Device Therapy and Arrhythmia Management in Left Ventricular Assist Device Recipients: A Scientific Statement From the American Heart Association.

Left ventricular assist devices (LVADs) are an increasingly used strategy for the management of patients with advanced heart failure with reduced ejection fraction. Although these devices effectively improve survival, atrial and ventricular arrhythmias are common, predispose these patients to additional risk, and complicate patient management. However, there is no consensus on best practices for the medical management of these arrhythmias or on the optimal timing for procedural interventions in patients with refractory arrhythmias. Although the vast majority of these patients have preexisting cardiovascular implantable electronic devices or cardiac resynchronization therapy, given the natural history of heart failure, it is common practice to maintain cardiovascular implantable electronic device detection and therapies after LVAD implantation. Available data, however, are conflicting on the efficacy of and optimal device programming after LVAD implantation. Therefore, the primary objective of this scientific statement is to review the available evidence and to provide guidance on the management of atrial and ventricular arrhythmias in this unique patient population, as well as procedural interventions and cardiovascular implantable electronic device and cardiac resynchronization therapy programming strategies, on the basis of a comprehensive literature review by electrophysiologists, heart failure cardiologists, cardiac surgeons, and cardiovascular nurse specialists with expertise in managing these patients. The structure and design of commercially available LVADs are briefly reviewed, as well as clinical indications for device implantation. The relevant physiological effects of long-term exposure to continuous-flow circulatory support are highlighted, as well as the mechanisms and clinical significance of arrhythmias in the setting of LVAD support.

A Multi-Institutional Simulation Boot Camp for Pediatric Cardiac Critical Care Nurse Practitioners.

OBJECTIVES: Assess the effect of a simulation "boot camp" on the ability of pediatric nurse practitioners to identify and treat a low cardiac output state in postoperative patients with congenital heart disease. Additionally, assess the pediatric nurse practitioners' confidence and satisfaction with simulation training. DESIGN: Prospective pre/post interventional pilot study. SETTING: University simulation center. SUBJECTS: Thirty acute care pediatric nurse practitioners from 13 academic medical centers in North America. INTERVENTIONS: We conducted an expert opinion survey to guide curriculum development. The curriculum included didactic sessions, case studies, and high-fidelity simulation, based on high-complexity cases, congenital heart disease benchmark procedures, and a mix of lesion-specific postoperative complications. To cover multiple, high-complexity cases, we implemented Rapid Cycle Deliberate Practice method of teaching for selected simulation scenarios using an expert driven checklist. MEASUREMENTS AND MAIN RESULTS: Knowledge was assessed with a pre-/posttest format (maximum score, 100%). A paired-sample t test showed a statistically significant increase in the posttest scores (mean [SD], pre test, 36.8% [14.3%] vs post test, 56.0% [15.8%]; p < 0.001). Time to recognize and treat an acute deterioration was evaluated through the use of selected high-fidelity simulation. Median time improved overall "time to task" across these scenarios. There was a significant increase in the proportion of clinically time-sensitive tasks completed within 5 minutes (pre, 60% [30/50] vs post, 86% [43/50]; p = 0.003] Confidence and satisfaction were evaluated with a validated tool ("Student Satisfaction and Self-Confidence in Learning"). Using a five-point Likert scale, the participants reported a high level of satisfaction (4.7 ± 0.30) and performance confidence (4.8 ± 0.31) with the simulation experience. CONCLUSIONS: Although simulation boot camps have been used effectively for training physicians and educating critical care providers, this was a novel approach to educating pediatric nurse practitioners from multiple academic centers. The course improved overall knowledge, and the pediatric nurse practitioners reported satisfaction and confidence in the simulation experience.

Update on surgical sepsis syndrome.

BACKGROUND: Sepsis is a serious complication in surgical patients, and is associated with prolonged hospital stay and high mortality rates. The definitions of sepsis have been revisited recently. This article reviews how definitions have changed over the years, and provides an update on basic pathobiology and essential aspects of treatment. METHODS: PubMed was searched for reports published in English before October 2016, using the search terms 'surgical sepsis' AND 'surgical ICU'. The reference lists of articles identified in the search were also checked. Other relevant literature was selected based on personal knowledge of developments in the field of sepsis. RESULTS: Sepsis is defined as the presence of infection plus associated organ dysfunction. It occurs as the result of a dysregulated host response to the infection. Prevention of infection is an important means of limiting the development of sepsis. Treatment relies on source control, appropriate antibiotics and organ support. Research continues in an attempt to identify effective immunomodulatory therapies. CONCLUSION: Sepsis is an important and serious complication of surgery, and precautions must be taken to try to prevent infection in surgical patients. If sepsis develops, rapid diagnosis is crucial so that appropriate source control, antimicrobial therapy and organ support can be started early in the course of disease. New techniques enabling a better classification of a patient's particular sepsis profile will enable more personalized therapy.

[Low-flow low-gradient aortic valve stenosis : Current evidence]. / "Low-flow-low-gradient"-Aortenklappenstenose : Aktuelle Evidenz.

Many patients with severe aortic stenosis have a "low-flow, low-gradient" aortic stenosis. The management of these patients can be quite difficult, as these patients often show impairment of the left ventricle, which can lead to false measurements of the severity of stenosis and also leads to a higher risk during aortic valve replacement. More diagnostic tools than only standard echocardiography are needed to correctly differentiate true severe aortic stenosis from pseudo severe aortic stenosis.

[Perioperative Care of Low Cardiac Output Syndrome].

Low cardiac syndrome( LOS) is the imbalance of the oxygen supply and demand at the tissue due to reduced oxygen supply by decreased cardiac function. The causes of the cardiac dysfunction are insufficient cardioplegia, elongation of aortic clamp or cardiopulmonary bypass (CPB) duration, incomplete revascularization, and so on. The preventions of LOS are myocardial protections intraoperatively. The most important myocardial protection is to accomplish more quickly, accurately and safety to operation. And today, cardioplegia is essential for surgery requiring CPB. The integrated myocardia protection is likely to be effective to the patients who suffer low cardiac function. LOS is commonly defined the decreased cardiac index (CI)[<2.0~2.2 l/min/m2], systolic blood pressure (<80~90 mmHg) and the signs of tissue malperfusion, in the absence of hypovolemia. The treatment of LOS is, at first, the correction of hypovolemia, then rhythm control, adjustment of preload and afterload. When it does not recover from LOS despite adequate treatment, the mechanical circulatory assist devices should be introduced without hesitation.

A randomized controlled trial of levosimendan to reduce mortality in high-risk cardiac surgery patients (CHEETAH): Rationale and design.

OBJECTIVE: Patients undergoing cardiac surgery are at risk of perioperative low cardiac output syndrome due to postoperative myocardial dysfunction. Myocardial dysfunction in patients undergoing cardiac surgery is a potential indication for the use of levosimendan, a calcium sensitizer with 3 beneficial cardiovascular effects (inotropic, vasodilatory, and anti-inflammatory), which appears effective in improving clinically relevant outcomes. DESIGN: Double-blind, placebo-controlled, multicenter randomized trial. SETTING: Tertiary care hospitals. INTERVENTIONS: Cardiac surgery patients (n = 1,000) with postoperative myocardial dysfunction (defined as patients with intraaortic balloon pump and/or high-dose standard inotropic support) will be randomized to receive a continuous infusion of either levosimendan (0.05-0.2 µg/[kg min]) or placebo for 24-48 hours. MEASUREMENTS AND MAIN RESULTS: The primary end point will be 30-day mortality. Secondary end points will be mortality at 1 year, time on mechanical ventilation, acute kidney injury, decision to stop the study drug due to adverse events or to start open-label levosimendan, and length of intensive care unit and hospital stay. We will test the hypothesis that levosimendan reduces 30-day mortality in cardiac surgery patients with postoperative myocardial dysfunction. CONCLUSIONS: This trial is planned to determine whether levosimendan could improve survival in patients with postoperative low cardiac output syndrome. The results of this double-blind, placebo-controlled randomized trial may provide important insights into the management of low cardiac output in cardiac surgery.

Delayed extracorporeal membrane oxygenation in children after cardiac surgery: two-institution experience.

OBJECTIVE: There are limited data on the outcomes of children receiving delayed (≥7 days) extracorporeal membrane oxygenation after cardiac surgery. The primary aim of this project is to identify the aetiology and outcomes of extracorporeal membrane oxygenation in children receiving delayed (≥7 days) extracorporeal membrane oxygenation after cardiac surgery. PATIENTS AND METHODS: We conducted a retrospective review of all children ≤18 years supported with delayed extracorporeal membrane oxygenation after cardiac surgery between the period January, 2001 and March, 2012 at the Arkansas Children's Hospital, United States of America, and Royal Children's Hospital, Australia. The data collected in our study included patient demographic information, diagnoses, extracorporeal membrane oxygenation indication, extracorporeal membrane oxygenation support details, medical and surgical history, laboratory, microbiological, and radiographic data, information on organ dysfunction, complications, and patient outcomes. The outcome variables evaluated in this report included: survival to hospital discharge and current survival with emphasis on neurological, renal, pulmonary, and other end-organ function. RESULTS: During the study period, 423 patients undergoing cardiac surgery were supported with extracorporeal membrane oxygenation at two institutions, with a survival of 232 patients (55%). Of these, 371 patients received extracorporeal membrane oxygenation <7 days after cardiac surgery, with a survival of 205 (55%) patients, and 52 patients received extracorporeal membrane oxygenation ≥7 days after cardiac surgery, with a survival of 27 (52%) patients. The median duration of extracorporeal membrane oxygenation run for the study cohort was 5 days (interquartile range: 3, 10). In all, 14 patients (25%) received extracorporeal membrane oxygenation during active cardiopulmonary resuscitation with chest compressions. There were 24 patients (44%) who received dialysis while being on extracorporeal membrane oxygenation. There were eight patients (15%) who had positive blood cultures and four patients (7%) who had positive urine cultures while being on extracorporeal membrane oxygenation. There were nine patients (16%) who had bleeding complications associated with extracorporeal membrane oxygenation runs. There were 10 patients (18%) who had cerebrovascular thromboembolic events associated with extracorporeal membrane oxygenation runs. Of these, 19 patients are still alive with significant comorbidities. CONCLUSIONS: This study demonstrates that mortality outcomes are comparable among children receiving extracorporeal membrane oxygenation ≥7 days and <7 days after cardiac surgery. The proportion of patients receiving extracorporeal membrane oxygenation ≥7 days is small and the aetiology diverse.

Predictors of low cardiac output syndrome after isolated coronary artery bypass grafting.

Low cardiac output syndrome (LCOS) is one of the most important complications following coronary artery bypass grafting (CABG) and results in higher morbidity and mortality. However, few reports have focused on the predictors of LCOS following CABG. This study aimed to evaluate the predictors of LCOS following isolated CABG through the review of 1524 consecutive well-documented patients in a single center, retrospective trial.The relevant preoperative and intraoperative data of patients with complete information from medical records undergoing isolated CABG from January 2010 to December 2013 in our center were investigated and retrospectively analyzed. LCOS was considered when the following criteria were met: signs of impairment of body perfusion and need for inotropic support with vasoactive drugs or mechanical circulatory support with an intra-aortic balloon pump to maintain systolic blood pressure greater than 90 mmHg.LCOS developed in 205 patients following CABG, accounting for 13.5% of the total population. The in-hospital mortality in the LCOS group was significantly higher than that in the non-LCOS group (25.4% versus 1.8%, P < 0.0001). In addition to the length of ICU stay and postoperative hospital stay, LCOS was correlated with negative cerebral, respiratory and renal outcomes. Through univariate analysis and then logistic regression analysis, the predictors of LCOS following CABG included older age (age > 65 years) (OR = 1.85, 95%CI 1.27-3.76), impaired left ventricular function (OR = 2.05, 95%CI 1.53-4.54), on-pump CABG (OR = 2.16, 95%CI 1.53-4.86), emergent CPB (OR = 9.15, 95%CI 3.84-16.49), and incomplete revascularization (OR = 2.62, 95%CI 1.79-5.15).LCOS following isolated CABG caused higher mortality, higher rates of morbidity, and longer ICU and postoperative hospital stays. Older age, impaired left ventricular function, on-pump CABG, emergent CPB, and incomplete revascularization were identified as 5 predictors of LCOS following isolated CABG surgery.

Shoshin Beriberi With Low Cardiac Output and Hemodynamic Deterioration Treated Dramatically by Thiamine Administration.

"Shoshin beriberi", which is a fulminant form of cardiovascular beriberi accompanied by hemodynamic deterioration with high cardiac output and decreased systemic blood pressure, caused by thiamine deficiency due to alcoholic abuse or malnutrition, is often difficult to address because of its rarity and non-specific symptoms. We here present a patient with a history of alcoholic abuse who had suffered hemodynamic deterioration with extremely low cardiac output refractory to extracorporeal membrane oxygenation and intravenous catecholamine support, which was improved dramatically by bolus intravenous thiamine administration. Such a type with low cardiac output would be the most severe form of Shoshin beriberi, and cannot be rescued without diagnostic administration of thiamine.

A multicenter study of primary graft failure after infant heart transplantation: impact of extracorporeal membrane oxygenation on outcomes.

Primary graft failure is the major cause of mortality in infant HTx. The aim of this study was to characterize the indication and outcomes of infants requiring ECMO support due to primary graft failure after HTx. We performed a retrospective review of all infants (<1 yr) who underwent Htx from three institutions. From 1999 to 2008, 92 infants (<1 yr) received Htx. Sixteen children (17%) required ECMO after Htx due to low cardiac output syndrome. Eleven (69%) infants were successfully weaned off ECMO, and 9 (56%) infants were discharged with a mean follow-up of 2.3 ± 2.5 yr. Mean duration of ECMO in survivors was 5.4 days (2-7 days) compared with eight days (2-10 days) in non-survivors (p = NS). The five-yr survival rate for all patients was 75%; however, the five-yr survival rate was 40% in the ECMO cohort vs. 80% in the non-ECMO cohort (p = 0.0001). Graft function within one month post-Htx was similar and normal between ECMO and non-ECMO groups (shortening fraction = 42 ± 3 vs. 40 ± 2, p = NS). For infants, ECMO support for primary graft failure had a lower short-term and long-term survival rate vs. non-ECMO patients. Duration of ECMO did not adversely impact graft function and is an acceptable therapy for infants after HTx for low cardiac output syndrome.

Extracorporeal life support with an integrated left ventricular vent in children with a low cardiac output.

BACKGROUND: The aim of this study was to evaluate our experience in central extracorporeal life support with an integrated left ventricular vent in children with cardiac failure. METHODS: Eight children acquired extracorporeal life support with a left ventricular vent, either after cardiac surgery (n = 4) or during an acute cardiac illness (n = 4). The ascending aorta and right atrium were cannulated. The left ventricular vent was inserted through the right superior pulmonary vein and connected to the venous line on the extracorporeal life support such that active left heart decompression was achieved. RESULTS: No patient died while on support, seven patients were successfully weaned from it and one patient was transitioned to a biventricular assist device. The median length of support was 6 days (range 5-10 days). One patient died while in the hospital, despite successful weaning from extracorporeal life support. No intra-cardiac thrombus or embolic stroke was observed. No patient developed relevant intracranial bleeding resulting in neurological dysfunction during and after extracorporeal life support. CONCLUSIONS: In case of a low cardiac output and an insufficient inter-atrial shunt, additional left ventricular decompression via a vent could help avoid left heart distension and might promote myocardial recovery. In pulmonary dysfunction, separate blood gas analyses from the venous cannula and the left ventricular vent help detect possible coronary hypoxia when the left ventricle begins to recover. We recommend the use of central extracorporeal life support with an integrated left ventricular vent in children with intractable cardiac failure.

Erythrocytosis and severe asphyxia: two different causes of neonatal myocardial infarction.

Neonatal acute myocardial infarction is a rare event that carries a high mortality rate. We describe the cases of two newborns who survived acute myocardial infarction and discuss the management. The first neonate was born with severe asphyxia and left ventricular myocardial infarction with ventricular tachycardia. In this patient, systemic flow was maintained by right-to-left shunting through the patent ductus arteriosus. The second neonate presented with a haematocrit of 80% and an inferolateral myocardial infarction. Intensive treatment of low cardiac output syndrome led to survival of both high-risk neonates. In the follow-up, at 48 and 4 months, respectively, ventricular function recovered in both patients.

[Veno-arterial extracorporeal membrane oxygenation. Indications, limitations and practical implementation]. / Venoarterielle extrakorporale Membranoxygenierung. Indikationen, Limitationen und praktische Anwendung.

Due to the technical advances in pumps, oxygenators and cannulas, veno-arterial extracorporeal membrane oxygenation (va-ECMO) or extracorporeal life support (ECLS) has been widely used in emergency medicine and intensive care medicine for several years. An accepted indication is peri-interventional cardiac failure in cardiac surgery (postcardiotomy low cardiac output syndrome). Furthermore, especially the use of va-ECMO for other indications in critical care medicine, such as in patients with severe sepsis with septic cardiomyopathy or in cardiopulmonary resuscitation has tremendously increased. The basic indications for va-ECMO are therapy refractory cardiac or cardiopulmonary failure. The fundamental purpose of va-ECMO is bridging the function of the lungs and/or the heart. Consequently, this support system does not represent a causal therapy by itself; however, it provides enough time for the affected organ to recover (bridge to recovery) or for the decision for a long-lasting organ substitution by a ventricular assist device or by transplantation (bridge to decision). Although the outcome for bridged patients seems to be favorable, it should not be forgotten that the support system represents an invasive procedure with potentially far-reaching complications. Therefore, the initiation of these systems needs a professional and experienced (interdisciplinary) team, sufficient resources and an individual approach balancing the risks and benefits. This review gives an overview of the indications, complications and contraindications for va-ECMO. It discusses its advantages in organ transplantation and transport of critically ill patients. The reader will learn the differences between peripheral and central cannulation and how to monitor and manage va-ECMO.

[Perioperative management of patients with cardiomyopathies: preface and comments].

Cardiomyopathies are a heterogeneous group of diseases of the myocardium. Cardiomyopathies are characterized by myocardial dysfunction resulting in heart failure due to systolic dysfunction and/or diastolic dysfunction. Prognosis of the patients with cardiomyopathies is usually poor due to progressive heart failure. Sudden death due to serious arrhythmia is not uncommon. Because of the heterogeneity of cardiomyopathies, the perioperative management of the patients with cardiomyopathies varies according to the pathological physiology. Management of low cardiac output is important as well as arrhythmias. Because of arrhythmias such as atrial fibrillation and poor ventricular function, anticoagulation is also important. Through evaluation and management of implantable pacemakers and implantable cardioverter defibrillator are essential.

Cardiac index assessment by the pressure recording analytic method in critically ill unstable patients after cardiac surgery.

OBJECTIVE: The authors measured cardiac index in unstable patients after cardiac surgery with the Pressure Recording Analytic Method (PRAM) and compared it with the reference method of thermodilution (ThD) with the pulmonary artery catheter; using the hypothesis that there were no significant differences between the 2 methods. DESIGN: A prospective study. SETTING: Cardiac surgery intensive care unit in a teaching hospital. PARTICIPANTS: Ninety-four measurements from 59 patients with ongoing high doses of inotropic drugs and/or an intra-aortic balloon pump for low-cardiac-output syndrome after cardiac surgery were studied. INTERVENTIONS: The pulmonary artery catheter and the radial or femoral arterial catheter for measuring blood pressure were already in place for standard hemodynamic monitoring. MEASUREMENTS AND MAIN RESULTS: The mean of the total CI measurements was 2.94 ± 0.67 L/min/m(2) with PRAM and 2.95 ± 0.63 L/min/m(2) with ThD, with no significant difference according to the linear mixed models analysis. The PRAM and ThD techniques were similar in unstable patients without atrial fibrillation (mean bias 0.047 ± 0.395 L/min/m(2) and a percentage error of 29%), while no agreement between PRAM and ThD was found in unstable patients with atrial fibrillation (mean bias 0.195 ± 0.885 L/min/m(2) and a percentage error of 69%). CONCLUSION: Cardiac index measurements after cardiac surgery performed with PRAM and with ThD showed a good agreement in hemodynamically unstable patients given high doses of inotropes and/or an IABP in patients in sinus rhythm, but not in those with atrial fibrillation.

Temporary atrial pacing for cardiac output after pediatric cardiac surgery.

Pediatric cardiothoracic surgery is often associated with low cardiac output in the postoperative period. This study sought to determine whether increasing heart rate via temporary atrial pacing is beneficial in augmenting cardiac output. Patients younger than 18 years who underwent cardiothoracic surgery and had no perioperative arrhythmias were eligible for the study. Patients not paced postoperatively were atrial paced at a rate of 15 % above the intrinsic sinus rate (not to exceed 170 beats per minute, less for older patients) for 15 min. Patients paced for cardiac output postoperatively had their pacemakers paused for 15 min. Markers of cardiac output were measured before and after the intervention. Of the 60 patients who consented to participate, 30 completed the study. Failure to complete the study was due to tachycardia (n = 13), lack of pacing wires (n = 7), junctional rhythm (n = 4), advanced atrioventricular block (n = 3), and other cause (n = 3). Three patients were paced at baseline. There was no change in arteriovenous oxygen saturation difference, mean arterial blood pressure, central venous pressure, toe temperature, or lactate with atrial pacing. Atrial pacing was associated with a decrease in head and flank near-infrared spectroscopy (p = 0.01 and <0.01 respectively). Secondary analysis found an inverse relationship between mean arterial pressure response to pacing and bypass time. Temporary atrial pacing does not improve cardiac output after pediatric cardiac surgery and may be deleterious. Future research may identify subsets of patients who benefit from this strategy. Practitioners considering this strategy should carefully evaluate each patient's response to atrial pacing before its implementation.

Role of intraoperative regional oxygen saturation using near infrared spectroscopy in the prediction of low output syndrome after pediatric heart surgery.

BACKGROUND: We report on the applicability of intraoperative regional oxygen saturation (rSO2) desaturation score by near-infrared spectroscopy in the early detection of postoperative low output state (LOS) in infants with congenital heart disease who underwent cardiac surgery. MATERIALS AND METHODS: Between July and October 2011 the intra- and immediate postoperative courses of 22 patients undergoing elective cardiac surgery for congenital heart disease were analyzed. The intraoperative cerebral and somatic rSO2 were measured and a rSO2 desaturation score calculated (by multiplying the rSO2 below 50% of the threshold by seconds). The aim of the study was to evaluate the applicability of intraoperative rSO2 de-saturation score in the early detection of postoperative LOS. RESULTS: Thirteen of 22 patients (62%) had an intraoperative cerebral rSO2 desaturation score >3000% per second. Patients with a rSO2 de-saturation score >3000% per second had a significantly lower intraoperative central venous saturation (SvO2, p = 0.002), cardiac index (CI, p = 0.004), oxygen availability indexed (DO2I, p = 0.0004), and a significantly higher extraction of oxygen (ERO2, p = 0.0005) when compared to patients with a rSO2 desaturation score <3000% per second. Nine patients had postoperative LOS; all of them had an intraoperative rSO2 de-saturation score >3000% per second (9/13 patients, 69%; p = 0.001) requiring prompt treatment with major inotropic support, surface hypothermia, and extracorporeal membrane oxygenation (ECMO) support (n = 4). Twenty-one patients survived. One patient died from ventricular failure and inability to wean from ECMO support. CONCLUSION: The intraoperative use of NIRS provided an early warning sign of hemodynamic or metabolic compromise, enabling early and rapid intervention to prevent or reduce the severity of potentially life-threatening complications.

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.