ECMO PAL: using deep neural networks for survival prediction in venoarterial extracorporeal membrane oxygenation

Algor-ethics: charting the ethical path for AI in critical care

The integration of Clinical Decision Support Systems (CDSS) based on artificial intelligence (AI) in healthcare is groundbreaking evolution with enormous potential, but its development and ethical implementation, presents unique challenges, particularly in critical care, where physicians often deal with life-threating conditions requiring rapid actions and patients unable to participate in the decisional process. Moreover, development of AI-based CDSS is complex and should address different sources of bias, including data acquisition, health disparities, domain shifts during clinical use, and cognitive biases in decision-making. In this scenario algor-ethics is mandatory and emphasizes the integration of 'Human-in-the-Loop' and 'Algorithmic Stewardship' principles, and the benefits of advanced data engineering. The establishment of Clinical AI Departments (CAID) is necessary to lead AI innovation in healthcare, ensuring ethical integrity and human-centered development in this rapidly evolving field.

Blood flow and emboli transport patterns during venoarterial extracorporeal membrane oxygenation: A computational fluid dynamics study

PROBLEM

Despite advances in Venoarterial Extracorporeal Membrane Oxygenation (VA-ECMO), a significant mortality rate persists due to complications. The non-physiological blood flow dynamics of VA-ECMO may lead to neurological complications and organ ischemia. Continuous retrograde high-flow oxygenated blood enters through a return cannula placed in the femoral artery which opposes the pulsatile deoxygenated blood ejected by the left ventricle (LV), which impacts upper body oxygenation and subsequent hyperoxemia. The complications underscore the critical need to comprehend the impact of VA-ECMO support level and return cannula size, as mortality remains a significant concern.

AIM

The aim of this study is to predict and provide insights into the complications associated with VA-ECMO using computational fluid dynamics (CFD) simulations. These complications will be assessed by characterising blood flow and emboli transport patterns through a comprehensive analysis of the influence of VA-ECMO support levels and arterial return cannula sizes.

METHODS

Patient-specific 3D aortic and major branch models, derived from a male patient's CT scan during VA-ECMO undergoing respiratory dysfunction, were analyzed using CFD. The investigation employed species transport and discrete particle tracking models to study ECMO blood (oxygenated) mixing with LV blood (deoxygenated) and to trace emboli transport patterns from potential sources (circuit, LV, and aorta wall). Two cannula sizes (15 Fr and 19 Fr) were tested alongside varying ECMO pump flow rates (50%, 70%, and 90% of the total cardiac output).

RESULTS

Cannula size did not significantly affect oxygen transport. At 90% VA-ECMO support, all arteries distal to the aortic arch achieved 100% oxygen saturation. As support level decreased, oxygen transport to the upper body also decreased to a minimum saturation of 73%. Emboli transport varied substantially between emboli origin and VAECMO support level, with the highest risk of cerebral emboli coming from the LV with a 15 Fr cannula at 90% support.

CONCLUSION

Arterial return cannula sizing minimally impacted blood oxygen distribution; however, it did influence the distribution of emboli released from the circuit and aortic wall. Notably, it was the support level alone that significantly affected the mixing zone of VA-ECMO and cardiac blood, subsequently influencing the risk of embolization of the cardiogenic source and oxygenation levels across various arterial branches.

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.

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.