Search

Background:With the high consumption of medications due to multimorbidity, understanding the quality of drug use for vulnerable nursing home residents is essential. The paper's aim is to investigate the association of potentially inappropriate medication use based on Beers criteria and specific potentially inappropriate medication groups with unplanned hospitalization in nursing home residents. Methods: This retrospective cohort study consisted of 234 newly admitted consecutive residents aged 65 years and older to one highly accredited nursing home. Cox proportionally hazards regression using stepwise forward method was used to compute hazard ratios and 95% confidence intervals for the association between medication use and time to first hospitalization. Results: Out of a total of 234 subjects, 56% of the residents had been hospitalized at least once within one year of nursing home admission. Sixty-four percent of the residents were taking at least one potentially inappropriatemedication. When accounting for both polypharmacy and potentially inappropriate medication factors, use of two or more potentially inappropriate medications was significantly associated with an increase in hospitalization (HR 2.110, 95% CI 1.358-3.278, p = 0.001). Several combinations of potentially inappropriate medications involving anticholinergic agent were associated with a higher risk of hospitalization in certain subgroups. Further study with a larger representative study sample is warranted to confirm these findings. Conclusion: Routine medication review for potentially inappropriate medications should be performed for all nursing home resident at admission. Special attention should be paid to residents with use of two or more potentially inappropriate medications due to association with higher hospitalization risk. [ABSTRACT FROM AUTHOR]

The estimation of the Barthel Index scale (BI) is a significant method for measuring the performance of Activities Daily Living (ADL), where the prediction of ADL is crucial for providing rehabilitation care management and recovery for patients after stroke, therefore in this paper, nine various Machine Learning (ML) algorithms were implemented in a medical dataset contains 776 records from 313 patients 208 of them are men: 208 and 150 are women with multiple features collected from them for predicting and classifying the BI status as clinical decision support for determining the ADL of post-stroke patients. Meanwhile, we have applied feature selection using the chi-squared test to reduce the number of features in the dataset. The results showed that the Decision Tree (DT), XGBoost (XGB), and AdaBoost (ADB) classifiers performed the highest performance achieved with 100% correctness in terms of accuracy, sensitivity, specificity, error, and Area Under Curve (AUC) on both the full and reduced features datasets. [ABSTRACT FROM AUTHOR]