Leveraging Discrete Choice Experiments for User-Centric Requirements Prioritization in mHealth Applications

2025-11-23

AI Summary

Adaptive user interfaces (AUIs) in mHealth applications for chronic disease management face adoption barriers due to heterogeneous user preferences. This study pioneers the application of discrete choice experiments (DCEs) to prioritize mHealth requirements, employing a six-attribute, multi-level choice design and a mixed logit model to quantify user preferences and trade-offs regarding AUI features. Heterogeneity analyses were conducted across age, gender, health status, and coping mechanisms. Results indicate that controllability, infrequent adaptation, and minor interface adjustments significantly enhance user acceptance, whereas frequent feature updates and caregiver involvement diminish perceived value. Based on these findings, we propose a data-driven AUI design optimization framework. This framework provides empirical evidence and stratified adaptation strategies to support personalized, acceptable, and context-aware mHealth interface design.

Technology Category

• Humans and AI: Intelligent User Interfaces
• Machine Learning: Learning Preferences or Rankings
• Knowledge Representation and Reasoning: Preferences

Application Category

• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Fairness, privacy, and diversity in economic environments

Abstract

Mobile health (mHealth) applications are widely used for chronic disease management, but usability and accessibility challenges persist due to the diverse needs of users. Adaptive User Interfaces (AUIs) offer a personalized solution to enhance user experience, yet barriers to adoption remain. Understanding user preferences and trade-offs is essential to ensure widespread acceptance of adaptation designs. This study identifies key factors influencing user preferences and trade-offs in mHealth adaptation design. A Discrete Choice Experiment (DCE) was conducted with 186 participants who have chronic diseases and use mHealth applications. Participants were asked to select preferred adaptation designs from choices featuring six attributes with varying levels. A mixed logit model was used to analyze preference heterogeneity and determine the factors most likely influencing adoption. Additionally, subgroup analyses were performed to explore differences by age, gender, health conditions, and coping mechanisms. Maintaining usability while ensuring controllability over adaptations, infrequent adaptations, and small-scale changes are key factors that facilitate the adoption of adaptive mHealth app designs. In contrast, frequently used functions and caregiver involvement can diminish the perceived value of such adaptations. This study employs a data-driven approach to quantify user preferences, identify key trade-offs, and reveal variations across demographic and behavioral subgroups through preference heterogeneity modeling. Furthermore, our results offer valuable guidance for developing future adaptive mHealth applications and lay the groundwork for continued exploration into requirements prioritization within the field of software engineering.

Problem

• Identifying user preferences for adaptive mHealth app designs through choice experiments
• Analyzing trade-offs in adaptation frequency and controllability for chronic disease users
• Quantifying preference variations across demographic subgroups using statistical modeling

Innovation

• Discrete Choice Experiment quantifies user preferences
• Mixed logit model analyzes preference heterogeneity
• Subgroup analysis reveals demographic variation factors