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
[Preprint]. 2024 Jan 11:rs.3.rs-3848514.
doi: 10.21203/rs.3.rs-3848514/v1.

Predicting Acute Brain Injury in Venoarterial Extracorporeal Membrane Oxygenation Patients with Tree-Based Machine Learning: Analysis of the Extracorporeal Life Support Organization Registry

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

Predicting Acute Brain Injury in Venoarterial Extracorporeal Membrane Oxygenation Patients with Tree-Based Machine Learning: Analysis of the Extracorporeal Life Support Organization Registry

Andrew Kalra et al. Res Sq. .

Update in

Abstract

Objective: To determine if machine learning (ML) can predict acute brain injury (ABI) and identify modifiable risk factors for ABI in venoarterial extracorporeal membrane oxygenation (VA-ECMO) patients.

Design: Retrospective cohort study of the Extracorporeal Life Support Organization (ELSO) Registry (2009-2021).

Setting: International, multicenter registry study of 676 ECMO centers.

Patients: Adults (≥18 years) supported with VA-ECMO or extracorporeal cardiopulmonary resuscitation (ECPR).

Interventions: None.

Measurements and main results: Our primary outcome was ABI: central nervous system (CNS) ischemia, intracranial hemorrhage (ICH), brain death, and seizures. We utilized Random Forest, CatBoost, LightGBM and XGBoost ML algorithms (10-fold leave-one-out cross-validation) to predict and identify features most important for ABI. We extracted 65 total features: demographics, pre-ECMO/on-ECMO laboratory values, and pre-ECMO/on-ECMO settings.Of 35,855 VA-ECMO (non-ECPR) patients (median age=57.8 years, 66% male), 7.7% (n=2,769) experienced ABI. In VA-ECMO (non-ECPR), the area under the receiver-operator characteristics curves (AUC-ROC) to predict ABI, CNS ischemia, and ICH was 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 ABI. Longer ECMO duration, higher 24h ECMO pump flow, and higher on-ECMO PaO2 were associated with ABI.Of 10,775 ECPR patients (median age=57.1 years, 68% male), 16.5% (n=1,787) experienced ABI. The AUC-ROC for ABI, CNS ischemia, and ICH was 0.72, 0.73, and 0.69, respectively. The true positive, true negative, false positive, false negative, positive, and negative predictive values were 61%, 70%, 30%, 39%, 29% and 90%, respectively, for ABI. Longer ECMO duration, younger age, and higher 24h ECMO pump flow were associated with ABI.

Conclusions: This is the largest study predicting neurological complications on sufficiently powered international ECMO cohorts. Longer ECMO duration and higher 24h pump flow were associated with ABI in both non-ECPR and ECPR VA-ECMO.

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

PubMed Disclaimer

Conflict of interest statement

Financial/nonfinancial disclosures: Dr. Brodie receives research support from and consults for LivaNova. He has been on the medical advisory boards for Xenios, Medtronic, Inspira and Cellenkos. He is the President-elect of the Extracorporeal Life Support Organization (ELSO) and the Chair of the Executive Committee of the International ECMO Network (ECMONet), and he writes for UpToDate. Dr. Ventetuolo has been a consultant or served on advisory boards for Merck, Janssen, and Regeneron, outside of the submitted work. The authors do not have any additional conflicts of interest to declare. SMC is supported by NHLBI (1K23HL157610) and Hyperfine (SAFE MRI ECMO study). Additional Declarations: The authors declare no competing interests.

Figures

Figure 1
Figure 1
All 65 variables incorporated into our machine learning models including laboratory values, ECMO settings, demographics, other variables, and our primary outcome (acute brain injury). BP: blood pressure. CI: cardiac index. DBP: diastolic blood pressure. DPAP: diastolic pulmonary arterial pressure. ECMO: extracorporeal membrane oxygenation. EEG: electroencephalogram. FiO2: fraction of inspired oxygen. HFV: high frequency ventilator. MPAP: mean pulmonary arterial pressure. PaO2: partial pressure of oxygen. PaCO2: partial pressure of carbon dioxide. PCWP: pulmonary capillary wedge pressure. PEEP: positive-end expiratory pressure. PIP: peak inspiratory pressure. SPAP: systolic pulmonary arterial pressure. SaO2: arterial blood gas oxygen saturation. SpO2: peripheral oxygen saturation. SvO2: mixed venous oxygen saturation.
Figure 2
Figure 2
Flowchart of study cohort (VA-ECMO and ECPR patients) from the ELSO Registry in 2009–2020. ECMO = extracorporeal membrane oxygenation, VA = venoarterial, VV = venovenous, Conversion = VA -> VV or VV -> VA, ECPR = extracorporeal cardiopulmonary resuscitation, VVA = venovenoarterial, Other = mode not defined, VP = venopulmonary
Figure 3
Figure 3
Receiver-operating characteristic curves for predicting A) acute brain injury (ABI), B) central nervous system (CNS) ischemia, and C) intracranial hemorrhage (ICH) in venoarterial extracorporeal membrane oxygenation (VA-ECMO) patients and for predicting D) ABI, E) CNS ischemia, and F) ICH in extracorporeal cardiopulmonary resuscitation (ECPR) patients.
Figure 4
Figure 4
Feature Importance Scores for A) acute brain injury, B) central nervous system ischemia, and C) intracranial hemorrhage in VA-ECMO (non-ECPR) patients. AP: arterial pressure. BP: blood pressure. CI: cardiac index. DBP: diastolic blood pressure. DPAP: diastolic pulmonary arterial pressure. ECMO: extracorporeal membrane oxygenation. EEG: electroencephalogram. FiO2: fraction of inspired oxygen. HFV: high frequency ventilator. MPAP: mean pulmonary arterial pressure. PaO2: partial pressure of oxygen. PaCO2: partial pressure of carbon dioxide. PCWP: pulmonary capillary wedge pressure. PEEP: positive-end expiratory pressure. PIP: peak inspiratory pressure. SPAP: systolic pulmonary arterial pressure. SaO2: arterial blood gas oxygen saturation. SpO2: peripheral oxygen saturation. SvO2: mixed venous oxygen saturation. Vent: ventilator.
See this image and copyright information in PMC

References

    1. Thiagarajan RR, Barbaro RP, Rycus PT, et al.: Extracorporeal Life Support Organization Registry International Report 2016. ASAIO J 2017; 63(1):60–67 - PubMed
    1. Cho SM, 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 CS, Etchill E, Dong J, et al.: Neuromonitoring detects brain injury in patients receiving extracorporeal membrane oxygenation support. J Thorac Cardiovasc Surg 2021 - PubMed
    1. Shou BL, Ong CS, 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 BL, Wilcox C, Florissi I, et al.: Early Low Pulse Pressure in VA-ECMO Is Associated with Acute Brain Injury. Neurocrit Care 2022 - PMC - PubMed

Publication types

LinkOut - more resources