Understanding the determinants of mHealth apps adoption in Bangladesh: A SEM-Neural network approach

Due to the low adoption rate of mHealth apps, the apps designers need to understand the factors behind adoption. But understanding the determinants of mHealth apps adoption remains unclear. Comparatively less attention has been given to the factors affecting the adoption of mHealth apps among the young generation. This study aims to examine the factors influencing behavioral intention and actual usage behavior of mHealth apps among technology prone young generation. The research model has extracted variables from the widely accepted Unified Theory of Acceptance and Use of Technology (UTAUT2) alongside privacy, lifestyles, self-efficacy and trust. Required data were collected from mHealth apps users in Bangladesh. Firstly, this study confirmed that performance expectancy, social influence, hedonic motivation and privacy exerted a positive influence on behavioral intention whereas facilitating conditions, self-efficacy, trust and lifestyle had an influence on both behavioral intention and actual usage behavior. Secondly, the Neural Network Model was employed to rank relatively significant predictors obtained from structural equation modeling (SEM). This study contributes to the growing literature on the use of mHealth apps in trying to elevate the quality of patients' lives. The new methodology and findings from this study will significantly contribute to the extant literature of technology adoption and mHealth apps adoption intention especially. Therefore, for practitioners concerned with fostering mHealth apps adoption, the findings stress the importance of adopting an integrated approach centered on key findings of this study. •The focus of this study was to explore the factors influencing behavioral intention and actual usage behavior of mHealth apps.•The conceptual model was proposed based on the extended Unified Theory of Acceptance and Use of Technology (UTAUT2) and other factors.•The results support the significant role of self-efficacy, privacy, trust, lifestyle and some UTAUT2 factors.•Additionally, Neural Network Model was also employed to rank relatively significant predictors obtained from SEM.•Neural Network Model indicates the Trust and Hedonic Motivation as the most significant predictor.