Background Dysphonia influences the quality of life by interfering with communication. However, a laryngoscopic examination is expensive and not readily accessible in primary care units. Experienced laryngologists are required to achieve an accurate diagnosis. Objective This study sought to detect various vocal fold diseases through pathological voice recognition using artificial intelligence. Methods We collected 189 normal voice samples and 552 samples of individuals with voice disorders, including vocal atrophy (n=224), unilateral vocal paralysis (n=50), organic vocal fold lesions (n=248), and adductor spasmodic dysphonia (n=30). The 741 samples were divided into 2 sets: 593 samples as the training set and 148 samples as the testing set. A convolutional neural network approach was applied to train the model, and findings were compared with those of human specialists. Results The convolutional neural network model achieved a sensitivity of 0.66, a specificity of 0.91, and an overall accuracy of 66.9% for distinguishing normal voice, vocal atrophy, unilateral vocal paralysis, organic vocal fold lesions, and adductor spasmodic dysphonia. Compared with the accuracy of human specialists, the overall accuracy rates were 60.1% and 56.1% for the 2 laryngologists and 51.4% and 43.2% for the 2 general ear, nose, and throat doctors. Conclusions Voice alone could be used for common vocal fold disease recognition through a deep learning approach after training with our Mandarin pathological voice database. This approach involving artificial intelligence could be clinically useful for screening general vocal fold disease using the voice. The approach includes a quick survey and a general health examination. It can be applied during telemedicine in areas with primary care units lacking laryngoscopic abilities. It could support physicians when prescreening cases by allowing for invasive examinations to be performed only for cases involving problems with automatic recognition or listening and for professional analyses of other clinical examination results that reveal doubts about the presence of pathologies.

Background Triangular fibrocartilage complex (TFCC) has become an interest over the last few decades, discovering its understanding in anatomy, pathomechanism, biomechanics, and management in treatments. Currently, TFCC does not have a golden standard procedure, and not one surgical procedure is superior to the other. This study is to evaluate the comparative outcomes in TFCC patients that underwent either in all-inside arthroscopic suture anchors or the arthroscopic transosseous suture technique. Method From 2017 to 2019, 30 patients were analyzed. Eight patients were in an arthroscopic transosseous group and 22 patients were in an all-inside arthroscopic group. Comparison between patients’ flexion and extension range of motion (ROM), grip strength, and visual analog pain scale (VAS) preoperative and six-month follow-up were analyzed. Result There were significant increases in flexion ROM, extension ROM, and VAS between preoperative and postoperative in all-inside arthroscopic and arthroscopic transosseous. Only the all-inside arthroscopic group had a significant increase in grip strength. Postoperative flexion ROM had a significant difference between all-inside arthroscopic and arthroscopic transosseous. Conclusion Both the all-inside arthroscopic suture anchor technique and the arthroscopic transosseous suture technique are appropriate treatments to treat patients with TFCC. Both procedures have achieved the ultimate goal of improved longevity and optimal function. Level of evidence Level III; retrospective comparative cohort study.

rhinoplasty using liquid silicone. Furthermore, the reported median time between exposure to foreign material and the onset of symptoms of autoimmune diseases was 1 month and ranged from 2 weeks to 5 years. 2 This case demonstrates that the period between liquid silicone injection and the onset of autoimmune disease can exceed 20 years. Thus, clinicians must consider the possibility of liquid silicone-induced autoimmune disease when presented with patients reporting a history of liquid silicone injection.

Background: Taiwan always had low case rates of COVID-19 compared with other countries due to its immediate control and preventive measures. However, the effects of its policies that started on 2020 for otolaryngology patients were unknown; therefore, the aim of this study was to analyze the nationwide database to know the impact of COVID-19 preventative measures on the diseases and cases of otolaryngology in 2020. Method: A case-compared, retrospective, cohort database study using the nationwide database was collected from 2018 to 2020. All of the information from outpatients and unexpected inpatients with diagnoses, odds ratios, and correlation matrix was analyzed. Results: The number of outpatients decreased in 2020 compared to in 2018 and 2019. Thyroid disease and lacrimal system disorder increased in 2020 compared to 2019. There was no difference in carcinoma in situ, malignant neoplasm, cranial nerve disease, trauma, fracture, and burn/corrosion/frostbite within three years. There was a highly positive correlation between upper and lower airway infections. Conclusions: COVID-19 preventative measures can change the numbers of otolaryngology cases and the distributions of the disease. Efficient redistribution of medical resources should be developed to ensure a more equitable response for the future.

BACKGROUND Dysphonia influences the quality of life by interfering with communication. However, laryngoscopic examination is expensive and not readily accessible in primary care units. Experienced laryngologists are required to achieve an accurate diagnosis. OBJECTIVE This study sought to detect various vocal fold diseases through pathological voice recognition using artificial intelligence. METHODS We collected 29 normal voice samples and 527 samples of individuals with voice disorders, including vocal atrophy (n=210), unilateral vocal paralysis (n=43), organic vocal fold lesions (n=244), and adductor spasmodic dysphonia (n=30). The 556 samples were divided into two sets: 440 samples as the training set and 116 samples as the testing set. A convolutional neural network approach was applied to train the model and findings were compared with human specialists. RESULTS The convolutional neural network model achieved a sensitivity of 0.70, a specificity of 0.90, and an overall accuracy of 65.5% for distinguishing normal voice, vocal atrophy, unilateral vocal paralysis, organic vocal fold lesions, and adductor spasmodic dysphonia. Compared to human specialists, the overall accuracy was 58.6% and 49.1% for the two laryngologists, and 38.8% and 34.5% for the two general ear, nose, and throat doctors. CONCLUSIONS We developed an artificial intelligence-based screening tool for common vocal fold diseases, which possessed high specificity after training with our Mandarin pathological voice database. This approach has clinical potential to use artificial intelligence for general vocal fold disease screening via voice and includes a quick survey during a general health examination. It can be applied in telemedicine for areas that lack laryngoscopic abilities in primary care units.