Dataset Information

Emergency admission parameters for predicting in-hospital mortality in patients with acute exacerbations of chronic obstructive pulmonary disease with hypercapnic respiratory failure.

ABSTRACT:

Background

Acute exacerbation of chronic obstructive pulmonary disease (AECOPD) is a common presentation in emergency departments (ED) that can be fatal. This study aimed to develop a mortality risk assessment model for patients presenting to the ED with AECOPD and hypercapnic respiratory failure.

Methods

We analysed 601 participants who were presented to an ED of a tertiary hospital with AECOPD between 2018 and 2020. Patient demographics, vital signs, and altered mental status were assessed on admission; moreover, the initial laboratory findings and major comorbidities were assessed. We used least absolute shrinkage and selection operator (LASSO) regression to identify predictors for establishing a nomogram for in-hospital mortality. Predictive ability was assessed using the area under the receiver operating curve (AUC). A 500 bootstrap method was applied for internal validation; moreover, the model's clinical utility was evaluated using decision curve analysis (DCA). Additionally, the nomogram was compared with other prognostic models, including CRB65, CURB65, BAP65, and NEWS.

Results

Among the 601 patients, 19 (3.16%) died during hospitalization. LASSO regression analysis identified 7 variables, including respiratory rate, PCO₂, lactic acid, blood urea nitrogen, haemoglobin, platelet distribution width, and platelet count. These 7 variables and the variable of concomitant pneumonia were used to establish a predictive model. The nomogram showed good calibration and discrimination for mortality (AUC 0.940; 95% CI 0.895-0.985), which was higher than that of previous models. The DCA showed that our nomogram had clinical utility.

Conclusions

Our nomogram, which is based on clinical variables that can be easily obtained at presentation, showed favourable predictive accuracy for mortality in patients with AECOPD with hypercapnic respiratory failure.

SUBMITTER: Chen L

PROVIDER: S-EPMC8349105 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:ObjectiveTo predict hospital admission at the time of ED triage using patient history in addition to information collected at triage.MethodsThis retrospective study included all adult ED visits between March 2014 and July 2017 from one academic and two community emergency rooms that resulted in either admission or discharge. A total of 972 variables were extracted per patient visit. Samples were randomly partitioned into training (80%), validation (10%), and test (10%) sets. We trained a series of nine binary classifiers using logistic regression (LR), gradient boosting (XGBoost), and deep neural networks (DNN) on three dataset types: one using only triage information, one using only patient history, and one using the full set of variables. Next, we tested the potential benefit of additional training samples by training models on increasing fractions of our data. Lastly, variables of importance were identified using information gain as a metric to create a low-dimensional model.ResultsA total of 560,486 patient visits were included in the study, with an overall admission risk of 29.7%. Models trained on triage information yielded a test AUC of 0.87 for LR (95% CI 0.86-0.87), 0.87 for XGBoost (95% CI 0.87-0.88) and 0.87 for DNN (95% CI 0.87-0.88). Models trained on patient history yielded an AUC of 0.86 for LR (95% CI 0.86-0.87), 0.87 for XGBoost (95% CI 0.87-0.87) and 0.87 for DNN (95% CI 0.87-0.88). Models trained on the full set of variables yielded an AUC of 0.91 for LR (95% CI 0.91-0.91), 0.92 for XGBoost (95% CI 0.92-0.93) and 0.92 for DNN (95% CI 0.92-0.92). All algorithms reached maximum performance at 50% of the training set or less. A low-dimensional XGBoost model built on ESI level, outpatient medication counts, demographics, and hospital usage statistics yielded an AUC of 0.91 (95% CI 0.91-0.91).ConclusionMachine learning can robustly predict hospital admission using triage information and patient history. The addition of historical information improves predictive performance significantly compared to using triage information alone, highlighting the need to incorporate these variables into prediction models.

Project description:BackgroundThe use of ward-based noninvasive ventilation (NIV) for acute hypercapnic respiratory failure (AHRF) unrelated to chronic obstructive pulmonary disease (COPD) remains controversial. This study evaluated the outcomes and failure rates associated with NIV application in the ward-based setting for patients with AHRF unrelated to COPD.MethodsA multicentre, retrospective cohort study of patients with AHRF unrelated to COPD was conducted. COPD was not the main reason for hospital admission, treated with ward-based NIV between February 2004 and December 2018. All AHRF patients were eligible; exclusion criteria comprised COPD patients, age < 18 years, pre-NIV pH < 7.35, or a lack of pre-NIV blood gas. In-hospital mortality was the primary outcome; univariable and multivariable models were constructed. The obesity-related AHRF group included patients with AHRF due to obesity hypoventilation syndrome (OHS), and the non-obesity-related AHRF group included patients with AHRF due to pneumonia, bronchiectasis, neuromuscular disease, or fluid overload.ResultsIn total, 479 patients were included in the analysis; 80.2% of patients survived to hospital discharge. Obesity-related AHRF was the indication for NIV in 39.2% of all episodes and was the aetiology with the highest rate of survival to hospital discharge (93.1%). In the multivariable analysis, factors associated with a higher risk of in-hospital mortality were increased age (odds ratio, 95% CI: 1.034, 1.017-1.051, P < 0.001) and pneumonia on admission (5.313, 2.326-12.131, P < 0.001). In the obesity-related AHRF group, pre-NIV pH < 7.15 was associated with significantly increased in-hospital mortality (7.800, 1.843-33.013, P=0.005); however, a pre-NIV pH 7.15-7.25 was not associated with increased in-hospital mortality (2.035, 0.523-7.915, P=0.305).ConclusionPre-NIV pH and age have been identified as important predictors of surviving ward-based NIV treatment. Moreover, these data support the use of NIV in ward-based settings for obesity-related AHRF patients with pre-NIV pH thresholds down to 7.15. However, future controlled trials are required to confirm the effectiveness of NIV use outside critical care settings for obesity-related AHRF.

Project description:RationaleAcute hypercapnic respiratory failure (AHRF) treated with non-invasive ventilation in the ICU is frequently caused by chronic obstructive pulmonary disease (COPD) exacerbations and obesity-hypoventilation syndrome, the latter being most often associated with obstructive sleep apnea. Overlap syndrome (a combination of COPD and obstructive sleep apnea) may represent a major burden in this population, and specific diagnostic pathways are needed to improve its detection early after ICU discharge.ObjectivesTo evaluate whether pulmonary function tests can identify a high probability of obstructive sleep apnea in AHRF survivors and outperform common screening questionnaires to identify the disorder.MethodsFifty-three patients surviving AHRF (31 males; median age 67 years (interquartile range: 62-74) participated in the study. Anthropometric data were recorded and body plethysmography was performed 15 days after ICU discharge. A sleep study was performed 3 months after ICU discharge.ResultsThe apnea-hypopnea index was negatively associated with static hyperinflation as measured by the residual volume to total lung capacity ratio in the % of predicted (coefficient = -0.64; standard error 0.17; 95% CI -0.97 to -0.31; p<0.001). A similar association was observed in COPD patients only: coefficient = -0.65; standard error 0.19; 95% CI -1.03 to -0.26; p = 0.002. Multivariate analysis with penalized maximum likelihood confirmed that the residual volume to total lung capacity ratio was the main contributor for apnea-hypopnea index variance in addition to classic predictors. Screening questionnaires to select patients at risk for sleep-disordered breathing did not perform well.ConclusionsIn AHRF survivors, static hyperinflation is negatively associated with the apnea-hypopnea index in both COPD and non-COPD patients. Measuring static hyperinflation in addition to classic predictors may help to increase the recognition of obstructive sleep apnea as common screening tools are of limited value in this specific population.