Application of Artificial Intelligence and Data Science in Detecting the Impact of Usability from Evaluation of Mobile Health Applications

Kayode, Olamide; Al Jaber, Tareq; Gordon, Neil

Abstract

Mobile health (mHealth) applications have demonstrated immense potential for facilitating preventative care and disease management through intuitive platforms. However, realizing transformational health objectives relies on creating accessible tools optimized for different users. This research analyses mHealth app usability data sourced from online repositories to reveal the impact of usability (ease of use) from evaluating mobile health applications. Thoroughly examining interfaces with a utilization of statistical tests of significance, platform, integra-tions, and various application features shows complex relationships between usability and users experience. This work shows that applying random forest models can accurately classify the ease-of-use of mHealth applications. This work sheds light on the connections between design choices and their effects, guiding intentional improvements to expand the reach of mHealth. It does so by providing insights into the subtle ways that people interact with mHealth applications. The methodologies and findings provide actionable insights for developers and practitioners passionate about advancing digital healthcare.

Citation

Kayode, O., Al Jaber, T., & Gordon, N. (2024). Application of Artificial Intelligence and Data Science in Detecting the Impact of Usability from Evaluation of Mobile Health Applications. International Journal on Engineering Technologies and Informatics, 5(1), 1-9. https://doi.org/10.51626/ijeti.2024.05.00070

• Journal Article Type: Article
• Acceptance Date: Jan 29, 2024
• Online Publication Date: Jan 31, 2024
• Publication Date: Jan 31, 2024
• Deposit Date: Feb 29, 2024
• Publicly Available Date: Mar 5, 2024
• Journal: International Journal on Engineering Technologies and Informatics
• Peer Reviewed: Peer Reviewed
• Volume: 5
• Issue: 1
• Pages: 1-9
• DOI: https://doi.org/10.51626/ijeti.2024.05.00070
• Keywords: MHealth applications; Usability; Artificial intelligence; Data science; Artificial neural network; Chi-square; Random forest; Evaluation metrics; Random oversampling; Feature engineering; Feature selection; Cross validation; Research hypothesis; P-value
• Public URL: https://hull-repository.worktribe.com/output/4567159
• Publisher URL: https://skeenapublishers.com/journal/ijeti/IJETI-05-00070.pdf