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.

Dentistry's intrinsic link to provision of services for persons with disabilities.

This article provides the dentist with a background on disabilities, education, practice and provision of services related to statutory and regulatory requirements, particularly the Americans with Disabilities Act anrid the California Fair Employment and Housing Act.

Applications of qualitative grounded theory methodology to investigate hearing loss: protocol for a qualitative systematic review.

INTRODUCTION: Hearing loss is a chronic condition affecting 12 million individuals in the UK. People with hearing loss regularly experience difficulties interacting in everyday conversations. These difficulties in communication can result in a person with hearing loss withdrawing from social situations and becoming isolated. While hearing loss research has largely deployed quantitative methods to investigate various aspects of the condition, qualitative research is becoming more widespread. Grounded theory is a specific qualitative methodology that has been used to establish novel theories on the experiences of living with hearing loss. METHOD AND ANALYSIS: The aim of this systematic review is to establish how grounded theory has been applied to investigate the psychosocial aspects of hearing loss. Methods are reported according to the Preferred Reporting Items for Systematic Reviews and Meta-Analysis Protocols 2015 checklist. Studies included in this review will have applied grounded theory as an overarching methodology or have grounded theory embedded among other methodologies. Studies included will have adult participants (≥18 years) who are either people with an acquired hearing loss, their family and friends (communication partners), or healthcare practitioners including audiologists, general practitioners, ear, nose and throat specialists and hearing therapists. The quality of application of grounded theory in each study will be assessed using the Guideline for Reporting and Evaluating Grounded Theory Research Studies. ETHICS AND DISSEMINATION: As only secondary data will be used in this systematic review, ethical approval is not required. No other ethical issues are foreseen. This review is registered with the International Prospective Register of Systematic Reviews (http://www.crd.york.ac.uk/PROSPERO). Findings will be disseminated via peer-reviewed publications and at relevant academic conferences. Findings may also be published in relevant professional and third sector newsletters and magazines as appropriate. Data will inform future research and guideline development. PROSPERO REGISTRATION NUMBER: CRD42019134197.

Speech recognition materials and ceiling effects: considerations for cochlear implant programs.

Cochlear implant recipients have demonstrated remarkable increases in speech perception since US FDA approval was granted in 1984. Improved performance is due to a number of factors including improved cochlear implant technology, evolving speech coding strategies, and individuals with increasingly more residual hearing receiving implants. Despite this evolution, the same recommendations for pre- and postimplant speech recognition testing have been in place for over 10 years in the United States. To determine whether new recommendations are warranted, speech perception performance was assessed for 156 adult, postlingually deafened implant recipients as well as 50 hearing aid users on monosyllabic word recognition (CNC) and sentence recognition in quiet (HINT and AzBio sentences) and in noise (BKB-SIN). Results demonstrated that for HINT sentences in quiet, 28% of the subjects tested achieved maximum performance of 100% correct and that scores did not agree well with monosyllables (CNC) or sentence recognition in noise (BKB-SIN). For a more difficult sentence recognition material (AzBio), only 0.7% of the subjects achieved 100% performance and scores were in much better agreement with monosyllables and sentence recognition in noise. These results suggest that more difficult materials are needed to assess speech perception performance of postimplant patients - and perhaps also for determining implant candidacy.

[The effect of hyperbaric oxygen therapy to different degree of hearing loss and types of threshold curve in sudden deafness patients].

OBJECTIVE: To investigate the effect of hyperbaric oxygen therapy to different degrees of hearing loss and different types of threshold curve in sudden deafness patients, and establish a personalized therapy, so as to promote clinical effect to sudden deafness. METHOD: One hundred and twenty cases were divided into two groups respectively (each group 60 cases). Drug treatment had been used in group A for two weeks. The patients in group B received drug treatment combined with hyperbaric oxygen therapy for two weeks. According to the different degrees of hearing loss and the types of audiogram in two groups, the statistical analysis to the difference of hyperbaric oxygen therapeutic effect was done. RESULT: The effective rates was statistically different (chi2 = 8.044, P < 0.01) between group A (60.00%, 36/60) and group B (83.33%, 50/60). There was no statistical difference between two treatment program in mild and the profound deafness patients. The statistical difference could been found between moderate and the severe deafness, the value of chi2 and p were 4.969, 5.560 and 0.040, 0.035, respectively. In group A, the statistical difference could only been found between mild and the profound deafness patients (chi2 = 6.739, P < 0.05). In group B, the statistical difference could been found in mild and the profound deafness, the moderate and the profound deafness, the severe and the profound deafness patients. The value of chi2 were 11.500, 15.058,10.221 and P < 0.01 respectively. The effective rates was no statistical difference in two treatment programs in the upsloping audiogram and the profound deafness. The statistical difference could been found between the downsloping and the flat audiogram, with the value of chi2 and p were 5.144 and 5.969, P < 0.05, respectively. In group A, the statistical difference could been found between the ascending and descending audiogram, the ascending and the flat audiogram,the ascending type and the profound deafness. The value of chi2 were 6.188, 7.247, 8.082 and P < 0.05, respectively. No statistical difference could been found among the other types of audiogram. In group B, no statistical difference could been found among all types of audiogram. CONCLUSION: The effect of hyperbaric oxygen therapy varies with degree of hearing loss and audiogram type. Drug treatment combined with HBOT can promote clinical effect for patients in moderate deafness and severe deafness, the descending and flat type of audiogram.

Hipoacusia neurosensorial bilateral del prematuro (Guías Clínicas de Prematurez) / Bilateral sensorineural hearing loss of prematurity (Clinical Guidelines for Prematurity)

Objetivo general: Generar recomendaciones basadas en la mejor evidencia disponible acerca de prevención, tratamiento y rehabilitación de la hipoacusia bilateral neurosensorial en recién nacidos y niños menores de 4 años