An Empirical Study of Factor Identification in Smart Health-Monitoring Wearable Device

Smart Health-Monitoring Wearable Device (SHMWD) is one of the solutions to improve health-care quality and accessibility through early detection and prevention. A comprehensive framework of factor identification of SHMWD from wide-ranging considerations is needed. Indeed, quantitative support of identifying significant factors/features affecting product rating and review needs to be studied as well. This article aims to identify 123 environmental factors (EFs) and their associated categories of SHMWD from various perspectives, determine the important EFs based on customers' interest, and investigate the significant levels of EFs and each category on product rating, the significant EFs of each category, the correlation among EFs, and the principle components of the data set. Data analysis was conducted based on real data collected online (n = 769). Statistical learning methods, including relative weighted method, analysis of variance, hypothesis testing, multiple regression analysis, backward elimination method, and principle component analysis, are employed to analyze the collected data. We also identify the top 15 important EFs which can be further incorporated in product development and maintenance. For researchers, this article points to the improvement directions of the current technologies applied in SHMWD as well as the new technologies to be implemented in the area of human-machine interactions. For practitioners, this article provides the managerial suggestions of time and resource allocation to the development team given each team may have different focused category and a general guide of feature selection for product development and maintenance and improvement for customer satisfaction.