EUVIMEDSkopri EUVIMED
Open access

A Deep Learning Framework for Predicting Patient Decannulation on Extracorporeal Membrane Oxygenation Devices: Development and Model Analysis Study

Joshua Fuller iD, Alexey Abramov iD, Dana Mullin iD, James Beck iD, Philippe Lemaitre iD, Elham Azizi iD

JMIR Biomedical Engineering · 2024-02-02 · 9 · e48497

DOI: 10.2196/48497 ↗

At a glance

Journal article in JMIR Biomedical Engineering, published online on 2024-02-02. Written by Joshua Fuller and 5 co-authors. Institution: Vagelos College of Physicians and Surgeons, Columbia University, New York City, NY, United States. Cited 15 times so far (Crossref); 25 references. The full text is freely available in PubMed Central.

AstrattSubjectsDettalji biblijografiċiCiteRelated studies

Abstract (original language)

Background

Venovenous extracorporeal membrane oxygenation (VV-ECMO) is a therapy for patients with refractory respiratory failure. The decision to decannulate someone from extracorporeal membrane oxygenation (ECMO) often involves weaning trials and clinical intuition. To date, there are limited prognostication metrics to guide clinical decision–making to determine which patients will be successfully weaned and decannulated.

Objective

This study aims to assist clinicians with the decision to decannulate a patient from ECMO, using Continuous Evaluation of VV-ECMO Outcomes (CEVVO), a deep learning–based model for predicting success of decannulation in patients supported on VV-ECMO. The running metric may be applied daily to categorize patients into high-risk and low-risk groups. Using these data, providers may consider initiating a weaning trial based on their expertise and CEVVO.

Methods

Data were collected from 118 patients supported with VV-ECMO at the Columbia University Irving Medical Center. Using a long short-term memory–based network, CEVVO is the first model capable of integrating discrete clinical information with continuous data collected from an ECMO device. A total of 12 sets of 5-fold cross validations were conducted to assess the performance, which was measured using the area under the receiver operating characteristic curve (AUROC) and average precision (AP). To translate the predicted values into a clinically useful metric, the model results were calibrated and stratified into risk groups, ranging from 0 (high risk) to 3 (low risk). To further investigate the performance edge of CEVVO, 2 synthetic data sets were generated using Gaussian process regression. The first data set preserved the long-term dependency of the patient data set, whereas the second did not.

Results

CEVVO demonstrated consistently superior classification performance compared with contemporary models (P

Subjects

Author keywords

AIECMOVVartificial intelligenceclinical AIclinical decision supportdynamic dataextracorporeal membrane oxygenationhealth informaticsmachine learningsupervised learningtime seriesvenovenous

Authors and institutions

  • Vagelos College of Physicians and Surgeons, Columbia University, New York City, NY, United States.
  • Department of Surgery, Columbia University Irving Medical Center, New York, NY, United States.
  • Clinical Perfusion, New York Presbyterian Hospital, New York, NY, United States.
  • Department of Biomedical Engineering, Columbia University, New York City, NY, United States.
  • Irving Institute for Cancer Dynamics, Columbia University, New York, NY, United States.
  • Department of Computer Science, Columbia University, New York, NY, United States.

ORCID profiles: Joshua Fuller, Alexey Abramov, Dana Mullin, James Beck, Philippe Lemaitre, Elham Azizi

Cite

APA

Fuller, J., Abramov, A., Mullin, D., Beck, J., Lemaitre, P., & Azizi, E. (2024). A Deep Learning Framework for Predicting Patient Decannulation on Extracorporeal Membrane Oxygenation Devices: Development and Model Analysis Study. JMIR Biomedical Engineering, 9, e48497. https://doi.org/10.2196/48497

Vancouver

Fuller J, Abramov A, Mullin D, Beck J, Lemaitre P, Azizi E. A Deep Learning Framework for Predicting Patient Decannulation on Extracorporeal Membrane Oxygenation Devices: Development and Model Analysis Study. JMIR Biomedical Engineering. 2024;9:e48497. doi:10.2196/48497

BibTeX
@article{Fuller2024,
  author = {Fuller, Joshua and Abramov, Alexey and Mullin, Dana and Beck, James and Lemaitre, Philippe and Azizi, Elham},
  title = {A Deep Learning Framework for Predicting Patient Decannulation on Extracorporeal Membrane Oxygenation Devices: Development and Model Analysis Study},
  journal = {JMIR Biomedical Engineering},
  year = {2024},
  volume = {9},
  pages = {e48497},
  doi = {10.2196/48497}
}
Start for free →