Search

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. [ABSTRACT FROM AUTHOR]

This study elucidated whether the adverse effect of soil salinity is different between Populus yunnanensis Dode males and females under climate change. We hypothesized that the magnitude and direction of sexual responses to elevated C[O.sub.2] and warming will be modified by soil salinity in dioecious plants. Populus yunnanensis was employed as a model species to study sexual responses in growth, photosynthesis, carbohydrate accumulation, and C and N allocation to elevated C[O.sub.2] and temperature under soil salinity. Cuttings were divided into control and salt groups and were exposed to two C[O.sub.2] regimes (ambient C[O.sub.2] and double ambient C[O.sub.2]) and two temperature regimes (ambient temperature and ambient temperature + 2.2°C) in growth chambers. Males exhibited a greater down-regulation of the net photosynthesis rate ([A.sub.net]) than did females at elevated C[O.sub.2], primarily due to their poorer carbon sink-source balance and lower N availability. In the salt group, unlike in the control group, warming showed a positive effect on the growth of both females and males, and elevated C[O.sub.2] and temperature had a positive synergistic effect on the growth of both sexes. Sexual growth differences under soil salinity were reduced by elevated C[O.sub.2], temperature, and a combination of both. These results provide evidence for sexually different responses to environmental changes in dioecious plants and support the idea that sex ratios will shift under climate change. Key words: dioecy, photosynthetic acclimation, elevated C[O.sub.2], elevated temperature, soil salinity. Cette etude a permis de determiner si la salinite du sol aun effet nefaste different chez les sujets males et femelles de Populus yunnanensis Dode dans le contexte des changements climatiques. Nous avons fait l'hypothese que l'ampleur et le sens de la reaction des genres a une concentration elevee de C[O.sub.2] et au rechauffement seraient modifies par la salinite du sol chez les plantes dioiques. Populus yunnanensis a ete utilise comme espece modele pour etudier l'effet d'une augmentation de la concentration de C[O.sub.2] et de la temperature sur la croissance, la photosynthese, l'accumulation d'hydrates de carbone ainsi que l'allocation de C et N chez chacun des genres lorsque la salinite du sol est elevee. Des boutures ont ete divisees en deux groupes (temoin et sol salin) et exposees a deux regimes de C[O.sub.2] (1x et 2x la concentration ambiante) et deux regimes de temperature (temperature ambiante et temperature ambiante plus 2,2°C) dans des chambres de croissance. La regulation negative du taux net de photosynthese ([A.sub.net]) etait plus prononcee chez les males que chez les femelles lorsque la concentration de C[O.sub.2] etait elevee, principalement a cause de leur bilan puits-source de carbone et de la plus faible disponibilite de N. Sur sol salin, contrairement au groupe temoin, le rechauffement a eu un effet positif sur la croissance des femelles et des males et la combinaison d'une concentration elevee de C[O.sub.2] et d'une temperature plus chaude a produit un effet synergique positif sur la croissance des deux genres. Les differences de croissance entre les genres dans des conditions de salinite elevee etaient reduites par une concentration elevee de C[O.sub.2], par une temperature plus chaude et par ces deux facteurs combines. Ces resultats fournissent la preuve que les genres reagissent differemment aux changements environnementaux chez les plantes dioiques et supportent l'idee que le ratio des genres sera modifie par les changements climatiques. [Traduit par la Redaction] Mots-cles: dioecie, acclimatation photosynthetique, concentration elevee de C[O.sub.2], temperature elevee, salinite du sol., 1. Introduction Because of human activities and the use of fossil fuel, atmospheric C[O.sub.2] concentration has dramatically increased since preglacial times and is predicted to reach 700 µmol[mol.sup.-1] by the [...]