Background: There have been many scales to predict pneumonia in stroke patients, but they are so complex, making it difficult to apply in practice. Therefore, we conducted this study to assess the role of the National Institutes of Health Stroke Scale (NIHSS) and the Gugging Swallowing Screen (GUSS) in predicting stroke-associated pneumonia (SAP). These scales are routinely used in stroke patients. Therefore, their application in predicting SAP risk will be of high value in clinical practice. There has been no previous study evaluating the effectiveness of SAP risk prediction for each of these scales. Aim: This study aimed to compare the value of NIHSS and GUSS in SAP prediction and their convenience in clinical practice. Methods: It was a cohort study. The receiver operating characteristics (ROC) curves were constructed to assess the sensitivity (Se) and specificity (Sp) of the scales. Area under the curves (AUC) were calculated, and we compared them. Results: NIHSS had a medium value of predictor of SAP with AUC 0.764 (95% CI 0.735-0.792), 65.4% Se, 76.5% Sp. GUSS had good value in predicting SAP with AUC 0.858 (95% CI 0.833-0.880), 80.5% Se, 80.1% Sp. Pairwise comparison of ROCs curves demonstrated that the difference between two AUCs was significant (p < 0.01). Performing GUSS required 24.5 ± 6.7 minutes, 2.5 times longer than NIHSS (9.9 ± 2.0 minutes). Conclusion: GUSS had a better predictive value of SAP than NIHSS. But NIHSS was more convenient in clinical practice because of its simple instrument and quick performance.
Combining classifiers in an ensemble is beneficial in achieving better prediction than using a single classifier. Furthermore, each classifier can be associated with a weight in the aggregation to boost the performance of the ensemble system. In this work, we propose a novel dynamic weighted ensemble method. Based on the observation that each classifier provides a different level of confidence in its prediction, we propose to encode the level of confidence of a classifier by associating with each classifier a credibility threshold, computed from the entire training set by minimizing the entropy loss function with the mini-batch gradient descent method. On each test sample, we measure the confidence of each classifier's output and then compare it to the credibility threshold to determine whether a classifier should be attended in the aggregation. If the condition is satisfied, the confidence level and credibility threshold are used to compute the weight of contribution of the classifier in the aggregation. By this way, we are not only considering the presence but also the contribution of each classifier based on the confidence in its prediction on each test sample. The experiments conducted on a number of datasets show that the proposed method is better than some benchmark algorithms including a non-weighted ensemble method, two dynamic ensemble selection methods, and two Boosting methods.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.