Efficiency of artificial intelligence methods for hearing loss type classification : an evaluation

• Autorzy: Kassjański Michał , Kulawiak Marcin , Przewoźny Tomasz , Tretiakow Dmitry , Kuryłowicz Jagoda , Molisz Andrzej , Koźmiński Krzysztof , Kwaśniewska Aleksandra , Mierzwińska-Dolny Paulina , Grono Miłosz

Identyfikatory

DOI

10.14313/JAMRIS/3‐2024/1

• Języki publikacji: EN

Abstrakty

EN

The evaluation of hearing loss is primarily conducted by pure tone audiometry testing, which is often regarded as golden standard for assessing auditory function. If the presence of hearing loss is determined, it is possible to differentiate between three types of hearing loss: sensorineural, conductive, and mixed. This study presents a comprehensive comparison of a variety of AI classification models, performed on 4007 pure tone audiometry samples that have been labeled by professional audiologists in order to develop an automatic classifier of hearing loss type. The tested models include Logistic Regression, Support Vector Machines, Stochastic Gradient Descent, Decision Trees, Random Forest, Feedforward Neural Network (FNN), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU). The presented work also investigates the influence of training dataset augmentation with the use of a Conditional Generative Adversarial Network on the performance of machine learning algorithms and examines the impact of various standardization procedures on the effectiveness of deep learning architectures. Overall, the highest classification performance, was achieved by LSTM with an out-of-training accuracy of 97.56%.

Słowa kluczowe

EN

classification; hearing loss types; pure-tone audiometry; RNN; LSTM; evaluation

• Wydawca: Łukasiewicz Industrial Research Institute for Automation and Measurements PIAP
• Czasopismo: Journal of Automation Mobile Robotics and Intelligent Systems
• Rocznik: 2024
• Tom: Vol. 18, No. 3
• Strony: 28--38
• Opis fizyczny: Bibliogr. 22 poz., rys.

Twórcy

autor

Kassjański Michał

• Department of Geoinformatics, Faculty of Electronics, Telecommunications and Informatics, Gdansk University of Technology, 80-233, Gdansk, Poland

autor

Kulawiak Marcin

• Department of Geoinformatics, Faculty of Electronics, Telecommunications and Informatics, Gdansk University of Technology, 80-233, Gdansk, Poland

autor

Przewoźny Tomasz

• Department of Otolaryngology, Medical University of Gdansk, Smoluchowskiego Str. 17, 80-214 Gdansk, Poland

autor

Tretiakow Dmitry

• Department of Otolaryngology, the Nicolaus Copernicus Hospital in Gdansk, Copernicus Healthcare Entity, Powstancow Warszawskich str. 1/2, 80-152, Gdansk, Poland

autor

Kuryłowicz Jagoda

• Department of Otolaryngology, Medical University of Gdansk, 80‐214, Gdansk, Poland

autor

Molisz Andrzej

• Department of Otolaryngology, Medical University of Gdansk, 80-214, Gdansk, Poland

autor

Koźmiński Krzysztof

• Student’s Scientific Circle of Otolaryngology, Medical University of Gdańsk, 80-214 Gdansk, Poland

autor

Kwaśniewska Aleksandra

• Department of Otolaryngology, Laryngological Oncology and Maxillofacial Surgery, University Hospital No. 2, 85-168, Bydgoszcz, Poland

autor

Mierzwińska-Dolny Paulina

• Student’s Scientific Circle of Otolaryngology, Medical University of Gdańsk, 80-214 Gdansk, Poland

autor

Grono Miłosz

• Student’s Scientific Circle of Otolaryngology, Medical University of Gdańsk, 80-214 Gdansk, Poland

Bibliografia

• [1] World Health Organization, World report on hearing. Geneva: World Health Organization, 2021.
• [2] R. W. Baloh and J. C. Jen, “Hearing and Equilibrium,” Jan. 2012, doi: 10.1016/b978-1-4377-1604-7.00436-x.
• [3] M. Kassjański et al., “Detecting type of hearing loss with different AI classification methods: a performance review,” Computer Science and Information Systems (FedCSIS), 2019 Federated Conference, Sep. 2023, doi: 10.15439/2023f3083.
• [4] C. Belitz, H. Ali, and J. Hansen, “A Machine Learning Based Clustering Protocol for Determining Hearing Aid Initial Configurations from Pure-Tone Audiograms,” PubMed Central, Sep. 2019, doi: 10.21437/interspeech.2019-3091.
• [5] F. Charih, M. Bromwich, A. E. Mark, R. Lefrançois, and J. R. Green, “Data-Driven Audiogram Classification for Mobile Audiometry,” Scientific Reports, vol. 10, no. 1, Mar. 2020, doi: 10.1038/s41598-020-60898-3.
• [6] A. Elkhouly et al., “Data-driven audiogram classifier using data normalization and multi-stage feature selection,” Scientific Reports, vol. 13, no. 1, Feb. 2023, doi: 10.1038/s41598-022-25 411-y.
• [7] E. Elbaşı and M. Obali, “Classification of Hearing Losses Determined through the Use of Audiom- etry Using Data Mining,” Conference: 9th International Conference on Electronics,Computer and Computation.
• [8] M. G. Crowson et al., “AutoAudio: Deep Learning for Automatic Audiogram Interpretation,” Journal of Medical Systems, vol. 44, no. 9, Aug. 2020, doi: 10.1007/s10916-020-01627-1.
• [9] H. Shojaeemend and H. Ayatollahi, “Automated Audiometry: A Review of the Implementation and Evaluation Methods,” Healthcare Informatics Research, vol. 24, no. 4, pp. 263–275, Oct. 2018, doi: 10.4258/hir.2018.24.4.263.
• [10] Guidelines for Manual Pure-Tone Threshold Audiometry,” American Speech-LanguageHearing Association. https://www.asha.org/policy/GL2005-00014/ (accessed Dec. 5, 2023).
• [11] M. Mirza and S. Osindero, “Conditional Generative Adversarial Nets,” arXiv.org, 2014. https: //arxiv.org/abs/1411.1784.
• [12] Z. Zhao, A. Kunar, Van, R. Birke, and L. Y. Chen, “CTAB-GAN: Effective Table Data Synthesizing,” arXiv (Cornell University), Feb. 2021.
• [13] L. Xu et al., “Modeling Tabular Data using Conditional GAN.” Available: https://proceedings.neurips.cc/paper_files/paper/2019/file/254ed7d2de3b23ab10936522dd547b78-Paper.pdf (accessed Dec 5, 2023).
• [14] A. M. Annaswamy and Massoud Amin, IEEE Vision for Smart Grid Controls: 2030 and Beyond. Piscataway, Usa Ieee, 2013.
• [15] M. Shanker, M. Y. Hu, and M. S. Hung, “Effect of data standardization on neural network training,” Omega, vol. 24, no. 4, pp. 385–397, Aug. 996, doi: 10.1016/0305-0483(96)00010-2.
• [16] S. Hochreiter and J. Schmidhuber, “Long Short-Term Memory,” Neural Computation, vol. 9, no. 8, pp. 1735–1780, Nov. 1997, doi: 10.1162/neco.1997.9.8.1735.
• [17] I. Banerjee et al., “Comparative effectiveness of convolutional neural network (CNN) and recurent neural network (RNN) architectures for radiology text report classification,” Artificial Intelligence in Medicine, vol. 97, pp. 79–88, Jun. 2019, doi: 10.1016/j.artmed.2018.11.004.
• [18] “Recurrent Neural Networks in Medical Data Analysis and Classifications,” Applied Computing in Medicine and Health, pp. 147–165, Jan. 2016, doi: 10.1016/B978-0-12-803468-2.00007-2.
• [19] C. Ferri, J. Hernández-Orallo, and R. Modroiu, “An experimental comparison of performance easures for classification,” Pattern Recognition Letters, vol. 30, no. 1, pp. 27–38, Jan. 2009, doi: 10.1016/j.patrec.2008.08.010.
• [20] D. J. Hand and R. J. Till, “A Simple Generalisation of the Area Under the ROC Curve for Multiple Class Classification Problems,” Machine Learning, vol. 45, no. 2, pp. 171–186, 2001, doi: 10.1023/a:1010920819831.
• [21] M. Kassjański, M. Kulawiak, and Tomasz Przewoźny, “Development of an AI-based audiogram classification method for patient referral,” Computer Science and Information Systems (FedCSIS), 2019 Federated Conference on, Sep. 2022, doi: 10.15439/2022f66.
• [22] L. B. V. de Amorim, G. D. C. Cavalcanti, and R. M. O. Cruz, “The choice of scaling technique matters for classification performance,” Applied Soft Computing, vol. 133, p. 109924, Jan. 2023, doi: 10.1016/j.asoc.2022.109924.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).