No abstract

Background: Dysphagia is common in elderly patients with dementia and is one of the common clinical geriatric syndromes. It imposes a heavy burden on patients and their caregivers and is becoming an important public health problem. This study examined the association between dysphagia in older dementia patients in the ICU and the subsequent adverse health outcomes they experience. Patients and Methods: A retrospective analysis of adults (≥65 years) with dementia in ICUs of a Boston tertiary academic medical center was conducted. Using the International Classification of Diseases' Ninth and Tenth Revisions, dementia patients were identified. The study cohort comprised 1009 patients, median age 84.82 years, 56.6% female, predominantly White (72.9%). Patients were grouped based on swallowing function: dysphagia (n=282) and no-dysphagia (n=727). Dysphagia was identified via positive bedside swallowing screening. Primary outcomes were 90-and 180-day mortality, secondary outcomes included aspiration pneumonia, pressure injury, and delirium. Cohort characteristics were compared using the Wilcoxon rank-sum and chi-square tests. Dysphagia and outcomes correlations were examined via Kaplan-Meier survival analysis, Cox proportional-hazards regression models, logistic regression models, and subgroup analysis. Results: After adjusting for covariates, the results from multivariate Cox proportional-hazards regression indicated that dysphagia was significantly associated with increased 90-day (HR=1.36, 95% CI=1.07-1.73, E-value=1.78) and 180-day (HR=1.47, 95% CI=1.18-1.82, E-value=1.94) mortality; the multifactorial logistic regression results indicated that dysphagia was associated with significant increases in pressure injury (OR=1.58, 95% CI=1.11-2.23, E-value=1.83) and aspiration pneumonia occurrence (OR=4.04, 95% CI=2.72-6.01, E-value=7.54), but was not significantly associated with delirium prevalence (OR=1.27, 95% CI=0.93-1.74). Conclusion: Dysphagia is likely to increase the risk of adverse health outcomes in older adults with dementia in ICU, and these adverse outcomes mostly include 90-and 180-day mortality, aspiration pneumonia, and pressure injury.

BACKGROUND Background: Acute hypoxic respiratory failure (AHRF) accounts for a large proportion of intensive care unit admissions. High flow nasal cannula (HFNC) is an emerging respiratory support technique that may improve oxygenation levels in patients. However, failure of HFNC may result in delayed intubation, prolonged mechanical ventilation and increased risk of increased mortality. Timely and accurate prediction of HFNC failure is of clinical importance. OBJECTIVE Objective: to develope and validate prediction models for high flow nasal cannula failure in patients with acute hypoxic respiratory failure. METHODS Methods: Firstly, the least absolute shrinkage and selection operator regression analysis was used as the feature selection for HFNC failure, and the features suitable for constructing the prediction model were selected by the lowest λ of the minimum mean cross-validation error. Next, four machine learning algorithms, C5.0, random forest (RF), extreme random tree (ERT) and extreme gradient boosting (XGBoost), were selected to construct the prediction models. Finally, the models are validated using receiver operating characteristic (ROC) curves and exact recall (PR) curves, model evaluation metrics, calibration plots and decision curve analysis, and further evaluated by internal validation. RESULTS Results: The study included 739 patients. Of those, 232 (31.4%) patients experienced HFNC failure. The areas under the receiver operating characteristic curves (AUROCs) of the C5.0, random forest, extremely randomized trees , and Extreme Gradient Boosting models were 0.807, 0.819, 0.816, and 0.818, respectively, which were higher than the ROX (AUROC=0.603) and mROX (AUROC=0.579) indexes. Similarly, the areas under the precision-recall curves (AUPRs) of the C5.0, RF, ERT, and XGBoost models were 0.813, 0.837, 0.832, and 0.839, respectively, which were higher than the ROX (AUPR=0.646) and mROX (AUPR=0.609) indexes. The ERT model had the most balanced predictive performance (sensitivity 0.701, specificity 0.817, accuracy 0.761, and balanced accuracy 0.759). The calibration curves demonstrated that the predicted risk probabilities among the ML models and the observed probabilities maintained good consistency. The results of the decision-curve analysis indicated the clinical validity of the ML model. CONCLUSIONS Conclusions: This study has developed an interpretable ML model for accurately predicting the risk of HFNC failure in patients with AHRF. The model had better predictive performance than the existing ROX and mROX indexes. CLINICALTRIAL Trial registration: None