Fig 6
Context in source publication
Context 1
... these results, which have been cross-validated using the 5-fold method, would seem to indicate a general prevalence of the RNN architecture in processing audiometry data, establishing an effectiveness hierarchy of RNN models is a more complex matter. Although LSTM has shown the best classification accuracy, when analysed in terms of confusion matrix, the lowest number of False Positives (FP) was obtained by GRU ( Figures 6 and 7), with LSTM taking second place. In comparison, the simple RNN produced over 62% more False Positives than LSTM and 85% more than GRU. ...
Similar publications
Citations
... In addition to differences in background and line colours, audiograms can also differ in the amount of information conveyed (e.g. they may contain data for a single ear or both). Consequently, a universal classification solution for tonal audiometry results cannot rely on an image classifier 26 . ...
... During a previous study 26 www.nature.com/scientificreports/ rate of 0.2%, which enabled its clinical application. ...
Hearing problems are commonly diagnosed with the use of tonal audiometry, which measures a patient’s hearing threshold in both air and bone conduction at various frequencies. Results of audiometry tests, usually represented graphically in the form of an audiogram, need to be interpreted by a professional audiologist in order to determine the exact type of hearing loss and administer proper treatment. However, the small number of professionals in the field can severely delay proper diagnosis. The presented work proposes a neural network solution for classification of tonal audiometry data. The solution, based on the Bidirectional Long Short-Term Memory architecture, has been devised and evaluated for classifying audiometry results into four classes, representing normal hearing, conductive hearing loss, mixed hearing loss, and sensorineural hearing loss. The network was trained using 15,046 test results analysed and categorised by professional audiologists. The proposed model achieves 99.33% classification accuracy on datasets outside of training. In clinical application, the model allows general practitioners to independently classify tonal audiometry results for patient referral. In addition, the proposed solution provides audiologists and otolaryngologists with access to an AI decision support system that has the potential to reduce their burden, improve diagnostic accuracy, and minimise human error.
