Key result
Bayesian MCMC predictive model demonstrates good discrimination for in-ICU mortality with an AUC of ~0.81.
Observational (n=1,111)
No
Effect estimate: AUC 0.809 (95% CI 0.747-0.862)
Absolute Event Rate: 0.809% vs 0.81%
A Bayesian MCMC approach successfully developed predictive models for in-ICU mortality with good discrimination (AUC ~0.8) in a Malaysian ICU cohort.
Supports Bayesian MCMC ICU mortality models in Malaysia; leaves open external validation before clinical adoption.
BACKGROUND AND OBJECTIVES: There are not many studies that attempt to model intensive care unit (ICU) risk of death in developing countries, especially in South East Asia. The aim of this study was to propose and describe application of a Bayesian approach in modeling in-ICU deaths in a Malaysian ICU. METHODS: This was a prospective study in a mixed medical-surgery ICU in a multidisciplinary tertiary referral hospital in Malaysia. Data collection included variables that were defined in Acute Physiology and Chronic Health Evaluation IV (APACHE IV) model. Bayesian Markov Chain Monte Carlo (MCMC) simulation approach was applied in the development of four multivariate logistic regression predictive models for the ICU, where the main outcome measure was in-ICU mortality risk. The performance of the models were assessed through overall model fit, discrimination and calibration measures. Results from the Bayesian models were also compared against results obtained using frequentist maximum likelihood method. RESULTS: The study involved 1,286 consecutive ICU admissions between January 1, 2009 and June 30, 2010, of which 1,111 met the inclusion criteria. Patients who were admitted to the ICU were generally younger, predominantly male, with low co-morbidity load and mostly under mechanical ventilation. The overall in-ICU mortality rate was 18.5% and the overall mean Acute Physiology Score (APS) was 68.5. All four models exhibited good discrimination, with area under receiver operating characteristic curve (AUC) values approximately 0.8. Calibration was acceptable (Hosmer-Lemeshow p-values > 0.05) for all models, except for model M3. Model M1 was identified as the model with the best overall performance in this study. CONCLUSION: Four prediction models were proposed, where the best model was chosen based on its overall performance in this study. This study has also demonstrated the promising potential of the Bayesian MCMC approach as an alternative in the analysis and modeling of in-ICU mortality outcomes.
No takes yet. Share an insight, caveat, or question.
Wong et al. (2016) conducted an observational in Critically ill patients requiring intensive care (n=1,111). Bayesian MCMC predictive model (Model M1) vs. Frequentist maximum likelihood model was evaluated on Model discrimination for in-ICU mortality (AUC) (AUC 0.809, 95% CI 0.747-0.862). A Bayesian Markov Chain Monte Carlo predictive model (Model M1) demonstrated good discrimination (AUC 0.809) and acceptable calibration for predicting in-ICU mortality in a Malaysian intensive care unit.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: