Automated hearing loss type classification based on pure tone audiometry data.
AI decision support system
Audiogram
Bi-LSTM
Classification
Hearing loss
Tonal audiometry
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
20 06 2024
20 06 2024
Historique:
received:
29
02
2024
accepted:
07
06
2024
medline:
21
6
2024
pubmed:
21
6
2024
entrez:
20
6
2024
Statut:
epublish
Résumé
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.
Identifiants
pubmed: 38902305
doi: 10.1038/s41598-024-64310-2
pii: 10.1038/s41598-024-64310-2
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
14203Informations de copyright
© 2024. The Author(s).
Références
Blazer, D. G. & Tucci, D. L. Hearing loss and psychiatric disorders: A review. Psychol. Med. 49(6), 891–897. https://doi.org/10.1017/s0033291718003409 (2018).
doi: 10.1017/s0033291718003409
pubmed: 30457063
World Health Organization. World Report on Hearing. WHO. Available at: https://www.who.int/publications/i/item/9789240020481 (2021)
Glossary. National Institute of Deafness and Other Communication Disorders. Available at: https://www.nidcd.nih.gov/glossary
Ballantyne, J. C., Graham, J. M. & Baguley, D. Ballantyne’s Deafness (Wiley, 2009).
Margolis, R. H. & Saly, G. L. Distribution of hearing loss characteristics in a clinical population. Ear Hear. 29, 524–532. https://doi.org/10.1097/AUD.0b013e3181731e2e (2008).
doi: 10.1097/AUD.0b013e3181731e2e
pubmed: 18600134
Jin, D. et al. Artificial intelligence in radiology. Artif Intell Med https://doi.org/10.1016/b978-0-12-821259-2.00014-4 (2021).
doi: 10.1016/b978-0-12-821259-2.00014-4
Monshi, M. M. A., Poon, J. & Chung, V. Deep learning in generating radiology reports: A survey. Artif. Intell. Med. 106, 101878. https://doi.org/10.1016/j.artmed.2020.101878 (2020).
doi: 10.1016/j.artmed.2020.101878
pubmed: 32425358
pmcid: 7227610
Wasmann, J.-W.A. et al. Computational audiology: New approaches to advance hearing health care in the digital age. Ear Hear. 42(6), 1499–1507. https://doi.org/10.1097/aud.0000000000001041 (2021).
doi: 10.1097/aud.0000000000001041
pubmed: 33675587
pmcid: 8417156
Elbaşı, E., Obali, M. Classification of hearing losses determined through the use of audiometry using data mining, in Conference: 9th International Conference on Electronics, Computer and Computation (2012).
Walker, J. J., Cleveland, L. M., Davis, J. L. & Seales, J. S. Audiometry screening and interpretation. Am. Fam. Phys. 87(1), 41–47 (2013).
Chandrasekhar, S. S. et al. Clinical practice guideline: Sudden hearing loss (Update). Otolaryngol. Head Neck Surg. 161(1_suppl), 1-S45. https://doi.org/10.1177/0194599819859885 (2019).
doi: 10.1177/0194599819859885
Wardenga, N. et al. Hearing aid treatment for patients with mixed hearing loss. Part II: Speech recognition in comparison to direct acoustic cochlear stimulation. Audiol. Neurotol. 25(3), 133–142. https://doi.org/10.1159/000504285 (2020).
doi: 10.1159/000504285
Margolis, R. H. & Saly, G. L. Toward a standard description of hearing loss. Int. J. Audiol. 46(12), 746–758. https://doi.org/10.1080/14992020701572652 (2007).
doi: 10.1080/14992020701572652
pubmed: 18049964
Audiometric classification of hearing impairments. International Bureau for Audiophonology. Available at: https://www.biap.org/en/recommandations/recommendations/tc-02-classification/213-rec-02-1-en-audiometric-classification-of-hearing-impairments/file (1996).
Margolis, R. H. & Saly, G. L. Asymmetric hearing loss: Definition, validation, and prevalence. Otol. Neurotol. 29(4), 422–431. https://doi.org/10.1097/MAO.0b013e31816c7c09 (2008).
doi: 10.1097/MAO.0b013e31816c7c09
pubmed: 18418281
Lee, C.-Y., Hwang, J.-H., Hou, S.-J. & Liu, T.-C. Using cluster analysis to classify audiogram shapes. Int. J. Audiol. 49(9), 628–633. https://doi.org/10.3109/14992021003796887 (2010).
doi: 10.3109/14992021003796887
pubmed: 20553102
Pasta, A., Petersen, M. K., Jensen, K. J., and Larsen, J. Rethinking hearing aids as recommender systems, in CEUR Workshop Proceedings, Vol. 2439, 11–17 (2019).
Guo, R., Liang, R., Wang, Q. & Zou, C. Hearing loss classification algorithm based on the insertion gain of hearing aid. Multimed. Tools Appl. https://doi.org/10.1007/s11042-023-14886-0 (2023).
doi: 10.1007/s11042-023-14886-0
Belitz, C., et al. A machine learning based clustering protocol for determining hearing aid initial configurations from pure-tone audiograms, in Interspeech. https://doi.org/10.21437/interspeech.2019-3091 (2019).
Charih, F., Bromwich, M., Mark, A. E., Lefrançois, R. & Green, J. R. Data-driven audiogram classification for mobile audiometry. Sci. Rep. https://doi.org/10.1038/s41598-020-60898-3 (2020).
doi: 10.1038/s41598-020-60898-3
pubmed: 32127604
pmcid: 7054524
Abeer, E. et al. Data-driven audiogram classifier using data normalization and multi-stage feature selection. Sci. Rep. https://doi.org/10.1038/s41598-022-25411-y (2023).
doi: 10.1038/s41598-022-25411-y
Crowson, M. G. et al. AutoAudio: Deep learning for automatic audiogram interpretation. J. Med. Syst. https://doi.org/10.1007/s10916-020-01627-1 (2020).
doi: 10.1007/s10916-020-01627-1
pubmed: 32770269
Barbour, D. L. & Wasmann, J.-W.A. Performance and potential of machine learning audiometry. Hear. J. 74(3), 40–44. https://doi.org/10.1097/01.hj.0000737592.24476.88 (2021).
doi: 10.1097/01.hj.0000737592.24476.88
Aziz, B., Riaz, N., Rehman, A., Ur Malik, M. I. & Malik, K. I. Colligation of hearing loss and chronic otitis media. Pak. J. Med. Health Sci. 15(8), 1817–1819. https://doi.org/10.53350/pjmhs211581817 (2021).
doi: 10.53350/pjmhs211581817
Raghavan, A., Patnaik, U. & Bhaudaria, A. S. An observational study to compare prevalence and demography of sensorineural hearing loss among military personnel and civilian population. Indian J. Otolaryngol. Head Neck Surg. 74(S1), 410–415. https://doi.org/10.1007/s12070-020-02180-6 (2020).
doi: 10.1007/s12070-020-02180-6
pubmed: 36032851
pmcid: 9411472
Kassjański, M., Kulawiak, M. and Przewoźny, M. Development of an AI-based audiogram classification method for patient referral, in Computer Science and Information Systems (FedCSIS), 2019 Federated Conference on. https://doi.org/10.15439/2022f66 (2022).
Guidelines for Manual Pure-tone Threshold Audiometry, Vol. 20, 297–301 (ASHA, 1978).
Gao, L., Zhang, L., Liu, C. & Wu, S. Handling imbalanced medical image data: A deep-learning-based one-class classification approach. Artif. Intell. Med. 108, 101935. https://doi.org/10.1016/j.artmed.2020.101935 (2020).
doi: 10.1016/j.artmed.2020.101935
pubmed: 32972664
pmcid: 7519174
Zhu, M. et al. Class weights random forest algorithm for processing class imbalanced medical data. IEEE Access 6, 4641–4652. https://doi.org/10.1109/ACCESS.2018.2789428 (2018).
doi: 10.1109/ACCESS.2018.2789428
Farid, DMd. & Mofizur Rahman, C. Assigning weights to training instances increases classification accuracy. Int. J. Data Min. Knowl. Manag. Process 3(1), 13–25. https://doi.org/10.5121/ijdkp.2013.3102 (2013).
doi: 10.5121/ijdkp.2013.3102
Hou, L., et al. Normalization helps training of quantized LSTM. Neural Inf. Process. Syst. (2019).
de Amorim, L. B. V., Cavalcanti, G. D. C. & Cruz, R. M. O. The choice of scaling technique matters for classification performance. Appl. Soft Comput. 133, 109924. https://doi.org/10.1016/j.asoc.2022.109924 (2023).
doi: 10.1016/j.asoc.2022.109924
Kassjański, M. et al. Detecting type of hearing loss with different AI classification methods: A performance review, in Computer Science and Information Systems (FedCSIS), 2019 Federated Conference On. https://doi.org/10.15439/2023f3083 (2023).
Banerjee, I. et al. Comparative effectiveness of convolutional neural network (CNN) and recurrent neural network (RNN) architectures for radiology text report classification. Artif. Intell. Med. 97, 79–88. https://doi.org/10.1016/j.artmed.2018.11.004 (2019).
doi: 10.1016/j.artmed.2018.11.004
pubmed: 30477892
Wang, L., Wang, H., Song, Y. & Wang, Q. MCPL-based FT-LSTM: Medical representation learning-based clinical prediction model for time series events. IEEE Access 7, 70253–70264. https://doi.org/10.1109/access.2019.2919683 (2019).
doi: 10.1109/access.2019.2919683
Sun, C., Hong, S., Song, M., & Li, H. (2020). A review of deep learning methods for irregularly sampled medical time series data.
Bengio, Y., Simard, P. & Frasconi, P. Learning long-term dependencies with gradient descent is difficult. IEEE Trans. Neural Netw. 5(2), 157–166. https://doi.org/10.1109/72.279181 (1994).
doi: 10.1109/72.279181
pubmed: 18267787
Schuster, M. & Paliwal, K. K. Bidirectional recurrent neural networks. IEEE Trans. Signal Process. 45(11), 2673–2681. https://doi.org/10.1109/78.650093 (1997).
doi: 10.1109/78.650093
Prusty, S., Patnaik, S. & Dash, S. K. SKCV: Stratified K-fold cross-validation on ML classifiers for predicting cervical cancer. Front Nanotechnol https://doi.org/10.3389/fnano.2022.972421 (2022).
doi: 10.3389/fnano.2022.972421
Dietterich, T. G. Approximate statistical tests for comparing supervised classification learning algorithms. Neural Comput. 10(7), 1895–1923. https://doi.org/10.1162/089976698300017197 (1998).
doi: 10.1162/089976698300017197
pubmed: 9744903
Kassjański, M. et al. Efficiency of artificial intelligence methods for hearing loss type classification: An evaluation. J. Autom. Mob. Robot. Intell. Syst. (in press).
Salzberg, S. L. C4.5: Programs for machine learning by J. Ross Quinlan. Morgan Kaufmann Publishers, Inc., 1993. Mach. Learn. 16(3), 235–240. https://doi.org/10.1007/bf00993309 (1994).
doi: 10.1007/bf00993309
Zhang, Y., Liu, Q. and Song, L. Sentence-state LSTM for text representation, in Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). https://doi.org/10.18653/v1/p18-1030 (2018).
Kowsher, Md. et al. LSTM-ANN & BiLSTM-ANN: Hybrid deep learning models for enhanced classification accuracy. Procedia Comput. Sci. 193, 131–140. https://doi.org/10.1016/j.procs.2021.10.013 (2021).
doi: 10.1016/j.procs.2021.10.013
Khan, M., Wang, H., Ngueilbaye, A. & Elfatyany, A. End-to-end multivariate time series classification via hybrid deep learning architectures. Pers. Ubiquit. Comput. https://doi.org/10.1007/s00779-020-01447-7 (2020).
doi: 10.1007/s00779-020-01447-7
da Silva, D. G. et al. Comparing long short-term memory (LSTM) and bidirectional LSTM deep neural networks for power consumption prediction. Energy Rep. 10, 3315–3334. https://doi.org/10.1016/j.egyr.2023.09.175 (2023).
doi: 10.1016/j.egyr.2023.09.175
Pirani, M., Thakkar, P., Jivrani, P., Bohara, M.H. and Garg, D. A comparative analysis of ARIMA, GRU, LSTM and BiLSTM on financial time series forecasting, in 2022 IEEE International Conference on Distributed Computing and Electrical Circuits and Electronics (ICDCECE). https://doi.org/10.1109/icdcece53908.2022.9793213 (2022).
Shahin, A. I. & Almotairi, S. A deep learning BiLSTM encoding-decoding model for COVID-19 pandemic spread forecasting. Fractal Fract. 5(4), 175. https://doi.org/10.3390/fractalfract5040175 (2021).
doi: 10.3390/fractalfract5040175
Abdul Lateh, M. et al. Handling a small dataset problem in prediction model by employ artificial data generation approach: A review. J. Phys. Conf. Ser. 892, 012016. https://doi.org/10.1088/1742-6596/892/1/012016 (2017).
doi: 10.1088/1742-6596/892/1/012016
Guidelines for Audiometric Symbols. Committee on Audiologic Evaluation, 25–30. (American Speech-Language-Hearing Association, 1990).