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.

Dexamethasone treatment for the acute respiratory distress syndrome: a multicentre, randomised controlled trial.

BACKGROUND: There is no proven specific pharmacological treatment for patients with the acute respiratory distress syndrome (ARDS). The efficacy of corticosteroids in ARDS remains controversial. We aimed to assess the effects of dexamethasone in ARDS, which might change pulmonary and systemic inflammation and result in a decrease in duration of mechanical ventilation and mortality. METHODS: We did a multicentre, randomised controlled trial in a network of 17 intensive care units (ICUs) in teaching hospitals across Spain in patients with established moderate-to-severe ARDS (defined by a ratio of partial pressure of arterial oxygen to the fraction of inspired oxygen of 200 mm Hg or less assessed with a positive end-expiratory pressure of 10 cm H2O or more and FiO2 of 0·5 or more at 24 h after ARDS onset). Patients with brain death, terminal-stage disease, or receiving corticosteroids or immunosuppressive drugs were excluded. Eligible patients were randomly assigned based on balanced treatment assignments with a computerised randomisation allocation sequence using blocks of 10 opaque, sealed envelopes to receive immediate treatment with dexamethasone or continued routine intensive care (control group). Patients in the dexamethasone group received an intravenous dose of 20 mg once daily from day 1 to day 5, which was reduced to 10 mg once daily from day 6 to day 10. Patients in both groups were ventilated with lung-protective mechanical ventilation. Allocation concealment was maintained at all sites during the trial. Primary outcome was the number of ventilator-free days at 28 days, defined as the number of days alive and free from mechanical ventilation from day of randomisation to day 28. Secondary outcome was all-cause mortality 60 days after randomisation. All analyses were done according to the intention-to-treat principle. This study is registered with ClinicalTrials.gov, NCT01731795. FINDINGS: Between March 28, 2013, and Dec 31, 2018, we enrolled 277 patients and randomly assigned 139 patients to the dexamethasone group and 138 to the control group. The trial was stopped by the data safety monitoring board due to low enrolment rate after enrolling more than 88% (277/314) of the planned sample size. The mean number of ventilator-free days was higher in the dexamethasone group than in the control group (between-group difference 4·8 days [95% CI 2·57 to 7·03]; p<0·0001). At 60 days, 29 (21%) patients in the dexamethasone group and 50 (36%) patients in the control group had died (between-group difference -15·3% [-25·9 to -4·9]; p=0·0047). The proportion of adverse events did not differ significantly between the dexamethasone group and control group. The most common adverse events were hyperglycaemia in the ICU (105 [76%] patients in the dexamethasone group vs 97 [70%] patients in the control group), new infections in the ICU (eg, pneumonia or sepsis; 33 [24%] vs 35 [25%]), and barotrauma (14 [10%] vs 10 [7%]). INTERPRETATION: Early administration of dexamethasone could reduce duration of mechanical ventilation and overall mortality in patients with established moderate-to-severe ARDS. FUNDING: Fundación Mutua Madrileña, Instituto de Salud Carlos III, The European Regional Development's Funds, Asociación Científica Pulmón y Ventilación Mecánica.

A Prognostic Enrichment Strategy for Selection of Patients With Acute Respiratory Distress Syndrome in Clinical Trials.

OBJECTIVES: Incomplete or ambiguous evidence for identifying high-risk patients with acute respiratory distress syndrome for enrollment into randomized controlled trials has come at the cost of an unreasonable number of negative trials. We examined a set of selected variables early in acute respiratory distress syndrome to determine accurate prognostic predictors for selecting high-risk patients for randomized controlled trials. DESIGN: A training and testing study using a secondary analysis of data from four prospective, multicenter, observational studies. SETTING: A network of multidisciplinary ICUs. PATIENTS: We studied 1,200 patients with moderate-to-severe acute respiratory distress syndrome managed with lung-protective ventilation. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: We evaluated different thresholds for patient's age, PaO2/FIO2, plateau pressure, and number of extrapulmonary organ failures to predict ICU outcome at 24 hours of acute respiratory distress syndrome diagnosis. We generated 1,000 random scenarios as training (n = 900, 75% of population) and testing (n = 300, 25% of population) datasets and averaged the logistic coefficients for each scenario. Thresholds for age (< 50, 50-70, > 70 yr), PaO2/FIO2 (≤ 100, 101-150, > 150 mm Hg), plateau pressure (< 29, 29-30, > 30 cm H2O), and number of extrapulmonary organ failure (< 2, 2, > 2) stratified accurately acute respiratory distress syndrome patients into categories of risk. The model that included all four variables proved best to identify patients with the highest or lowest risk of death (area under the receiver operating characteristic curve, 0.86; 95% CI, 0.84-0.88). Decision tree analyses confirmed the accuracy and robustness of this enrichment model. CONCLUSIONS: Combined thresholds for patient's age, PaO2/FIO2, plateau pressure, and extrapulmonary organ failure provides prognostic enrichment accuracy for stratifying and selecting acute respiratory distress syndrome patients for randomized controlled trials.

A Quantile Analysis of Plateau and Driving Pressures: Effects on Mortality in Patients With Acute Respiratory Distress Syndrome Receiving Lung-Protective Ventilation.

OBJECTIVES: The driving pressure (plateau pressure minus positive end-expiratory pressure) has been suggested as the major determinant for the beneficial effects of lung-protective ventilation. We tested whether driving pressure was superior to the variables that define it in predicting outcome in patients with acute respiratory distress syndrome. DESIGN: A secondary analysis of existing data from previously reported observational studies. SETTING: A network of ICUs. PATIENTS: We studied 778 patients with moderate to severe acute respiratory distress syndrome. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: We assessed the risk of hospital death based on quantiles of tidal volume, positive end-expiratory pressure, plateau pressure, and driving pressure evaluated at 24 hours after acute respiratory distress syndrome diagnosis while ventilated with standardized lung-protective ventilation. We derived our model using individual data from 478 acute respiratory distress syndrome patients and assessed its replicability in a separate cohort of 300 acute respiratory distress syndrome patients. Tidal volume and positive end-expiratory pressure had no impact on mortality. We identified a plateau pressure cut-off value of 29 cm H2O, above which an ordinal increment was accompanied by an increment of risk of death. We identified a driving pressure cut-off value of 19 cm H2O where an ordinal increment was accompanied by an increment of risk of death. When we cross tabulated patients with plateau pressure less than 30 and plateau pressure greater than or equal to 30 with those with driving pressure less than 19 and driving pressure greater than or equal to 19, plateau pressure provided a slightly better prediction of outcome than driving pressure in both the derivation and validation cohorts (p < 0.0000001). CONCLUSIONS: Plateau pressure was slightly better than driving pressure in predicting hospital death in patients managed with lung-protective ventilation evaluated on standardized ventilator settings 24 hours after acute respiratory distress syndrome onset.

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.