Comparison of two methods in determining hearing loss type and hearing loss degree: mobile application coded with artificial neural networks and conditional structures
Abstract Background Determining the type and degree of hearing loss is important in the treatment of loss or in the selection of assistive hearing aids to be used. In this study, it is aimed to distinguish the types and degrees of hearing loss with loops created by codes written using deep learning...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2025-07-01
|
| Series: | The Egyptian Journal of Otolaryngology |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s43163-025-00849-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849769745850564608 |
|---|---|
| author | Ahmet Yasin Disci Ozlem Konukseven Rukiye Tanisir Disci |
| author_facet | Ahmet Yasin Disci Ozlem Konukseven Rukiye Tanisir Disci |
| author_sort | Ahmet Yasin Disci |
| collection | DOAJ |
| description | Abstract Background Determining the type and degree of hearing loss is important in the treatment of loss or in the selection of assistive hearing aids to be used. In this study, it is aimed to distinguish the types and degrees of hearing loss with loops created by codes written using deep learning methods and conditional structures. Method A data set consisting of 1000 pure tone airway and pure tone bone conduction hearing tests performed in the audiology clinic was prepared for this study. The Spyder plugin of the Python program was used for the artificial neural network algorithm. While 800 of the tests in the dataset were used to train the machine, 200 test results were used to check the accuracy of the machine results. The audiogram types taught to the machine are interpreted with the artificial neural network algorithm and matched with each of the hearing loss types and degrees. Eclipse IDE for Java Developers-2021–03 program in Java programming language was used for the codes written with conditional structures. Hearing thresholds in each row in the dataset are looped with conditional constructs to determine the type and degree of hearing loss. After teaching with 800 audiogram results in artificial neural network modeling, the result was tested with 200 audiogram results. Results An accuracy of 94.5% was obtained in artificial intelligence learning when determining the type of hearing loss, and 95% when determining the degree of hearing loss. In the loop prepared using conditional constructs, an accuracy rate of 96.4% was obtained when determining the type of hearing loss and 100% when determining the degree of hearing loss. Conclusions It has been seen that computer-based programs can be used to determine the type and degree of hearing loss. |
| format | Article |
| id | doaj-art-90d871c995bb4ceaabb4b48ec4992aff |
| institution | DOAJ |
| issn | 2090-8539 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | The Egyptian Journal of Otolaryngology |
| spelling | doaj-art-90d871c995bb4ceaabb4b48ec4992aff2025-08-20T03:03:20ZengSpringerOpenThe Egyptian Journal of Otolaryngology2090-85392025-07-0141111610.1186/s43163-025-00849-9Comparison of two methods in determining hearing loss type and hearing loss degree: mobile application coded with artificial neural networks and conditional structuresAhmet Yasin Disci0Ozlem Konukseven1Rukiye Tanisir Disci2Department of Audiology, Faculty of Health Sciences, Istanbul Aydin UniversityDepartment of Audiology, Faculty of Health Sciences, Istanbul Aydin UniversityDepartment of Audiology, Faculty of Health Sciences, Istanbul Aydin UniversityAbstract Background Determining the type and degree of hearing loss is important in the treatment of loss or in the selection of assistive hearing aids to be used. In this study, it is aimed to distinguish the types and degrees of hearing loss with loops created by codes written using deep learning methods and conditional structures. Method A data set consisting of 1000 pure tone airway and pure tone bone conduction hearing tests performed in the audiology clinic was prepared for this study. The Spyder plugin of the Python program was used for the artificial neural network algorithm. While 800 of the tests in the dataset were used to train the machine, 200 test results were used to check the accuracy of the machine results. The audiogram types taught to the machine are interpreted with the artificial neural network algorithm and matched with each of the hearing loss types and degrees. Eclipse IDE for Java Developers-2021–03 program in Java programming language was used for the codes written with conditional structures. Hearing thresholds in each row in the dataset are looped with conditional constructs to determine the type and degree of hearing loss. After teaching with 800 audiogram results in artificial neural network modeling, the result was tested with 200 audiogram results. Results An accuracy of 94.5% was obtained in artificial intelligence learning when determining the type of hearing loss, and 95% when determining the degree of hearing loss. In the loop prepared using conditional constructs, an accuracy rate of 96.4% was obtained when determining the type of hearing loss and 100% when determining the degree of hearing loss. Conclusions It has been seen that computer-based programs can be used to determine the type and degree of hearing loss.https://doi.org/10.1186/s43163-025-00849-9Hearing lossConditional structuresMachine learningArtificial intelligence |
| spellingShingle | Ahmet Yasin Disci Ozlem Konukseven Rukiye Tanisir Disci Comparison of two methods in determining hearing loss type and hearing loss degree: mobile application coded with artificial neural networks and conditional structures The Egyptian Journal of Otolaryngology Hearing loss Conditional structures Machine learning Artificial intelligence |
| title | Comparison of two methods in determining hearing loss type and hearing loss degree: mobile application coded with artificial neural networks and conditional structures |
| title_full | Comparison of two methods in determining hearing loss type and hearing loss degree: mobile application coded with artificial neural networks and conditional structures |
| title_fullStr | Comparison of two methods in determining hearing loss type and hearing loss degree: mobile application coded with artificial neural networks and conditional structures |
| title_full_unstemmed | Comparison of two methods in determining hearing loss type and hearing loss degree: mobile application coded with artificial neural networks and conditional structures |
| title_short | Comparison of two methods in determining hearing loss type and hearing loss degree: mobile application coded with artificial neural networks and conditional structures |
| title_sort | comparison of two methods in determining hearing loss type and hearing loss degree mobile application coded with artificial neural networks and conditional structures |
| topic | Hearing loss Conditional structures Machine learning Artificial intelligence |
| url | https://doi.org/10.1186/s43163-025-00849-9 |
| work_keys_str_mv | AT ahmetyasindisci comparisonoftwomethodsindetermininghearinglosstypeandhearinglossdegreemobileapplicationcodedwithartificialneuralnetworksandconditionalstructures AT ozlemkonukseven comparisonoftwomethodsindetermininghearinglosstypeandhearinglossdegreemobileapplicationcodedwithartificialneuralnetworksandconditionalstructures AT rukiyetanisirdisci comparisonoftwomethodsindetermininghearinglosstypeandhearinglossdegreemobileapplicationcodedwithartificialneuralnetworksandconditionalstructures |