Multi-modal Prediction of Extracorporeal Support-a Resource Intensive Therapy, Utilizing a Large National Database

Overview

Journal JAMIA Open

Date 2025 Jan 7

PMID 39764170

Authors

Daoyi Zhu

Bing Xue

Neel Shah

Philip Richard Orrin Payne

Chenyang Lu

Ahmed Sameh Said

Affiliations

Soon will be listed here.

Abstract

Objective: Extracorporeal membrane oxygenation (ECMO) is among the most resource-intensive therapies in critical care. The COVID-19 pandemic highlighted the lack of ECMO resource allocation tools. We aimed to develop a continuous ECMO risk prediction model to enhance patient triage and resource allocation.

Material And Methods: We leveraged multimodal data from the National COVID Cohort Collaborative (N3C) to develop a hierarchical deep learning model, labeled "PreEMPT-ECMO" (Prediction, Early Monitoring, and Proactive Triage for ECMO) which integrates static and multi-granularity time series features to generate continuous predictions of ECMO utilization. Model performance was assessed across time points ranging from 0 to 96 hours prior to ECMO initiation, using both accuracy and precision metrics.

Results: Between January 2020 and May 2023, 101 400 patients were included, with 1298 (1.28%) supported on ECMO. PreEMPT-ECMO outperformed established predictive models, including Logistic Regression, Support Vector Machine, Random Forest, and Extreme Gradient Boosting Tree, in both accuracy and precision at all time points. Model interpretation analysis also highlighted variations in feature contributions through each patient's clinical course.

Discussion And Conclusions: We developed a hierarchical model for continuous ECMO use prediction, utilizing a large multicenter dataset incorporating both static and time series variables of various granularities. This novel approach reflects the nuanced decision-making process inherent in ECMO initiation and has the potential to be used as an early alert tool to guide patient triage and ECMO resource allocation. Future directions include prospective validation and generalizability on non-COVID-19 refractory respiratory failure, aiming to improve patient outcomes.

References

Anai M, Akaike K, Iwagoe H, Akasaka T, Higuchi T, Miyazaki A . Decrease in hemoglobin level predicts increased risk for severe respiratory failure in COVID-19 patients with pneumonia. Respir Investig. 2020; 59(2):187-193. PMC: 7682330. DOI: 10.1016/j.resinv.2020.10.009. View

Bennett T, Moffitt R, Hajagos J, Amor B, Anand A, Bissell M . Clinical Characterization and Prediction of Clinical Severity of SARS-CoV-2 Infection Among US Adults Using Data From the US National COVID Cohort Collaborative. JAMA Netw Open. 2021; 4(7):e2116901. PMC: 8278272. DOI: 10.1001/jamanetworkopen.2021.16901. View

Zhang Y, Ji B, Zhou Z . ECMO support for COVID-19: a balancing act. Lancet. 2021; 397(10269):94-95. PMC: 7834053. DOI: 10.1016/S0140-6736(20)32515-0. View

Savarimuthu S, BinSaeid J, Harky A . The role of ECMO in COVID-19: Can it provide rescue therapy in those who are critically ill?. J Card Surg. 2020; 35(6):1298-1301. PMC: 7280692. DOI: 10.1111/jocs.14635. View

. Does extracorporeal membrane oxygenation improve survival in neonates with congenital diaphragmatic hernia? The Congenital Diaphragmatic Hernia Study Group. J Pediatr Surg. 1999; 34(5):720-4; discussion 724-5. DOI: 10.1016/s0022-3468(99)90363-9. View

Collins G, Moons K, Dhiman P, Riley R, Beam A, Van Calster B . TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods. BMJ. 2024; 385:e078378. PMC: 11019967. DOI: 10.1136/bmj-2023-078378. View

Combes A, Brodie D, Bartlett R, Brochard L, Brower R, Conrad S . Position paper for the organization of extracorporeal membrane oxygenation programs for acute respiratory failure in adult patients. Am J Respir Crit Care Med. 2014; 190(5):488-96. DOI: 10.1164/rccm.201404-0630CP. View

Ramanathan K, Antognini D, Combes A, Paden M, Zakhary B, Ogino M . Planning and provision of ECMO services for severe ARDS during the COVID-19 pandemic and other outbreaks of emerging infectious diseases. Lancet Respir Med. 2020; 8(5):518-526. PMC: 7102637. DOI: 10.1016/S2213-2600(20)30121-1. View

Haiduc A, Alom S, Melamed N, Harky A . Role of extracorporeal membrane oxygenation in COVID-19: A systematic review. J Card Surg. 2020; 35(10):2679-2687. DOI: 10.1111/jocs.14879. View

10.

Gao L, Li X, Song J, Shen H . Hierarchical LSTMs with Adaptive Attention for Visual Captioning. IEEE Trans Pattern Anal Mach Intell. 2019; 42(5):1112-1131. DOI: 10.1109/TPAMI.2019.2894139. View

11.

Fernando S, Qureshi D, Tanuseputro P, Fan E, Munshi L, Rochwerg B . Mortality and costs following extracorporeal membrane oxygenation in critically ill adults: a population-based cohort study. Intensive Care Med. 2019; 45(11):1580-1589. DOI: 10.1007/s00134-019-05766-z. View

12.

Shekar K, Badulak J, Peek G, Boeken U, Dalton H, Arora L . Extracorporeal Life Support Organization Coronavirus Disease 2019 Interim Guidelines: A Consensus Document from an International Group of Interdisciplinary Extracorporeal Membrane Oxygenation Providers. ASAIO J. 2020; 66(7):707-721. PMC: 7228451. DOI: 10.1097/MAT.0000000000001193. View

13.

Schlapbach L, Chiletti R, Straney L, Festa M, Alexander D, Butt W . Defining benefit threshold for extracorporeal membrane oxygenation in children with sepsis-a binational multicenter cohort study. Crit Care. 2020; 23(1):429. PMC: 6937937. DOI: 10.1186/s13054-019-2685-1. View

14.

Hayden S, Albert T, Watkins T, Swenson E . Anemia in critical illness: insights into etiology, consequences, and management. Am J Respir Crit Care Med. 2012; 185(10):1049-57. PMC: 5448578. DOI: 10.1164/rccm.201110-1915CI. View

15.

Loughlin P, Sebat F, Kellett J . Respiratory Rate: The Forgotten Vital Sign-Make It Count!. Jt Comm J Qual Patient Saf. 2018; 44(8):494-499. DOI: 10.1016/j.jcjq.2018.04.014. View

16.

Stephens A, Seman M, Diehl A, Pilcher D, Barbaro R, Brodie D . ECMO PAL: using deep neural networks for survival prediction in venoarterial extracorporeal membrane oxygenation. Intensive Care Med. 2023; 49(9):1090-1099. PMC: 10499722. DOI: 10.1007/s00134-023-07157-x. View

17.

Liu L, Ortiz-Soriano V, Neyra J, Chen J . KIT-LSTM: Knowledge-guided Time-aware LSTM for Continuous Clinical Risk Prediction. Proceedings (IEEE Int Conf Bioinformatics Biomed). 2023; 2022:1086-1091. PMC: 10151119. DOI: 10.1109/bibm55620.2022.9994931. View

18.

Axiaq A, Haiduc A, Alom S, Melamed N, Harky A . Extracorporeal membrane oxygenation in COVID-19: Supplementary considerations. J Card Surg. 2020; 35(12):3673-3674. DOI: 10.1111/jocs.15026. View

19.

Landi I, Glicksberg B, Lee H, Cherng S, Landi G, Danieletto M . Deep representation learning of electronic health records to unlock patient stratification at scale. NPJ Digit Med. 2020; 3:96. PMC: 7367859. DOI: 10.1038/s41746-020-0301-z. View

20.

Supady A, Badulak J, Evans L, Curtis J, Brodie D . Should we ration extracorporeal membrane oxygenation during the COVID-19 pandemic?. Lancet Respir Med. 2021; 9(4):326-328. PMC: 8009624. DOI: 10.1016/S2213-2600(21)00131-4. View