxygenation for severe acute respiratory failure. The Respiratory Extracorporeal Membrane Oxygenation Survival Prediction (RESP) score. Am J Respir Crit Care Med. 2014; 189(11):1374-82. DOI: 10.1164/rccm.201311-2023OC. View

18.

Baek M, Lee S, Chung C, Cho W, Cho Y, Park S . Improvement in the survival rates of extracorporeal membrane oxygenation-supported respiratory failure patients: a multicenter retrospective study in Korean patients. Crit Care. 2019; 23(1):1. PMC: 6318967. DOI: 10.1186/s13054-018-2293-5. View

19.

Harris C, Millman K, van der Walt S, Gommers R, Virtanen P, Cournapeau D . Array programming with NumPy. Nature. 2020; 585(7825):357-362. PMC: 7759461. DOI: 10.1038/s41586-020-2649-2. View

20.

Hilder M, Herbstreit F, Adamzik M, Beiderlinden M, Burschen M, Peters J . Comparison of mortality prediction models in acute respiratory distress syndrome undergoing extracorporeal membrane oxygenation and development of a novel prediction score: the PREdiction of Survival on ECMO Therapy-Score (PRESET-Score). Crit Care. 2017; 21(1):301. PMC: 5728043. DOI: 10.1186/s13054-017-1888-6. View