Bioinformatics-driven deep learning for nail disease diagnosis: A novel approach to improve healthcare outcomes
In order to increase awareness of the importance of nail care in preventing disease and enhancing quality of life, this study investigates the use of convolutional neural networks, or CNNs. Onychomycosis and other nail disorders are quite prevalent worldwide and are associated with inadequate person...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2025-01-01
|
| Series: | BIO Web of Conferences |
| Online Access: | https://www.bio-conferences.org/articles/bioconf/pdf/2025/03/bioconf_ichbs2025_01024.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832098696901165056 |
|---|---|
| author | Ardianto Rian Yusuf Dede Sumantri Raden Bagus Bambang Febrina Dina Al-Hakim Rosyid R. Ariyanto Arif Setia Sandi |
| author_facet | Ardianto Rian Yusuf Dede Sumantri Raden Bagus Bambang Febrina Dina Al-Hakim Rosyid R. Ariyanto Arif Setia Sandi |
| author_sort | Ardianto Rian |
| collection | DOAJ |
| description | In order to increase awareness of the importance of nail care in preventing disease and enhancing quality of life, this study investigates the use of convolutional neural networks, or CNNs. Onychomycosis and other nail disorders are quite prevalent worldwide and are associated with inadequate personal cleanliness. The study used a dataset of 655 nail photos that had been pre-processed to 224x224 pixel resolution and categorized into 17categories. The CNN model performed well in identifying illnesses like “Leukonychia,” achieving an overall accuracy of 83%; however, it needs to be improved for underrepresented classifications like “Pale Nail.” The study recommends data augmentation, model parameter optimization, and dataset expansion to improve accuracy. To confirm dependability in practical contexts, testing with clinical datasets is also advised. A user-friendly interface for wider accessibility is one of the future aims, which will allow for prompt and precise preliminary diagnosis. This study shows how CNN-based technologies can be used to quickly and easily identify nail disorders, improving access to treatment and preventing disease |
| format | Article |
| id | doaj-art-4e5b84397a0048278c418ecf68d6a371 |
| institution | Kabale University |
| issn | 2117-4458 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | EDP Sciences |
| record_format | Article |
| series | BIO Web of Conferences |
| spelling | doaj-art-4e5b84397a0048278c418ecf68d6a3712025-02-05T10:42:50ZengEDP SciencesBIO Web of Conferences2117-44582025-01-011520102410.1051/bioconf/202515201024bioconf_ichbs2025_01024Bioinformatics-driven deep learning for nail disease diagnosis: A novel approach to improve healthcare outcomesArdianto Rian0Yusuf Dede1Sumantri Raden Bagus Bambang2Febrina Dina3Al-Hakim Rosyid R.4Ariyanto Arif Setia Sandi5Department of Informatics, Universitas Harapan Bangsa, Karangklesem Purwokerto SelatanDepartment of Informatics, Universitas Al-Irsyad Cilacap, Wanasari Sidanegara Cilacap TengahDepartment of Informatics, Universitas Al-Irsyad Cilacap, Wanasari Sidanegara Cilacap TengahDepartment of Pharmacy, Universitas Harapan Bangsa, Raden Patah Ledug BanyumasDepartment of Information System, Universitas Harapan BangsaDepartment of Information System, Universitas Harapan BangsaIn order to increase awareness of the importance of nail care in preventing disease and enhancing quality of life, this study investigates the use of convolutional neural networks, or CNNs. Onychomycosis and other nail disorders are quite prevalent worldwide and are associated with inadequate personal cleanliness. The study used a dataset of 655 nail photos that had been pre-processed to 224x224 pixel resolution and categorized into 17categories. The CNN model performed well in identifying illnesses like “Leukonychia,” achieving an overall accuracy of 83%; however, it needs to be improved for underrepresented classifications like “Pale Nail.” The study recommends data augmentation, model parameter optimization, and dataset expansion to improve accuracy. To confirm dependability in practical contexts, testing with clinical datasets is also advised. A user-friendly interface for wider accessibility is one of the future aims, which will allow for prompt and precise preliminary diagnosis. This study shows how CNN-based technologies can be used to quickly and easily identify nail disorders, improving access to treatment and preventing diseasehttps://www.bio-conferences.org/articles/bioconf/pdf/2025/03/bioconf_ichbs2025_01024.pdf |
| spellingShingle | Ardianto Rian Yusuf Dede Sumantri Raden Bagus Bambang Febrina Dina Al-Hakim Rosyid R. Ariyanto Arif Setia Sandi Bioinformatics-driven deep learning for nail disease diagnosis: A novel approach to improve healthcare outcomes BIO Web of Conferences |
| title | Bioinformatics-driven deep learning for nail disease diagnosis: A novel approach to improve healthcare outcomes |
| title_full | Bioinformatics-driven deep learning for nail disease diagnosis: A novel approach to improve healthcare outcomes |
| title_fullStr | Bioinformatics-driven deep learning for nail disease diagnosis: A novel approach to improve healthcare outcomes |
| title_full_unstemmed | Bioinformatics-driven deep learning for nail disease diagnosis: A novel approach to improve healthcare outcomes |
| title_short | Bioinformatics-driven deep learning for nail disease diagnosis: A novel approach to improve healthcare outcomes |
| title_sort | bioinformatics driven deep learning for nail disease diagnosis a novel approach to improve healthcare outcomes |
| url | https://www.bio-conferences.org/articles/bioconf/pdf/2025/03/bioconf_ichbs2025_01024.pdf |
| work_keys_str_mv | AT ardiantorian bioinformaticsdrivendeeplearningfornaildiseasediagnosisanovelapproachtoimprovehealthcareoutcomes AT yusufdede bioinformaticsdrivendeeplearningfornaildiseasediagnosisanovelapproachtoimprovehealthcareoutcomes AT sumantriradenbagusbambang bioinformaticsdrivendeeplearningfornaildiseasediagnosisanovelapproachtoimprovehealthcareoutcomes AT febrinadina bioinformaticsdrivendeeplearningfornaildiseasediagnosisanovelapproachtoimprovehealthcareoutcomes AT alhakimrosyidr bioinformaticsdrivendeeplearningfornaildiseasediagnosisanovelapproachtoimprovehealthcareoutcomes AT ariyantoarifsetiasandi bioinformaticsdrivendeeplearningfornaildiseasediagnosisanovelapproachtoimprovehealthcareoutcomes |