Accepted for/Published in: Journal of Medical Internet Research
Date Submitted: Nov 20, 2022
Date Accepted: Mar 31, 2024
Mental Wellness Self-care in Singapore with mindline.sg: A Framework for the Development of a Digital Mental Health Platform for Behaviour Change
ABSTRACT
Background:
Singapore, like the rest of Asia, faces persistent challenges to mental health promotion including stigma around unwellness and seeking treatment, low mental health literacy, a lack of trained mental health personnel, and underdevelopment of mental healthcare ecosystems. The COVID-19 pandemic created a surge in mental healthcare needs, giving new impetus to addressing these shortcomings. The pandemic situation also accelerated the acceptance and adoption of digital health solutions, creating a new opportunity for innovative approaches to quickly scale solutions to address mental healthcare needs in the region.
Objective:
In June 2020, the Singaporean government launched mindline.sg, a digital mental health resource website that has grown to include over 500 curated local mental health resources, a novel self-assessment tool, an AI chatbot (Wysa) designed to deliver digital therapeutic exercises, and a tailored version of the website for working adults called mindline at work. The platform was developed to be anonymous and to contain authoritative and localised content at multiple levels of progressive engagement. The goal of the platform is to empower all in Singapore to take charge of their own mental health and to be able to offer basic support to those around them through the ease and convenience of a barrier-free digital solution.
Methods:
Website utilisation is primarily measured through click-level data analytics captured via Google Analytics and custom APIs, which in turn drive a customised analytics infrastructure based on Metabase. Unique, non-bounced, extensive, and return users are reported. Self-assessments are recorded only if completed, and Wysa AI chatbot usage is only measured if a user lands on Wysa’s platform.
Results:
In the two years following launch (1 July 2020 through 30 June 2022), the website received over 447,000 visitors (about 15% of the target population of three million), 62% of which explore the site or engage with resources, and about 10% of those engaged users return. The most popular features on the platform were the dialogue-based therapeutic exercises delivered by the Wysa AI chatbot and the novel self-assessment tool, which were used by 25.5% and 10.8% of non-bounced visitors, respectively. On mindline at work, the rates of non-bounced visitors who explored the site extensively (i.e., spent 40 seconds or more exploring resources) and who returned were 51.6% and 13.4% over a year, respectively, compared to 35.2% and 11.4%, respectively, on the generic mindline.sg site in the same year.
Conclusions:
The site has achieved desired reach and has seen a strong growth rate in the number of visitors, and a key learning from implementation is that substantial and sustained digital marketing campaigns and strategic outreach partnerships are required to achieve this reach when initiating such a platform. An extensible and customisable analytics infrastructure was also found to be necessary to support these efforts. The digital therapeutic exercises delivered by the AI chatbot and the self-assessment tool successfully progress user engagement. The customised site for working adults appears to successfully increase engagement among this subpopulation. It is not possible to validate these hypotheses definitively due to limitations on user tracking purposefully introduced to ensure actual and perceived anonymity. The framework shows promise for the development of platforms in communities around Asia and those facing similar challenges to mental health promotion.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.