Kinematic analysis of the hyoid bone in a videofluorosopic swallowing study (VFSS) is important for assessing dysphagia. However, calibrating the hyoid bone movement is time-consuming, and its reliability shows wide variation. Computer-assisted analysis has been studied to improve the efficiency and accuracy of hyoid bone identification and tracking, but its performance is limited. In this study, we aimed to design a robust network that can track hyoid bone movement automatically without human intervention. Using 69,389 frames from 197 VFSS files as the data set, a deep learning model for detection and trajectory prediction was constructed and trained by the BiFPN-U-Net(T) network. The present model showed improved performance when compared with the previous models: an area under the curve (AUC) of 0.998 for pixelwise accuracy, an accuracy of object detection of 99.5%, and a Dice similarity of 90.9%. The bounding box detection performance for the hyoid bone and reference objects was superior to that of other models, with a mean average precision of 95.9%. The estimation of the distance of hyoid bone movement also showed higher accuracy. The deep learning model proposed in this study could be used to detect and track the hyoid bone more efficiently and accurately in VFSS analysis.

Motion classification can be performed using biometric signals recorded by electroencephalography (EEG) or electromyography (EMG) with noninvasive surface electrodes for the control of prosthetic arms. However, current single-modal EEG and EMG based motion classification techniques are limited owing to the complexity and noise of EEG signals, and the electrode placement bias, and low-resolution of EMG signals. We herein propose a novel system of two-dimensional (2D) input image feature multimodal fusion based on an EEG/EMG-signal transfer learning (TL) paradigm for detection of hand movements in transforearm amputees. A feature extraction method in the frequency domain of the EEG and EMG signals was adopted to establish a 2D image. The input images were used for training on a model based on the convolutional neural network algorithm and TL, which requires 2D images as input data. For the purpose of data acquisition, five transforearm amputees and nine healthy controls were recruited. Compared with the conventional single-modal EEG signal trained models, the proposed multimodal fusion method significantly improved classification accuracy in both the control and patient groups. When the two signals were combined and used in the pretrained model for EEG TL, the classification accuracy increased by 4.18–4.35% in the control group, and by 2.51–3.00% in the patient group.

Objective To identify the variables of videofluoroscopic swallowing study (VFSS) that are useful for predicting the risk of aspiration pneumonia in elderly patients with dysphagia.Methods A total of 251 patients (aged 65 years or more) were included and divided into a pneumonia group (n=133) and a non-pneumonia group (n=118). The pneumonia group included patients who had been diagnosed with aspiration pneumonia, and individuals in the non-pneumonia group did not have pneumonia but were referred for VFSS. The medical records and results of VFSS were reviewed and compared between the groups retrospectively.Results The pneumonia group exhibited a male preponderance and a higher 8-point Penetration-Aspiration Scale (8PPAS) score. The mean values of 8PPAS score for swallowing thick liquid and rice porridge was significantly higher in the pneumonia group. The pharyngeal delay time (PDT) and pharyngeal transit time (PTT) were significantly longer in the pneumonia group. The amounts of vallecular and pyriform sinus residue were increased in the pneumonia group. The delay in swallowing reflex and the decrease in laryngeal elevation were more frequently observed in the pneumonia group. Among those variables, PDT and PTT were identified as significant predictors of aspiration pneumonia based on logistic regression analysis.Conclusion The present study delineated the findings of VFSS, suggesting an increased risk of aspiration pneumonia in elderly patients with dysphagia. The results demonstrate that prolonged PDT and PTT are significant predictors of aspiration pneumonia.

Diabetic sensorimotor polyneuropathy (DSPN) is a major complication in patients with diabetes mellitus (DM), and early detection or prediction of DSPN is important for preventing or managing neuropathic pain and foot ulcer. Our aim is to delineate whether machine learning techniques are more useful than traditional statistical methods for predicting DSPN in DM patients. Four hundred seventy DM patients were classified into four groups (normal, possible, probable, and confirmed) based on clinical and electrophysiological findings of suspected DSPN. Three ML methods, XGBoost (XGB), support vector machine (SVM), and random forest (RF), and their combinations were used for analysis. RF showed the best area under the receiver operator characteristic curve (AUC, 0.8250) for differentiating between two categories—criteria by clinical findings (normal, possible, and probable groups) and those by electrophysiological findings (confirmed group)—and the result was superior to that of linear regression analysis (AUC = 0.6620). Average values of serum glucose, International Federation of Clinical Chemistry (IFCC), HbA1c, and albumin levels were identified as the four most important predictors of DSPN. In conclusion, machine learning techniques, especially RF, can predict DSPN in DM patients effectively, and electrophysiological analysis is important for identifying DSPN.