Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Jun 8:20:64-88.
doi: 10.1016/j.xjon.2024.06.001. eCollection 2024 Aug.

Acute brain injury risk prediction models in venoarterial extracorporeal membrane oxygenation patients with tree-based machine learning: An Extracorporeal Life Support Organization Registry analysis

Andrew Kalra  1   2 , Preetham Bachina  1 , Benjamin L Shou  1 , Jaeho Hwang  3 , Meylakh Barshay  4 , Shreyas Kulkarni  4 , Isaac Sears  4 , Carsten Eickhoff  5   6   7 , Christian A Bermudez  8 , Daniel Brodie  9 , Corey E Ventetuolo  10 , Bo Soo Kim  9 , Glenn J R Whitman  1 , Adeel Abbasi  10 , Sung-Min Cho  1   11 ; Collaborators
Collaborators, Affiliations

Acute brain injury risk prediction models in venoarterial extracorporeal membrane oxygenation patients with tree-based machine learning: An Extracorporeal Life Support Organization Registry analysis

Andrew Kalra et al. JTCVS Open. .

Abstract

Objective: We aimed to determine if machine learning can predict acute brain injury and to identify modifiable risk factors for acute brain injury in patients receiving venoarterial extracorporeal membrane oxygenation.

Methods: We included adults (age ≥18 years) receiving venoarterial extracorporeal membrane oxygenation or extracorporeal cardiopulmonary resuscitation in the Extracorporeal Life Support Organization Registry (2009-2021). Our primary outcome was acute brain injury: central nervous system ischemia, intracranial hemorrhage, brain death, and seizures. We used Random Forest, CatBoost, LightGBM, and XGBoost machine learning algorithms (10-fold leave-1-out cross-validation) to predict and identify features most important for acute brain injury. We extracted 65 total features: demographics, pre-extracorporeal membrane oxygenation/on-extracorporeal membrane oxygenation laboratory values, and pre-extracorporeal membrane oxygenation/on-extracorporeal membrane oxygenation settings.

Results: Of 35,855 patients receiving venoarterial extracorporeal membrane oxygenation (nonextracorporeal cardiopulmonary resuscitation) (median age of 57.8 years, 66% were male), 7.7% (n = 2769) experienced acute brain injury. In venoarterial extracorporeal membrane oxygenation (nonextracorporeal cardiopulmonary resuscitation), the area under the receiver operator characteristic curves to predict acute brain injury, central nervous system ischemia, and intracranial hemorrhage were 0.67, 0.67, and 0.62, respectively. The true-positive, true-negative, false-positive, false-negative, positive, and negative predictive values were 33%, 88%, 12%, 67%, 18%, and 94%, respectively, for acute brain injury. Longer extracorporeal membrane oxygenation duration, higher 24-hour extracorporeal membrane oxygenation pump flow, and higher on-extracorporeal membrane oxygenation partial pressure of oxygen were associated with acute brain injury. Of 10,775 patients receiving extracorporeal cardiopulmonary resuscitation (median age of 57.1 years, 68% were male), 16.5% (n = 1787) experienced acute brain injury. The area under the receiver operator characteristic curves for acute brain injury, central nervous system ischemia, and intracranial hemorrhage were 0.72, 0.73, and 0.69, respectively. Longer extracorporeal membrane oxygenation duration, older age, and higher 24-hour extracorporeal membrane oxygenation pump flow were associated with acute brain injury.

Conclusions: In the largest study predicting neurological complications with machine learning in extracorporeal membrane oxygenation, longer extracorporeal membrane oxygenation duration and higher 24-hour pump flow were associated with acute brain injury in nonextracorporeal cardiopulmonary resuscitation and extracorporeal cardiopulmonary resuscitation venoarterial extracorporeal membrane oxygenation.

Keywords: Extracorporeal Life Support Organization; acute brain injury; extracorporeal membrane oxygenation; machine learning; neurological complications.

PubMed Disclaimer

Conflict of interest statement

D.B. receives research support from and consults for LivaNova; has been on the medical advisory boards for Xenios, Medtronic, Inspira, and Cellenkos; is the President-elect of the ELSO and the Chair of the Executive Committee of the International ECMO Network (ECMONet); and writes for UpToDate. C.E.V. has been a consultant or served on advisory boards for Merck, Janssen, and Regeneron, outside of the submitted work. S.M.C. is supported by the National Heart, Lung, and Blood Institute (1K23HL157610) and Hyperfine (SAFE MRI ECMO study). All other authors reported no conflicts of interest. The Journal policy requires editors and reviewers to disclose conflicts of interest and to decline handling or reviewing manuscripts for which they may have a conflict of interest. The editors and reviewers of this article have no conflicts of interest.

Figures

None
Graphical abstract
None
Most important factors for predicting ABI in 35,855 patients on VA-ECMO.
Figure 1
Figure 1
All 65 variables incorporated into our ML models including laboratory values, ECMO settings, demographics, other variables, and primary outcome (ABI). BP, Blood pressure; PaCO2, partial pressure of carbon dioxide; PaO2, partial pressure of oxygen; PCWP, pulmonary capillary wedge pressure; DPAP, diastolic pulmonary arterial pressure; SpO2, peripheral oxygen saturation; SvO2, mixed venous oxygen saturation; MPAP, mean pulmonary arterial pressure; SaO2, arterial blood gas oxygen saturation; SPAP, systolic pulmonary arterial pressure; HCO3, bicarbonate; ECMO, extracorporeal membrane oxygenation; FiO2, fraction of inspired oxygen; PEEP, positive-end expiratory pressure; PIP, peak inspiratory pressure; EEG, electroencephalogram.
Figure 2
Figure 2
Flowchart of study cohort (VA-ECMO and ECPR patients) from the ELSO Registry in 2009-2020. ELSO, Extracorporeal Life Support Organization; ECMO, extracorporeal membrane oxygenation; VV, venovenous; Conversion, VA→VV or VV→VA; VVA, venovenoarterial; Other, mode not defined; VP, venopulmonary; VA, venoarterial; ECPR, extracorporeal cardiopulmonary resuscitation.
Figure 3
Figure 3
Receiver-operating characteristic curves for predicting (A) ABI, (B) CNS ischemia, and (C) ICH in patients receiving VA-ECMO. ECPR, Extracorporeal cardiopulmonary resuscitation.
Figure 4
Figure 4
Feature importance in increasing importance (ascending) for each neurological outcome: (A) ABI, (B) CNS ischemia, and (C) ICH in patients receiving VA-ECMO. VA-ECMO, Venoarterial extracorporeal membrane oxygenation.
Figure 5
Figure 5
Summary of key study findings. ML identified longer ECMO duration (in days) and higher 24-hour ECMO pump flow rates as the most important risk factors for ABI in patients receiving VA-ECMO. Better standardized neurological monitoring is required to detect the true prevalence across ELSO centers. VA-ECMO, Venoarterial extracorporeal membrane oxygenation; ECPR, extracorporeal cardiopulmonary resuscitation.
Figure E1
Figure E1
SHAP value plots for (A) ABI, (B) CNS ischemia, and (C) ICH in patients receiving VA-ECMO. VA-ECMO, Venoarterial extracorporeal membrane oxygenation; ECMO, extracorporeal membrane oxygenation; PaO2, partial pressure of oxygen; HCO3, bicarbonate; BP, blood pressure; SaO2, arterial blood gas oxygen saturation; PIP, peak inspiratory pressure; SvO2, mixed venous oxygen saturation; DBP, diastolic blood pressure.
Figure E2
Figure E2
ROC curves for predicting (A) ABI, (B) CNS ischemia, and (C) ICH in patients receiving ECPR. ECPR, Extracorporeal cardiopulmonary resuscitation.
Figure E3
Figure E3
Feature importance scores for (A) ABI, (B) CNS ischemia, and (C) ICH in patients receiving ECPR. ECPR, Extracorporeal cardiopulmonary resuscitation; ECMO, extracorporeal membrane oxygenation; PaO2, partial pressure of oxygen; HCO3, bicarbonate; BP, blood pressure; SaO2, arterial blood gas oxygen saturation; PIP, peak inspiratory pressure; SvO2, mixed venous oxygen saturation; DBP, diastolic blood pressure.
Figure E4
Figure E4
SHAP value plots for (A) ABI, (B) CNS ischemia, and (C) ICH in patients receiving ECPR. ECPR, Extracorporeal cardiopulmonary resuscitation; ECMO, extracorporeal membrane oxygenation; PaO2, partial pressure of oxygen; HCO3, bicarbonate; BP, blood pressure; SaO2, arterial blood gas oxygen saturation; PIP, peak inspiratory pressure; SvO2, mixed venous oxygen saturation; DBP, diastolic blood pressure.
See this image and copyright information in PMC

Update of

References

    1. Thiagarajan R.R., Barbaro R.P., Rycus P.T., et al. Extracorporeal life support organization registry international report 2016. ASAIO J. 2017;63(1):60–67. - PubMed
    1. Cho S.M., Canner J., Chiarini G., et al. Modifiable risk factors and mortality from ischemic and hemorrhagic strokes in patients receiving venoarterial extracorporeal membrane oxygenation: results from the extracorporeal life support organization registry. Crit Care Med. 2020;48(10):e897–e905. - PMC - PubMed
    1. Ong C.S., Etchill E., Dong J., et al. Neuromonitoring detects brain injury in patients receiving extracorporeal membrane oxygenation support. J Thorac Cardiovasc Surg. 2023;165:2104–2110.e1. - PubMed
    1. Shou B.L., Ong C.S., Premraj L., et al. Arterial oxygen and carbon dioxide tension and acute brain injury in extracorporeal cardiopulmonary resuscitation patients: analysis of the extracorporeal life support organization registry. J Heart Lung Transplant. 2023;42(4):503–511. - PMC - PubMed
    1. Shou B.L., Wilcox C., Florissi I., et al. Early low pulse pressure in VA-ECMO is associated with acute brain injury. Neurocrit Care. 2023;38:612–621. - PMC - PubMed

LinkOut - more resources