We aimed to develop an automated detector that determines laryngeal invasion during swallowing. Laryngeal invasion, which causes significant clinical problems, is defined as two or more points on the penetration–aspiration scale (PAS). We applied two three-dimensional (3D) stream networks for action recognition in videofluoroscopic swallowing study (VFSS) videos. To detect laryngeal invasion (PAS 2 or higher scores) in VFSS videos, we employed two 3D stream networks for action recognition. To establish the robustness of our model, we compared its performance with those of various current image classification-based architectures. The proposed model achieved an accuracy of 92.10%. Precision, recall, and F1 scores for detecting laryngeal invasion (≥PAS 2) in VFSS videos were 0.9470 each. The accuracy of our model in identifying laryngeal invasion surpassed that of other updated image classification models (60.58% for ResNet101, 60.19% for Swin-Transformer, 63.33% for EfficientNet-B2, and 31.17% for HRNet-W32). Our model is the first automated detector of laryngeal invasion in VFSS videos based on video action recognition networks. Considering its high and balanced performance, it may serve as an effective screening tool before clinicians review VFSS videos, ultimately reducing the burden on clinicians.

Background: Viscosity is a common focus in the diet of patients with dysphagia. However, adhesiveness is an equally significant property that can affect swallowing function, even in semi-solid foods with similar levels of viscosity. The purpose of this study was to classify the adhesiveness of food into stages and determine whether these classifications are relevant to swallowing function. Methods: This study included 30 healthy elderly adults aged 65 years. After categorizing adhesiveness into three levels based on the results of the sensory test, 30 participants were asked to swallow representative foods at each level. A videofluoroscopic swallowing study (VFSS) was performed to determine the presence or absence of pharyngeal residues based on the level of adhesiveness. The chi-square test was used to verify whether there was a difference in remnants according to the level of adhesiveness, and significance was judged with a p-value of less than 0.05. Results: Adhesiveness was categorized into three distinct levels: level 1 (0–4 mJ), level 2 (4–18 mJ), and level 3 (>18 mJ). Upon examining the subjects presenting with residual material, we observed three cases of level 1 adhesiveness, 16 cases of level 2, and 25 cases of level 3. The chi-square test was used to assess the statistical significance between the levels, revealing a significant difference with a p-value < 0.0001. Conclusions: We presented the level of adhesiveness by dividing it into three stages and proved that it is meaningful in relation to the swallowing function. Selecting and recommending foods with an appropriate level of adhesiveness will help enhance swallowing safety in older adults.