AI-Enhanced User Interface Refactoring for Legacy Healthcare Portals
DOI:
https://doi.org/10.15662/IJEETR.2024.0605018Keywords:
Healthcare, AI, Legacy, User Interface, Portal, RefactoringAbstract
Most of the healthcare portals have continued using legacy codes that restrain their
accessibility and usability. This paper reports on an AI-assisted refactoring engine,
and how it creates and automatically corrects accessibility problems in the legacy
front-end code, using natural language processing (NLP). The system was analyzed
with a healthcare portal that is comparable to the Medicare and Retirement platform
developed by UnitedHealthcare and managed to fix 81 percent of ARIA and semantic
HTML errors. The findings indicate that AI can have a profound positive impact on
manual labor and workload decrease, code compliance, and user experience. This
research paper has proven that the idea of AI-based code refactoring has the potential
to transform outdated yet useful healthcare systems in a quick and inclusive way.
References
Ferreira, F., Borges, H. S., & Valente, M. T. (2024). Refactoring react-based Web apps. Journal of
Systems and Software, 215, 112105. https://doi.org/10.1016/j.jss.2024.112105
[2] Nguyen, T. (2024). Evaluating automated accessibility checker tools. In WWU Honors College
Senior Projects [Thesis]. https://cedar.wwu.edu/wwu_honors/805
[3] Kapula, K. & National Science Foundation. (2024). AUTOMATED EVALUATION OF DIGITAL
ACCESSIBILITY: A TEASER ON WCAG ANALYZER SYSTEMS. Journal of Computational Analysis
and Applications, 2895–2902. https://doi.org/10.48047/jocaaa.2024.33.06.116
[4] Mirchev, M., Costea, A., Singh, A. K., & Roychoudhury, A. (2024). Assured automatic programming
via large language models. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2410.18494
[5] Wang, Y., Wang, W., Joty, S. R., & Hoi, S. C. H. (2021). CodeT5: Identifier-Aware Unified Pre
Trained Encoder-Decoder models for code understanding and generation. arXiv (Cornell
University). https://doi.org/10.48550/arxiv.2109.00859
[6] Pandi, S. B., Binta, S. A., & Kaushal, S. (2023). Artificial intelligence for technical debt management
in software development. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2306.10194
[7] Singh, P. (2024, July 3). Transforming Healthcare through AI: Enhancing Patient Outcomes and
Bridging Accessibility Gaps. Journal of https://thesciencebrigade.com/JAIR/article/view/237 Artificial Intelligence Research.
[8] Chaturvedi, R. (2023, May 31). Robotic Process Automation (RPA) in Healthcare: Transforming
revenue cycle operations. https://ijritcc.org/index.php/ijritcc/article/view/11045
[9] Poghosyan, A., Harutyunyan, A., Davtyan, E., Petrosyan, K., & Baloian, N. (2024). A Study on
Automated Problem Troubleshooting in Cloud Environments with Rule Induction and Verification.
Applied Sciences, 14(3), 1047. https://doi.org/10.3390/app14031047
[10] Liu, M., Wang, J., Lin, T., Ma, Q., Fang, Z., & Wu, Y. (2024). An empirical study of the code
generation of Safety-Critical Software using LLMS. Applied Sciences, 14(3), 1046.
https://doi.org/10.3390/app14031046
[11] Nie, L., Liu, H., Sun, J., Said, K. S., Hong, S., Xue, L., Wei, Z., Zhao, Y., & Li, M. (2024). SoK:
Detection and Repair of Accessibility https://doi.org/10.48550/arxiv.2411.19727 Issues. arXiv (Cornell University).
[12] Vijayvergiya, M., Salawa, M., Budiselić, I., Zheng, D., Lamblin, P., Ivanković, M., Carin, J., Lewko,
M., Andonov, J., Petrović, G., Tarlow, D., Maniatis, P., & Just, R. (2024). AI-Assisted Assessment
of Coding Practices in Modern Code Review. AIware 2024: Proceedings of the 1st ACM
International Conference on https://doi.org/10.1145/3664646.3665664 AI-Powered Software, 85–93.
[13] Jin, H., Lee, S., Shin, H., & Kim, J. (2024). Teach AI How to Code: Using Large Language Models
as Teachable Agents for Programming Education. CHI ’24: Proceedings of the 2024 CHI Conference on Human
Factors
https://doi.org/10.1145/3613904.3642349
[14] Souza, A., De Souza Filho, J. C., Bezerra, C., Alves, V. A., Lima, L., Marques, A. B., & Monteiro, I. T.
(2024). Accessibility Evaluation of Web Systems for People with Visual Impairments: Findings
from a Literature Survey. IHC ’24: Proceedings of the XXIII Brazilian Symposium on Human
Factors in Computing Systems, 1–13. https://doi.org/10.1145/3702038.3702090
[15] Sung, C., Kusano, M., Sinha, N., & Wang, C. (2016). Static DOM event dependency analysis for
testing web applications. FSE 2016: Proceedings of the 2016 24th ACM SIGSOFT International
Symposium on Foundations https://doi.org/10.1145/2950290.2950292 of Software Engineering, 447–459.
