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.

Clinical relevance of timing of assessment of ICU mortality in patients with moderate-to-severe Acute Respiratory Distress Syndrome.

Mortality is a frequently reported outcome in clinical studies of acute respiratory distress syndrome (ARDS). However, timing of mortality assessment has not been well characterized. We aimed to identify a crossing-point between cumulative survival and death in the intensive care unit (ICU) of patients with moderate-to-severe ARDS, beyond which the number of survivors would exceed the number of deaths. We hypothesized that this intersection would occur earlier in a successful clinical trial vs. observational studies of moderate/severe ARDS and predict treatment response. We conducted an ancillary study of 1580 patients with moderate-to-severe ARDS managed with lung-protective ventilation to assess the relevance and timing of measuring ICU mortality rates at different time-points during ICU stay. First, we analyzed 1303 patients from four multicenter, observational cohorts enrolling consecutive patients with moderate/severe ARDS. We assessed cumulative ICU survival from the time of moderate/severe ARDS diagnosis to ventilatory support discontinuation within 7-days, 28-days, 60-days, and at ICU discharge. Then, we compared these findings to those of a successful randomized trial of 277 moderate/severe ARDS patients. In the observational cohorts, ICU mortality (487/1303, 37.4%) and 28-day mortality (425/1102, 38.6%) were similar (p = 0.549). Cumulative proportion of ICU survivors and non-survivors crossed at day-7; after day-7, the number of ICU survivors was progressively higher compared to non-survivors. Measures of oxygenation, lung mechanics, and severity scores were different between survivors and non-survivors at each point-in-time (p < 0.001). In the trial cohort, the cumulative proportion of survivors and non-survivors in the treatment group crossed before day-3 after diagnosis of moderate/severe ARDS. In clinical ARDS studies, 28-day mortality closely approximates and may be used as a surrogate for ICU mortality. For patients with moderate-to-severe ARDS, ICU mortality assessment within the first week of a trial might be an early predictor of treatment response.

Normothermic Regional Perfusion in Pediatric Controlled Donation After Circulatory Death Can Lead to Optimal Organ Utilization and Posttransplant Outcomes.

BACKGROUND: The benefits of normothermic regional perfusion (NRP) in posttransplant outcomes after controlled donation after the determination of death by circulatory criteria (cDCD) has been shown in different international adult experiences. However, there is no information on the use of NRP in pediatric cDCD donors. METHODS: This is a multicenter, retrospective, observational cohort study describing the pediatric (<18 y) cDCD procedures performed in Spain, using either abdominal NRP or thoracoabdominal NRP and the outcomes of recipients of the obtained organs. RESULTS: Thirteen pediatric cDCD donors (age range, 2-17 y) subject to abdominal NRP or thoracoabdominal NRP were included. A total of 46 grafts (24 kidneys, 11 livers, 8 lungs, 2 hearts, and 1 pancreas) were finally transplanted (3.5 grafts per donor). The mean functional warm ischemic time was 15 min (SD 6 min)' and the median duration of NRP was 87 min (interquartile range, 69-101 min). One-year noncensored for death kidney graft survival was 91.3%. The incidence of delayed graft function was 13%. One-year' noncensored-for-death liver graft survival was 90.9%. All lung and pancreas recipients had an excellent evolution. One heart recipient died due to a septic shock. CONCLUSIONS: This is the largest experience of pediatric cDCD using NRP as graft preservation method. Although our study has several limitations, such as its retrospective nature and the small sample size, its reveals that NRP may increase the utilization of cDCD pediatric organs and offer optimal recipients' outcomes.

The PANDORA Study: Prevalence and Outcome of Acute Hypoxemic Respiratory Failure in the Pre-COVID-19 Era.

OBJECTIVES: To establish the epidemiological characteristics, ventilator management, and outcomes in patients with acute hypoxemic respiratory failure (AHRF), with or without acute respiratory distress syndrome (ARDS), in the era of lung-protective mechanical ventilation (MV). DESIGN: A 6-month prospective, epidemiological, observational study. SETTING: A network of 22 multidisciplinary ICUs in Spain. PATIENTS: Consecutive mechanically ventilated patients with AHRF (defined as Pao2/Fio2 ≤ 300 mm Hg on positive end-expiratory pressure [PEEP] ≥ 5 cm H2O and Fio2 ≥ 0.3) and followed-up until hospital discharge. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Primary outcomes were prevalence of AHRF and ICU mortality. Secondary outcomes included prevalence of ARDS, ventilatory management, and use of adjunctive therapies. During the study period, 9,803 patients were admitted: 4,456 (45.5%) received MV, 1,271 (13%) met AHRF criteria (1,241 were included into the study: 333 [26.8%] met Berlin ARDS criteria and 908 [73.2%] did not). At baseline, tidal volume was 6.9 ± 1.1 mL/kg predicted body weight, PEEP 8.4 ± 3.1 cm H2O, Fio2 0.63 ± 0.22, and plateau pressure 21.5 ± 5.4 cm H2O. ARDS patients received higher Fio2 and PEEP than non-ARDS (0.75 ± 0.22 vs 0.59 ± 0.20 cm H2O and 10.3 ± 3.4 vs 7.7 ± 2.6 cm H2O, respectively [p < 0.0001]). Adjunctive therapies were rarely used in non-ARDS patients. Patients without ARDS had higher ventilator-free days than ARDS (12.2 ± 11.6 vs 9.3 ± 9.7 d; p < 0.001). All-cause ICU mortality was similar in AHRF with or without ARDS (34.8% [95% CI, 29.7-40.2] vs 35.5% [95% CI, 32.3-38.7]; p = 0.837). CONCLUSIONS: AHRF without ARDS is a very common syndrome in the ICU with a high mortality that requires specific studies into its epidemiology and ventilatory management. We found that the prevalence of ARDS was much lower than reported in recent observational studies.

Malignancies in Deceased Organ Donors: The Spanish Experience.

BACKGROUND: To better define the risk of malignancy transmission through organ transplantation, we review the Spanish experience on donor malignancies. METHODS: We analyzed the outcomes of recipients of organs obtained from deceased donors diagnosed with a malignancy during 2013-2018. The risk of malignancy transmission was classified as proposed by the Council of Europe. RESULTS: Of 10 076 utilized deceased donors, 349 (3.5%) were diagnosed with a malignancy. Of those, 275 had a past (n = 168) or current (n = 107) history of malignancy known before the transplantation of organs into 651 recipients. Ten malignancies met high-risk criteria. No donor-transmitted cancer (DTC) was reported after a median follow-up of 24 (interquartile range [IQR]: 19-25) mo. The other 74 donors were diagnosed with a malignancy after transplantation. Within this group, 64 donors (22 with malignancies of high or unacceptable risk) whose organs were transplanted into 126 recipients did not result in a DTC after a median follow-up of 26 (IQR: 22-37) mo, though a prophylactic transplantectomy was performed in 5 patients. The remaining 10 donors transmitted an occult malignancy to 16 of 25 recipients, consisting of lung cancer (n = 9), duodenal adenocarcinoma (n = 2), renal cell carcinoma (n = 2), extrahepatic cholangiocarcinoma (n = 1), prostate cancer (n = 1), and undifferentiated cancer (n = 1). After a median follow-up of 14 (IQR: 11-24) mo following diagnosis, the evolution was fatal in 9 recipients. In total, of 802 recipients at risk, 16 (2%) developed a DTC, which corresponds to 6 cases per 10 000 organ transplants. CONCLUSIONS: Current standards may overestimate the risk of malignancy transmission. DTC is an infrequent but difficult to eliminate complication.

Abdominal normothermic regional perfusion in controlled donation after circulatory determination of death liver transplantation: Outcomes and risk factors for graft loss.

Postmortem normothermic regional perfusion (NRP) is a rising preservation strategy in controlled donation after circulatory determination of death (cDCD). Herein, we present results for cDCD liver transplants performed in Spain 2012-2019, with outcomes evaluated through December 31, 2020. Results were analyzed retrospectively and according to recovery technique (abdominal NRP [A-NRP] or standard rapid recovery [SRR]). During the study period, 545 cDCD liver transplants were performed with A-NRP and 258 with SRR. Median donor age was 59 years (interquartile range 49-67 years). Adjusted risk estimates were improved with A-NRP for overall biliary complications (OR 0.300, 95% CI 0.197-0.459, p < .001), ischemic type biliary lesions (OR 0.112, 95% CI 0.042-0.299, p < .001), graft loss (HR 0.371, 95% CI 0.267-0.516, p < .001), and patient death (HR 0.540, 95% CI 0.373-0.781, p = .001). Cold ischemia time (HR 1.004, 95% CI 1.001-1.007, p = .021) and re-transplantation indication (HR 9.552, 95% CI 3.519-25.930, p < .001) were significant independent predictors for graft loss among cDCD livers with A-NRP. While use of A-NRP helps overcome traditional limitations in cDCD liver transplantation, opportunity for improvement remains for cases with prolonged cold ischemia and/or technically complex recipients, indicating a potential role for complimentary ex situ perfusion preservation techniques.

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.

Improved short-term outcomes of kidney transplants in controlled donation after the circulatory determination of death with the use of normothermic regional perfusion.

Normothermic regional perfusion (NRP) allows the in situ perfusion of organs with oxygenated blood in donation after the circulatory determination of death (DCDD). We aimed at evaluating the impact of NRP on the short-term outcomes of kidney transplants in controlled DCDD (cDCDD). This is a multicenter, nationwide, retrospective study comparing cDCDD kidneys obtained with NRP versus the standard rapid recovery (RR) technique. During 2012-2018, 2302 cDCDD adult kidney transplants were performed in Spain using NRP (n = 865) or RR (n = 1437). The study groups differed in donor and recipient age, warm, and cold ischemic time and use of ex situ machine perfusion. Transplants in the NRP group were more frequently performed in high-volume centers (≥90 transplants/year). Through matching by propensity score, two cohorts with a total of 770 patients were obtained. After the matching, no statistically significant differences were observed between the groups in terms of primary nonfunction (p = .261) and mortality at 1 year (p =  .111). However, the RR of kidneys was associated with a significantly increased odds of delayed graft function (OR 1.97 [95% CI 1.43-2.72]; p < .001) and 1-year graft loss (OR 1.77 [95% CI 1.01-3.17]; p = .034). In conclusion, compared with RR, NRP appears to improve the short-term outcomes of cDCDD kidney transplants.

Results in liver transplantation using grafts from donors after controlled circulatory death: A single-center experience comparing donor grafts harvested after controlled circulatory death to those harvested after brain death.

BACKGROUND: In recent years, interest in donation after cardiac death (DCD) has increased. Although DCD liver transplantation (LT) has demonstrated satisfactory long-term outcomes, different studies have shown poorer patient and graft survival after DCD than after donation after brain death (DBD). This study aimed to evaluate the results of LT using controlled DCD (cDCD) donors, specifically the incidence of primary non-function and ischemic cholangiopathy (IC), and to compare these results with those of LT using DBD in the same time period. METHODS: Between June 2012 and July 2018, we performed 66 transplants using cDCD and 258 with DBD grafts. RESULTS: The incidence of IC was similar in both groups (2% in DBD, 1.5% in DCD; P = .999). No significant differences were found for overall graft and patient survival rates between the groups at 1 and 2 years post-transplantation. CONCLUSIONS: This study provided evidence that cDCD donors exhibit excellent graft and patient survival outcomes. When the warm ischemia time is <30 minutes and cold ischemia time is <6 hours, the graft and patient survival rates and the incidence of IC in DCD are similar to those in DBD, even when using donors without age restrictions.

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.

Is Overall Mortality the Right Composite Endpoint in Clinical Trials of Acute Respiratory Distress Syndrome?

OBJECTIVES: Overall mortality in patients with acute respiratory distress syndrome is a composite endpoint because it includes death from multiple causes. In most acute respiratory distress syndrome trials, it is unknown whether reported deaths are due to acute respiratory distress syndrome or the underlying disease, unrelated to the specific intervention tested. We investigated the causes of death after contracting acute respiratory distress syndrome in a large cohort. DESIGN: A secondary analysis from three prospective, multicenter, observational studies. SETTING: A network of multidisciplinary ICUs. PATIENTS: We studied 778 patients with moderate-to-severe acute respiratory distress syndrome treated with lung-protective ventilation. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: We examined death in the ICU from individual causes. Overall ICU mortality was 38.8% (95% CI, 35.4-42.3). Causes of acute respiratory distress syndrome modified the risk of death. Twenty-three percent of deaths occurred from refractory hypoxemia due to nonresolving acute respiratory distress syndrome. Most patients died from causes unrelated to acute respiratory distress syndrome: 48.7% of nonsurvivors died from multisystem organ failure, and cancer or brain injury was involved in 37.1% of deaths. When quantifying the true burden of acute respiratory distress syndrome outcome, we identified 506 patients (65.0%) with one or more exclusion criteria for enrollment into current interventional trials. Overall ICU mortality of the "trial cohort" (21.3%) was markedly lower than the parent cohort (relative risk, 0.55; 95% CI, 0.43-0.70; p < 0.000001). CONCLUSIONS: Most deaths in acute respiratory distress syndrome patients are not directly related to lung damage but to extrapulmonary multisystem organ failure. It would be challenging to prove that specific lung-directed therapies have an effect on overall survival.

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.

Lung donor treatment protocol in brain dead-donors: A multicenter study.

BACKGROUND: The shortage of lung donors for transplantation is the main limitation among patients awaiting this type of surgery. We previously demonstrated that an intensive lung donor-treatment protocol succeeded in increasing the lung procurement rate. We aimed to validate our protocol for centers with or without lung transplant programs. METHODS: A quasi-experimental study was performed to compare lung donor rate before (historical group, 2010 to 2012) and after (prospective group, 2013) the application of a lung management protocol for donors after brain death (DBDs) in six Spanish hospitals. Lung donor selection criteria remained unchanged in both periods. Outcome measures for lung recipients were early survival and primary graft dysfunction (PGD) rates. RESULTS: A total of 618 DBDs were included: 453 in the control period and 165 in the protocol period. Donor baseline characteristics were similar in both periods. Lung donation rate in the prospective group was 27.3%, more than twice that of the historical group (13%; p < 0.001). The number of lungs retrieved, grafts transplanted, and transplants performed more than doubled over the study period. No differences in early recipients' survival between groups were observed (87.6% vs. 84.5%; p = 0.733) nor in the rate of PGD. CONCLUSION: Implementing our intensive lung donor-treatment protocol increases lung procurement rates. This allows more lung transplants to be performed without detriment to either early survival or PGD rate.

The ALIEN study: incidence and outcome of acute respiratory distress syndrome in the era of lung protective ventilation.

PURPOSE: While our understanding of the pathogenesis and management of acute respiratory distress syndrome (ARDS) has improved over the past decade, estimates of its incidence have been controversial. The goal of this study was to examine ARDS incidence and outcome under current lung protective ventilatory support practices before and after the diagnosis of ARDS. METHODS: This was a 1-year prospective, multicenter, observational study in 13 geographical areas of Spain (serving a population of 3.55 million at least 18 years of age) between November 2008 and October 2009. Subjects comprised all consecutive patients meeting American-European Consensus Criteria for ARDS. Data on ventilatory management, gas exchange, hemodynamics, and organ dysfunction were collected. RESULTS: A total of 255 mechanically ventilated patients fulfilled the ARDS definition, representing an incidence of 7.2/100,000 population/year. Pneumonia and sepsis were the most common causes of ARDS. At the time of meeting ARDS criteria, mean PaO(2)/FiO(2) was 114 ± 40 mmHg, mean tidal volume was 7.2 ± 1.1 ml/kg predicted body weight, mean plateau pressure was 26 ± 5 cmH(2)O, and mean positive end-expiratory pressure (PEEP) was 9.3 ± 2.4 cmH(2)O. Overall ARDS intensive care unit (ICU) and hospital mortality was 42.7% (95%CI 37.7-47.8) and 47.8% (95%CI 42.8-53.0), respectively. CONCLUSIONS: This is the first study to prospectively estimate the ARDS incidence during the routine application of lung protective ventilation. Our findings support previous estimates in Europe and are an order of magnitude lower than those reported in the USA and Australia. Despite use of lung protective ventilation, overall ICU and hospital mortality of ARDS patients is still higher than 40%.