Prognostic models for mortality risk in patients requiring ECMO

Abstract

Purpose: To provide an overview and evaluate the performance of mortality prediction models for patients requiring extracorporeal membrane oxygenation (ECMO) support for refractory cardiocirculatory or respiratory failure.Methods: A systematic literature search was undertaken to identify studies developing and/or validating multivariable prediction models for all-cause mortality in adults requiring or receiving veno-arterial (V-A) or veno-venous (V-V) ECMO. Estimates of model performance (observed versus expected (O:E) ratio and c-statistic) were summarized using random effects models and sources of heterogeneity were explored by means of meta-regression. Risk of bias was assessed using the Prediction model Risk Of BiAS Tool (PROBAST).Results: Among 4905 articles screened, 96 studies described a total of 58 models and 225 external validations. Out of all 58 models which were specifically developed for ECMO patients, 14 (24%) were ever externally validated. Discriminatory ability of frequently validated models developed for ECMO patients (i.e., SAVE and RESP score) was moderate on average (pooled c-statistics between 0.66 and 0.70), and comparable to general intensive care population-based models (pooled c-statistics varying between 0.66 and 0.69 for the Simplified Acute Physiology Score II (SAPS II), Acute Physiology and Chronic Health Evaluation II (APACHE II) score and Sequential Organ Failure Assessment (SOFA) score). Nearly all models tended to underestimate mortality with a pooled O:E > 1. There was a wide variability in reported performance measures of external validations, reflecting a large between-study heterogeneity. Only 1 of the 58 models met the generally accepted Prediction model Risk Of BiAS Tool criteria of good quality. Importantly, all predicted outcomes were conditional on the fact that ECMO support had already been initiated, thereby reducing their applicability for patient selection in clinical practice. Conclusions:A large number of mortality prediction models have been developed for ECMO patients, yet only a minority has been externally validated. Furthermore, we observed only moderate predictive performance, large heterogeneity between-study populations and model performance, and poor methodological quality overall. Most importantly, current models are unsuitable to provide decision support for selecting individuals in whom initiation of ECMO would be most beneficial, as all models were developed in ECMO patients only and the decision to start ECMO had, therefore, already been made.

Days spent on non-invasive ventilation support: can it determine when to initiate VV- ECMO? Observational study in a cohort of Covid-19 patients

“…We suggest, based on our findings, that the time spent between NIV support and initiation of VV-ECMO should be considered and evaluated as an interesting clinical parameter to be included in the mortality prediction scores for VV-ECMO although further and larger studies are needed to confirm our findings [ 32 ].…”

Retrospective analysis of factors associated with outcome in veno-venous extra-corporeal membrane oxygenation

“…It is here worth to mention that most non-ARDS patients in our cohort underwent VV-ECMO before or after LTx, and such patients were not specifically included in the model applied to develop the RESP score [ 25 , 37 ]. In addition, in a recent study evaluating several mortality prediction scores, the RESP score had only a moderate discriminative performance [ 38 ]. Second, patients in the non-ARDS group suffered from pathologies more rapidly reversible than ARDS (e.g.…”

Clinical decision support for ExtraCorporeal Membrane Oxygenation: Will we fly by wire?

“…We recently summarized all existing prognostic models in the setting of ECMO and identified a total of 58 models that were specifically designed to predict mortality based on variables collected shortly before or after initiation of ECMO. 15 Discriminative performance of frequently externally validated models 7 , 8 ( Table 1 ) was moderate on average but highly variable across different external validation cohorts. Most importantly, all models were based on cohorts in which ECMO had already been initiated.…”