Background: In the context of "Internet +" medical treatment, mobile health applications provide services for people in a new way, making it possible for people to carry out health management anytime and anywhere. According to the survey data, the most powerful consumers in the field of mobile health applications are those aged 24 to 35. Thus, it can be seen, it is particularly important to study the preferences of young people for mobile health applications.
Methods: This study established a domain-adaptive mobile health application evaluation model based on users’ experience, and used an interactive algorithm combining machine learning and Delphi method to calculate the weight distribution of evaluation factors. Compared with previous studies, the establishment of evaluation index based on user experience of youth groups can more comprehensively measure users' demand for mobile health application service quality. Meanwhile, the mobile health application evaluation system established in this study adopts feedback mechanism to realize dynamic evaluation of mobile health applications.
Results: The cognitive level of information (weighting 52%) was only four percentage points higher than the emotional level (weighting 48%). The importance of the four criteria is content information on cognition (weighting 31%), interaction information on emotion (weighting 29%), interaction information on cognition (weighting 21%), and content information on emotion (weighting 19%) in descending order. Among 20 sub-criteria, less disruptive (weighting 17.8%), security (weighting 10.9%), utility (weighting 9.3%), reliability (weighting 8.1%), navigational (weighting 6.7%) occupy an important position.
Conclusion: We find that the weights assigned to sociability, personalization, aesthetics, and interestingness accounted for a significant proportion of the total weights assigned; however, universality and learnability were poorly weighted. These results have important reference value for the development of mobile health applications.
Service evaluation, Mobile health application, Domain adaptive, Machine learning, Delphi