Pure tone audiogram classification using deep learning techniques.

OBJECTIVE: Pure tone audiometry has played a critical role in audiology as the initial diagnostic tool, offering vital insights for subsequent analyses. This study aims to develop a robust deep learning framework capable of accurately classifying audiograms across various commonly encountered tasks. DESIGN, SETTING, AND PARTICIPANTS: This single-centre retrospective study was conducted in accordance with the STROBE guidelines. A total of 12 518 audiograms were collected from 6259 patients aged between 4 and 96 years, who underwent pure tone audiometry testing between February 2018 and April 2022 at Tongji Hospital, Tongji Medical College, Wuhan, China. Three experienced audiologists independently annotated the audiograms, labelling the hearing loss in degrees, types and configurations of each audiogram. MAIN OUTCOME MEASURES: A deep learning framework was developed and utilised to classify audiograms across three tasks: determining the degrees of hearing loss, identifying the types of hearing loss, and categorising the configurations of audiograms. The classification performance was evaluated using four commonly used metrics: accuracy, precision, recall and F1-score. RESULTS: The deep learning method consistently outperformed alternative methods, including K-Nearest Neighbors, ExtraTrees, Random Forest, XGBoost, LightGBM, CatBoost and FastAI Net, across all three tasks. It achieved the highest accuracy rates, ranging from 96.75% to 99.85%. Precision values fell within the range of 88.93% to 98.41%, while recall values spanned from 89.25% to 98.38%. The F1-score also exhibited strong performance, ranging from 88.99% to 98.39%. CONCLUSIONS: This study demonstrated that a deep learning approach could accurately classify audiograms into their respective categories and could contribute to assisting doctors, particularly those lacking audiology expertise or experience, in better interpreting pure tone audiograms, enhancing diagnostic accuracy in primary care settings, and reducing the misdiagnosis rate of hearing conditions. In scenarios involving large-scale audiological data, the automated classification system could be used as a research tool to efficiently provide a comprehensive overview and statistical analysis. In the era of mobile audiometry, our deep learning framework can also help patients quickly and reliably understand their self-tested audiograms, potentially encouraging timely consultations with audiologists for further evaluation and intervention.

[Applying a rigid curved video laryngoscope in laryngeal microsurgery of patients with difficult laryngeal exposure].

Objective:To test the feasibility of a rigid curved video laryngoscope in laryngeal microsurgery of patients with difficult laryngeal exposure. Methods:Thirteen patients with difficult laryngeal exposure underwent microlayngeal surgery using a new-design rigid curved video laryngoscope. The clinical data were collected and analyzed. Results:In all of the 13 patients with difficult laryngeal exposure,the fully exposure rate of glottis was 100% using a new-design rigid curved laryngoscope.But only 7 precise surgeries using our rigid curved instruments were completed successfully. Conclusion:Rigid curved laryngoscope is a useful tool to in treating patients with difficult laryngeal exposure in microlaryngeal surgery. Satisfactory glottis exposure, magnified surgical field and precise maneuver of the lesions could be achieved. But manipulation of this tool is challenging, which warrants further investigation．.

Expression of α2-Na/K-ATPase in C57BL/6J Mice Inner Ear and Its Relationship with Age-related Hearing Loss.

K+ cycling in the cochlea is critical to maintain hearing. Many sodium-potassium pumps are proved to participate in K+ cycling, such as Na/K-ATPase. The α2-Na/K-ATPase is an important isoform of Na/K-ATPase. The expression of α2-Na/K-ATPase in the cochlea is not clear. In this study, we used C57BL/6 mice as a model of presbycusis and implemented immunohistochemistry staining and quantitative real time-PCR, and the α2-Na/K-ATPase expression pattern was confirmed in the inner ear. It was found α2-Na/K-ATPase was expressed widely in cochlea and its mRNA and protein expression was gradually reduced with aging (4-, 14-, 26- and 48-weeks old mice). We suspected that, the down-regulation of α2-Na/K-ATPase expression might be associated with the remodeling of K+ cycling, degeneration of morphological structure and decrease of hearing function in aging C57 mice. In conclusion, we speculated that the reduction of α2-Na/K-ATPase might play an important role in the pathogenesis of age-related hearing loss.

Analysis of thyroid dysfunction in patients with sudden sensorineural hearing loss.

BACKGROUND: Sudden sensorineural hearing loss (SSHL) refers to the sudden occurrence of unexplained sensorineural hearing loss. The present study showed that different systemic diseases had different influence on the occurrence and hearing outcome of SSHL. Thyroid hormone is one of the important factors for the development of fetal ear and auditory function. However, the distribution of thyroid dysfunction in SSHL patients and the effect of thyroid dysfunction on the occurrence and hearing outcome of SSHL has not been studied. METHODS: In this study, a retrospective analysis had been done in 676 patients with SSHL. We had described the distribution of thyroid function in patients with SSHL in detail, and by the statistical method, analyzed the relationship between the hearing outcome and thyroid dysfunction, respectively. RESULTS: In all patients, 24.41% (165/676) had abnormal thyroid function testing results. The onset age of SSHL in FT3 abnormal group (including low and high group) was younger than that in normal FT3 group. Recovery group had more patients with lower-than-normal T3 level as compared to non-recovery patients. Significant associations between T3 levels and hearing outcome were observed in the subgroup with longer time elapse between symptom onset and treatment (≥14 d). CONCLUSION: The incidence of thyroid dysfunction in SSHL is significantly higher than in the general population. There was obvious relationship between T3 and FT3 item of thyroid dysfunction and the onset time and hearing outcome of SSHL, which indicated that T3 or FT3 indicator may be one of the affecting factors for the SSHL. Early screening and diagnosis of thyroid dysfunction, especial T3 level, may help to evaluate the prognosis in SSHL patients.

Elevated expression of yes­associated protein is associated with the malignant status and prognosis of laryngeal squamous cell carcinoma.

Previous studies have demonstrated that elevated yes­associated protein (YAP) expression is associated with tumor aggression and poor prognosis in various types of human cancer. However, the clinicopathological significance and the prognostic value of YAP in laryngeal squamous cell carcinoma (LSCC) is unknown. The aim of the present study was to identify the expression pattern and prognostic significance of YAP in patients with LSCC. YAP mRNA and protein expression levels were examined in fresh and archived LSCC samples using the reverse transcription­quantitative polymerase chain reaction, immunohistochemistry (IHC) and western blotting. The association between YAP expression levels with the malignant status and prognosis of patients with LSCC was analyzed. Upregulated protein and mRNA expression levels of YAP were detected in LSCC tissues compared with paired healthy surgical margin tissues. Positive expression of YAP was identified in 84/121 (69.4%) LSCC tissues and in 4/30 (13.3%) healthy surgical margin tissues by IHC. Positive YAP protein expression was significantly associated with clinical stage, TNM classification, lymph node metastasis and differentiated degree. Patients with positive YAP expression exhibited a significantly decreased overall survival time compared with patients with negative YAP expression (P=0.0002). Multivariate analysis indicated that the level of YAP expression was an independent prognostic factor for poor survival in patients with LSCC (P=0.012). In conclusion, the expression level of YAP was significantly increased in LSCC and associated with the malignant status of LSCC. Therefore, YAP may represent a novel biomarker for predicting the prognosis of patients with LSCC.

[Clinical observation on inhalation of pulmicort in patients with chronic rhinosinusitis after surgery].

OBJECTIVE: Whether inhalation of pulmicort into the sinus of chronic rhinosinusitis patients could improve reepithelization after endoscopic sinus surgery was assessed. METHOD: Prospective study 60 patients with chronic rhinosinusitis after endoscopic sinus surgery were divided into 2 groups randomized, the one was treatment group, and the other was control group. The patients in treatment group received inhalation of pulmicort 2 ml plus 0.5% Aeuromycin solution 10 ml by oxygen driving force, once a day, persisting for 3 weeks. The patients in control group received Rhinocort. Besides the different therapies above mentioned above therapy was different, two groups received the same conventional route therapy. To observe the time of reepithelization under nasal endoscope, was observed, respectively. RESULT: The average time of reepithelization in treatment group was (5.3333 +/- 0.9942) weeks. The other group was (6.6667 +/- 1.3476) weeks, the statistical difference between the two groups was very significant. CONCLUSION: Inhalation of pulmicort into the sinus can promote reepithelization and shorten the time of treatment.