ObjectiveTo investigate the inter-rater agreement using the Videofluoroscopic Dysphagia Scale (VDS).MethodThe present study was designed as a multicenter, single-blind trial. A Videofluoroscopic Swallowing Study (VFSS) was performed using the protocol described by J.A Logemann. Thick-fluid, pureed food, mechanically altered food, regularly textured food, and thin-fluid boluses were sequentially swallowed. Each participant received a 3 ml bolus followed by a 5 ml bolus of each food material, in the order mentioned above. All study procedures were video recorded. Discs containing these video recordings in random order were distributed to interpreters who were blinded to the participant information. The video recordings were evaluated using a standardized VDS sheet and the inter-rater reliability was calculated.ResultsIn total, 100 patients participated in this study and 10 interpreters analyzed the findings. Inter-rater reliability was fair in terms of lip closure (κ: 0.325), oral transit time (0.253), delayed triggering of pharyngeal swallowing (0.300), vallecular residue (0.275), laryngeal elevation (0.345), pyriform sinus residue (0.310), coating of the pharyngeal wall (0.310), and aspiration (0.393). However, other parameters of the oral phase were lower than those of the pharyngeal phase (0.06-0.153). Moreover, the summation of VDS reliability (intraclass correlation coefficient: 0.556) showed moderate agreement.ConclusionVDS shows a moderate rate of agreement for evaluating the swallowing function. However, many of the parameters demonstrated a lower rate of agreement, particularly the oral phase parameters.

This is the first time that a swallowing screening tool for patients with acute stroke has been revalidated in a larger population from another stroke center. The validity of a swallow screening test may vary according to different stroke severities.

Coronary heart disease (CHD) is one of the severe health issues and is one of the most common types of heart diseases. It is the most frequent cause of mortality across the globe due to the lack of a healthy lifestyle. Owing to the fact that a heart attack occurs without any apparent symptoms, an intelligent detection method is inescapable. In this article, a new CHD detection method based on a machine learning technique, e.g., classifier ensembles, is dealt with. A two-tier ensemble is built, where some ensemble classifiers are exploited as base classifiers of another ensemble. A stacked architecture is designed to blend the class label prediction of three ensemble learners, i.e., random forest, gradient boosting machine, and extreme gradient boosting. The detection model is evaluated on multiple heart disease datasets, i.e., Z-Alizadeh Sani, Statlog, Cleveland, and Hungarian, corroborating the generalisability of the proposed model. A particle swarm optimization-based feature selection is carried out to choose the most significant feature set for each dataset. Finally, a two-fold statistical test is adopted to justify the hypothesis, demonstrating that the performance differences of classifiers do not rely upon an assumption. Our proposed method outperforms any base classifiers in the ensemble with respect to 10-fold cross validation. Our detection model has performed better than current existing models based on traditional classifier ensembles and individual classifiers in terms of accuracy, F1, and AUC. This study demonstrates that our proposed model adds a considerable contribution compared to the prior published studies in the current literature.