Dataset Information

Predicting in-hospital mortality in pneumonia-associated septic shock patients using a classification and regression tree: a nested cohort study.

ABSTRACT: Background:Pneumonia complicated by septic shock is associated with significant morbidity and mortality. Classification and regression tree methodology is an intuitive method for predicting clinical outcomes using binary splits. We aimed to improve the prediction of in-hospital mortality in patients with pneumonia and septic shock using decision tree analysis. Methods:Classification and regression tree models were applied to all patients with pneumonia-associated septic shock in the international, multicenter Cooperative Antimicrobial Therapy of Septic Shock database between 1996 and 2015. The association between clinical factors (time to appropriate antimicrobial therapy, severity of illness) and in-hospital mortality was evaluated. Accuracy in predicting clinical outcomes, sensitivity, specificity, and area under receiver operating curve of the final model was evaluated in training (n?=?2111) and testing datasets (n?=?2111). Results:The study cohort contained 4222 patients, and in-hospital mortality was 51%. The mean time from onset of shock to administration of appropriate antimicrobials was significantly higher for patients who died (17.2 h) compared to those who survived (5.0 h). In the training dataset (n?=?2111), a tree model using Acute Physiology and Chronic Health Evaluation II Score, lactate, age, and time to appropriate antimicrobial therapy yielded accuracy of 73% and area under the receiver operating curve 0.75. The testing dataset (n?=?2111) had accuracy of 69% and area under the receiver operating curve 0.72. Conclusions:Overall mortality (51%) in patients with pneumonia complicated by septic shock is high. Increased time to administration of antimicrobial therapy, Acute Physiology and Chronic Health Evaluation II Score, serum lactate, and age were associated with increased in-hospital mortality. Classification and regression tree methodology offers a simple prognostic model with good performance in predicting in-hospital mortality.

SUBMITTER: Speiser JL

PROVIDER: S-EPMC6186142 | biostudies-literature | 2018

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predicting in-hospital mortality in pneumonia-associated septic shock patients using a classification and regression tree: a nested cohort study.

Speiser Jaime L JL Karvellas Constantine J CJ Shumilak Geoffery G Sligl Wendy I WI Mirzanejad Yazdan Y Gurka Dave D Kumar Aseem A Kumar Anand A

Journal of intensive care 20181012

<h4>Background</h4>Pneumonia complicated by septic shock is associated with significant morbidity and mortality. Classification and regression tree methodology is an intuitive method for predicting clinical outcomes using binary splits. We aimed to improve the prediction of in-hospital mortality in patients with pneumonia and septic shock using decision tree analysis.<h4>Methods</h4>Classification and regression tree models were applied to all patients with pneumonia-associated septic shock in t ...[more]

PMID: 30349726

Similar Datasets

Project description:OBJECTIVES:Sepsis care is becoming a more common target for hospital performance measurement, but few studies have evaluated the acceptability of sepsis or septic shock mortality as a potential performance measure. In the absence of a gold standard to identify septic shock in claims data, we assessed agreement and stability of hospital mortality performance under different case definitions. DESIGN:Retrospective cohort study. SETTING:U.S. acute care hospitals. PATIENTS:Hospitalized with septic shock at admission, identified by either implicit diagnosis criteria (charges for antibiotics, cultures, and vasopressors) or by explicit International Classification of Diseases, 9th revision, codes. INTERVENTIONS:None. MEASUREMENTS AND MAIN RESULTS:We used hierarchical logistic regression models to determine hospital risk-standardized mortality rates and hospital performance outliers. We assessed agreement in hospital mortality rankings when septic shock cases were identified by either explicit International Classification of Diseases, 9th revision, codes or implicit diagnosis criteria. Kappa statistics and intraclass correlation coefficients were used to assess agreement in hospital risk-standardized mortality and hospital outlier status, respectively. Fifty-six thousand six-hundred seventy-three patients in 308 hospitals fulfilled at least one case definition for septic shock, whereas 19,136 (33.8%) met both the explicit International Classification of Diseases, 9th revision, and implicit septic shock definition. Hospitals varied widely in risk-standardized septic shock mortality (interquartile range of implicit diagnosis mortality: 25.4-33.5%; International Classification of Diseases, 9th revision, diagnosis: 30.2-38.0%). The median absolute difference in hospital ranking between septic shock cohorts defined by International Classification of Diseases, 9th revision, versus implicit criteria was 37 places (interquartile range, 16-70), with an intraclass correlation coefficient of 0.72, p value of less than 0.001; agreement between case definitions for identification of outlier hospitals was moderate (kappa, 0.44 [95% CI, 0.30-0.58]). CONCLUSIONS:Risk-standardized septic shock mortality rates varied considerably between hospitals, suggesting that septic shock is an important performance target. However, efforts to profile hospital performance were sensitive to septic shock case definitions, suggesting that septic shock mortality is not currently ready for widespread use as a hospital quality measure.

Project description:BACKGROUND:In the typical setting of gene-selection problems from high-dimensional data, e.g., gene expression data from microarray or next-generation sequencing-based technologies, an enormous volume of high-throughput data is generated, and there is often a need for a simple, computationally-inexpensive, non-parametric screening procedure than can quickly and accurately find a low-dimensional variable subset that preserves biological information from the original very high-dimensional data (dimension p > 40,000). This is in contrast to the very sophisticated variable selection methods that are computationally expensive, need pre-processing routines, and often require calibration of priors. RESULTS:We present a tree-based sequential CART (S-CART) approach to variable selection in the binary classification setting and compare it against the more sophisticated procedures using simulated and real biological data. In simulated data, we analyze S-CART performance versus (i) a random forest (RF), (ii) a fully-parametric Bayesian stochastic search variable selection (SSVS), and (iii) the moderated t-test statistic from the LIMMA package in R. The simulation study is based on a hierarchical Bayesian model, where dataset dimensionality, percentage of significant variables, and substructure via dependency vary. Selection efficacy is measured through false-discovery and missed-discovery rates. In all scenarios, the S-CART method is seen to consistently outperform SSVS and RF in both speed and detection accuracy. We demonstrate the utility of the S-CART technique both on simulated data and in a control-treatment mouse study. We show that the network analysis based on the S-CART-selected gene subset in essence recapitulates the biological findings of the study using only a fraction of the original set of genes considered in the study's analysis. CONCLUSIONS:The relatively simple-minded gene selection algorithms like S-CART may often in practical circumstances be preferred over much more sophisticated ones. The advantage of the "greedy" selection methods utilized by S-CART and the likes is that they scale well with the problem size and require virtually no tuning or training while remaining efficient in extracting the relevant information from microarray-like datasets containing large number of redundant or irrelevant variables. AVAILABILITY:The MATLAB 7.4b code for the S-CART implementation is available for download from https://neyman.mcg.edu/posts/scart.zip.

Project description:Background/aimAssessing prognosis for acetaminophen-induced acute liver failure (APAP-ALF) patients often presents significant challenges. King's College (KCC) has been validated on hospital admission, but little has been published on later phases of illness. We aimed to improve determinations of prognosis both at the time of and following admission for APAP-ALF using Classification and Regression Tree (CART) models.MethodsCART models were applied to US ALFSG registry data to predict 21-day death or liver transplant early (on admission) and post-admission (days 3-7) for 803 APAP-ALF patients enrolled 01/1998-09/2013. Accuracy in prediction of outcome (AC), sensitivity (SN), specificity (SP), and area under receiver-operating curve (AUROC) were compared between 3 models: KCC (INR, creatinine, coma grade, pH), CART analysis using only KCC variables (KCC-CART) and a CART model using new variables (NEW-CART).ResultsTraditional KCC yielded 69% AC, 90% SP, 27% SN, and 0.58 AUROC on admission, with similar performance post-admission. KCC-CART at admission offered predictive 66% AC, 65% SP, 67% SN, and 0.74 AUROC. Post-admission, KCC-CART had predictive 82% AC, 86% SP, 46% SN and 0.81 AUROC. NEW-CART models using MELD (Model for end stage liver disease), lactate and mechanical ventilation on admission yielded predictive 72% AC, 71% SP, 77% SN and AUROC 0.79. For later stages, NEW-CART (MELD, lactate, coma grade) offered predictive AC 86%, SP 91%, SN 46%, AUROC 0.73.ConclusionCARTs offer simple prognostic models for APAP-ALF patients, which have higher AUROC and SN than KCC, with similar AC and negligibly worse SP. Admission and post-admission predictions were developed.Key points• Prognostication in acetaminophen-induced acute liver failure (APAP-ALF) is challenging beyond admission • Little has been published regarding the use of King's College Criteria (KCC) beyond admission and KCC has shown limited sensitivity in subsequent studies • Classification and Regression Tree (CART) methodology allows the development of predictive models using binary splits and offers an intuitive method for predicting outcome, using processes familiar to clinicians • Data from the ALFSG registry suggested that CART prognosis models for the APAP population offer improved sensitivity and model performance over traditional regression-based KCC, while maintaining similar accuracy and negligibly worse specificity • KCC-CART models offered modest improvement over traditional KCC, with NEW-CART models performing better than KCC-CART particularly at late time points.

Project description:OBJECTIVES:To assess the variability in short-term sepsis mortality by hospital among Centers for Medicare and Medicaid Services beneficiaries in the United States during 2013-2014. DESIGN:A retrospective cohort design. SETTING:Hospitalizations from 3,068 acute care hospitals that participated in the Centers for Medicare and Medicaid Services inpatient prospective payment system in 2013 and 2014. PATIENTS:Medicare fee-for-service beneficiaries greater than or equal to 65 years old who had an inpatient hospitalization coded with present at admission severe sepsis or septic shock. INTERVENTIONS:None. MEASUREMENTS AND MAIN RESULTS:Individual level mortality was assessed as death at or within 7 days of hospital discharge and aggregated to calculate hospital-level mortality rates. We used a logistic hierarchal linear model to calculate mortality risk-adjusted for patient characteristics. We quantified variability among hospitals using the median odds ratio and calculated risk-standardized mortality rates for each hospital. The overall crude mortality rate was 34.7%. We found significant variability in mortality by hospital (p < 0.001). The middle 50% of hospitals had similar risk-standardized mortality rates (32.7-36.9%), whereas the decile of hospitals with the highest risk-standardized mortality rates had a median mortality rate of 40.7%, compared with a median of 29.2% for hospitals in the decile with the lowest risk-standardized mortality rates. The median odds ratio (1.29) was lower than the adjusted odds ratios for several measures of patient comorbidities and severity of illness, including present at admission organ dysfunction, no identified source of infection, and age. CONCLUSIONS:In a large study of present at admission sepsis among Medicare beneficiaries, we showed that mortality was most strongly associated with underlying comorbidities and measures of illness on arrival. However, after adjusting for patient characteristics, mortality also modestly depended on where a patient with sepsis received care, suggesting that efforts to improve sepsis outcomes in lower performing hospitals could impact sepsis survival.

Project description:BACKGROUND:Assessment of disease severity in patients with septic shock (SS) is crucial in determining optimal level of care. In both pre- and in-hospital settings, the clinical picture alone is not sufficient for assessing disease severity and outcomes. Because blood lactate level is included in the clinical criteria of SS it should be considered to improve the assessment of its severity. This study aims to investigate the relationship between pre-hospital blood lactate level and 30-day mortality in patients with SS. METHODS:From 15 April 2017 to 15 April 2019, patients with SS requiring pre-hospital Mobile Intensive Care Unit intervention (MICU) were prospectively included in the LAPHSUS study, an observational, non-randomized controlled study. Pre-hospital blood lactate levels were measured at the time of first contact between the patients and the MICU. RESULTS:Among the 183 patients with septic shock requiring action by the MICU drawn at random from LAPHSUS study patients, six (3%) were lost to follow-up on the 30th day and thus 177 (97%) were analyzed for blood lactate levels (mean age 70 ± 14 years). Pulmonary, urinary and digestive infections were probably the cause of the SS in respectively 58%, 21% and 11% of the cases. The 30-day overall mortality was 32%. Mean pre-hospital lactatemia was significantly different between patients who died and those who survived (respectively 7.1 ± 4.0 mmol/L vs. 5.9 ± 3.5 mmol/L, p < 10-3). Using Cox regression analysis adjusted for potential confounders we showed that a pre-hospital blood lactate level ? 4 mmol/L significantly predicted 30-day mortality in patients with SS (adjusted hazard ratio = 2.37, 95%CI (1.01-5.57), p = 0.04). CONCLUSION:In this study, we showed that pre-hospital lactatemia predicts 30-day mortality in patients with septic shock handled by the MICU. Further studies will be needed to evaluate if pre-hospital lactatemia alone or combined with clinical scores could affect the triage decision-making process for those patients.

Project description:Patients with severe infections and especially sepsis have a high in-hospital mortality, but even hospital survivors face long-term sequelae, decreased health-related quality of life, and high risk of death, suggesting a great need for specialized aftercare. However, data regarding a potential benefit of post-discharge rehabilitation in these patients are scarce. In this retrospective matched cohort study the claim data of a large German statutory health care insurer was analyzed. 83,974 hospital survivors having suffered from septic shock, sepsis, and severe infections within the years 2009-2016 were identified using an ICD abstraction strategy closely matched to the current Sepsis-3 definition. Cases were analyzed and compared with their matched pairs to determine their 5-year mortality and the impact of post-discharge rehabilitation. Five years after hospital discharge, mortality of initial hospital survivors were still increased after septic shock (HRadj 2.03, 95%-CI 1.87 to 2.19; P<0.001), sepsis (HRadj 1.73, 95%-CI 1.71 to 1.76; P<0.001), and also in survivors of severe infections without organ dysfunction (HRadj 1.70, 95%-CI 1.65 to 1.74; P<0.001) compared to matched controls without infectious diseases. Strikingly, patients treated in rehabilitation facilities showed a significantly improved 5-year survival after suffering from sepsis or septic shock (HRadj 0.81, 95%-CI 0.77 to 0.85; P<0.001) as well as severe infections without organ dysfunction (HRadj 0.81, 95%-CI 0.73 to 0.90; P<0.001) compared to matched patients discharged to home or self-care. Long-term mortality and morbidity of hospital survivors are markedly increased after septic shock, sepsis and severe infections without organ dysfunction, but best 5-year survival was recorded in patients discharged to a rehabilitation facility in all three groups. Thus, our data suggest that specialized aftercare programs may help to improve long-term outcome in these patients and warrants more vigilance in future investigations.

Project description:ImportanceCoronavirus disease 2019 patients have an increased risk of thrombotic complications that may reflect immunothrombosis, a process characterized by blood clotting, endothelial dysfunction, and the release of neutrophil extracellular traps. To date, few studies have investigated longitudinal changes in immunothrombosis biomarkers in these patients. Furthermore, how these longitudinal changes differ between coronavirus disease 2019 patients and noncoronavirus disease septic patients with pneumonia are unknown.ObjectivesIn this pilot observational study, we investigated the utility of immunothrombosis biomarkers for distinguishing between coronavirus disease 2019 patients and noncoronavirus disease septic patients with pneumonia. We also evaluated the utility of the biomarkers for predicting ICU mortality in these patients.Design setting and participantsThe participants were ICU patients with coronavirus disease 2019 (n = 14), noncoronavirus disease septic patients with pneumonia (n = 19), and healthy age-matched controls (n = 14).Main outcomes and measuresNine biomarkers were measured from plasma samples (on days 1, 2, 4, 7, 10, and/or 14). Analysis was based on binomial logit models and receiver operating characteristic analyses.ResultsCell-free DNA, d-dimer, soluble endothelial protein C receptor, protein C, soluble thrombomodulin, fibrinogen, citrullinated histones, and thrombin-antithrombin complexes have significant powers for distinguishing coronavirus disease 2019 patients from healthy individuals. In comparison, fibrinogen, soluble endothelial protein C receptor, antithrombin, and cell-free DNA have significant powers for distinguishing coronavirus disease 2019 from pneumonia patients. The predictors of ICU mortality differ between the two patient groups: soluble thrombomodulin and citrullinated histones for coronavirus disease 2019 patients, and protein C and cell-free DNA or fibrinogen for pneumonia patients. In both patient groups, the most recent biomarker values have stronger prognostic value than their ICU day 1 values.Conclusions and relevanceFibrinogen, soluble endothelial protein C receptor, antithrombin, and cell-free DNA have utility for distinguishing coronavirus disease 2019 patients from noncoronavirus disease septic patients with pneumonia. The most important predictors of ICU mortality are soluble thrombomodulin/citrullinated histones for coronavirus disease 2019 patients, and protein C/cell-free DNA for noncoronavirus disease pneumonia patients. This hypothesis-generating study suggests that the pathophysiology of immunothrombosis differs between the two patient groups.

Dataset Information

Predicting in-hospital mortality in pneumonia-associated septic shock patients using a classification and regression tree: a nested cohort study.

Publications

Predicting in-hospital mortality in pneumonia-associated septic shock patients using a classification and regression tree: a nested cohort study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure