Abstract
Hearing Loss affects an ever-growing number of people of all ages. It can occur due to a multitude of sources such as genetics, diseases, ageing, or noise exposure. If not treated properly and timely it may lead to socioeconomic difficulties such as poor job performance, hardship in finding a job, and social isolation.
In this work, we propose HyTEA, a framework based on Evolutionary Computation to create Decision Tree like models to identify people that are likely to be diagnosed with hearing loss, so they can be called for screening by a health professional. To achieve this, we will use historic data about patients who have been diagnosed with hearing problems and complement it with publicly available socioeconomic information. The models created should provide some understanding of the reason a decision is being made since this is key for health professionals.
To build Decision Trees we usually rely on greedy induction algorithms which may result in overfitting of the training data. To counter this problem, HyTEA uses a combination of two Evolutionary Algorithms, namely Structured Grammatical Evolution and Differential Evolution to generate Decision Trees.
The results show that HyTEA is capable of consistently modelling the problem space and predicting hearing loss with an accuracy of approximately 73%. Additionally, we propose a visualisation tool based on t-SNE to help identify the patients that are being wrongly classified.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Aliabadi, M., Farhadian, M., Darvishi, E.: Prediction of hearing loss among the noise exposed workers in a steel factory using artificial intelligence approach. Int. Arch. Occup. Environ. Health 88, 779–787 (2014). https://doi.org/10.1007/s00420-014-1004-z
Barros, R., Basgalupp, M., de Carvalho, A., Freitas, A.: A survey of evolutionary algorithms for decision-tree induction. IEEE Trans. Syst. Man Cybern. Part C Appl. Rev. 42, 291–312 (2012). https://doi.org/10.1109/TSMCC.2011.2157494
Chen, F., Cao, Z., Grais, E.M., Zhao, F.: Contributions and limitations of using machine learning to predict noise-induced hearing loss. Int. Arch. Occup. Environ. Health 94(5), 1097–1111 (2021). https://doi.org/10.1007/s00420-020-01648-w
Chen, X., Zhou, Q., Lan, R., Wang, S., Zhang, Y.D., Luo, X.: Sensorineural hearing loss classification via deep-HLNet and few-shot learning. Multimedia Tools Appl. 80, 1–14 (2021). https://doi.org/10.1007/s11042-020-09702-y
ElahiShirvan, H., Ghotbi-Ravandi, M., Zare, S., Ahsaee, M.: Using audiometric data to weigh and prioritize factors that affect workers’ hearing loss through support vector machine (svm) algorithm. Sound Vibr. 54, 99–112 (2020). https://doi.org/10.32604/sv.2020.08839
Farhadian, M., Aliabadi, M., Darvishi, E.: Empirical estimation of the grades of hearing impairment among industrial workers based on new artificial neural networks and classical regression methods. Ind. J. Occup. Environ. Med. 19, 165337 (2015). https://doi.org/10.4103/0019-5278.165337
Github: nunolourenco/sge3. https://github.com/nunolourenco/sge3. Accessed 29 Dec 2021
Greenwell, B., Tvaryanas, A., Maupin, G.: Risk factors for hearing decrement among U.S. air force aviation-related personnel. Aerosp. Med. Human Perform. 89, 80–86 (2018). https://doi.org/10.3357/AMHP.4988.2018
Lourenço, N., Assunção, F., Pereira, F.B., Costa, E., Machado, P.: Structured grammatical evolution: a dynamic approach. In: Ryan, C., O’Neill, M., Collins, J.J. (eds.) Handbook of Grammatical Evolution, pp. 137–161. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-78717-6_6
Lourenço, N., Ferrer, J., Pereira, F.B., Costa, E.: A comparative study of different grammar-based genetic programming approaches. In: McDermott, J., Castelli, M., Sekanina, L., Haasdijk, E., García-Sánchez, P. (eds.) EuroGP 2017. LNCS, vol. 10196, pp. 311–325. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-55696-3_20
Lourenço, N., Pereira, F.B., Costa, E.: Unveiling the properties of structured grammatical evolution. Genetic Program. Evolvable Mach. 17(3), 251–289 (2016). https://doi.org/10.1007/s10710-015-9262-4
Van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579–2605 (2008)
Park, K.V., et al.: Machine learning models for predicting hearing prognosis in unilateral idiopathic sudden sensorineural hearing loss. Clin. Exp. Otorhinolaryngol. 13, 148–156 (2020). https://doi.org/10.21053/ceo.2019.01858
PORDATA. https://www.pordata.pt/ (2019). Accessed 19 Dec 2021
Portal de Transparência do SNS. https://www.sns.gov.pt/transparencia/ (2019). Accessed 19 Dec 2021
Saremi, M., Yaghmaee, F.: Evolutionary decision tree induction with multi-interval discretization, pp. 1–6 (2014). https://doi.org/10.1109/IranianCIS.2014.6802543
SciPy: differential evolution. https://docs.scipy.org. Accessed 29 Dec 2021
Storn, R., Price, K.: Differential evolution – a simple and efficient heuristic for global optimization over continuous space. J. Global Optim. 114, 341–359 (1997). https://doi.org/10.1023/A:1008202821328
Zare, S., Ghotbi Ravandi, M.R., ElahiShirvan, H., Ahsaee, M., Rostami, M.: Predicting and weighting the factors affecting workers’ hearing loss based on audiometric data using c5 algorithm. Ann. Glob. Health 85, 88 (2019). https://doi.org/10.5334/aogh.2522
Zare, S., Hasheminejad, N., Shirvan, H., Hasanvand, D., Hemmatjo, R., Ahmadi, S.: Assessing individual and environmental sound pressure level and sound mapping in Iranian safety shoes factory. Roman. J. Acoust. Vibr. 15, 20–25 (2018)
Zhao, Y., et al.: Machine learning models for the hearing impairment prediction in workers exposed to complex industrial noise: a pilot study. Ear Hear. 40, 1 (2018). https://doi.org/10.1097/AUD.0000000000000649
Zhao, Y., Tian, Y., Zhang, M., Li, J., Qiu, W.: Development of an automatic classifier for the prediction of hearing impairment from industrial noise exposure. J. Acoust. Soc. Am. 145, 2388–2400 (2019). https://doi.org/10.1121/1.5096643
Acknowledgements
This work was funded by FEDER funds through the Operational Programme Competitiveness Factors- COMPETE and national funds by FCT - Foundation for Science and Technology (POCI-01-0145-FEDER-029297, CISUC - UID/CEC/ 00326/2020) and within the scope of the project A4A: Audiology for All (CENTRO-01-0247-FEDER-047083) financed by the Operational Program for Competitiveness and Internationalisation of PORTUGAL 2020 through the European Regional Development Fund.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Miranda, F., Polisciuc, E., Lourenço, N. (2023). HyTEA: Hybrid Tree Evolutionary Algorithm. In: Legrand, P., et al. Artificial Evolution. EA 2022. Lecture Notes in Computer Science, vol 14091. Springer, Cham. https://doi.org/10.1007/978-3-031-42616-2_2
Download citation
DOI: https://doi.org/10.1007/978-3-031-42616-2_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-42615-5
Online ISBN: 978-3-031-42616-2
eBook Packages: Computer ScienceComputer Science (R0)