The PRESERVE mortality risk score and analysis of long-term outcomes after extracorporeal membrane oxygenation for severe acute respiratory distress syndrome

Ethical Considerations for Mechanical Support

Extracorporeal life support (ECLS) has the ability to support patients with severe forms of cardiac and respiratory failure. Rapid expansion of ECLS, its resource-intensive and invasive nature, and the high acuity illness of supported patients have raised important questions. Specific issues include identification of patients most likely to benefit, the appropriate duration of support amid uncertain prognosis, and what to do when patients become dependent on ECLS but no longer have hope for recovery or transplantation. Careful deliberation of ethical principles and potential dilemmas should be made when considering the use of ECLS in advanced cardiopulmonary failure.

Early Prediction of Mortality Risk in Acute Respiratory Distress Syndrome: Systematic Review and Meta-Analysis

BACKGROUND

Acute respiratory distress syndrome (ARDS) is a life-threatening condition associated with high mortality rates. Despite advancements in critical care, reliable early prediction methods for ARDS-related mortality remain elusive. Accurate risk assessment is crucial for timely intervention and improved patient outcomes. Machine learning (ML) techniques have emerged as promising tools for mortality prediction in patients with ARDS, leveraging complex clinical datasets to identify key prognostic factors. However, the efficacy of ML-based models remains uncertain. This systematic review aims to assess the value of ML models in the early prediction of ARDS mortality risk and to provide evidence supporting the development of simplified, clinically applicable ML-based scoring tools for prognosis.

OBJECTIVE

This study systematically reviewed available literature on ML-based ARDS mortality prediction models, primarily aiming to evaluate the predictive performance of these models and compare their efficacy with conventional scoring systems. It also sought to identify limitations and provide insights for improving future ML-based prediction tools.

METHODS

A comprehensive literature search was conducted across PubMed, Web of Science, the Cochrane Library, and Embase, covering publications from inception to April 27, 2024. Studies developing or validating ML-based ARDS mortality predicting models were considered for inclusion. The methodological quality and risk of bias were assessed using the Prediction Model Risk of Bias Assessment Tool (PROBAST). Subgroup analyses were performed to explore heterogeneity in model performance based on dataset characteristics and validation approaches.

RESULTS

In total, 21 studies involving a total of 31,291 patients with ARDS were included. The meta-analysis demonstrated that ML models achieved relatively high predictive performance. In the training datasets, the pooled concordance index (C-index) was 0.84 (95% CI 0.81-0.86), while for in-hospital mortality prediction, the pooled C-index was 0.83 (95% CI 0.81-0.86). In the external validation datasets, the pooled C-index was 0.81 (95% CI 0.78-0.84), and the corresponding value for in-hospital mortality prediction was 0.80 (95% CI 0.77-0.84). ML models outperformed traditional scoring tools, which demonstrated lower predictive performance. The pooled area under the receiver operating characteristic curve (ROC-AUC) for standard scoring systems was 0.7 (95% CI 0.67-0.72). Specifically, 2 widely used clinical scoring systems, the Sequential Organ Failure Assessment (SOFA) and Simplified Acute Physiology Score II (SAPS-II), demonstrated ROC-AUCs of 0.64 (95% CI 0.62-0.67) and 0.70 (95% CI 0.66-0.74), respectively.

CONCLUSIONS

ML-based models exhibited superior predictive accuracy over conventional scoring tools, suggesting their potential use in early ARDS mortality risk assessment. However, further research is needed to refine these models, improve their interpretability, and enhance their clinical applicability. Future efforts should focus on developing simplified, efficient, and user-friendly ML-based prediction tools that integrate seamlessly into clinical workflows. Such advancements may facilitate the early identification of high-risk patients, enabling timely interventions and personalized, risk-based prevention strategies to improve ARDS outcomes.

High-Granularity Machine Learning Prediction of Acute Brain Injury in Patients Receiving Venoarterial Extracorporeal Membrane Oxygenation

Acute brain injury (ABI) is prevalent among patients undergoing venoarterial extracorporeal membrane oxygenation (VA-ECMO) and significantly impact recovery. Early prediction of ABI could enable timely interventions to prevent adverse outcomes, but existing predictive methods remain suboptimal. This study aimed to enhance ABI prediction using machine learning (ML) models and high-temporal-resolution granular data. We retrospectively analyzed 355 VA-ECMO patients treated at Johns Hopkins Hospital (JHH) from 2016 to 2024, collecting over 3 million data points from the JHH Research Electronic Data Capture (REDCap) database, with an average of 80,000 data points per patient. Acute brain injury was defined as ischemic stroke, intracranial hemorrhage, hypoxic-ischemic brain injury, or seizure. Four ML models were used: Random Forest, Categorical Boosting, Adaptive Boosting, and Extreme Gradient Boosting. Among 355 patients (median age 59 years, 56.9% male), 13.5% developed ABI. The models achieved an optimal area under the receiver operating characteristic curve (AUROC) of 0.79, accuracy of 87%, sensitivity of 53%, specificity of 99%, and precision-recall (PR)-AUC of 0.47. Key predictors included high minimum values of systolic blood pressure and variability in on-ECMO pulse pressure. High-resolution granular data enhanced ML performance for ABI prediction. Future efforts should focus on integrating continuous data platforms to enable real-time monitoring and personalized care, optimizing patient outcomes.

Experience with extracorporeal membrane oxygenation support in Latin America between 2016 and 2020

OBJECTIVE

To document the experience with ECMO therapy in healthcare institutions across Latin America between 2016 and 2020.

DESIGN

Cross-sectional study.

SETTING

Private and public health institutions from 7 countries.

PARTICIPANTS

ECMO Intensive Care Units.

INTERVENTIONS

None.

MAIN VARIABLES OF INTEREST

General characteristics of the center (country, ELSO center, year of first cannulation, public or private network, ECMO devices available, mobile ECMO), professional category (nurses, physicians, specialists and other professionals), nurse-to-patient ratio, interventions applied(support indications, scores, mechanical ventilation at ECMO commencement, anticoagulation and hemolysis, circuit monitoring and patient perfusion, antibiotic prophylaxis), and patient outcomes (complications and survival) in ECMO centers.

RESULTS

Thirteen ECMO units were included. These units reported 133 consoles and 1629 ECMO cannulations. Of these, 1018 corresponded to adult patients, 468 to pediatric patients, and 143 to newborn infants. A total of 310 medical specialists were involved in ECMO care, of whom 70.3% had received ECMO training. The nurse-to-patient ratio was 1:1 in most centers (76.9%, n = 10). Amongst adult patients, the most common indication for initiating ECMO support was refractory hypoxemia, whereas in pediatric patients, it was a post-cardiotomy shock. The mean overall survival rate of the patients at the time of decannulation was 55.7% (95%CI 53.0-58.3).

CONCLUSIONS

The ICUs with ECMO in Latin America participating in this study have demonstrated operational capabilities enabling them to achieve outcomes comparable to those of other ECMO units across the world.

Effect of Respiratory Support Type and Total Duration on Weaning From Venovenous Extracorporeal Membrane Oxygenation in COVID-19 Patients

Background: We evaluated the impact of noninvasive respiratory support (NRS) and invasive mechanical ventilation duration before venovenous extracorporeal membrane oxygenation (VV-ECMO) on weaning from venovenous ECMO and survival. Methods: In a retrospective single-center study, we studied subjects with COVID-19 ARDS treated with VV-ECMO. The subjects were divided and analyzed according to the cut-off of NRS, invasive ventilation, and total duration of respiratory support. Results: We identified a cut-off of NRS duration of 4 days, invasive ventilation duration of 5 days, and total respiratory support duration of 8 days. Weaning from VV-ECMO was observed in 63% (15/24) of subjects with NRS duration ≤ 4 days and in 16% (4/25) of subjects with NRS > 4 days (P = .001), in 50% (17/34) of subjects with invasive ventilation duration ≤ 5 days, in 13% (2/15) of subjects with invasive ventilation duration > 5 days (P = .02), in 68% (13/19) of subjects with total support duration < 8 days, and in 20% (6/30) of subjects with total support duration > 8 days (P = .001). The survival probability at 200 days demonstrated a statistically significant difference in NRS and total support duration comparison (P = .001 and P = .004, respectively). We did not find a statistically significant survival difference according to invasive ventilation duration (P = .13). Conclusions: In our population, the increase in NRS and total support days before ECMO could hamper weaning from VV-ECMO support. However, due to the pandemic, the small sample size, and the lack of precise data on ventilation settings, caution should be exercised in universalizing these results.

Quality of Life and Mental Health in COVID-ARDS Survivors After V-V ECMO Support: Results from the Freiburg ECMO Outcome Study (FEOS)

Introduction: Desirable outcome after venovenous extracorporeal membrane oxygenation for acute respiratory distress syndrome (ARDS) is frequently defined by survival. However, quality of life (QoL) and mental health status may take precedence over mere survival, from a patient-centered perspective. We aimed to evaluate QoL and mental health status in survivors after V-V ECMO for coronavirus disease 2019 (COVID-19)-related ARDS, hypothesizing a similar QoL comparable to the general population. Methods: All patients supported with venovenous ECMO for COVID-19-related ARDS between 01/2020 and 03/2022 in our center were included. Survivors were invited to participate in a follow-up interview assessing QoL, anxiety, and depression one year after hospital discharge. Primary endpoint was the quality of life, measured by the SF-36 questionnaire, with results compared to data from the DEGS1 study (German normative population). Results: During the study period, 97 patients received venovenous ECMO for COVID-19 ARDS at our ICU. Overall, 43/97 (44.3%) survived, and 21/97 (21.6%) completed the SF-36 questionnaire. The median follow-up duration was 1.7 years. Patients who completed the SF-36 were significantly younger than those who did not (48.7 vs. 55.6 years, p = 0.012); other patient characteristics and ECMO parameters were similar between those with and without questionnaire. Anxiety, depression, and post-traumatic stress disorder were detected in 33%, 14%, and 29% of patients, respectively. Compared to the German normative population, ECMO survivors had significantly lower QoL (mean 77.2 vs. 61.0, p < 0.001). Conclusions: QoL and mental health status after venovenous ECMO for ARDS was significantly lower compared to the normative population. These findings highlight the importance of further research and comprehensive follow-up care for ECMO survivors.

Rationale and recommendations for occupational therapy and physiotherapy in positioning adults with acute respiratory failure connected to extracorporeal membrane oxygenation. A narrative review

Extracorporeal membrane oxygenation (ECMO) is a life support system that facilitates gas exchange in patients experiencing catastrophic respiratory failure. ECMO connection can last from a few days to several weeks, resulting in muscle atrophy, pathological changes in the lengths of both active and passive joint stabilising structures, and alterations in the alignment of body segments. These dysfunctions may be exacerbated if patients do not maintain proper positioning, which can delay rehabilitation. Therapeutic positioning (TP) is a fundamental tool in caring for patients hospitalised in the intensive care unit. Adequate TP application helps prevent immobility complications, promotes body alignment, and enhances the patient's functionality during recovery. From a biomechanical perspective, TP supports preserving essential musculoskeletal functions such as strength, joint mobility, and endurance, facilitating patient participation in meaningful activities. Its implementation should be based on biomechanical principles, personalised adaptations, and continuous monitoring to ensure effectiveness in rehabilitation. This review examines the rationale for TP in adults with acute respiratory failure on ECMO from occupational and physical therapy perspectives. Additionally, recommendations are provided to improve the application of this intervention, particularly in the increasingly common context of prone positioning in patients with ECMO.

Machine Learning-Based First-Day Mortality Prediction for Venoarterial Extracorporeal Membrane Oxygenation: The Novel RESCUE-24 Score

Extracorporeal membrane oxygenation (ECMO) provides critical cardiac support, but predicting outcomes remains a challenge. We enrolled 1,748 adult venoarterial (VA)-ECMO patients at the National Taiwan University Hospital between 2010 and 2021. The overall mortality rate was 68.2%. Machine learning with the random survival forest (RSF) model demonstrated superior prediction for in-hospital mortality (area under the curve [AUC]: 0.953, 95% confidence interval (CI): 0.925-0.981), outperforming the Sequential Organ Failure Assessment (SOFA; 0.753 [0.689-0.817]), Acute Physiology and Chronic Health Evaluation (APACHE) II (0.737 [0.672-0.802]), Survival after Venoarterial ECMO (SAVE; 0.624 [0.551-0.697]), ENCOURAGE (0.675 [0.606-0.743]), and Simplified Acute Physiology Score (SAPS) III (0.604 [0.533-0.675]) scores. Failure to achieve 25% clearance at 8 hours and 50% at 16 hours significantly increased mortality risk (HR: 1.65, 95% CI: 1.27-2.14, p < 0.001; HR: 1.25, 95% CI: 1.02-1.54, p = 0.035). Based on the RSF-derived variable importance, the RESCUE-24 Score was developed, assigning points for lactic acid clearance (10 for <50% at 16 hours, 6 for <25% at 8 hours), SvO2 <75% (3 points), oliguria <500 ml (2 points), and age ≥60 years (2 points). Patients were classified into low risk (0-2), medium risk (3-20), and high risk (≥21). The medium- and high-risk groups exhibited significantly higher in-hospital mortality compared with the low-risk group (HR: 1.93 [1.46-2.55] and 5.47 [4.07-7.35], p < 0.002, respectively). Kaplan-Meier analysis confirmed that improved lactic acid clearance at 8 and 16 hours was associated with better survival (log-rank p < 0.001). The three groups of the RESCUE-24 Score also showed significant survival differences (log-rank p < 0.001). In conclusion, machine learning can help identify high-risk populations for tailored management. Achieving optimal lactic acid clearance within 24 hours is crucial for improving survival outcomes.

Two-year trajectory of functional recovery and quality of life in post-intensive care syndrome: a multicenter prospective observational study on mechanically ventilated patients with coronavirus disease-19

BACKGROUND

Post-intensive care syndrome (PICS) affects the quality of life (QOL) of survivors of critical illness. Although PICS persists for a long time, the longitudinal changes in each component and their interrelationships over time both remain unclear. This multicenter prospective study investigated the 2-year trajectory of PICS and its components as well as factors contributing to deterioration or recovery in mechanically ventilated patients with coronavirus disease 2019 (COVID-19), and also attempted to identify possible countermeasures.

METHODS

Patients who survived COVID-19 requiring mechanical ventilation completed questionnaires on the Barthel index, Short-Memory Questionnaire, Hospital Anxiety and Depression Scale, and EuroQol 5 dimensions 5-level every six months over a two-year period. Scores were weighted to account for dropouts, and the trajectory of each functional impairment was evaluated with alluvial diagrams. The prevalence of PICS and factors impairing or restoring function were examined using generalized estimating equations considering trajectories.

RESULTS

Among 334 patients, PICS prevalence rates in the four completed questionnaires were 72.1, 78.5, 77.6, and 82.0%, with cognitive impairment being the most common and lower QOL being noted when multiple impairments coexisted. Physical function and QOL indicated that many patients exhibited consistent trends of either recovery or deterioration. In contrast, cognitive function and mental health revealed considerable variability, with many patients showing fluctuating ratings in the later surveys. Delirium was associated with worse physical and mental health and poor QOL, while prolonged ventilation was associated with poor QOL. Living with family was associated with the recovery of all functions and QOL, while extracorporeal membrane oxygenation (ECMO) was associated with the recovery of cognitive function and mental health.

CONCLUSIONS

Critically ill patients had PICS for a long period and followed different trajectories for each impairment component. Based on trajectories, known PICS risk factors such as prolonged ventilation and delirium were associated with impaired recovery, while ECMO and the presence of family were associated with recovery from PICS. In critically ill COVID-19 patients, delirium management and family interventions may play an important role in promoting recovery from PICS.

TRIAL REGISTRATION NUMBER

UMIN000041276, August 01, 2020.

[Acute respiratory distress syndrome : Pathophysiology, definition and treatment strategies]

Acute respiratory distress syndrome (ARDS) is defined as an acute inflammatory syndrome leading to increased pulmonary capillary leakage and subsequent interstitial and alveolar pulmonary edema. Hypoxia is the predominant symptom. The definition of ARDS comprises acute onset, bilateral patchy infiltration on chest X‑ray and a reduction of the ratio of arterial partial pressure of oxygen (PaO2) to the fraction of inspired oxygen (FiO2), which also determines the classification into mild (≤ 300), moderate (≤ 200) and severe (≤ 100) ARDS. Treating the underlying cause is the only causal treatment measure. The aim of adjunctive therapy is the maintenance of life or organ functions by ensuring an adequate gas exchange without further damaging the lungs. Adjunctive therapy consists mainly of individually adapted "protective" ventilation treatment and the prone position. In severest ARDS, the use of venovenous extracorporeal membrane oxygenation (VV-ECMO) can improve survival if strict criteria for indications and contraindications are followed.

Mechanical Circulatory Support Devices in the Older Adults

As the field of mechanical circulatory support (MCS) continues to advance and resuscitation protocols are being refined, older adults patients previously not considered for MCS are now being supported. MCS devices can broadly be classified based on the duration of support into temporary or durable devices. Although mortality is higher in the older adults, carefully selected patients, MCS support can be valuable and lead to excellent recovery. Age itself should not preclude patients from being candidates for MCS because we must not restrict the progress of science in medicine for any age.

Trauma-related psychopathologies after extracorporeal membrane oxygenation support: A systematic review and meta-analysis

Extracorporeal Membrane Oxygenation (ECMO) use is associated with substantial psychiatric morbidity in patients and their families. This systematic review and meta-analysis quantifies the prevalence of post-traumatic stress disorder (PTSD), anxiety, and depression among ECMO survivors and their families. Included studies enrolled patients on ECMO or their families and reported at least one trauma-related psychopathology. Of 1767 screened studies, 55 were included (5146 participants): 50 in adult ECMO survivors, one in pediatric ECMO survivors, and four in families of ECMO patients (two adult, two pediatric.). The pooled prevalence of PTSD was 19% in adult ECMO survivors, 20% in pediatric ECMO survivors, 25% in families of adult ECMO patients, and 21% in families of pediatric ECMO patients. The pooled prevalence of anxiety was 30% in adult ECMO survivors, 8% in pediatric ECMO survivors, 67% in families of adult ECMO patients, and 46% in families of pediatric ECMO patients. The pooled prevalence of depression was 24% in adult ECMO survivors, 8% in pediatric ECMO survivors, 50% in families of adult ECMO patients, and 32% in families of pediatric ECMO patients. This meta-analysis demonstrates a high prevalence of trauma-related psychopathologies surrounding ECMO use, highlighting the need for interventions to improve post-ECMO outcomes.

Signs of Hemolysis Predict Mortality and Ventilator Associated Pneumonia in Severe Acute Respiratory Distress Syndrome Patients Undergoing Veno-Venous Extracorporeal Membrane Oxygenation

Cell-free hemoglobin (CFH) is used to detect hemolysis and was recently suggested to trigger acute lung injury. However, its role has not been elucidated in severe acute respiratory distress syndrome (ARDS) patients undergoing extracorporeal membrane oxygenation (ECMO). We investigated the association of carboxyhemoglobin (COHb) and haptoglobin-two indirect markers of hemolysis-with mortality in critically ill patients undergoing veno-venous ECMO (VV-ECMO) with adjusted and longitudinal models (primary aim). Secondary aims included assessment of association between COHb and haptoglobin with the development of ventilator-associated pneumonia (VAP) and with hemodynamics. We retrospectively collected physiological, laboratory biomarkers, and outcome data in 147 patients undergoing VV-ECMO for severe ARDS. Forty-seven patients (32%) died in the intensive care unit (ICU). Average levels of COHb and haptoglobin were higher and lower, respectively, in patients who died. Higher haptoglobin was associated with lower pulmonary (PVR) and systemic vascular resistance, whereas higher COHb was associated with higher PVR. Carboxyhemoglobin was an independent predictor of VAP. Both haptoglobin and COHb independently predicted ICU mortality. In summary, indirect signs of hemolysis including COHb and haptoglobin are associated with modulation of vascular tone, VAP, and ICU mortality in respiratory ECMO. These findings suggest that CFH may be a mechanism of injury in this patient population.

Efficacy of high-flow nasal oxygen therapy in cancer patients with concurrent acute hypoxemic respiratory failure: a retrospective propensity score study

Acute respiratory failure is the leading cause of intensive care unit (ICU) admission of cancer patients. Studies of the efficacy of high-flow nasal cannula (HFNC) therapy were rarely conducted in cancer populations. We here compared the clinical effects of HFNC therapy and conventional oxygen therapy (COT) in cancer patients with concurrent acute hypoxemic respiratory failure (AHRF). In this single-center retrospective study, cancer patients with concurrent acute hypoxic respiratory failure either received initial oxygen therapy via HFNC (HFNC group, 68 patients) or received initial oxygen therapy via a nasal cannula, simple mask, or mask with reservoir bag (COT group, 133 patients). Groups were propensity score matched. Differences in respiratory rate (RR), heart rate (HR), and PaO2/FiO2 ratio before and after treatment in the two groups were compared using a mixed-effects model. The 28-day mortality risk was explored using a Cox proportional hazards model. The 24-h and 48-h PaO2/FIO2 ratios were significantly higher in the HFNC than in the COT group (210.5 mmHg vs. 178.5 mmHg; P < 0.01; 217.1 mm Hg vs. 181.6 mm Hg; P < 0.01, respectively). Differences in RR and HR between the groups at each time point were nonsignificant. The 28-day mortality rate was 17.4% vs. 38.1% for the HFNC and COT groups, respectively (P < 0.01). Hazard ratio was significantly higher for COT group (HR 2.6, 95% confidence interval 1.3, 5.3). Compared with COT, HFNC use for initial oxygen therapy can improve PaO2/FIO2 ratio and survival rate in cancer patients with AHRF.

An investigation into the contributing factors to survival of ARDS patients supported by veno-venous ECMO

INTRODUCTION

This study aimed to identify characteristics associated with survival during and post Extra Corporeal Membrane Oxygenation (ECMO) therapy, in patients with acute respiratory distress syndrome (ARDS) during the COVID-19 pandemic.

METHODS

A retrospective observational study on 94 consecutive patients with confirmed COVID-19 induced ARDS supported by ECMO was carried out 49/94 (52.7%) patients survived to hospital discharge.

RESULTS

Non-survivors were found to have significantly (p < .05) higher: Pre-ECMO International normalized ratios (INR), carbon dioxide partial pressure (pCO2), Acute Kidney Injury (AKI) scores and blood urea levels. Also, lower pre-ECMO peak inspiratory pressures (PIP), mean arterial pressure, saturation of arterial oxygen (SaO2), blood bicarbonate levels (HCO3), blood Ph and fewer trials off ECMO with shorter combined trial off times. Patients that did not survive were more likely to have renal impairment and have received peri-ECMO haemofiltration. Poor prognosis was significantly associated with: receiving pre-ECMO nitric oxide (HR = 3.047, CI = 1.247-7.447, p = .015), renal impairment (HR = 3.023, CI = 1.586-5.763, p < .001), AKI of 2 (HR = 3.611, CI = 1.382-9.441, p = .009) or 3 (HR = 3.275, CI = 1.235-8.685, p = .017), peri-ECMO haemofiltration (HR = 2.412, CI = 1.310-4.442, p = .005) and the ABO blood group B (HR = 3.103, CI = 1.335-7.212, p = .008). pre-ECMO high CO2 (HR = 1.134, CI = 1.031-1.248, p = .010), blood lactate (HR = 1.350, CI = 1.156-1.576, p < .001), INR (HR = 2.571, CI = 1.438-4.598, p=<0.001) and lower blood Ph (HR = 0.023, CI = 0.002-0.210, p < .001).

CONCLUSIONS

Commonly used mortality scores may not be of use in a COVID-19 cohort of ECMO patients. The initiation of ECMO needs to be implemented prior to metabolic derangements, renal and fulminant respiratory failure.

Mortality on extracorporeal membrane oxygenation: Evaluation of independent risk factors and causes of death during venoarterial and venovenous support

INTRODUCTION

Most patients on extracorporeal membrane oxygenation (ECMO) decease during therapy on the system. However, the actual causes of death have not been studied sufficiently. This study analyses the etiology, prevalence, and risk factors for the outcome variable death during ongoing ECMO for all patients and divided according to venoarterial (VA) or venovenous (VV) support.

METHODS

We retrospectively analysed all patients receiving ECMO support at our institution between March 2006 to January 2021. Only the patients deceased during ongoing support were included.

RESULTS

2016 patients were placed on VA (n = 1168; 58%) or VV (n = 848; 42%) ECMO; 759 patients (37.7%) deceased on support. The causes of death differed between the support types: VA ECMO patients mostly died from cerebral ischemia (34%), low-cardiac output (LCO; 24.1%) and multi-organ failure (MOF; 21.6%), whereas in VV ECMO cases, refractory respiratory failure (28.2%), and sepsis (20.4%) dominated. Multivariate regression analysis revealed cardiopulmonary resuscitation (CPR) and acidosis prior to ECMO as risk factors for dying on VA ECMO, while high inotropic doses pre-ECMO, a high fraction of inspired oxygen on day 1, elevated lactate dehydrogenase, and international normalized ratio levels lead to an unfavourable outcome in VV ECMO patients.

CONCLUSION

Even in highly experienced centers, ECMO mortality remains high and occurs mainly on support or 24 h after its termination. The causes of death differ between VV and VA ECMO, depending on the underlying diseases responsible for the need of extracorporeal support.

External Validation of the PREdiction of Survival on Extracorporeal Membrane Oxygenation Therapy (PRESET) Score: A Single-Center Cohort Experience

Acute respiratory distress syndrome (ARDS) is a life-threatening condition affecting >10% of intensive care unit (ICU) patients worldwide with a mortality of up to 59% depending on severity. Extracorporeal membrane oxygenation (ECMO) is a potentially life-saving procedure in severe ARDS but is technically and financially challenging. In recent years, various scoring systems have been proposed to select patients most likely to benefit from ECMO, with the PREdiction of Survival on ECMO Therapy (PRESET) score being one of the most used. We collected data from 283 patients with ARDS of various etiology who underwent veno-venous (V-V) ECMO therapy at a German tertiary care ICU from January 2012 to December 2022. Median age in the cohort was 56 years, and 64.31% were males. The in-hospital mortality rate was 50.88% (n = 144). The median (25%; 75% quartile) severity scores were 38 (31; 49) for Simplified Acute Physiology Score (SAPS) II, 12 (10; 13) for Sequential Organ Failure Assessment (SOFA) and 7 (5; 8) for PRESET. Simplified Acute Physiology Score-II displayed the best prognostic value (area under the receiver operating characteristic [AUROC]: 0.665 [confidence interval (CI): 0.574-0.756; p = 0.046]). Prediction performance was weak in all analyzed scores despite good calibration. Simplified Acute Physiology Score-II had the best discrimination after adjustment of our original cohort. The use of scores explored in this study for patient selection for eligibility for V-V ECMO is not recommendable.

Lessons Learned From Extracorporeal Life Support Practice and Outcomes During the COVID-19 Pandemic

Extracorporeal membrane oxygenation is increasingly being used to support patients with hypoxemic respiratory failure and cardiogenic shock. During the COVID-19 pandemic, consensus guidance recommended extracorporeal life support for patients with COVID-19-related cardiopulmonary disease refractory to optimal conventional therapy, prompting a substantial expansion in the use of this support modality. Extracorporeal membrane oxygenation was particularly integral to the bridging of COVID-19 patients to heart or lung transplantation. Limited human and physical resources precluded widespread utilization of mechanical support during the COVID-19 pandemic, necessitating careful patient selection and optimal management by expert healthcare teams for judicious extracorporeal membrane oxygenation use. This review outlines the evidence supporting the use of extracorporeal life support in COVID-19, describes the practice and outcomes of extracorporeal membrane oxygenation for COVID-19-related respiratory failure and cardiogenic shock, and proposes lessons learned for the implementation of extracorporeal membrane oxygenation as a bridge to transplantation in future public health emergencies.

Extracorporeal membrane oxygenation for tuberculosis-related acute respiratory distress syndrome: An international multicentre retrospective cohort study

OBJECTIVE

To report the outcomes of patients with severe tuberculosis (TB)-related acute respiratory distress syndrome (ARDS) on extracorporeal membrane oxygenation (ECMO), including predictors of 90-day mortality and associated complications.

METHODS

An international multicenter retrospective study was conducted in 20 ECMO centers across 13 countries between 2002 and 2022.

RESULTS

We collected demographic data, clinical details, ECMO-related complications, and 90-day survival status for 79 patients (median APACHE II score of 20 [25th to 75th percentile, 16 to 28], median age 39 [28 to 48] years, PaO2/FiO2 ratio of 69 [55 to 82] mmHg before ECMO) who met the inclusion criteria. Thoracic computed tomography showed that 61 patients (77%) had cavitary TB, while 18 patients (23%) had miliary TB. ECMO-related complications included major bleeding (23%), ventilator-associated pneumonia (41%), and bloodstream infections (32%). The overall 90-day survival rate was 51%, with a median ECMO duration of 20 days [10 to 34] and a median ICU stay of 42 days [24 to 65]. Among patients on VV ECMO, those with miliary TB had a higher 90-day survival rate than those with cavitary TB (90-day survival rates of 81% vs. 46%, respectively; log-rank P = 0.02). Multivariable analyses identified older age, drug-resistant TB, and pre-ECMO SOFA scores as independent predictors of 90-day mortality.

CONCLUSION

The use of ECMO for TB-related ARDS appears to be justifiable. Patients with miliary TB have a much better prognosis compared to those with cavitary TB on VV ECMO.

The relationship between body mass index and mortality is not linear in patients requiring venovenous extracorporeal support

OBJECTIVE

Morbid obesity may influence candidacy for venovenous extracorporeal membrane oxygenation (VVECMO) support. Indeed, body mass index (BMI) >40 is considered to be a relative contraindication due to increased mortality observed in patients with BMI above this value. There is scant evidence to characterize this relationship beyond speculating about the technical challenges of cannulation and difficulty in optimizing flows. We examined a national cohort to evaluate the influence of BMI on mortality in patients requiring VVECMO for severe acute respiratory syndrome coronavirus 2 infection.

METHODS

We performed a retrospective cohort analysis on National COVID Cohort Collaborative data evaluating 1,033,229 patients with BMI ≤60 from 31 US hospital systems diagnosed with severe acute respiratory syndrome virus coronavirus 2 infection from September 2019 to August 2022. We performed univariate and multivariable mixed-effects logistic regression analysis on data pertaining to those who required VVECMO support during their hospitalization. A subgroup risk-adjusted analysis comparing ECMO mortality in patients with BMI 40 to 60 with the 25th, 50th, and 75th BMI percentile was performed. Outcomes of interest included BMI, age, comorbidity score, body surface area, and ventilation days.

RESULTS

A total of 774 adult patients required VVECMO. Of these, 542 were men, median age was 47 years, mean adjusted Charlson Comorbidity Index was 1, and median BMI was 33. Overall mortality was 47.8%. There was a nonsignificant overall difference in mortality across hospitals (SD, 0.31; 95% CI, 0-0.57). After mixed multivariable logistic regression analysis, advanced age (P < .0001) and Charlson Comorbidity Index (P = .009) were each associated with increased mortality. Neither gender (P = .14) nor duration on mechanical ventilation (P = .39) was associated with increased mortality. An increase in BMI from 25th to 75th percentile was not associated with a difference in mortality (P = .28). In our multivariable mixed-effects logistic regression analysis, there exists a nonlinear relationship between BMI and mortality. Between BMI of 25 and 32, patients experienced an increase in mortality. However, between BMI of 32 and 37, the adjusted mortality in these patients subsequently decreased. Our subgroup analysis comparing BMIs 40 to 60 with the 25th, 50th, and 75th percentile of BMI found no significant difference in ECMO mortality between BMI values of 40 and 60 with the 25th, 50th, 75th percentile.

CONCLUSIONS

Advancing age and higher CCI are each associated with increased risk for mortality in patients requiring VVECMO. A nonlinear relationship exists between mortality and BMI and those between 32 and 37 have lower odds of mortality than those between BMI 25 and 32. This nonlinear pattern suggests a need for further adjudication of the contraindications associated with VVECMO, particularly those based solely on BMI.

Model for End-Stage Liver Disease Including Na, Age, and Sex Is Powerful Predictor of Survival in COVID-19 Patients on Extracorporeal Membrane Oxygenation

AIM

Extracorporeal membrane oxygenation (ECMO) is resource-intensive, is associated with significant morbidity and mortality, and requires careful patient selection. This study examined whether the model for end-stage liver disease (MELD) score is a suitable predictor of in-hospital mortality in patients with COVID-19.

MATERIALS AND METHODS

We retrospectively assessed patients with COVID-19 on ECMO at our institution from March 2020 to May 2021. MELD scoring was performed using laboratory values recorded prior to ECMO initiation. A multiple logistic regression model was established.

RESULTS

A total of 66 patients with COVID-19 on ECMO were included (median age of 58.5 years; 83.3% male). The in-hospital mortality was 74.2%. In relation to mortality, patients with MELD Na scores >13.8 showed 6.5-fold higher odds, patients aged >53.5 years showed 18.4-fold higher odds, and male patients showed 15.9-fold higher odds. The predictive power of a model combining the MELD Na with age and sex was significant (AUC = 0.883, p < 0.001). The findings in the COVID-19 patients were not generalizable to a group of non-COVID-19 patients on ECMO.

CONCLUSIONS

A model combining the MELD Na, age, and sex has high predictive power for in-hospital mortality in patients with COVID-19 on ECMO, and it may be clinically useful for guiding patient selection in critically ill COVID-19 patients both now and in the future, should the virus widely re-emerge.

Risk factors and prognostic modeling in bridging extracorporeal membrane oxygenation patients before lung transplantation

Background

The increased use of preoperative extracorporeal membrane oxygenation (ECMO) as a life support system before lung transplantation demands a better understanding of the associated prognostic factors. This study aims to discern the critical factors influencing the survival outcomes of ECMO patients and design a prognostic model tailored to this patient group.

Methods

We retrospectively gathered and analyzed baseline and clinical data of patients who underwent preoperative bridging ECMO before lung transplantation from the United Network for Organ Sharing (UNOS) database. Univariate and multivariate Cox regression analyses were conducted and a prognostic model was generated to identify the independent factors influencing survival outcomes in these patients. The predictive model was cross-validated using the k-fold method where k=5.

Results

Our study included 1,202 patients. Both single and multiple analyses showed that age over 51 years, high body mass index (BMI), a history of dialysis before transplantation, donor hypertension, prolonged cold ischemia time, and high serum total bilirubin are adverse prognostic factors for the survival of ECMO-bridged lung transplant patients. Using the multivariate analysis, we created a prognosis model and a nomogram to predict 1-year post-transplant survival, with a receiver operating characteristic (ROC) curve area of 0.760 in internal validation. The 1-year survival rate calibration curve supported the nomogram's accuracy.

Conclusions

This study involved the development of a survival prognosis model for patients undergoing lung transplantation with preoperative ECMO bridging, which was validated through extensive data analysis. The prognosis model exhibited high accuracy and predictive capability, effectively predicting the survival outcomes of patients both pre- and post-surgery.

Role of age as eligibility criterion for ECMO in patients with ARDS: meta-regression analysis

BACKGROUND

Age as an eligibility criterion for V-V ECMO is widely debated and varies among healthcare institutions. We examined how age relates to mortality in patients undergoing V-V ECMO for ARDS.

METHODS

Systematic review and meta-regression of clinical studies published between 2015 and June 2024. Studies involving at least 6 ARDS patients treated with V-V ECMO, with specific data on ICU and/or hospital mortality and patient age were included. The search strategy was executed in PubMed, limited to English-language. COVID-19 and non-COVID-19 populations were analyzed separately. Meta-regressions of mortality outcomes on age were performed using gender, BMI, SAPS II, APACHE II, Charlson comorbidity index or SOFA as covariates.

RESULTS

In non-COVID ARDS, the meta-regression of 173 studies with 56,257 participants showed a significant positive association between mean age and ICU/hospital mortality. In COVID-19 ARDS, a significant relationship between mean age and ICU mortality, but not hospital mortality, was found in 103 studies with 21,255 participants. Sensitivity analyses confirmed these findings, highlighting a linear relationship between age and mortality in both groups. For each additional year of mean age, ICU mortality increased by 1.2% in non-COVID ARDS and 1.9% in COVID ARDS.

CONCLUSIONS

The relationship between age and ICU mortality is linear and shows no inflection point. Consequently, no age cut-off can be recommended for determining patient eligibility for V-V ECMO.

VV-ECMO in critical COVID-19 obese patients: a cohort study

BACKGROUND

Obesity causes significant difficulties in successful extracorporeal membrane oxygenation (ECMO) support and may interfere with patient outcomes. During the COVID-19 pandemic, we experienced an increased number of obese patients supported with ECMO in our intensive care unit due to severe illness in this population.

METHODS

We designed a single-center retrospective study to identify prognostic factors for 180-day survival in obese critical COVID-19 patients receiving venovenous ECMO (VV-ECMO). We included adult critical COVID-19 patients on VV-ECMO, who were obese and overweight (according to the World Health Organization) and admitted to a tertiary hospital's intensive care unit from April 1, 2020, to May 31, 2022. Univariate logistic regression analysis was performed to assess differences in 180-day mortality.

RESULTS

Forty-one patients were included. The median age was 55 (IQR 45-60) years, and 70.7% of the patients were male. The median body mass index (BMI) was 36 (IQR 31-42.5) kg/m2; 39% of patients had a BMI ≥ 40 kg/m2. The participants had 3 (IQR 1.5-4) days of mechanical ventilation prior to ECMO, and 63.4% were weaned from VV-ECMO support after a median of 19 (IQR 10-34) days. The median ICU length of stay was 31.9 (IQR 17.5-44.5) days. The duration of mechanical ventilation was 30 (IQR 19-49.5) days. The 180-day mortality rate was 41.5%. Univariate logistic regression analysis revealed that a higher BMI was associated with greater 180-day survival (OR 1.157 [1.038-1.291], p = 0.009). Younger age, female sex, less invasive ventilation time before ECMO, and fewer complications at the time of ECMO cannulation were associated with greater 180-day survival [OR 0.858 (0.774-0.953), p 0.004; OR 0.074 (0.008-0.650), p 0.019; OR 0.612 (0.401-0.933), p 0.022; OR 0.13 (0.03-0.740), p 0.022), respectively].

CONCLUSION

In this retrospective cohort of critical COVID-19 obese adult patients supported by VV-ECMO, a higher BMI, younger age, and female sex were associated with greater 180-day survival. A shorter invasive ventilation time before ECMO and fewer complications at ECMO cannulation were also associated with increased survival.

Thrombolysis before venoarterial ECMO for high-risk pulmonary embolism: a retrospective cohort study

PURPOSE

Despite systemic thrombolysis, a few patients with high-risk pulmonary embolism (PE) remain hemodynamically unstable. Venoarterial extracorporeal membrane oxygenation (VA-ECMO) is a considerable lifesaving therapy but systemic thrombolysis before cannulation could carry a high risk of hemorrhage and alter the prognosis.

METHODS

Between June 2012 and June 2023, we retrospectively analyzed from three intensive care units in Sorbonne University, ECMO-related complications and 90-day mortality for high-risk PE patients who received ECMO without previous systemic thrombolysis compared to those cannulated after systemic thrombolysis failure. Hospital discharge survivors were assessed for long-term health-related quality of life and echocardiographic evaluations.

RESULTS

72 high-risk PE patients [median age 48 (37-61) years, Simplified Acute Physiology Score II (SAPS II) 74 (60-85)] were placed on VA-ECMO for 5 (5-7) days. 31 (43%) patients underwent pre-ECMO thrombolysis (thrombolysis ECMO group, T +) compared to 41 patients (57%, no thrombolysis ECMO group, T-). There was more pre-ECMO cardiac arrest in the thrombolysis ECMO group (94% vs. 67%, p = 0.02). Ninety-day survival was not different between groups (39% vs 46%, log-rank test, p = 0.31). There was no difference in severe hemorrhages (61% vs 59%, p = 1). Twenty-five over 28 patients attended follow-up at a median time of 69 (52-95) months. Long-term quality of life was acceptable and none of them experienced chronic thromboembolic pulmonary hypertension.

CONCLUSIONS

Ninety-day survival and bleeding events rates did not differ in patients treated with VA-ECMO after systemic thrombolysis compared to those who were not. Recent systemic thrombolysis, as a single parameter, should not be considered as a contraindication for VA-ECMO in high-risk PE.

Acute brain injury risk prediction models in venoarterial extracorporeal membrane oxygenation patients with tree-based machine learning: An Extracorporeal Life Support Organization Registry analysis

Objective

We aimed to determine if machine learning can predict acute brain injury and to identify modifiable risk factors for acute brain injury in patients receiving venoarterial extracorporeal membrane oxygenation.

Methods

We included adults (age ≥18 years) receiving venoarterial extracorporeal membrane oxygenation or extracorporeal cardiopulmonary resuscitation in the Extracorporeal Life Support Organization Registry (2009-2021). Our primary outcome was acute brain injury: central nervous system ischemia, intracranial hemorrhage, brain death, and seizures. We used Random Forest, CatBoost, LightGBM, and XGBoost machine learning algorithms (10-fold leave-1-out cross-validation) to predict and identify features most important for acute brain injury. We extracted 65 total features: demographics, pre-extracorporeal membrane oxygenation/on-extracorporeal membrane oxygenation laboratory values, and pre-extracorporeal membrane oxygenation/on-extracorporeal membrane oxygenation settings.

Results

Of 35,855 patients receiving venoarterial extracorporeal membrane oxygenation (nonextracorporeal cardiopulmonary resuscitation) (median age of 57.8 years, 66% were male), 7.7% (n = 2769) experienced acute brain injury. In venoarterial extracorporeal membrane oxygenation (nonextracorporeal cardiopulmonary resuscitation), the area under the receiver operator characteristic curves to predict acute brain injury, central nervous system ischemia, and intracranial hemorrhage were 0.67, 0.67, and 0.62, respectively. The true-positive, true-negative, false-positive, false-negative, positive, and negative predictive values were 33%, 88%, 12%, 67%, 18%, and 94%, respectively, for acute brain injury. Longer extracorporeal membrane oxygenation duration, higher 24-hour extracorporeal membrane oxygenation pump flow, and higher on-extracorporeal membrane oxygenation partial pressure of oxygen were associated with acute brain injury. Of 10,775 patients receiving extracorporeal cardiopulmonary resuscitation (median age of 57.1 years, 68% were male), 16.5% (n = 1787) experienced acute brain injury. The area under the receiver operator characteristic curves for acute brain injury, central nervous system ischemia, and intracranial hemorrhage were 0.72, 0.73, and 0.69, respectively. Longer extracorporeal membrane oxygenation duration, older age, and higher 24-hour extracorporeal membrane oxygenation pump flow were associated with acute brain injury.

Conclusions

In the largest study predicting neurological complications with machine learning in extracorporeal membrane oxygenation, longer extracorporeal membrane oxygenation duration and higher 24-hour pump flow were associated with acute brain injury in nonextracorporeal cardiopulmonary resuscitation and extracorporeal cardiopulmonary resuscitation venoarterial extracorporeal membrane oxygenation.

Recruitment-Potential-Oriented Mechanical Ventilation Protocol and Narrative Review for Patients with Acute Respiratory Distress Syndrome

Even though much progress has been made to improve clinical outcomes, acute respiratory distress syndrome (ARDS) remains a significant cause of acute respiratory failure. Protective mechanical ventilation is the backbone of supportive care for these patients; however, there are still many unresolved issues in its setting. The primary goal of mechanical ventilation is to improve oxygenation and ventilation. The use of positive pressure, especially positive end-expiratory pressure (PEEP), is mandatory in this approach. However, PEEP is a double-edged sword. How to safely set positive end-inspiratory pressure has long been elusive to clinicians. We hereby propose a pressure-volume curve measurement-based method to assess whether injured lungs are recruitable in order to set an appropriate PEEP. For the most severe form of ARDS, extracorporeal membrane oxygenation (ECMO) is considered as the salvage therapy. However, the high level of medical resources required and associated complications make its use in patients with severe ARDS controversial. Our proposed protocol also attempts to propose how to improve patient outcomes by balancing the possible overuse of resources with minimizing patient harm due to dangerous ventilator settings. A recruitment-potential-oriented evaluation-based protocol can effectively stabilize hypoxemic conditions quickly and screen out truly serious patients.

Comparison of venovenous extracorporeal membrane oxygenation, prone position and supine mechanical ventilation for severely hypoxemic acute respiratory distress syndrome: a network meta-analysis

PURPOSE

Severe acute respiratory distress syndrome (ARDS) with PaO2/FiO2 < 80 mmHg is a life-threatening condition. The optimal management strategy is unclear. The aim of this meta-analysis was to compare the effects of low tidal volumes (Vt), moderate Vt, prone ventilation, and venovenous extracorporeal membrane oxygenation (VV-ECMO) on mortality in severe ARDS.

METHODS

We performed a frequentist network meta-analysis of randomised controlled trials (RCTs) with participants who had severe ARDS and met eligibility criteria for VV-ECMO or had PaO2/FiO2 < 80 mmHg. We applied the Grades of Recommendation, Assessment, Development, and Evaluation (GRADE) methodology to discern the relative effect of interventions on mortality and the certainty of the evidence.

RESULTS

Ten RCTs including 812 participants with severe ARDS were eligible. VV-ECMO reduces mortality compared to low Vt (risk ratio [RR] 0.77, 95% confidence interval [CI] 0.59-0.99, moderate certainty) and compared to moderate Vt (RR 0.75, 95% CI 0.57-0.98, low certainty). Prone ventilation reduces mortality compared to moderate Vt (RR 0.78, 95% CI 0.66-0.93, high certainty) and compared to low Vt (RR 0.81, 95% CI 0.63-1.02, moderate certainty). We found no difference in the network comparison of VV-ECMO compared to prone ventilation (RR 0.95, 95% CI 0.72-1.26), but inferences were based solely on indirect comparisons with very low certainty due to very wide confidence intervals.

CONCLUSIONS

In adults with ARDS and severe hypoxia, both VV-ECMO (low to moderate certainty evidence) and prone ventilation (moderate to high certainty evidence) improve mortality relative to low and moderate Vt strategies. The impact of VV-ECMO versus prone ventilation remains uncertain.

Extracorporeal Membrane Oxygenation for Respiratory Failure: A Narrative Review

Extracorporeal membrane oxygenation support for respiratory failure in the intensive care unit continues to have an expanded role in select patients. While acute respiratory distress syndrome remains the most common indication, extracorporeal membrane oxygenation may be used in other causes of refractory hypoxemia and/or hypercapnia. The most common configuration is veno-venous extracorporeal membrane oxygenation; however, in specific cases of refractory hypoxemia or right ventricular failure, some patients may benefit from veno-pulmonary extracorporeal membrane oxygenation or veno-venoarterial extracorporeal membrane oxygenation. Patient selection and extracorporeal circuit management are essential to successful outcomes. This narrative review explores the physiology of extracorporeal membrane oxygenation, indications and contraindications, ventilator management, extracorporeal circuit management, troubleshooting hypoxemia, complications, and extracorporeal membrane oxygenation weaning in patients with respiratory failure. As the footprint of extracorporeal membrane oxygenation continues to expand, it is essential that clinicians understand the underlying physiology and management of these complex patients.

ECMO is associated with decreased hospital mortality in COVID-19 ARDS

This study determined whether compared to conventional mechanical ventilation (MV), extracorporeal membrane oxygenation (ECMO) is associated with decreased hospital mortality or fibrotic changes in patients with COVID-19 acute respiratory distress syndrome. A cohort of 72 patients treated with ECMO and 390 with conventional MV were analyzed (February 2020-December 2021). A target trial was emulated comparing the treatment strategies of initiating ECMO vs no ECMO within 7 days of MV in patients with a PaO2/FiO2 < 80 or a PaCO2 ≥ 60 mmHg. A total of 222 patients met the eligibility criteria for the emulated trial, among whom 42 initiated ECMO. ECMO was associated with a lower risk of hospital mortality (hazard ratio [HR], 0.56; 95% confidence interval [CI] 0.36-0.96). The risk was lower in patients who were younger (age < 70 years), had less comorbidities (Charlson comorbidity index < 2), underwent prone positioning before ECMO, and had driving pressures ≥ 15 cmH2O at inclusion. Furthermore, ECMO was associated with a lower risk of fibrotic changes (HR, 0.30; 95% CI 0.11-0.70). However, the finding was limited due to relatively small number of patients and differences in observability between the ECMO and conventional MV groups.

Intelligence among ear deformities and cleft lip and/or alveolus and/or cleft palate patients during 50 years in Israel

PURPOSE

We evaluated hearing loss and general intelligence among persons with auricle anomalies and cleft lip and/or alveolus and/or cleft palate (CLAP).

METHODS

A nationwide cross-sectional study of data recorded during 1966-2019, as mandatory pre-military recruitment of individuals.

RESULTS

Of 3 182 892 adolescents, 548 were diagnosed with auricle anomalies and 2072 with CLAP. For the latter, the adjusted odds ratios for the low, low to medium and medium general intelligence categories compared to the highest category were 1.4 [95% CI 1.5-1.2], 1.2 [95% CI 1.4-1.1] and 1.1 [95% CI 1.2-0.9] respectively. The corresponding values for the auricle anomalies were not significant.

CONCLUSIONS

General intelligence was impaired among individuals with CLAP, but no significant correlation was found among individuals suffering from auricle anomalies.

Predictors of mortality and transfusion requirements in venoarterial extracorporeal membrane oxygenation patients

OBJECTIVE

The aim of this study was to evaluate the prognostic impact of variables, including thrombocytopenia and the amount of platelet transfusion, for predicting survival in venoarterial extracorporeal membrane oxygenation (ECMO) recipients. Additionally, we aimed to identify the predictors of increased transfusion requirement during venoarterial ECMO support.

METHODS

All patients who received venoarterial ECMO between December 2008 and March 2020 were retrospectively analyzed. Univariate and multivariate Cox regressions were used to evaluate in-hospital mortality according to variables including thrombocytopenia and daily average of platelet concentrate transfusion. Stepwise multiple linear regression analysis was used to identify independent predictors for transfusion requirements.

RESULTS

Analysis of 218 patients demonstrated severe thrombocytopenia as an independent predictor of in-hospital mortality (hazard ratio = 2.840, 95% CI: 1.593-5.063, P < .001), along with age, pre-ECMO cardiac arrest, and pH. In contrast, the amount of platelet transfusion was not associated with in-hospital mortality. Multiple variables, including the type of indication for ECMO were associated with transfusion requirements.

CONCLUSION

Our findings identified severe thrombocytopenia as an independent prognostic factor of in-hospital mortality. However, daily average platelet transfusion was not associated with survival outcomes. Additionally, our study identified predictive variables of increased transfusion requirements.

Morbid obesity's impact on COVID-19 patients requiring venovenous extracorporeal membrane oxygenation: The covid-19 critical care consortium database review

Introduction: Obesity is associated with a worse prognosis in COVID-19 patients with acute respiratory distress syndrome (ARDS). Veno-venous (V-V) Extracorporeal Membrane Oxygenation (ECMO) can be a rescue option, however, the direct impact of morbid obesity in this select group of patients remains unclear.Methods: This is an observational study of critically ill adults with COVID-19 and ARDS supported by V-V ECMO. Data are from 82 institutions participating in the COVID-19 Critical Care Consortium international registry. Patients were admitted between 12 January 2020 to 27 April 2021. They were stratified based on Body Mass Index (BMI) at 40 kg/m2. The endpoint was survival to hospital discharge.Results: Complete data available on 354 of 401 patients supported on V-V ECMO. The characteristics of the high BMI (>40 kg/m2) and lower BMI (≤40 kg/m2) groups were statistically similar. However, the 'high BMI' group were comparatively younger and had a lower APACHE II score. Using survival analysis, older age (Hazard Ratio, HR 1.49 per-10-years, CI 1.25-1.79) and higher BMI (HR 1.15 per-5 kg/m2 increase, CI 1.03-1.28) were associated with a decreased patient survival. A safe BMI threshold above which V-V ECMO would be prohibitive was not apparent and instead, the risk of an adverse outcome increased linearly with BMI.Conclusion: In COVID-19 patients with severe ARDS who require V-V ECMO, there is an increased risk of death associated with age and BMI. The risk is linear and there is no BMI threshold beyond which the risk for death greatly increases.

A Mortality Prediction Score for Patients With Veno-Venous Extracorporeal Membrane Oxygenation (VV-ECMO): The PREDICT VV-ECMO Score

Mortality prediction for patients with the severe acute respiratory distress syndrome (ARDS) supported with veno-venous extracorporeal membrane oxygenation (VV-ECMO) is challenging. Clinical variables at baseline and on day 3 after initiation of ECMO support of all patients treated from October 2010 through April 2020 were analyzed. Multivariate logistic regression analysis was used to identify score variables. Internal and external (Monza, Italy) validation was used to evaluate the predictive value of the model. Overall, 272 patients could be included for data analysis and creation of the PREDICT VV-ECMO score. The score comprises five parameters (age, lung fibrosis, immunosuppression, cumulative fluid balance, and ECMO sweep gas flow on day 3). Higher score values are associated with a higher probability of hospital death. The score showed favorable results in derivation and external validation cohorts (area under the receiver operating curve, AUC derivation cohort 0.76 [95% confidence interval, CI, 0.71-0.82] and AUC validation cohort 0.74 [95% CI, 0.67-0.82]). Four risk classes were defined: I ≤ 30, II 31-60, III 61-90, and IV ≥ 91 with a predicted mortality of 28.2%, 56.2%, 84.8%, and 96.1%, respectively. The PREDICT VV-ECMO score suggests favorable performance in predicting hospital mortality under ongoing ECMO support providing a sound basis for further evaluation in larger cohorts.

Adjunctive Therapies in Acute Respiratory Distress Syndrome

Despite significant advances in understanding acute respiratory distress syndrome (ARDS), mortality rates remain high. The appropriate use of adjunctive therapies can improve outcomes, particularly for patients with moderate to severe hypoxia. In this review, the authors discuss the evidence basis behind prone positioning, recruitment maneuvers, neuromuscular blocking agents, corticosteroids, pulmonary vasodilators, and extracorporeal membrane oxygenation and considerations for their use in individual patients and specific clinical scenarios. Because the heterogeneity of ARDS poses challenges in finding universally effective treatments, an individualized approach and continued research efforts are crucial for optimizing the utilization of adjunctive therapies and improving patient outcomes.

Outcomes of Severe ARDS COVID-19 Patients Denied for Venovenous ECMO Support: A Prospective Observational Comparative Study

Background: Few data are available concerning the outcome of patients denied venovenous extracorporeal membrane oxygenation (VV-ECMO) relative to severe acute respiratory distress syndrome (ARDS) due to COVID-19. Methods: We compared the 90-day survival rate of consecutive adult patients for whom our center was contacted to discuss VV-ECMO indication. Three groups of patients were created: patients for whom VV-ECMO was immediately indicated (ECMO-indicated group), patients for whom VV-ECMO was not indicated at the time of the call (ECMO-not-indicated group), and patients for whom ECMO was definitely contraindicated (ECMO-contraindicated group). Results: In total, 104 patients were referred for VV-ECMO support due to severe COVID-19 ARDS. Among them, 32 patients had immediate VV-ECMO implantation, 28 patients had no VV-ECMO indication, but 1 was assisted thereafter, and 44 patients were denied VV-ECMO for contraindication. Among the 44 patients denied, 30 were denied for advanced age, 24 for excessive prior duration of mechanical ventilation, and 16 for SOFA score >8. The 90-day survival rate was similar for the ECMO-indicated group and the ECMO-not-indicated group at 62.1 and 61.9%, respectively, whereas it was significantly lower (20.5%) for the ECMO-contraindicated group. Conclusions: Despite a low survival rate, 50% of patients were at home 3 months after being denied for VV-ECMO for severe ARDS due to COVID-19.

Age and associated outcomes among patients receiving venovenous extracorporeal membrane oxygenation for acute respiratory failure: analysis of the Extracorporeal Life Support Organization registry

PURPOSE

Venovenous extracorporeal membrane oxygenation (VV-ECMO) can be used to support patients with refractory acute respiratory failure, though guidance on patient selection is lacking. While age is commonly utilized as a factor in establishing the potential VV-ECMO candidacy of these patients, little is known regarding its association with outcome. We studied the association between increasing patient age and outcomes among patients with acute respiratory failure receiving VV-ECMO.

METHODS

In this registry-based cohort study, we used individual patient data from 144 centres. We included adult patients (≥ 18 years of age) receiving VV-ECMO from 2017 to 2022. The primary outcome was hospital mortality. Secondary outcomes included a composite of complications following initiation of VV-ECMO. We conducted Bayesian analyses to estimate the association between chronological age and outcomes.

RESULTS

We included 27,811 patients receiving VV-ECMO. Of these, 11,533 (41.5%) died in hospital. For the analysis conducted using weakly informed priors, and as compared to the reference category of age 18-29, the age brackets of 30-39 (odds ratio [OR] 1.17, 95% credible interval [CrI] 1.06-1.31), 40-49 (OR 1.65, 95% CrI 1.49-1.82), 50-59 (OR 2.39, 95% CrI 2.16-2.61), 60-69 (OR 3.29, 95% CrI 2.97-3.67), 70-79 (OR 4.57, 95% CrI 3.90-5.37), and ≥ 80 (OR 8.08, 95% CrI 4.85-13.74) were independently associated with increasing hospital mortality. Similar results were found between increasing age and post-ECMO complications.

CONCLUSIONS

Among patients receiving VV-ECMO for acute respiratory failure, increasing age is significantly associated with poorer outcomes, and this association emerges as early as 30 years of age.

Survival and Long-Term Functional Status of COVID-19 Patients Requiring Prolonged Extracorporeal Membrane Oxygenation Support

Rationale: Severe cases of acute respiratory distress syndrome (ARDS) may require prolonged (>28 d) extracorporeal membrane oxygenation (ECMO). In nonresolving disease, recovery is uncertain, and lung transplant may be proposed. Objectives: This study aims to identify the variables influencing survival and to describe the functional status of these patients at 6 months. Methods: This was a retrospective, multicenter, observational cohort study including patients requiring ECMO support for coronavirus disease (COVID-19)-related ARDS for >28 days. Multivariate analysis was performed using Cox regression in preselected variables and in least absolute shrinkage and selection operator selected variables. In a post hoc analysis to account for confounders and differences in awake strategy use by centers, treatment effects of the awake strategy were estimated using an augmented inverse probability weighting estimator with robust standard errors clustered by center. Results: Between March 15, 2020 and March 15, 2021, 120 patients required ECMO for >28 days. Sixty-four patients (53.3%) survived decannulation, 62 (51.7%) were alive at hospital discharge, and 61 (50.8%) were alive at 6-month follow-up. In the multivariate analysis, age (1.09; 95% confidence interval [CI], 1.03-1.15; P = 0.002) and an awake ECMO strategy (defined as the patient being awake, cooperative, and performing rehabilitation and physiotherapy with or without invasive mechanical ventilation at any time during the extracorporeal support) (0.14; 95% CI, 0.03-0.47; P = 0.003) were found to be predictors of hospital survival. At 6 months, 51 (42.5%) patients were at home, 42 (84.3%) of them without oxygen therapy. A cutoff point of 47 ECMO days had a 100% (95% CI, 76.8-100%) sensitivity and 60% (95% CI, 44.3-73.6%) specificity for oxygen therapy at 6 months, with 100% specificity being found in 97 days. Conclusions: Patients with COVID-19 who require ECMO for >28 days can survive with nonlimiting lung impairment. Age and an awake ECMO strategy may be associated with survival. Longer duration of support correlates with need for oxygen therapy at 6 months.

Long-term outcomes of patients supported with extracorporeal membrane oxygenation for acute respiratory distress syndrome: a systematic review and meta-analysis

BACKGROUND

Extracorporeal membrane oxygenation (ECMO) is increasingly used to support patients with severe acute respiratory distress syndrome (ARDS). The impact of ECMO on long-term outcomes of patients with severe ARDS is unclear.

METHODS

We searched electronic databases from inception to January 17th 2023. We selected clinical trials and observational studies reporting on long-term outcomes of patients supported with ECMO for ARDS. Health-related quality of life (HRQoL) was the primary outcome. Secondary outcomes included cognitive function, mental health, functional status, respiratory symptoms, and return to work.

RESULTS

Of the 7126 screened citations, 1 randomized clinical trial and 31 observational studies were included, of which 7 compared conventional mechanical ventilation (CMV) and ECMO. Overall quality of studies of the included studies was limited, with the majority being either low (45%) or fair (32%) quality. There was no significant difference in HRQoL measured with the SF-36 score between ECMO and CMV patients (physical component score [PCS]: mean difference 3.91 (- 6.22 to 14.05), mental component score [MCS] mean difference 1.33 (- 3.93 to 6.60)). There was no difference between cognitive function, mental health, functional status, and respiratory symptoms between ECMO and CMV, but data available for comparison were limited. There were high rates of disability for ECMO survivors with 49% of patients returning to work and 23% needing assistance at home on follow-up.

CONCLUSION

Survivors of ECMO for ARDS experience significant disability in multiple domains. Further studies are needed to examine the effect of ECMO on long-term outcomes of patients compared to CMV.

Venovenous extracorporeal membrane oxygenation for respiratory failure refractory to high frequency percussive ventilation

BACKGROUND

High frequency percussive ventilation (HFPV) has demonstrated improvements in gas exchange, but not in clinical outcomes.

OBJECTIVES

We utilize HFPV in patients failing conventional ventilation (CV), with rescue venovenous extracorporeal membrane oxygenation (VV ECMO) reserved for failure of HFPV, and we describe our experience with such a strategy.

METHODS

All adult patients (age >18 years) placed on HFPV for failure of CV at a single institution over a 10-year period were included. Those maintained on HFPV were compared to those that failed HFPV and required VV ECMO. Survival was compared to expected survival after upfront VV ECMO as estimated by VV ECMO risk prediction models.

RESULTS

Sixty-four patients were placed on HFPV for failure of CV over a 10-year period. After HFPV initiation, the P/F ratio rose from 76mmHg to 153.3mmHg in the 69 % of patients successfully maintained on HFPV. The P/F ratio only rose from 60.3mmHg to 67mmHg in the other 31 % of patients, and they underwent rescue ECMO with the P/F ratio rising to 261.6mmHg. The P/F ratio continued to improve in HFPV patients, while it declined in ECMO patients, such that at 24 h, the P/F ratio was greater in HFPV patients. The strongest independent predictor of failure of HFPV requiring rescue VV ECMO was a lower pO2 (p = .055). Overall in-hospital survival (59.4 %) was similar to that expected with upfront ECMO (RESP score: 57 %).

CONCLUSIONS

HFPV demonstrated significant and sustained improvements in gas exchange and may obviate the need for ECMO and its associated complications.

Long-Term Neuropsychiatric, Neurocognitive, and Functional Outcomes of Patients Receiving ECMO: A Systematic Review and Meta-Analysis

BACKGROUND AND OBJECTIVES

Despite the common occurrence of neurologic complications during extracorporeal membrane oxygenation (ECMO) support, data on long-term neuropsychiatric, neurocognitive, and functional outcomes are sparse. We aimed to determine the prevalence of long-term neuropsychiatric symptoms, neurocognitive and functional impairment, and favorable neurologic outcomes in adult patients who receive ECMO.

METHODS

PubMed, Embase, Cochrane, Web of Science, and Scopus were searched for text related to ECMO and neuropsychiatric, neurocognitive, and functional outcomes from inception to May 3, 2023. Our primary outcome was the prevalence of neuropsychiatric symptoms (pain/discomfort, anxiety, depression, posttraumatic stress disorder [PTSD], and sleep disturbance) at long-term (≥6 months) follow-up. Our secondary outcomes were the prevalence of neurocognitive impairment (memory, attention, and reasoning), functional impairment (daily activities, physical activity/mobility, and personal/self-care), and favorable neurologic outcomes (Cerebral Performance Category ≤2, modified Rankin scale ≤3, or Glasgow Outcome Scale ≥4). This study was registered in PROSPERO (CRD42023420565).

RESULTS

We included 59 studies with 3,280 patients (median age 54 years, 69% male). The cohort consisted of 86% venoarterial (VA)-ECMO (n = 2,819) and 14% venovenous (VV)-ECMO (n = 461) patients. More than 10 tools were used to assess neuropsychiatric and neurocognitive outcomes, indicating a lack of standardization in assessment methodologies. The overall prevalence of neuropsychiatric symptoms was 41% (95% CI 33%-49%): pain/discomfort (52%, 95% CI 42%-63%), sleep disturbance (37%, 95% CI 0%-98%), anxiety (36%, 95% CI 27%-46%), depression (31%, 95% CI 22%-40%), and PTSD (18%, 95% CI 9%-29%). The prevalence of neurocognitive impairment was 38% (95% CI 13%-65%). The prevalence of functional impairment was 52% (95% CI 40%-64%): daily activities (54%, 95% CI 41%-66%), mobility (41%, 95% CI 28%-54%), and self-care (21%, 95% CI 13%-31%). The prevalence of neuropsychiatric symptoms in VV-ECMO patients was higher than that in VA-ECMO patients (55% [95% CI 34%-75%] vs 32% [95% CI 23%-41%], p = 0.01), though the prevalence of neurocognitive and functional impairment was not different between the groups. The prevalence of favorable neurologic outcomes was not different at various follow-ups: 3 months (23%, 95% CI 12%-36%), 6 months (25%, 95% CI 16%-35%), and ≥1 year (28%, 95% CI 21%-36%, p = 0.68).

DISCUSSION

A substantial proportion of ECMO patients seemed to experience neuropsychiatric symptoms and neurocognitive and functional impairments at long-term follow-up. Considerable heterogeneity in methodology for gauging these outcomes exists, warranting the need for standardization. Multicenter prospective observational studies are indicated to further investigate risk factors for these outcomes in ECMO-supported patients.

Mesenchymal stem cells-based therapies for severe ARDS with ECMO: a review

Acute respiratory distress syndrome (ARDS) is the primary cause of respiratory failure in critically ill patients. Despite remarkable therapeutic advances in recent years, ARDS remains a life-threatening clinical complication with high morbidity and mortality, especially during the global spread of the coronavirus disease 2019 (COVID-19) pandemic. Previous studies have demonstrated that mesenchymal stem cell (MSC)-based therapy is a potential alternative strategy for the treatment of refractory respiratory diseases including ARDS, while extracorporeal membrane oxygenation (ECMO) as the last resort treatment to sustain life can help improve the survival of ARDS patients. In recent years, several studies have explored the effects of ECMO combined with MSC-based therapies in the treatment of ARDS, and some of them have demonstrated that this combination can provide better therapeutic effects, while others have argued that some critical issues need to be solved before it can be applied to clinical practice. This review presents an overview of the current status, clinical challenges and future prospects of ECMO combined with MSCs in the treatment of ARDS.

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.

Cohort profile: the China surgery and anesthesia cohort (CSAC)

The China Surgery and Anaesthesia Cohort (CSAC) study was launched in July 2020 and is an ongoing prospective cohort study recruiting patients aged 40-65 years who underwent elective surgeries with general anaesthesia across four medical centres in China. The general objective of the CSAC study is to improve our understanding of the complex interaction between environmental and genetic components as well as to determine their effects on a wide range of interested surgery/anaesthesia-related outcomes. To achieve this goal, we collected enriched phenotypic data, e.g., sociodemographic characteristics, lifestyle factors, perioperative neuropsychological changes, anaesthesia- and surgery-related complications, and medical conditions, at recruitment, as well as through both active (at 1, 3, 7 days and 1, 3, 6, 12 months after surgery) and passive (for more than 1 year after surgery) follow-up assessments. We also obtained omics data from blood samples. In addition, COVID-19-related information was collected from all participants since January 2023, immediately after COVID-19 restrictions were eased in China. As of July 18, 2023, 12,766 participants (mean age = 52.40 years, 57.93% were female) completed baseline data collection (response rate = 94.68%), among which approximately 70% donated blood and hair samples. The follow-up rates within 12 months after surgery were > 92%. Our initial analyses have demonstrated the incidence of and risk factors for chronic postsurgical pain (CPSP) and postoperative cognitive dysfunction (POCD) among middle-aged Chinese individuals, which may prompt further mechanistic exploration and facilitate the development of effective interventions for preventing those conditions. Additional studies, such as genome-wide association analyses for identifying the genetic determinants of CPSP and POCD, are ongoing, and their findings will be released in the future.

Predicting Acute Brain Injury in Venoarterial Extracorporeal Membrane Oxygenation Patients with Tree-Based Machine Learning: Analysis of the Extracorporeal Life Support Organization Registry

Objective

To determine if machine learning (ML) can predict acute brain injury (ABI) and identify modifiable risk factors for ABI in venoarterial extracorporeal membrane oxygenation (VA-ECMO) patients.

Design

Retrospective cohort study of the Extracorporeal Life Support Organization (ELSO) Registry (2009-2021).

Setting

International, multicenter registry study of 676 ECMO centers.

Patients

Adults (≥18 years) supported with VA-ECMO or extracorporeal cardiopulmonary resuscitation (ECPR).

Interventions

None.

Measurements and Main Results

Our primary outcome was ABI: central nervous system (CNS) ischemia, intracranial hemorrhage (ICH), brain death, and seizures. We utilized Random Forest, CatBoost, LightGBM and XGBoost ML algorithms (10-fold leave-one-out cross-validation) to predict and identify features most important for ABI. We extracted 65 total features: demographics, pre-ECMO/on-ECMO laboratory values, and pre-ECMO/on-ECMO settings.Of 35,855 VA-ECMO (non-ECPR) patients (median age=57.8 years, 66% male), 7.7% (n=2,769) experienced ABI. In VA-ECMO (non-ECPR), the area under the receiver-operator characteristics curves (AUC-ROC) to predict ABI, CNS ischemia, and ICH was 0.67, 0.67, and 0.62, respectively. The true positive, true negative, false positive, false negative, positive, and negative predictive values were 33%, 88%, 12%, 67%, 18%, and 94%, respectively for ABI. Longer ECMO duration, higher 24h ECMO pump flow, and higher on-ECMO PaO2 were associated with ABI.Of 10,775 ECPR patients (median age=57.1 years, 68% male), 16.5% (n=1,787) experienced ABI. The AUC-ROC for ABI, CNS ischemia, and ICH was 0.72, 0.73, and 0.69, respectively. The true positive, true negative, false positive, false negative, positive, and negative predictive values were 61%, 70%, 30%, 39%, 29% and 90%, respectively, for ABI. Longer ECMO duration, younger age, and higher 24h ECMO pump flow were associated with ABI.

Conclusions

This is the largest study predicting neurological complications on sufficiently powered international ECMO cohorts. Longer ECMO duration and higher 24h pump flow were associated with ABI in both non-ECPR and ECPR VA-ECMO.

Risk factors for prolonged mechanical ventilation in critically ill patients with influenza-related acute respiratory distress syndrome

BACKGROUND

Patients with influenza-related acute respiratory distress syndrome (ARDS) are critically ill and require mechanical ventilation (MV) support. Prolonged mechanical ventilation (PMV) is often seen in these cases and the optimal management strategy is not established. This study aimed to investigate risk factors for PMV and factors related to weaning failure in these patients.

METHODS

This retrospective cohort study was conducted by eight medical centers in Taiwan. All patients in the intensive care unit with virology-proven influenza-related ARDS requiring invasive MV from January 1 to March 31, 2016, were included. Demographic data, critical illness data and clinical outcomes were collected and analyzed. PMV is defined as mechanical ventilation use for more than 21 days.

RESULTS

There were 263 patients with influenza-related ARDS requiring invasive MV enrolled during the study period. Seventy-eight patients had PMV. The final weaning rate was 68.8% during 60 days of observation. The mortality rate in PMV group was 39.7%. Risk factors for PMV were body mass index (BMI) > 25 (kg/m2) [odds ratio (OR) 2.087; 95% confidence interval (CI) 1.006-4.329], extracorporeal membrane oxygenation (ECMO) use (OR 6.181; 95% CI 2.338-16.336), combined bacterial pneumonia (OR 4.115; 95% CI 2.002-8.456) and neuromuscular blockade use over 48 h (OR 2.8; 95% CI 1.334-5.879). In addition, risk factors for weaning failure in PMV patients were ECMO (OR 5.05; 95% CI 1.75-14.58) use and bacteremia (OR 3.91; 95% CI 1.20-12.69).

CONCLUSIONS

Patients with influenza-related ARDS and PMV have a high mortality rate. Risk factors for PMV include BMI > 25, ECMO use, combined bacterial pneumonia and neuromuscular blockade use over 48 h. In addition, ECMO use and bacteremia predict unsuccessful weaning in PMV patients.

Supervised machine learning model to predict mortality in patients undergoing venovenous extracorporeal membrane oxygenation from a nationwide multicentre registry

BACKGROUND

Existing models have performed poorly when predicting mortality for patients undergoing venovenous extracorporeal membrane oxygenation (VV-ECMO). This study aimed to develop and validate a machine learning (ML)-based prediction model to predict 90-day mortality in patients undergoing VV-ECMO.

METHODS

This study included 368 patients with acute respiratory failure undergoing VV-ECMO from 16 tertiary hospitals across South Korea between 2012 and 2015. The primary outcome was the 90-day mortality after ECMO initiation. The inputs included all available features (n=51) and those from the electronic health record (EHR) systems without preprocessing (n=40). The discriminatory strengths of ML models were evaluated in both internal and external validation sets. The models were compared with conventional models, such as respiratory ECMO survival prediction (RESP) and predicting death for severe acute respiratory distress syndrome on VV-ECMO (PRESERVE).

RESULTS

Extreme gradient boosting (XGB) (areas under the receiver operating characteristic curve, AUROC 0.82, 95% CI (0.73 to 0.89)) and light gradient boosting (AUROC 0.81 (95% CI 0.71 to 0.88)) models achieved the highest performance using EHR's and all other available features. The developed models had higher AUROCs (95% CI 0.76 to 0.82) than those of RESP (AUROC 0.66 (95% CI 0.56 to 0.76)) and PRESERVE (AUROC 0.71 (95% CI 0.61 to 0.81)). Additionally, we achieved an AUROC (0.75) for 90-day mortality in external validation in the case of the XGB model, which was higher than that of RESP (0.70) and PRESERVE (0.67) in the same validation dataset.

CONCLUSIONS

ML prediction models outperformed previous mortality risk models. This model may be used to identify patients who are unlikely to benefit from VV-ECMO therapy during patient selection.

Critical evaluation of established risk prediction models for acute respiratory distress syndrome in adult patients: A systematic review and meta-analysis

AIM

To assess the performance of validated prediction models for acute respiratory distress syndrome (ARDS) by systematic review and meta-analysis.

METHODS

Eight databases (Medline, CINAHL, Embase, The Cochrane Library, CNKI, WanFang Data, Sinomed, and VIP) were searched up to March 26, 2023. Studies developed and validated a prediction model for ARDS in adult patients were included. Items on study design, incidence, derivation methods, predictors, discrimination, and calibration were collected. The risk of bias was assessed by the Prediction model Risk of Bias Assessment Tool. Models with a reported area under the curve of the receiver operating characteristic (AUC) metric were analyzed.

RESULTS

A total of 25 studies were retrieved, including 48 unique prediction models. Discrimination was reported in all studies, with AUC ranging from 0.701 to 0.95. Emerged AUC value of the logistic regression model was 0.837 (95% CI: 0.814 to 0.859). Besides, the value in the ICU group was 0.856 (95% CI: 0.812 to 0.899), the acute pancreatitis group was 0.863 (95% CI: 0.844 to 0.882), and the postoperation group was 0.835 (95% CI: 0.808 to 0.861). In total, 24 of the included studies had a high risk of bias, which was mostly due to the improper methods in predictor screening (13/24), model calibration assessment (9/24), and dichotomization of continuous predictors (6/24).

CONCLUSIONS

This study shows that most prediction models for ARDS are at high risk of bias, and the discrimination ability of the model is excellent. Adherence to standardized guidelines for model development is necessary to derive a prediction model of value to clinicians.