Extracorporeal Support Prognostication-Time to Move the Goal Posts?

Carboxyhemoglobin predicts oxygenator performance and imminent oxygenator change in extracorporeal membrane oxygenation

BACKGROUND

The continuous exposure of blood to a non-biological surface during extracorporeal membrane oxygenation (ECMO) may lead to progressive thrombus formation in the oxygenator, hemolysis and consequently impaired gas exchange. In most centers oxygenator performance is monitored only on a once daily basis. Carboxyhemoglobin (COHb) is generated upon red cell lysis and is routinely measured with any co-oximetry performed to surveille gas exchange and acid-base homeostasis every couple of hours. This retrospective cohort study aims to evaluate COHb in the arterial blood gas as a novel marker of oxygenator dysfunction and its predictive value for imminent oxygenator change.

RESULTS

Out of the 484 screened patients on ECMO 89, cumulatively requiring 116 oxygenator changes within 1833 patient days, including 19,692 arterial COHb measurements were analyzed. Higher COHb levels were associated with lower post-oxygenator pO2 (estimate for log(COHb): - 2.176 [95% CI - 2.927, - 1.427], p < 0.0001) and with a shorter time to oxygenator change (estimate for log(COHb): - 67.895 [95% CI - 74.209, - 61.542] hours, p < 0.0001). COHb was predictive of oxygenator change within 6 h (estimate for log(COHb): 5.027 [95% CI 1.670, 15.126], p = 0.004).

CONCLUSION

COHb correlates with oxygenator performance and can be predictive of imminent oxygenator change. Therefore, longitudinal measurements of COHb in clinical routine might be a cheap and more granular candidate for ECMO surveillance that should be further analyzed in a controlled prospective trial design.

A Deep Learning Framework for Predicting Patient Decannulation on Extracorporeal Membrane Oxygenation Devices: Development and Model Analysis Study

BACKGROUND

Venovenous extracorporeal membrane oxygenation (VV-ECMO) is a therapy for patients with refractory respiratory failure. The decision to decannulate someone from extracorporeal membrane oxygenation (ECMO) often involves weaning trials and clinical intuition. To date, there are limited prognostication metrics to guide clinical decision-making to determine which patients will be successfully weaned and decannulated.

OBJECTIVE

This study aims to assist clinicians with the decision to decannulate a patient from ECMO, using Continuous Evaluation of VV-ECMO Outcomes (CEVVO), a deep learning-based model for predicting success of decannulation in patients supported on VV-ECMO. The running metric may be applied daily to categorize patients into high-risk and low-risk groups. Using these data, providers may consider initiating a weaning trial based on their expertise and CEVVO.

METHODS

Data were collected from 118 patients supported with VV-ECMO at the Columbia University Irving Medical Center. Using a long short-term memory-based network, CEVVO is the first model capable of integrating discrete clinical information with continuous data collected from an ECMO device. A total of 12 sets of 5-fold cross validations were conducted to assess the performance, which was measured using the area under the receiver operating characteristic curve (AUROC) and average precision (AP). To translate the predicted values into a clinically useful metric, the model results were calibrated and stratified into risk groups, ranging from 0 (high risk) to 3 (low risk). To further investigate the performance edge of CEVVO, 2 synthetic data sets were generated using Gaussian process regression. The first data set preserved the long-term dependency of the patient data set, whereas the second did not.

RESULTS

CEVVO demonstrated consistently superior classification performance compared with contemporary models (P<.001 and P=.04 compared with the next highest AUROC and AP). Although the model's patient-by-patient predictive power may be too low to be integrated into a clinical setting (AUROC 95% CI 0.6822-0.7055; AP 95% CI 0.8515-0.8682), the patient risk classification system displayed greater potential. When measured at 72 hours, the high-risk group had a successful decannulation rate of 58% (7/12), whereas the low-risk group had a successful decannulation rate of 92% (11/12; P=.04). When measured at 96 hours, the high- and low-risk groups had a successful decannulation rate of 54% (6/11) and 100% (9/9), respectively (P=.01). We hypothesized that the improved performance of CEVVO was owing to its ability to efficiently capture transient temporal patterns. Indeed, CEVVO exhibited improved performance on synthetic data with inherent temporal dependencies (P<.001) compared with logistic regression and a dense neural network.

CONCLUSIONS

The ability to interpret and integrate large data sets is paramount for creating accurate models capable of assisting clinicians in risk stratifying patients supported on VV-ECMO. Our framework may guide future incorporation of CEVVO into more comprehensive intensive care monitoring systems.

Validation of extracorporeal membrane oxygenation mortality prediction and severity of illness scores in an international COVID-19 cohort

BACKGROUND

Veno-venous extracorporeal membrane oxygenation (V-V ECMO) is a lifesaving support modality for severe respiratory failure, but its resource-intensive nature led to significant controversy surrounding its use during the COVID-19 pandemic. We report the performance of several ECMO mortality prediction and severity of illness scores at discriminating survival in a large COVID-19 V-V ECMO cohort.

METHODS

We validated ECMOnet, PRESET (PREdiction of Survival on ECMO Therapy-Score), Roch, SOFA (Sequential Organ Failure Assessment), APACHE II (acute physiology and chronic health evaluation), 4C (Coronavirus Clinical Characterisation Consortium), and CURB-65 (Confusion, Urea nitrogen, Respiratory Rate, Blood Pressure, age >65 years) scores on the ISARIC (International Severe Acute Respiratory and emerging Infection Consortium) database. We report discrimination via Area Under the Receiver Operative Curve (AUROC) and Area under the Precision Recall Curve (AURPC) and calibration via Brier score.

RESULTS

We included 1147 patients and scores were calculated on patients with sufficient variables. ECMO mortality scores had AUROC (0.58-0.62), AUPRC (0.62-0.74), and Brier score (0.286-0.303). Roch score had the highest accuracy (AUROC 0.62), precision (AUPRC 0.74) yet worst calibration (Brier score of 0.3) despite being calculated on the fewest patients (144). Severity of illness scores had AUROC (0.52-0.57), AURPC (0.59-0.64), and Brier Score (0.265-0.471). APACHE II had the highest accuracy (AUROC 0.58), precision (AUPRC 0.64), and best calibration (Brier score 0.26).

CONCLUSION

Within a large international multicenter COVID-19 cohort, the evaluated ECMO mortality prediction and severity of illness scores demonstrated inconsistent discrimination and calibration highlighting the need for better clinically applicable decision support tools.

Early Changes in Arterial Partial Pressure of Carbon Dioxide and Blood Pressure After Starting Extracorporeal Membrane Oxygenation in Children: Extracorporeal Life Support Organization Database Study of Neurologic Complications

OBJECTIVE

Neurologic complications in pediatric patients supported by extracorporeal membrane oxygenation (ECMO) are common and lead to morbidity and mortality; however, few modifiable factors are known.

DESIGN

Retrospective study of the Extracorporeal Life Support Organization registry (2010-2019).

SETTING

Multicenter international database.

PATIENTS

Pediatric patients receiving ECMO (2010-2019) for all indications and any mode of support.

INTERVENTIONS

None.

MEASUREMENTS AND MAIN RESULTS

We investigated if early relative change in Pa co2 or mean arterial blood pressure (MAP) soon after starting ECMO was associated with neurologic complications. The primary outcome of neurologic complications was defined as a report of seizures, central nervous system infarction or hemorrhage, or brain death. All-cause mortality (including brain death) was used as a secondary outcome.Out of 7,270 patients, 15.6% had neurologic complications. Neurologic complications increased when the relative Pa co2 decreased by greater than 50% (18.4%) or 30-50% (16.5%) versus those who had a minimal change (13.9%, p < 0.01 and p = 0.046). When the relative MAP increased greater than 50%, the rate of neurologic complications was 16.9% versus 13.1% those with minimal change ( p = 0.007). In a multivariable model adjusting for confounders, a relative decrease in Pa co2 greater than 30% was independently associated with greater odds of neurologic complication (odds ratio [OR], 1.25; 95% CI, 1.07-1.46; p = 0.005). Within this group, with a relative decrease in Pa co2 greater than 30%, the effects of increased relative MAP increased neurologic complications (0.05% per BP Percentile; 95% CI, 0.001-0.11; p = 0.05).

CONCLUSIONS

In pediatric patients, a large decrease in Pa co2 and increase in MAP following ECMO initiation are both associated with neurologic complications. Future research focusing on managing these issues carefully soon after ECMO deployment can potentially help to reduce neurologic complications.

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.

Prognostic models for mortality risk in patients requiring ECMO

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.

Utilizing big data from electronic health records in pediatric clinical care

Big data has the capacity to transform both pediatric healthcare delivery and research, but its potential has yet to be fully realized. Curation of large multi-institutional datasets of high-quality data has allowed for significant advances in the timeliness of quality improvement efforts. Improved access to large datasets and computational power have also paved the way for the development of high-performing, data-driven decision support tools and precision medicine approaches. However, implementation of these approaches and tools into pediatric practice has been hindered by challenges in our ability to adequately capture the heterogeneity of the pediatric population as well as the nuanced complexities of pediatric diseases such as sepsis. Moreover, there are large gaps in knowledge and definitive evidence demonstrating the utility, usability, and effectiveness of these types of tools in pediatric practice, which presents significant challenges to provider willingness to leverage these solutions. The next wave of transformation for pediatric healthcare delivery and research through big data and sophisticated analytics will require focusing efforts on strategies to overcome cultural barriers to adoption and acceptance. IMPACT: Big data from EHRs can be used to drive improvement in pediatric clinical care. Clinical decision support, artificial intelligence, machine learning, and precision medicine can transform pediatric care using big data from the EHR. This article provides a review of barriers and enablers for the effective use of data analytics in pediatric clinical care using pediatric sepsis as a use case. The impact of this review is that it will inform influencers of pediatric care about the importance of current trends in data analytics and its use in improving outcomes of care through EHR-based strategies.

Outcomes of patients with acute respiratory failure on veno-venous extracorporeal membrane oxygenation requiring additional circulatory support by veno-venoarterial extracorporeal membrane oxygenation

Objective

Veno-venous (V-V) extracorporeal membrane oxygenation (ECMO) is increasingly used to support patients with severe acute respiratory distress syndrome (ARDS). In case of additional cardio-circulatory failure, some experienced centers upgrade the V-V ECMO with an additional arterial return cannula (termed V-VA ECMO). Here we analyzed short- and long-term outcome together with potential predictors of mortality.

Design

Multicenter, retrospective analysis between January 2008 and September 2021.

Setting

Three tertiary care ECMO centers in Germany (Hannover, Bonn) and Switzerland (Zurich).

Patients

Seventy-three V-V ECMO patients with ARDS and additional acute cardio-circulatory deterioration required an upgrade to V-VA ECMO were included in this study.

Measurements and main results

Fifty-three patients required an upgrade from V-V to V-VA and 20 patients were directly triple cannulated. Median (Interquartile Range) age was 49 (28–57) years and SOFA score was 14 (12–17) at V-VA ECMO upgrade. Vasoactive-inotropic score decreased from 53 (12–123) at V-VA ECMO upgrade to 9 (3–37) after 24 h of V-VA ECMO support. Weaning from V-VA and V-V ECMO was successful in 47 (64%) and 40 (55%) patients, respectively. Duration of ECMO support was 12 (6–22) days and ICU length of stay was 32 (16–46) days. Overall ICU mortality was 48% and hospital mortality 51%. Two additional patients died after hospital discharge while the remaining patients survived up to two years (with six patients being lost to follow-up). The vast majority of patients was free from higher degree persistent organ dysfunction at follow-up. A SOFA score > 14 and higher lactate concentrations at the day of V-VA upgrade were independent predictors of mortality in the multivariate regression analysis.

Conclusion

In this analysis, the use of V-VA ECMO in patients with ARDS and concomitant cardiocirculatory failure was associated with a hospital survival of about 50%, and most of these patients survived up to 2 years. A SOFA score > 14 and elevated lactate levels at the day of V-VA upgrade predict unfavorable outcome.