Is There a Safe Plateau Pressure Threshold for Patients with Acute Lung Injury and Acute Respiratory Distress Syndrome?

Predicting ICU Mortality in Acute Respiratory Distress Syndrome Patients Using Machine Learning: The Predicting Outcome and STratifiCation of severity in ARDS (POSTCARDS) Study

OBJECTIVES

To assess the value of machine learning approaches in the development of a multivariable model for early prediction of ICU death in patients with acute respiratory distress syndrome (ARDS).

DESIGN

A development, testing, and external validation study using clinical data from four prospective, multicenter, observational cohorts.

SETTING

A network of multidisciplinary ICUs.

PATIENTS

A total of 1,303 patients with moderate-to-severe ARDS managed with lung-protective ventilation.

INTERVENTIONS

None.

MEASUREMENTS AND MAIN RESULTS

We developed and tested prediction models in 1,000 ARDS patients. We performed logistic regression analysis following variable selection by a genetic algorithm, random forest and extreme gradient boosting machine learning techniques. Potential predictors included demographics, comorbidities, ventilatory and oxygenation descriptors, and extrapulmonary organ failures. Risk modeling identified some major prognostic factors for ICU mortality, including age, cancer, immunosuppression, Pa o2 /F io2 , inspiratory plateau pressure, and number of extrapulmonary organ failures. Together, these characteristics contained most of the prognostic information in the first 24 hours to predict ICU mortality. Performance with machine learning methods was similar to logistic regression (area under the receiver operating characteristic curve [AUC], 0.87; 95% CI, 0.82-0.91). External validation in an independent cohort of 303 ARDS patients confirmed that the performance of the model was similar to a logistic regression model (AUC, 0.91; 95% CI, 0.87-0.94).

CONCLUSIONS

Both machine learning and traditional methods lead to promising models to predict ICU death in moderate/severe ARDS patients. More research is needed to identify markers for severity beyond clinical determinants, such as demographics, comorbidities, lung mechanics, oxygenation, and extrapulmonary organ failure to guide patient management.

Stratification for Identification of Prognostic Categories In the Acute RESpiratory Distress Syndrome (SPIRES) Score

OBJECTIVES

To develop a scoring model for stratifying patients with acute respiratory distress syndrome into risk categories (Stratification for identification of Prognostic categories In the acute RESpiratory distress syndrome score) for early prediction of death in the ICU, independent of the underlying disease and cause of death.

DESIGN

A development and validation study using clinical data from four prospective, multicenter, observational cohorts.

SETTING

A network of multidisciplinary ICUs.

PATIENTS

One-thousand three-hundred one patients with moderate-to-severe acute respiratory distress syndrome managed with lung-protective ventilation.

INTERVENTIONS

None.

MEASUREMENTS AND MAIN RESULTS

The study followed Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis guidelines for prediction models. We performed logistic regression analysis, bootstrapping, and internal-external validation of prediction models with variables collected within 24 hours of acute respiratory distress syndrome diagnosis in 1,000 patients for model development. Primary outcome was ICU death. The Stratification for identification of Prognostic categories In the acute RESpiratory distress syndrome score was based on patient's age, number of extrapulmonary organ failures, values of end-inspiratory plateau pressure, and ratio of Pao2 to Fio2 assessed at 24 hours of acute respiratory distress syndrome diagnosis. The pooled area under the receiver operating characteristic curve across internal-external validations was 0.860 (95% CI, 0.831-0.890). External validation in a new cohort of 301 acute respiratory distress syndrome patients confirmed the accuracy and robustness of the scoring model (area under the receiver operating characteristic curve = 0.870; 95% CI, 0.829-0.911). The Stratification for identification of Prognostic categories In the acute RESpiratory distress syndrome score stratified patients in three distinct prognostic classes and achieved better prediction of ICU death than ratio of Pao2 to Fio2 at acute respiratory distress syndrome onset or at 24 hours, Acute Physiology and Chronic Health Evaluation II score, or Sequential Organ Failure Assessment scale.

CONCLUSIONS

The Stratification for identification of Prognostic categories In the acute RESpiratory distress syndrome score represents a novel strategy for early stratification of acute respiratory distress syndrome patients into prognostic categories and for selecting patients for therapeutic trials.

Age, PaO2/FIO2, and Plateau Pressure Score: A Proposal for a Simple Outcome Score in Patients With the Acute Respiratory Distress Syndrome

OBJECTIVES

Although there is general agreement on the characteristic features of the acute respiratory distress syndrome, we lack a scoring system that predicts acute respiratory distress syndrome outcome with high probability. Our objective was to develop an outcome score that clinicians could easily calculate at the bedside to predict the risk of death of acute respiratory distress syndrome patients 24 hours after diagnosis.

DESIGN

A prospective, multicenter, observational, descriptive, and validation study.

SETTING

A network of multidisciplinary ICUs.

PATIENTS

Six-hundred patients meeting Berlin criteria for moderate and severe acute respiratory distress syndrome enrolled in two independent cohorts treated with lung-protective ventilation.

INTERVENTIONS

None.

MEASUREMENTS AND MAIN RESULTS

Using individual demographic, pulmonary, and systemic data at 24 hours after acute respiratory distress syndrome diagnosis, we derived our prediction score in 300 acute respiratory distress syndrome patients based on stratification of variable values into tertiles, and validated in an independent cohort of 300 acute respiratory distress syndrome patients. Primary outcome was in-hospital mortality. We found that a 9-point score based on patient's age, PaO2/FIO2 ratio, and plateau pressure at 24 hours after acute respiratory distress syndrome diagnosis was associated with death. Patients with a score greater than 7 had a mortality of 83.3% (relative risk, 5.7; 95% CI, 3.0-11.0), whereas patients with scores less than 5 had a mortality of 14.5% (p < 0.0000001). We confirmed the predictive validity of the score in a validation cohort.

CONCLUSIONS

A simple 9-point score based on the values of age, PaO2/FIO2 ratio, and plateau pressure calculated at 24 hours on protective ventilation after acute respiratory distress syndrome diagnosis could be used in real time for rating prognosis of acute respiratory distress syndrome patients with high probability.

Role of extracorporeal membrane oxygenation in adult respiratory failure: an overview

Extracorporeal membrane oxygenation (ECMO) provides complete or partial support of the heart and lungs. Ever since its inception in the 1960s, it has been used across all age groups in the management of refractory respiratory failure and cardiogenic shock. While it has gained widespread acceptance in the neonatal and pediatric physician community, ECMO remains a controversial therapy for Acute Respiratory Distress Syndrome (ARDS) in adults. Its popularity was revived during the swine flu (H1N1) pandemic and advancements in technology have contributed to its increasing usage. ARDS continues to be a potentially devastating condition with significant mortality rates. Despite gaining more insights into this entity over the years, mechanical ventilation remains the only life-saving, yet potentially harmful intervention available for ARDS. ECMO shows promise in this regard by offering less dependence on mechanical ventilation, thereby potentially reducing ventilator-induced injury. However, the lack of rigorous clinical data has prevented ECMO from becoming the standard of care in the management of ARDS. Therefore, the results of two large ongoing randomized trials, which will hopefully throw more light on the role of ECMO in the management of this disease entity, are keenly awaited. In this article we will provide a basic overview of the development of ECMO, the types of ECMO, the pathogenesis of ARDS, different ventilation strategies for ARDS, the role of ECMO in ARDS and the role of ECMO as a bridge to lung transplantation.

Pulmonary acute respiratory distress syndrome: positive end-expiratory pressure titration needs stress index

BACKGROUND

The heterogeneity of lung injury in pulmonary acute respiratory distress syndrome (ARDS) may have contributed to the greater response of hyperinflated area with positive end-expiratory pressure (PEEP). PEEP titrated by stress index can reduce the risk of alveolar hyperinflation in patients with pulmonary ARDS. The authors sought to investigate the effects of PEEP titrated by stress index on lung recruitment and protection after recruitment maneuver (RM) in pulmonary ARDS patients.

MATERIALS AND METHODS

Thirty patients with pulmonary ARDS were enrolled. After RM, PEEP was randomly set according to stress index, oxygenation, static pulmonary compliance (Cst), or lower inflection point (LIP) + 2 cmH2O strategies. Recruitment volume, gas exchange, respiratory mechanics, and hemodynamic parameters were collected.

RESULTS

PEEP titrated by stress index (15.1 ± 1.8 cmH2O) was similar to the levels titrated by oxygenation (14.5 ± 2.9 cmH2O), higher than that titrated by Cst (11.3 ± 2.5 cmH2O) and LIP (12.9 ± 1.6 cmH2O) (P < 0.05). Compared with baseline, PaO2/FiO2 and recruitment volume were significantly improved after PEEP titration with the four strategies (P < 0.05). PaO2/FiO2 and recruitment volume were similar when using PEEP titrated by stress index and oxygenation but higher than that titrated by Cst and LIP. Compared with baseline, lung compliance increased significantly when PEEP determined by Cst, but there was no difference of Cst in these four strategies. There was no influence of PEEP titration with the four strategies on hemodynamic parameters.

CONCLUSIONS

PEEP titration by stress index might be more beneficial for pulmonary ARDS patients after RM.

Model-based respiratory mechanics to titrate PEEP and monitor disease state for experimental ARDS subjects

Modelling the respiratory mechanics of mechanically ventilated (MV) patients can provide useful information to guide MV therapy. Two model-based methods were evaluated based on data from three experimental acute respiratory distress syndrome (ARDS) induced piglets and validated against values available from ventilators. A single compartment lung model with integral-based parameter identification was found to be effective in capturing fundamental respiratory mechanics during inspiration. The trends matched clinical expectation and provided better resolution than clinically derived linear model metrics. An expiration time constant model also captured the same trend in respiratory elastance. However, the assumption of constant resistance and a slightly higher fitting error results in less insight than the single compartment model. Further research is required to confirm its application in titrating to optimal MV settings.

Adaptive support ventilation versus conventional ventilation for total ventilatory support in acute respiratory failure

OBJECTIVE

To compare the short-term effects of adaptive support ventilation (ASV), an advanced closed-loop mode, with conventional volume or pressure-control ventilation in patients passively ventilated for acute respiratory failure.

DESIGN

Prospective crossover interventional multicenter trial.

SETTING

Six European academic intensive care units.

PATIENTS

Eighty-eight patients in three groups: patients with no obvious lung disease (n = 22), restrictive lung disease (n = 36) or obstructive lung disease (n = 30).

INTERVENTIONS

After measurements on conventional ventilation (CV) as set by the patients' clinicians, each patient was switched to ASV set to obtain the same minute ventilation as during CV (isoMV condition). If this resulted in a change in PaCO(2), the minute ventilation setting of ASV was readjusted to achieve the same PaCO(2) as in CV (isoCO(2) condition).

MEASUREMENTS AND RESULTS

Compared with CV, PaCO(2) during ASV in isoMV condition and minute ventilation during ASV in isoCO(2) condition were slightly lower, with lower inspiratory work/minute performed by the ventilator (p < 0.01). Oxygenation and hemodynamics were unchanged. During ASV, respiratory rate was slightly lower and tidal volume (Vt) slightly greater (p < 0.01), especially in obstructed patients. During ASV there were different ventilatory patterns in the three groups, with lower Vt in patients with restrictive disease and prolonged expiratory time in obstructed patients, thus mimicking the clinicians' choices for setting CV. In three chronic obstructive pulmonary disease patients the resulting Vt was unacceptably high.

CONCLUSIONS

Comparison between ASV and CV resulted either in similarities or in minor differences. Except for excessive Vt in a few obstructed patients, all differences were in favor of ASV.