Capillary refill time assessment after fluid challenge in patients on venoarterial extracorporeal membrane oxygenation: A retrospective study.

BACKGROUND: Monitoring fluid therapy is challenging in patients assisted with Veno-arterial ECMO. The aim of our study was to evaluate the usefulness of capillary refill time to assess the response to fluid challenge in patients assisted with VA-ECMO. METHODS: Retrospective monocentric study in a cardiac surgery ICU. We assess fluid responsiveness after a fluid challenge in patients on VA-ECMO. We recorded capillary refill time before and after fluid challenge and the evolution of global hemodynamic parameters. RESULTS: A total of 27 patients were included. The main indications for VA-ECMO were post-cardiotomy cardiogenic shock (44%). Thirteen patients (42%) were responders and 14 non-responders (58%). In the responder group, the index CRT decreased significantly (1.7 [1.5; 2.1] vs. 1.2 [1; 1.3] s; p = 0.01), whereas it remained stable in the non-responder group (1.4 [1.1; 2.5] vs. 1.6 [0.9; 1.9] s; p = 0.22). Diagnosis performance of CRT variation to assess response after fluid challenge shows an AUC of 0.68 (p = 0.10) with a sensitivity of 79% [95% CI, 52-92] and a specificity of 69% [95% CI, 42-87], with a threshold at 23%. CONCLUSION: In patients treated with VA-ECMO index capillary refill time is a reliable tool to assesses fluid responsiveness. SPECIALTY: Critical care, Cardiac surgery, ECMO.

A new machine learning algorithm to predict veno-arterial ECMO implantation after post-cardiotomy low cardiac output syndrome.

BACKGROUND: Post-cardiotomy low cardiac output syndrome (PC-LCOS) is a life-threatening complication after cardiac surgery involving a cardiopulmonary bypass (CPB). Mechanical circulatory support with veno-arterial membrane oxygenation (VA-ECMO) may be necessary in the case of refractory shock. The objective of the study was to develop a machine-learning algorithm to predict the need for VA-ECMO implantation in patients with PC-LCOS. PATIENTS AND METHODS: Patients were included in the study with moderate to severe PC-LCOS (defined by a vasoactive inotropic score (VIS) > 10 with clinical or biological markers of impaired organ perfusion or need for mechanical circulatory support after cardiac surgery) from two university hospitals in Paris, France. The Deep Super Learner, an ensemble machine learning algorithm, was trained to predict VA-ECMO implantation using features readily available at the end of a CPB. Feature importance was estimated using Shapley values. RESULTS: Between January 2016 and December 2019, 285 patients were included in the development dataset and 190 patients in the external validation dataset. The primary outcome, the need for VA-ECMO implantation, occurred respectively, in 16% (n = 46) and 10% (n = 19) in the development and the external validation datasets. The Deep Super Learner algorithm achieved a 0.863 (0.793-0.928) ROC AUC to predict the primary outcome in the external validation dataset. The most important features were the first postoperative arterial lactate value, intraoperative VIS, the absence of angiotensin-converting enzyme treatment, body mass index, and EuroSCORE II. CONCLUSIONS: We developed an explainable ensemble machine learning algorithm that could help clinicians predict the risk of deterioration and the need for VA-ECMO implantation in moderate to severe PC-LCOS patients.

Weaning from veno-arterial extra-corporeal membrane oxygenation: which strategy to use?

Refractory cardiogenic shock patients may be rescued by veno-arterial extracorporeal membrane oxygenation (VA ECMO). After a few days of mechanical assistance, the device can sometimes be successfully removed if the patient has partially or fully recovered from the condition that required the use of ECMO. The percentage of patients with refractory cardiogenic shock who are successfully weaned from ECMO varies from 31% to 76%. Weaning does not mean survival, because 20% to 65% of patients weaned from VA ECMO support do not survive to hospital discharge. The high death rate after successful weaning shows that many questions remain unresolved in this field. In this review, we will discuss the various factors influencing survival and a successful weaning from VA ECMO, in addition to weaning approaches proposed in the literature. Based on this information, we will propose a strategy to optimize the weaning process.