Anticoagulation management in pediatric extracorporeal membrane oxygenation (ECMO) is challenging with multiple laboratory measures utilized across institutions without consensus guidelines. These include partial thromboplastin time (PTT), thromboelastography (TEG), and antifactor Xa (aXa). We aimed to evaluate the consistency of TEG R-time, PTT, and aXa correlation to bivalirudin and heparin dosing. We conducted a single-center restrospective review of pediatric ECMO cases from 2018 to 2020 anticoagulated with bivalirudin or heparin. We collected up to 14 serial simultaneous TEG R-time, PTT, and aXa measurements over a 7 day ECMO course with corresponding bivalirudin or heparin dosing. We analyzed the correlation between bivalirudin, heparin, and the three measurements of anticoagulation. A total of 67 ECMO runs, 32 bivalirudin, and 35 heparin, and more than 1,500 laboratory values, of which >80% simultaneous, were analyzed. When assessing correlations at the individual patient level, there was no consistent correlation between dosing and at least one laboratory parameter in the majority of patients. Furthermore, 44% of the bivalirudin cohort and 37% of the heparin cohort exhibited no correlation with any parameters. There were statistically significant correlations only between bivalirudin and heparin dosing and the sum total of the different laboratory tests. These inconsistencies highlight the importance of multimodality testing of anticoagulation in the management of pediatric ECMO anticoagulation and cannot be relied on in isolation from bedside clinical judgment.
Advances in extracorporeal membrane oxygenation (ECMO) technology are associated with expanded indications, increased utilization and improved outcome. There is growing interest in developing ECMO prognostication scores to aid in bedside decision making. To date, the majority of available scores have been limited to mostly registry-based data and with mortality as the main outcome of interest. There continues to be a gap in clinically applicable decision support tools to aid in the timing of ECMO cannulation to improve patients’ long-term outcomes. We present a brief review of the commonly available adult and pediatric ECMO prognostication tools, their limitations, and future directions.
28 December 2022 in Journal of the American Medical Informatics Association
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. We included COVID-19 patients admitted to intensive care units for >24 hours 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 0-48 hours, compared to PaO2/FiO2 (PF) ratio, Sequential Organ Failure Assessment (SOFA) score, PREdiction of Survival on ECMO Therapy-Score (PRESET) score, logistic regression (LR), and 30 pre-selected clinical variables GBT Clinical GBT models, with area under the receiver operator curve (AUROC) and precision recall curve (AUPRC) metrics. ECMO prevalence was 2.89% and 1.73% in development and holdout cohorts. ForecastECMO had the best performance in both cohorts. At the 18-hour prediction horizon, a potentially clinically actionable pre-ECMO window, ForecastECMO had the highest AUROC (0.94 & 0.95) and AUPRC (0.54 & 0.37) in development and holdout cohorts in identifying ECMO patients without data 18-hours prior to ECMO. 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 multi-center validation would provide evidence for generalizability and real-world application of such models to improve patient outcomes.
OBJECTIVES: To identify and prioritize research questions for anticoagulation and hemostasis management of neonates and children supported with extracorporeal membrane oxygenation (ECMO) from the Pediatric ECMO Anticoagulation CollaborativE (PEACE) consensus. DATA SOURCES: Systematic review was performed using PubMed, EMBASE, and Cochrane Library (CENTRAL) databases from January 1988 to May 2021, followed by serial consensus conferences of international, interprofessional experts in the management of ECMO for critically ill neonates and children. STUDY SELECTION: The management of ECMO anticoagulation for critically ill neonates and children. DATA EXTRACTION: Within each of the eight subgroups, two authors reviewed all citations independently, with a third independent reviewer resolving any conflicts. DATA SYNTHESIS: Following the systematic review of MEDLINE, EMBASE, and Cochrane Library databases from January 1988 to May 2021, and the consensus process for clinical recommendations and consensus statements, PEACE panel experts constructed research priorities using the Child Health and Nutrition Research Initiative methodology. Twenty research topics were prioritized, falling within five domains (definitions and outcomes, therapeutics, anticoagulant monitoring, protocolized management, and impact of the ECMO circuit and its components on hemostasis). CONCLUSIONS: We present the research priorities identified by the PEACE expert panel after a systematic review of existing evidence informing clinical care of neonates and children managed with ECMO. More research is required within the five identified domains to ultimately inform and improve the care of this vulnerable population.