Survival benefit of extracorporeal membrane oxygenation in severe COVID-19: "perceived futility" and potential underestimation of ECMO's effect

What Are the Real Issues in Providing Extracorporeal Membrane Oxygenation (ECMO) Support: A Survey

INTRODUCTION

By using a novel survey our study aimed to assess the challenges ECMO and Critical Care (CC) teams face when initiating and managing patient's ECMO support.

METHODS

A qualitative survey-based observational study was performed of members of 2 Critical Care Medicine organizations involved in decision-making around the practice of Extracorporeal Membrane Oxygenation (ECMO). The range of exploratory questions covered ethical principles of informed consent, autonomy and goals of care discussions, beneficence, non-maleficence (offering life-sustaining treatments in end-of-life care), and justice (insurance-related limitations of treatment). Questions also covered pragmatic practice and quality improvement areas, such as exploring whether palliative care or ethics teams were involved in such decision-making.

RESULTS

305 members received the survey links, and a total of 61 completed surveys were received, for an overall response rate of 20% among all eligible members. Only 70% of the participants who manage ECMO patients are involved in the ECMO initiation decision process. The majority do not involve Ethics or Palliative care at the initial ECMO initiation decision step. Of the ethical and moral dilemmas reported, the majority revolved around 1. Prognostication of patients receiving VV and VA ECMO support, 2. Lack of knowledge of patient's wishes and goals, 3. Disconnect between expectations of families and outcomes and 4. Staff moral distress around when to stop ECMO in case of futility.

CONCLUSION

Our survey highlights areas of distress and dilemma which have been stressed before in the initiation, management, and outcomes of ECMO patients, however with the increasing use of this modality of cardiopulmonary mechanical support being offered, the survey results can offer a guidance using sound ethical principles.

Multi-horizon predictive models for guiding extracorporeal resource allocation in critically ill COVID-19 patients

OBJECTIVE

Extracorporeal membrane oxygenation (ECMO) resource allocation tools are currently lacking. We developed machine learning (ML) models for predicting COVID-19 patients at risk of receiving ECMO to guide patient triage and resource allocation.

MATERIAL AND METHODS

We included COVID-19 patients admitted to intensive care units for >24 h from March 2020 to October 2021, divided into training and testing development and testing-only holdout cohorts. We developed ECMO deployment timely prediction model ForecastECMO using Gradient Boosting Tree (GBT), with pre-ECMO prediction horizons from 0 to 48 h, compared to PaO2/FiO2 ratio, Sequential Organ Failure Assessment score, PREdiction of Survival on ECMO Therapy score, logistic regression, and 30 pre-selected clinical variables GBT Clinical GBT models, with area under the receiver operator curve (AUROC) and precision recall curve (AUPRC) metrics.

RESULTS

ECMO prevalence was 2.89% and 1.73% in development and holdout cohorts. ForecastECMO had the best performance in both cohorts. At the 18-h prediction horizon, a potentially clinically actionable pre-ECMO window, ForecastECMO, had the highest AUROC (0.94 and 0.95) and AUPRC (0.54 and 0.37) in development and holdout cohorts in identifying ECMO patients without data 18 h prior to ECMO.

DISCUSSION AND CONCLUSIONS

We developed a multi-horizon model, ForecastECMO, with high performance in identifying patients receiving ECMO at various prediction horizons. This model has potential to be used as early alert tool to guide ECMO resource allocation for COVID-19 patients. Future prospective multicenter validation would provide evidence for generalizability and real-world application of such models to improve patient outcomes.