Deep learning approach for dysphagia detection by syllable-based speech analysis with daily conversations.

Dysphagia, a disorder affecting the ability to swallow, has a high prevalence among the older adults and can lead to serious health complications. Therefore, early detection of dysphagia is important. This study evaluated the effectiveness of a newly developed deep learning model that analyzes syllable-segmented data for diagnosing dysphagia, an aspect not addressed in prior studies. The audio data of daily conversations were collected from 16 patients with dysphagia and 24 controls. The presence of dysphagia was determined by videofluoroscopic swallowing study. The data were segmented into syllables using a speech-to-text model and analyzed with a convolutional neural network to perform binary classification between the dysphagia patients and control group. The proposed model in this study was assessed in two different aspects. Firstly, with syllable-segmented analysis, it demonstrated a diagnostic accuracy of 0.794 for dysphagia, a sensitivity of 0.901, a specificity of 0.687, a positive predictive value of 0.742, and a negative predictive value of 0.874. Secondly, at the individual level, it achieved an overall accuracy of 0.900 and area under the curve of 0.953. This research highlights the potential of deep learning modal as an early, non-invasive, and simple method for detecting dysphagia in everyday environments.

Prognostic Value of Electroneuronography in Severe Cases of Facial Palsy.

OBJECTIVE: To examine the prognostic value of electroneuronography (ENoG) in predicting functional recovery in severe cases of acute facial palsy. METHODS: Patients with severe degrees of facial palsy (initial House-Brackmann [HB] grades IV to VI) with available electrodiagnostic studies conducted 2-4 weeks after symptom onset were reviewed retrospectively. The patients were categorized into "good recovery" and "poor recovery" groups, with the former showing mild to no dysfunction (HB I to III) and the latter exhibiting moderate to severe dysfunction (HB IV to VI) on follow-up evaluation, 2 months after onset. ENoG amplitudes in four facial muscles (frontalis, nasalis, orbicularis oculi, and orbicularis oris), as well as age, sex, affected side, disease etiology, comorbidities, and laboratory findings, were compared between the two groups. RESULTS: Thirty-seven patients were included. Twenty-nine of the patients showed "good recovery," and eight showed "poor recovery" at 2 months after symptom onset. Univariate analysis yielded no significant difference in age, sex, affected side, disease etiology, comorbidities, and laboratory findings between the two groups. Preserved ENoG amplitudes (individual, average, and trimmed means) were significantly higher in the good recovery group than in the poor recovery group (p<0.005). Sex (p=0.038) and the ENoG of the nasalis muscle, acquired 2-4 weeks from symptom onset (p=0.004), showed significant differences in multivariate regression analysis. CONCLUSION: This study suggests that the female sex and lower ENoG of the nasalis muscle, acquired 2-4 weeks from symptom onset, have negative prognostic value for the 2-month functional outcome of severe facial palsy cases.

Improved Muscle Mass and Function With Protein Supplementation in Older Adults With Sarcopenia: A Meta-Analysis.

OBJECTIVE: : To systematically review the effects of protein supplementation in older adults with sarcopenia. METHODS: : A systematic literature search was conducted in PubMed, Cochrane Library, and Embase databases until May 2023. The inclusion criteria were as follows: (1) randomized controlled trials with a quantitative study design; (2) studies with a study group of older adults with sarcopenia; (3) studies comparing muscle mass, muscle strength, and performance of older adults with sarcopenia after protein supplementation; and (4) studies published up to May 2023. RESULTS: : Six retrospective comparative studies, including 715 patients, met the inclusion criteria. The nutritional supplementation group exhibited significant improvement in appendicular skeletal muscle mass (standardized mean difference [SMD]=0.41; 95% confidence interval [CI], 0.24-0.58; p<0.001; I2=1%), while handgrip strength (SMD=0.37; 95% CI, -0.32-1.07; p=0.29; I2=94%) and Short Physical Performance Battery (SPPB) (SMD=0.35; 95% CI, -0.47-1.18; p=0.40; I2=94%) showed a tendency for improvement. CONCLUSION: : Nutritional supplementation with protein increased appendicular muscle mass in older adults with sarcopenia and improved handgrip strength and SPPB scores.