Key points are not available for this paper at this time.
The paper presents a novel approach to multifactorial disorder risk assessment through the development and deployment of a cross-platform application empowered by edge computing technology. Multifactorial disorders pose significant challenges to public health, necessitating accurate risk assessment tools for early detection and prevention. Leveraging a dataset sourced from the Behavioral Risk Factor Surveillance System (BRFSS), selected 17 relevant features and seven diseases for analysis, converting them into binary classification variables. Our study focused on training models within the. NET Maui framework, achieving promising results with the best-performing model exhibiting a macro-accuracy of 73.93%. Additionally, this study developed a risk assessment tool framework that integrates edge computing to enhance performance and accessibility. The framework incorporates feature selection and engineering techniques, optimizing the risk assessment process. Our cross-platform application guides users through a self-check process, allowing them to input personal information and obtain risk percentage assessments. Through this innovative approach, our study contributes to early detection efforts for multifactorial disorders while addressing limitations of existing risk assessment methods. Our findings underscore the potential of edge computing technology in revolutionizing healthcare applications, paving the way for more effective and accessible risk assessment tools.
Solomon et al. (Wed,) studied this question.