PMID- 38260374
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20240202
DP  - 2024 Jan 11
TI  - Predicting Acute Brain Injury in Venoarterial Extracorporeal Membrane Oxygenation 
      Patients with Tree-Based Machine Learning: Analysis of the Extracorporeal Life 
      Support Organization Registry.
LID - rs.3.rs-3848514 [pii]
LID - 10.21203/rs.3.rs-3848514/v1 [doi]
AB  - 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 PaO(2) 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.
FAU - Kalra, Andrew
AU  - Kalra A
AUID- ORCID: 0000-0001-8338-019X
AD  - Johns Hopkins University School of Medicine.
FAU - Bachina, Preetham
AU  - Bachina P
AD  - Johns Hopkins University School of Medicine.
FAU - Shou, Benjamin L
AU  - Shou BL
AUID- ORCID: 0000-0003-2825-3301
AD  - Johns Hopkins University School of Medicine.
FAU - Hwang, Jaeho
AU  - Hwang J
AUID- ORCID: 0000-0002-1803-2524
AD  - Johns Hopkins University School of Medicine.
FAU - Barshay, Meylakh
AU  - Barshay M
AUID- ORCID: 0000-0001-5611-024X
AD  - Warren Alpert Medical School of Brown University.
FAU - Kulkarni, Shreyas
AU  - Kulkarni S
AUID- ORCID: 0000-0002-6723-515X
AD  - Warren Alpert Medical School of Brown University.
FAU - Sears, Isaac
AU  - Sears I
AUID- ORCID: 0000-0002-3293-4524
AD  - Warren Alpert Medical School of Brown University.
FAU - Eickhoff, Carsten
AU  - Eickhoff C
AUID- ORCID: 0000-0001-9895-4061
AD  - University of Tubingen.
FAU - Bermudez, Christian A
AU  - Bermudez CA
AD  - Perelman School of Medicine at the University of Pennsylvania, Philadelphia.
FAU - Brodie, Daniel
AU  - Brodie D
AUID- ORCID: 0000-0002-0813-3145
AD  - Johns Hopkins University School of Medicine.
FAU - Ventetuolo, Corey E
AU  - Ventetuolo CE
AUID- ORCID: 0000-0002-4223-4775
AD  - Warren Alpert Medical School of Brown University.
FAU - Kim, Bo Soo
AU  - Kim BS
AD  - Johns Hopkins University School of Medicine.
FAU - Whitman, Glenn J R
AU  - Whitman GJR
AUID- ORCID: 0000-0003-3225-2360
AD  - Johns Hopkins University School of Medicine.
FAU - Abbasi, Adeel
AU  - Abbasi A
AD  - Warren Alpert Medical School of Brown University.
FAU - Cho, Sung-Min
AU  - Cho SM
AUID- ORCID: 0000-0002-5132-0958
AD  - Johns Hopkins University School of Medicine.
LA  - eng
GR  - K23 HL157610/HL/NHLBI NIH HHS/United States
PT  - Preprint
DEP - 20240111
PL  - United States
TA  - Res Sq
JT  - Research square
JID - 101768035
PMC - PMC10802703
OTO - NOTNLM
OT  - Extracorporeal Life Support Organization
OT  - acute brain injury
OT  - extracorporeal membrane oxygenation
OT  - machine learning
OT  - neurological complications
COIS- 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.
EDAT- 2024/01/23 12:43
MHDA- 2024/01/23 12:44
PMCR- 2024/01/22
CRDT- 2024/01/23 10:36
PHST- 2024/01/23 12:43 [pubmed]
PHST- 2024/01/23 12:44 [medline]
PHST- 2024/01/23 10:36 [entrez]
PHST- 2024/01/22 00:00 [pmc-release]
AID - rs.3.rs-3848514 [pii]
AID - 10.21203/rs.3.rs-3848514/v1 [doi]
PST - epublish
SO  - Res Sq [Preprint]. 2024 Jan 11:rs.3.rs-3848514. doi: 10.21203/rs.3.rs-3848514/v1.