Ex vivo lung perfusion in donation after circulatory death: A post hoc analysis of the Normothermic Ex Vivo Lung Perfusion as an Assessment of Extended/Marginal Donors Lungs trial.

OBJECTIVE: Donation after circulatory death (DCD) donors offer the ability to expand the lung donor pool and ex vivo lung perfusion (EVLP) further contributes to this ability by allowing for additional evaluation and resuscitation of these extended criteria donors. We sought to determine the outcomes of recipients receiving organs from DCD EVLP donors in a multicenter setting. METHODS: This was an unplanned post hoc analysis of a multicenter, prospective, nonrandomized trial that took place during 2011 to 2017 with 3 years of follow-up. Patients were placed into 3 groups based off procurement strategy: brain-dead donor (control), brain-dead donor evaluated by EVLP, and DCD donors evaluated by EVLP. The primary outcomes were severe primary graft dysfunction at 72 hours and survival. Secondary outcomes included select perioperative outcomes, and 1-year and 3-years allograft function and quality of life measures. RESULTS: The DCD EVLP group had significantly higher incidence of severe primary graft dysfunction at 72 hours (P = .03), longer days on mechanical ventilation (P < .001) and in-hospital length of stay (P = .045). Survival at 3 years was 76.5% (95% CI, 69.2%-84.7%) for the control group, 68.3% (95% CI, 58.9%-79.1%) for the brain-dead donor group, and 60.7% (95% CI, 45.1%-81.8%) for the DCD group (P = .36). At 3-year follow-up, presence observed bronchiolitis obliterans syndrome or quality of life metrics did not differ among the groups. CONCLUSIONS: Although DCD EVLP allografts might not be appropriate to transplant in every candidate recipient, the expansion of their use might afford recipients stagnant on the waitlist a viable therapy.

Percutaneous Venopulmonary Extracorporeal Membrane Oxygenation as Bridge to Lung Transplantation.

Mechanical circulatory support (MCS) as a bridge to lung transplant is an infrequent but accepted pathway in patients who have refractory end-stage pulmonary failure. The American Association of Thoracic Surgeons Expert Consensus Guidelines, published in 2023, recommends venovenous (VV) extracorporeal membrane oxygenation (ECMO) as the initial configuration for those patients who have failed conventional medical therapy, including mechanical ventilation, while waiting for lung transplantation and needing MCS. Alternatively, venoarterial (VA) ECMO can be used in patients with acute right ventricular failure, hemodynamic instability, or refractory respiratory failure. With the advancement in percutaneous venopulmonary (VP) ECMO cannulation techniques, this option is becoming an attractive configuration as bridge to lung transplantation. This configuration enhances stability of the right ventricle, prevents recirculation with direct introduction of pulmonary artery oxygenation, and promotes hemodynamic stability during mobility, rehabilitation, and sedation-weaning trials before lung transplantation. Here, we present a case series of eight percutaneous VP ECMO as bridge to lung transplant with all patients mobilized, awake, and successfully transplanted with survival to hospital discharge.

Lung transplant outcomes after acute respiratory distress syndrome requiring extracorporeal life support: Lessons from the COVID-19 pandemic.

OBJECTIVE: Lung transplant for acute respiratory distress syndrome in patients supported with extracorporeal membrane oxygenation was rare before 2020, but was rapidly adopted to rescue patients with COVID-19 with lung failure. This study aims to compare the outcomes of patients who underwent lung transplant for COVID-associated acute respiratory distress syndrome and non-COVID acute respiratory distress syndrome, and to assess the impact of type and duration of extracorporeal membrane oxygenation support on survival. METHODS: Using the United Network for Organ Sharing database, we identified 311 patients with acute respiratory distress syndrome who underwent lung transplant from 2007 to 2022 and performed a retrospective analysis of the patients who required extracorporeal membrane oxygenation preoperatively, stratified by COVID-associated acute respiratory distress syndrome and non-COVID acute respiratory distress syndrome listing diagnoses. The primary outcome was 1-year survival. Secondary outcomes included the effect of type and duration of extracorporeal membrane oxygenation on survival. RESULTS: During the study period, 236 patients with acute respiratory distress syndrome and preoperative extracorporeal membrane oxygenation underwent lung transplant; 181 patients had a listing diagnosis of COVID-associated acute respiratory distress syndrome (77%), and 55 patients had a listing diagnosis of non-COVID acute respiratory distress syndrome (23%). Patients with COVID-associated acute respiratory distress syndrome were older, were more likely to be female, had higher body mass index, and spent longer on the waitlist (all P < .02) than patients with non-COVID acute respiratory distress syndrome. The 2 groups had similar 1-year survival (85.8% vs 81.1%, P = .2) with no differences in postoperative complications. Patients with COVID-associated acute respiratory distress syndrome required longer times on extracorporeal membrane oxygenation pretransplant (P = .02), but duration of extracorporeal membrane oxygenation support was not a predictor of 1-year survival (P = .2). CONCLUSIONS: Despite prolonged periods of pretransplant extracorporeal membrane oxygenation support, selected patients with acute respiratory distress syndrome can undergo lung transplant safely with acceptable short-term outcomes. Appropriate selection criteria and long-term implications require further analysis.

TGF-ßR2 signaling coordinates pulmonary vascular repair after viral injury in mice and human tissue.

Disruption of pulmonary vascular homeostasis is a central feature of viral pneumonia, wherein endothelial cell (EC) death and subsequent angiogenic responses are critical determinants of the outcome of severe lung injury. A more granular understanding of the fundamental mechanisms driving reconstitution of lung endothelium is necessary to facilitate therapeutic vascular repair. Here, we demonstrated that TGF-ß signaling through TGF-ßR2 (transforming growth factor-ß receptor 2) is activated in pulmonary ECs upon influenza infection, and mice deficient in endothelial Tgfbr2 exhibited prolonged injury and diminished vascular repair. Loss of endothelial Tgfbr2 prevented autocrine Vegfa (vascular endothelial growth factor α) expression, reduced endothelial proliferation, and impaired renewal of aerocytes thought to be critical for alveolar gas exchange. Angiogenic responses through TGF-ßR2 were attributable to leucine-rich α-2-glycoprotein 1, a proangiogenic factor that counterbalances canonical angiostatic TGF-ß signaling. Further, we developed a lipid nanoparticle that targets the pulmonary endothelium, Lung-LNP (LuLNP). Delivery of Vegfa mRNA, a critical TGF-ßR2 downstream effector, by LuLNPs improved the impaired regeneration phenotype of EC Tgfbr2 deficiency during influenza injury. These studies defined a role for TGF-ßR2 in lung endothelial repair and demonstrated efficacy of an efficient and safe endothelial-targeted LNP capable of delivering therapeutic mRNA cargo for vascular repair in influenza infection.

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

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.

Development and validation of primary graft dysfunction predictive algorithm for lung transplant candidates.

BACKGROUND: Primary graft dysfunction (PGD) is the leading cause of early morbidity and mortality after lung transplantation. Accurate prediction of PGD risk could inform donor approaches and perioperative care planning. We sought to develop a clinically useful, generalizable PGD prediction model to aid in transplant decision-making. METHODS: We derived a predictive model in a prospective cohort study of subjects from 2012 to 2018, followed by a single-center external validation. We used regularized (lasso) logistic regression to evaluate the predictive ability of clinically available PGD predictors and developed a user interface for clinical application. Using decision curve analysis, we quantified the net benefit of the model across a range of PGD risk thresholds and assessed model calibration and discrimination. RESULTS: The PGD predictive model included distance from donor hospital to recipient transplant center, recipient age, predicted total lung capacity, lung allocation score (LAS), body mass index, pulmonary artery mean pressure, sex, and indication for transplant; donor age, sex, mechanism of death, and donor smoking status; and interaction terms for LAS and donor distance. The interface allows for real-time assessment of PGD risk for any donor/recipient combination. The model offers decision-making net benefit in the PGD risk range of 10% to 75% in the derivation centers and 2% to 10% in the validation cohort, a range incorporating the incidence in that cohort. CONCLUSION: We developed a clinically useful PGD predictive algorithm across a range of PGD risk thresholds to support transplant decision-making, posttransplant care, and enrich samples for PGD treatment trials.

The Impact of Donor Smoking on Primary Graft Dysfunction and Mortality after Lung Transplantation.

Rationale: Primary graft dysfunction (PGD) is the leading cause of early morbidity and mortality after lung transplantation. Prior studies implicated proxy-defined donor smoking as a risk factor for PGD and mortality. Objectives: We aimed to more accurately assess the impact of donor smoke exposure on PGD and mortality using quantitative smoke exposure biomarkers. Methods: We performed a multicenter prospective cohort study of lung transplant recipients enrolled in the Lung Transplant Outcomes Group cohort between 2012 and 2018. PGD was defined as grade 3 at 48 or 72 hours after lung reperfusion. Donor smoking was defined using accepted thresholds of urinary biomarkers of nicotine exposure (cotinine) and tobacco-specific nitrosamine (4-[methylnitrosamino]-1-[3-pyridyl]-1-butanol [NNAL]) in addition to clinical history. The donor smoking-PGD association was assessed using logistic regression, and survival analysis was performed using inverse probability of exposure weighting according to smoking category. Measurements and Main Results: Active donor smoking prevalence varied by definition, with 34-43% based on urinary cotinine, 28% by urinary NNAL, and 37% by clinical documentation. The standardized risk of PGD associated with active donor smoking was higher across all definitions, with an absolute risk increase of 11.5% (95% confidence interval [CI], 3.8% to 19.2%) by urinary cotinine, 5.7% (95% CI, -3.4% to 14.9%) by urinary NNAL, and 6.5% (95% CI, -2.8% to 15.8%) defined clinically. Donor smoking was not associated with differential post-lung transplant survival using any definition. Conclusions: Donor smoking associates with a modest increase in PGD risk but not with increased recipient mortality. Use of lungs from smokers is likely safe and may increase lung donor availability. Clinical trial registered with www.clinicaltrials.gov (NCT00552357).

Reevaluating Rehabilitation Practice for Patients Who Were Critically Ill After COVID-19 Infection: An Administrative Case Report.

OBJECTIVE: The goal of this case report is to describe the process, challenges, and opportunities of implementing rehabilitation for individuals who were critically ill and required both mechanical ventilation (MV) and extracorporeal membrane oxygenation (ECMO) support following a coronavirus 2019 (COVID-19) infection in an academic medical center. METHODS: This administrative case report is set in a heart and vascular intensive care unit, a 35-bed critical care unit that provides services for patients with various complex cardiovascular surgical interventions, including transplantation. Patients were admitted to the heart and vascular intensive care unit with either COVID-19 acute respiratory distress syndrome or pulmonary fibrosis for consideration of bilateral orthotropic lung transplantation. The authors describe the process of establishing rehabilitation criteria for patients who, by previously established guidelines, would be considered too ill to engage in rehabilitation. RESULTS: The rehabilitation team, in coordination with an interprofessional team of critical care providers including physicians, respiratory care providers, perfusionists, and registered nurses, collaborated to implement a rehabilitation program for patients with critical COVID-19 being considered for bilateral orthotropic lung transplantation. This was accomplished by (1) reviewing previously published guidelines and practices; (2) developing an interdisciplinary framework for the consideration of rehabilitation treatment; and (3) implementing the framework for patients in our heart and vascular intensive care unit. CONCLUSION: In response to the growing volume of patients admitted with critical COVID-19, the team initiated and developed an interprofessional framework and successfully provided rehabilitation services to patients who were critically ill. While resource-intensive, the process demonstrates that rehabilitation can be implemented on a case-by-case basis for select patients receiving extracorporeal membrane oxygenation and MV, who would previously have been considered too critically ill for rehabilitation services. IMPACT: Rehabilitating patients with end-stage pulmonary disease on extracorporeal membrane oxygenation and MV support is challenging but feasible with appropriate interprofessional collaboration and knowledge sharing.

Interpretable machine learning-based predictive modeling of patient outcomes following cardiac surgery.

BACKGROUND: The clinical applicability of machine learning predictions of patient outcomes following cardiac surgery remains unclear. We applied machine learning to predict patient outcomes associated with high morbidity and mortality after cardiac surgery and identified the importance of variables to the derived model's performance. METHODS: We applied machine learning to the Society of Thoracic Surgeons Adult Cardiac Surgery Database to predict postoperative hemorrhage requiring reoperation, venous thromboembolism (VTE), and stroke. We used permutation feature importance to identify variables important to model performance and a misclassification analysis to study the limitations of the model. RESULTS: The study dataset included 662,772 subjects who underwent cardiac surgery between 2015 and 2017 and 240 variables. Hemorrhage requiring reoperation, VTE, and stroke occurred in 2.9%, 1.2%, and 2.0% of subjects, respectively. The model performed remarkably well at predicting all 3 complications (area under the receiver operating characteristic curve, 0.92-0.97). Preoperative and intraoperative variables were not important to model performance; instead, performance for the prediction of all 3 outcomes was driven primarily by several postoperative variables, including known risk factors for the complications, such as mechanical ventilation and new onset of postoperative arrhythmias. Many of the postoperative variables important to model performance also increased the risk of subject misclassification, indicating internal validity. CONCLUSIONS: A machine learning model accurately and reliably predicts patient outcomes following cardiac surgery. Postoperative, as opposed to preoperative or intraoperative variables, are important to model performance. Interventions targeting this period, including minimizing the duration of mechanical ventilation and early treatment of new-onset postoperative arrhythmias, may help lower the risk of these complications.

Infectious complications associated with bronchial anastomotic dehiscence in lung transplant recipients.

INTRODUCTION: Bronchial anastomotic dehiscence (AD) is an uncommon complication following lung transplantation that carries significant morbidity and mortality. The objective of this study was to characterize fungal and bacterial infections in ADs, including whether infections following AD were associated with progression to bronchial stenosis. METHODS: This was a single-center study of 615 lung transplant recipients between 6/1/2015 and 12/31/2021. Airway complications were defined according to ISHLT consensus guidelines. RESULTS: 22 of the 615 recipients (3.6%) developed an AD. Bronchial ischemia or necrosis was common prior to dehiscence (68.1%). Fourteen (63.6%) recipients had bacterial airway infections, most commonly with Gram-negative rods, prior to dehiscence. Thirteen (59.1%) recipients had an associated pleural infection, most commonly with Candida species (30.8%). Post-dehiscence Aspergillus species were isolated in 4 recipients, 3 of which were de novo infections. Eleven had bacterial infections prior to dehiscence resolution, most commonly with Pseudomonas aeruginosa. Eleven recipients developed airway stenosis requiring dilation and/or stenting. Development of secondary infection prior to AD resolution was not associated with progression to stenosis (OR = .41, 95% CI = .05-3.30, p = .41). CONCLUSIONS: Gram-negative bacterial infections are common before and after AD. Pleural infection should be suspected in most cases. Infections prior to healing were not associated with subsequent development of airway stenosis.

Rehabilitation Characteristics and Outcomes for Lung Transplantation for COVID-19: A Case Series.

OBJECTIVE: Severe coronavirus disease 2019 (COVID-19) can result in irreversible lung damage, with some individuals requiring lung transplantation. The purpose of this case series is to describe the initial experience with the rehabilitation and functional outcomes of 9 patients receiving a lung transplant for COVID-19. METHODS: Nine individuals, ranging in age from 37 to 68 years, received bilateral orthotopic lung transplantation (BOLT) for COVID-19 between December 2020 and July 2021. Rehabilitation was provided before and after the transplant, including in-hospital rehabilitation, postacute care inpatient rehabilitation, and outpatient rehabilitation. RESULTS: Progress with mobility was limited in the pretransplant phase despite rehabilitation efforts. Following transplantation, 2 individuals expired before resuming rehabilitation, and 2 others had complications that delayed their progress. The remaining 5 experienced clinically important improvements in mobility and walking capacities. CONCLUSION: Considerable rehabilitation resources are required to care for individuals both before and after BOLT for COVID-19. Rehabilitation can have a profound impact on both functional and clinical outcomes for this unique patient population. IMPACT: There is limited literature on the rehabilitation efforts and outcomes for patients who received BOLT for COVID-19. Occupational therapists and physical therapists play an important role during the pretransplant and posttransplant recovery process for this novel patient population. LAY SUMMARY: Patients with a bilateral orthotopic lung transplant due to COVID-19 require a unique rehabilitation process. They have significant difficulties with activities of daily living and functional mobility across the pretransplant and posttransplant continuum of care, but progressive gains in functional performance may be possible with a comprehensive multidisciplinary rehabilitation program.

Cryoablation in lung transplantation: Its impact on pain, opioid use, and outcomes.

Objective: To assess the effect of intraoperative cryoablation on postoperative patient-reported pain, opioid use, and clinical outcomes in lung transplantation. Methods: We performed a single-center retrospective cohort study of adult lung transplant recipients from August 2017 to September 2018. We compared outcomes of patients who received intraoperative cryoablation of the intercostal nerves with those who did not. Primary outcomes were postoperative patient-reported pain scores and opioid use. Secondary outcomes included postoperative sedation and agitation levels and perioperative outcomes. Data were abstracted from patients' electronic health records. Results: Of the 102 patients transplanted, 45 received intraoperative cryoablation (intervention group) and 57 received the standard of care, which did not include intercostal or serratus blocks or immediate postoperative epidural placement (control group). The intervention group had significantly lower median and maximum postoperative pain scores at days 3 and 7 and significantly lower oral opioid use at days 3, 7, and 14 compared with the control group. Chronic opioid use at 3 and 6 months' posttransplant was lower in the intervention group. Differences in perioperative outcomes, including length of mechanical ventilation, sedation and agitation levels, and hospital stay, were not clinically meaningful. Survival at 30 days and 1 year was superior in the intervention compared with the control group. Conclusions: Findings suggest that use of intraoperative cryoablation is an effective approach for treating pain and reducing opioid use in patients who undergo lung transplant, but a randomized study across multiple institutions is needed to confirm these findings.

Intracannula Thrombus Formation Associated With Dual Lumen ProtekDuo Cannula in Extracorporeal Membrane Oxygenation (ECMO).

Extracorporeal membrane oxygenation (ECMO) is used in cases of severe respiratory failure refractory to medical management. Use of ECMO is increasing, along with new cannulation strategies including oxygenated right ventricular assist devices (oxy-RVADs). Multiple dual lumen cannulas are now available, which increase the potential for patient mobility and decrease the number of vascular access sites. However, dual lumen, single cannula flow can be limited by adequate inflow, requiring the need for an additional inflow cannula to meet patient demands. This cannula configuration may result in differential flows in the inflow and outflow limbs and altered flow dynamics, increasing the risk of intracannula thrombus. We describe a series of four patients treated with oxy-RVAD for COVID-19-associated respiratory failure complicated by dual lumen ProtekDuo intracannula thrombus.

Durable Left Ventricular Assist Device Outflow Graft Obstructions: Clinical Characteristics and Outcomes.

PURPOSE: We report on the clinical course and management of patients supported with durable implantable LVADs who developed outflow graft obstructions at a large academic center. METHODS: We performed a retrospective review of patients receiving LVAD support from 2012 through 2020. Patients who developed an outflow graft obstruction diagnosed by computed tomography angiography (CTA) or angiogram were identified, and patient characteristics and outcomes were reported. RESULTS: Of the 324 patients supported by LVAD at our institution, 11 patients (3.4%) were diagnosed with outflow graft obstructions. The most common presentation was low flow alarms, which was present in 10/11 patients, and the remaining patient presented with lightheadedness. Patients had minimal LDH elevation with 8/11 presenting with less than 2-fold the upper limit of normal. Transthoracic echocardiograms were not diagnostic, but CTA enabled non-invasive diagnoses in 8/11 of the patients. Three patients with extrinsic compression of the outflow graft successfully underwent endovascular stent placement, and three patients with outflow cannula kinks received supportive care. Of the five patients diagnosed with intraluminal thromboses, one received a heart transplant, one underwent an outflow graft revision, and three received supportive care due to comorbidities. CONCLUSION: Outflow graft obstructions remain a rare, but serious complication. The true prevalence of this entity is likely underestimated due to the non-specific clinical presentation. CTA is a pivotal non-invasive diagnostic step. Patients with external compression were successfully treated with endovascular stenting.

Quality and readability of online patient information on the left ventricular assist device.

BACKGROUND: As patients seek online health information to supplement their medical decision-making, the aim of this study is to assess the quality and readability of internet information on the left ventricular assist device (LVAD). METHODS: Three online search engines (Google, Bing, and Yahoo) were searched for "LVAD" and "Left ventricular assist device." Included websites were classified as academic, foundation/advocacy, hospital-affiliated, commercial, or unspecified. The quality of information was assessed using the JAMA benchmark criteria (0-4), DISCERN tool (16-80), and the presence of Health On the Net code (HONcode) accreditation. Readability was assessed using the Flesch Reading Ease score. RESULTS: A total of 38 unique websites were included. The average JAMA and DISCERN scores of all websites were 0.82 ± 1.11 and 52.45 ± 13.51, respectively. Academic sites had a significantly lower JAMA mean score than commercial (p < 0.001) and unspecified (p < 0.001) websites, as well as a significantly lower DISCERN, mean score than commercial sites (p = 0.002). HONcode certification was present in 6 (15%) websites analyzed, which had significantly higher JAMA (p < 0.001) and DISCERN (p < 0.016) mean scores than sites without HONcode certification. Readability was fairly difficult and at the level of high school students. CONCLUSIONS: The quality of online information on the LVAD is variable, and overall readability exceeds the recommended level for the public. Patients accessing online information on the LVAD should be referred to sites with HONcode accreditation. Academic institutions must provide higher quality online patient literature on LVADs.

Utilizing Machine Learning to Predict Neurological Injury in Venovenous Extracorporeal Membrane Oxygenation Patients: An Extracorporeal Life Support Organization Registry Analysis.

Background: Venovenous extracorporeal membrane oxygenation (VV-ECMO) is associated with acute brain injury (ABI), including central nervous system (CNS) ischemia (defined as ischemic stroke or hypoxic-ischemic brain injury) and intracranial hemorrhage (ICH). There is limited data on prediction models for ABI and neurological outcomes in VV-ECMO. Research Question: Can machine learning (ML) accurately predict ABI and identify modifiable factors of ABI in VV-ECMO? Study Design and Methods: We analyzed adult (≥18 years) VV-ECMO patients in the Extracorporeal Life Support Organization Registry (2009-2021) from 676 centers. ABI was defined as CNS ischemia, ICH, brain death, and seizures. Overall, 65 total variables were extracted including clinical characteristics and pre-ECMO and on-ECMO variables. Random Forest, CatBoost, LightGBM, and XGBoost ML algorithms (10-fold leave-one-out cross-validation) were used to predict ABI. Feature Importance Scores were used to pinpoint variables most important for predicting ABI. Results: Of 37,473 VV-ECMO patients (median age=48.1 years, 63% male), 2,644 (7.1%) experienced ABI: 610 (2%) and 1,591 (4%) experienced CNS ischemia and ICH, respectively. The median ECMO duration was 10 days (interquartile range=5-20 days). The area under the receiver-operating characteristics curves to predict ABI, CNS ischemia, and ICH were 0.67, 0.63, and 0.70, respectively. The accuracy, positive predictive, and negative predictive values for ABI were 79%, 15%, and 95%, respectively. ML identified pre-ECMO cardiac arrest as the most important risk factor for ABI while ECMO duration and bridge to transplantation as an indication for ECMO were associated with lower risk of ABI. Interpretation: This is the first study to use machine learning to predict ABI in a large cohort of VV-ECMO patients. Performance was sub-optimal due to the low reported prevalence of ABI with lack of standardization of neuromonitoring/imaging protocols and data granularity in the ELSO Registry. Standardized neurological monitoring and imaging protocols may improve machine learning performance to predict ABI.