Factors associated with 30-day in-hospital mortality in critically ill adult patients receiving extracorporeal membrane oxygenation: A retrospective cohort study

COMPREHENSIVE CHARACTERIZATION OF CYTOKINES IN PATIENTS UNDER EXTRACORPOREAL MEMBRANE OXYGENATION: EVIDENCE FROM INTEGRATED BULK AND SINGLE-CELL RNA SEQUENCING DATA USING MULTIPLE MACHINE LEARNING APPROACHES

ABSTRACT

Background : Extracorporeal membrane oxygenation (ECMO) is an effective technique for providing short-term mechanical support to the heart, lungs, or both. During ECMO treatment, the inflammatory response, particularly involving cytokines, plays a crucial role in pathophysiology. However, the potential effects of cytokines on patients receiving ECMO are not comprehensively understood. Methods : We acquired three ECMO support datasets, namely two bulk and one single-cell RNA sequencing (RNA-seq), from the Gene Expression Omnibus (GEO) combined with hospital cohorts to investigate the expression pattern and potential biological processes of cytokine-related genes (CRGs) in patients under ECMO. Subsequently, machine learning approaches, including support vector machine (SVM), random forest (RF), modified Lasso penalized regression, extreme gradient boosting (XGBoost), and artificial neural network (ANN), were applied to identify hub CRGs, thus developing a prediction model called CRG classifier. The predictive and prognostic performance of the model was comprehensively evaluated in GEO and hospital cohorts. Finally, we mechanistically analyzed the relationship between hub cytokines, immune cells, and pivotal molecular pathways. Results : Analyzing bulk and single-cell RNA-seq data revealed that most CRGs were significantly differentially expressed; the enrichment scores of cytokine and cytokine-cytokine receptor (CCR) interaction were significantly higher during ECMO. Based on multiple machine learning algorithms, nine key CRGs (CCL2, CCL4, IFNG, IL1R2, IL20RB, IL31RA, IL4, IL7, and IL7R) were used to develop the CRG classifier. The CRG classifier exhibited excellent prognostic values (AUC > 0.85), serving as an independent risk factor. It performed better in predicting mortality and yielded a larger net benefit than other clinical features in GEO and hospital cohorts. Additionally, IL1R2, CCL4, and IL7R were predominantly expressed in monocytes, NK cells, and T cells, respectively. Their expression was significantly positively correlated with the relative abundance of corresponding immune cells. Gene set variation analysis (GSVA) revealed that para-inflammation, complement and coagulation cascades, and IL6/JAK/STAT3 signaling were significantly enriched in the subgroup that died after receiving ECMO. Spearman correlation analyses and Mantel tests revealed that the expression of hub cytokines (IL1R2, CCL4, and IL7R) and pivotal molecular pathways scores (complement and coagulation cascades, IL6/JAK/STAT3 signaling, and para-inflammation) were closely related. Conclusion : A predictive model (CRG classifier) comprising nine CRGs based on multiple machine learning algorithms was constructed, potentially assisting clinicians in guiding individualized ECMO treatment. Additionally, elucidating the underlying mechanistic pathways of cytokines during ECMO will provide new insights into its treatment.

Development and external validation of a machine learning model for brain injury in pediatric patients on extracorporeal membrane oxygenation

BACKGROUND

Patients supported by extracorporeal membrane oxygenation (ECMO) are at a high risk of brain injury, contributing to significant morbidity and mortality. This study aimed to employ machine learning (ML) techniques to predict brain injury in pediatric patients ECMO and identify key variables for future research.

METHODS

Data from pediatric patients undergoing ECMO were collected from the Chinese Society of Extracorporeal Life Support (CSECLS) registry database and local hospitals. Ten ML methods, including random forest, support vector machine, decision tree classifier, gradient boosting machine, extreme gradient boosting, light gradient boosting machine, Naive Bayes, neural networks, a generalized linear model, and AdaBoost, were employed to develop and validate the optimal predictive model based on accuracy and area under the curve (AUC). Patients were divided into retrospective cohort for model development and internal validation, and one cohort for external validation.

RESULTS

A total of 1,633 patients supported by ECMO were included in the model development, of whom 181 experienced brain injury. In the external validation cohort, 30 of the 154 patients experienced brain injury. Fifteen features were selected for the model construction. Among the ML models tested, the random forest model achieved the best performance, with an AUC of 0.912 for internal validation and 0.807 for external validation.

CONCLUSION

The Random Forest model based on machine learning demonstrates high accuracy and robustness in predicting brain injury in pediatric patients supported by ECMO, with strong generalization capabilities and promising clinical applicability.

Prevalence and risk factors for in-hospital mortality of adult patients on veno-arterial extracorporeal membrane oxygenation for cardiogenic shock and cardiac arrest: A systematic review and meta-analysis

OBJECTIVES

To synthesize quantitative research findings on the prevalence and risk factors for in-hospital mortality of patients on veno-arterial extracorporeal membrane oxygenation (VA-ECMO).

METHODS

A comprehensive search was conducted for the period from May 2008 to December 2023 by searching the five electronic databases of PubMed, CINAHL, Web of Science, EMBASE, and Cochrane library. The quality of included studies was assessed using the Newcastle-Ottawa scale. The meta-analysis estimated the pooled odds ratio or standard mean difference and 95% confidence intervals.

RESULTS

A total of twenty-five studies with 10,409 patients were included in the analysis. The overall in-hospital mortality of patients on VA-ECMO was 56.7 %. In the subgroup analysis, in-hospital mortality of VA-ECMO for cardiogenic shock and cardiac arrest was 49.2 % and 75.2 %, respectively. The number of significant factors associated with an increased risk of in-hospital mortality in the pre-ECMO period (age, body weight, creatinine, chronic kidney disease, pH, and lactic acid) was greater than that in the intra- and post-ECMO periods. Renal replacement, bleeding, and lower limb ischemia were the most significant risk factors for in-hospital mortality in patients receiving VA-ECMO.

CONCLUSION

Early detection of the identified risk factors can contribute to reducing in-hospital mortality in patients on VA-ECMO. Intensive care unit nurses should provide timely and appropriate care before, during, and after VA-ECMO.

IMPLICATIONS FOR CLINICAL PRACTICE

Intensive care unit nurses should be knowledgeable about factors associated with the in-hospital mortality of patients on VA-ECMO to improve outcomes. The present findings may contribute to developing guidelines for reducing in-hospital mortality among patients considering ECMO.

Do patients receiving extracorporeal membrane-oxygenation need antibiotic prophylaxis? A systematic review and meta-analysis on 7,996 patients

BACKGROUND

Patients undergoing Extracorporeal Membrane Oxygenation (ECMO) are particularly susceptible to infections: 42% experience sepsis and 26% develop a nosocomial infection (NI). Whether antibiotic prophylaxis is effective in reducing mortality and its effects on the rate of NIs is currently unclear.

RESEARCH QUESTION

Can antibiotic prophylaxis decrease 30-day mortality for patients on ECMO? Can antibiotic prophylaxis prevent the occurrence of NIs in these patients?

STUDY DESIGN AND METHODS

A systematic review and meta-analysis was conducted. We searched PubMed, Scopus, and CINAHL libraries from inception to June 12, 2024. Two researchers were involved in abstract screening and three researchers were involved in full text selection.

RESULTS

A pooled population of 7,996 patients is represented by 5 retrospective studies. Reported mortality ranges between 46 and 58% and the NIs rate is between 14 and 62%. Regarding 30-day mortality, the random-effects model (I2 = 65%) indicates a non-statistically significant difference between the antibiotic prophylaxis group and the non-prophylaxis group (OR 0.76; 95%CI 0.37-1.59). For the NIs rate, a fixed-effect model (I2 = 36%) shows an OR of 0.81 (95%CI 0.71-0.92) in favor of the antibiotic prophylaxis group, with a number-needed-to-treat (NNT) of 39.7 patients.

CONCLUSION

According to a very low degree of certainty, antibiotic prophylaxis appears to have no impact on the 30-day mortality rate of ECMO recipients. The risk of NIs seems to decrease with antibiotic prophylaxis, even though the NNT is high. Prospective high-quality studies that address these specific clinical questions are necessary.

CLINICAL TRIAL REGISTRATION

PROSPERO: International prospective register of systematic reviews, 2024, CRD42024567037.

Effect of an evidence-based early rehabilitation program on adult patients with venovenous extracorporeal membrane oxygenation: A cohort study

OBJECTIVES

To assess the efficacy of early rehabilitation program for VV-ECMO patients and observe the influence on the respiratory and skeletal muscles.

DESIGN

A cohort study.

SETTING

The study was conducted with VVECMO patients in a comprehensive ICU with 32 beds.

MAIN OUTCOME MEASURES

Ultrasound measurements were performed on each patients on day 1, 4, 7, 10, and 14, including diaphragmatic excursion (DE), diaphragmatic thickening fraction (DTF), intercostal muscle thickening fraction (ICMTF), thickness of the rectus femoris (RF), thickness of vastus intermedius (VI), and rectus femoris cross-sectional area (RF-CSA). Data on basic characteristics, results of ultrasound measurements, patients outcomes and adverse events were collected.

RESULTS

22 patients received usual rehabilitation measures were set as the control group and 23 patients underwent early rehabilitation program were set as the study group. There were no differences in diaphragmatic excursion, diaphragmatic thickening fraction, intercostal muscle thickening fraction, thickness of rectus femoris, thickness of vastus intermedius, rectus femoris cross-sectional area between two groups on day 1 after VV-ECMO treatment (P > 0.05). The variation of diaphragmatic thickening fraction and intercostal muscle thickening fraction decreased on the day 7 and 14 after treatment (P < 0.05). The variation of vastus intermedius thickness and rectus femoris cross-sectional area in the study group was less compared with those in the control group on day 4, 7, 10 and 14. The ECMO duration in the study group was shorter than that in the control group (12.00 [10.00-16.25] days vs. 8.00 [6.00-12.25] days, P = 0.002), but there was no difference in the duration of mechanical ventilation.

CONCLUSION

Early rehabilitation program can ameliorate muscle atrophy. We recommend implementation of our rehabilitation program in VV-ECMO patients. This program can improve skeletal muscle atrophy and dysfunction in patients with VV-ECMO effectively and perhaps improve quality of life for patients in the future.

IMPLICATIONS FOR CLINICAL PRACTICE

Early rehabilitation program put higher demands bedside nurses. It requires them to observe conditions of VVECMO patients closely, assess the feasibility of rehabilitation promptly, and monitor for any adverse reactions. Ultrasound measurement is a noninvasive and useful tool to assess muscle atrophy in ICU patients. Early rehabilitation program can improve skeletal muscle atrophy and dysfunction in patients with VV-ECMO effectively.

Risk factors for neurological disability outcomes in patients under extracorporeal membrane oxygenation following cardiac arrest: An observational study

OBJECTIVES

This study aimed to identify factors associated with neurological and disability outcomes in patients who underwent ECMO following cardiac arrest.

METHODS

This retrospective, single-center, observational study included adult patients who received ECMO treatment for in-hospital cardiac arrest (IHCA) or out-of-hospital cardiac arrest (OHCA) between February 2016 and March 2020. Factors associated with neurological and disability outcomes in these patients who underwent ECMO were assessed.

SETTING

Hamad General Hospital, Qatar.

MAIN OUTCOME MEASURES

Neurological disability outcomes were assessed using the Modified Rankin Scale (mRS) and the Cerebral Performance Category (CPC) scale.

RESULTS

Among the 48 patients included, 37 (77 %) experienced OHCA, and 11 (23 %) had IHCA. The 28-day survival rate was 14 (29.2 %). Of the survivors, 9 (64.3 %) achieved a good neurological outcome, while 5 (35.7 %) experienced poor neurological outcomes. Regarding disability, 5 (35.7 %) of survivors had no disability, while 9 (64.3 %) had some form of disability. The results showed significantly shorter median time intervals in minutes, including collapse to cardiopulmonary resuscitation (CPR) (3 vs. 6, P = 0.001), CPR duration (12 vs. 35, P = 0.001), CPR to extracorporeal cardiopulmonary resuscitation (ECPR) (20 vs. 40, P = 0.001), and collapse-to-ECPR (23 vs. 45, P = 0.001), in the good outcome group compared to the poor outcome group.

CONCLUSION

This study emphasizes the importance of minimizing the time between collapse and CPR/ECMO initiation to improve neurological outcomes and reduce disability in cardiac arrest patients. However, no significant associations were found between outcomes and other demographic or clinical variables in this study. Further research with a larger sample size is needed to validate these findings.

IMPLICATIONS FOR CLINICAL PRACTICE

The study underscores the significance of reducing the time between collapse and the initiation of CPR and ECMO. Shorter time intervals were associated with improved neurological outcomes and reduced disability in cardiac arrest patients.

The occurrence of pressure injuries and related risk factors in patients undergoing extracorporeal membrane oxygenation for respiratory failure: A retrospective single centre study

INTRODUCTION

Limited data is available regarding the incidence of pressure injuries in patients who have undergone Extracorporeal Membrane Oxygenation (ECMO), a life-saving technique that provides respiratory support for hypoxemia that does not respond to conventional treatment.

AIM

To assess the incidence of pressure injuries and identify the risk factors in Acute Respiratory Distress Syndrome patients receiving ECMO.

METHODS

A retrospective observational study utilizing prospectively collected data was performed in an Italian intensive care unit, between 1 January 2012 and 30 April 2022 enrolling all consecutive patients with Acute Respiratory Distress Syndrome who underwent ECMO.

RESULTS

One hundred patients were included in this study. 67 patients (67%) developed pressure injuries during their intensive care unit stay, with a median of 2 (1-3) sites affected. The subgroup of patients with pressure injuries was more hypoxic before ECMO implementation, received more frequent continuous renal replacement therapy and prone positioning, and showed prolonged ECMO duration, intensive care unit and hospital length of stay compared to patients without pressure injuries. The logistic model demonstrated an independent association between the pO2/FiO2 ratio prior to ECMO initiation, the utilization of the prone positioning during ECMO, and the occurrence of pressure injuries.

CONCLUSIONS

The incidence of pressure injuries was elevated in patients with Adult Respiratory Distress Syndrome who received ECMO. The development of pressure injuries was found to be independently associated with hypoxemia before ECMO initiation and the utilization of prone positioning during ECMO.

IMPLICATIONS FOR CLINICAL PRACTICE

Patients who require ECMO for respiratory failure are at a high risk of developing pressure injuries. To ensure optimal outcomes during ECMO implementation and treatment, it is vital to implement preventive measures and to closely monitor skin health in at-risk areas.