Artificial intelligence-informed mobile mental health apps for young people: a mixed-methods approach on users’ and stakeholders’ perspectives

Abstract

Background Novel approaches in mobile mental health (mHealth) apps that make use of Artificial Intelligence (AI), Ecological Momentary Assessments, and Ecological Momentary Interventions have the potential to support young people in the achievement of mental health and wellbeing goals. However, little is known on the perspectives of young people and mental health experts on this rapidly advancing technology. This study aims to investigate the subjective needs, attitudes, and preferences of key stakeholders towards an AI–informed mHealth app, including young people and experts on mHealth promotion and prevention in youth. Methods We used a convergent parallel mixed–method study design. Two semi–structured online focus groups (n = 8) and expert interviews (n = 5) to explore users and stakeholders perspectives were conducted. Furthermore a representative online survey was completed by young people (n = 666) to investigate attitudes, current use and preferences towards apps for mental health promotion and prevention. Results Survey results show that more than two-thirds of young people have experience with mHealth apps, and 60% make regular use of 1–2 apps. A minority (17%) reported to feel negative about the application of AI in general, and 19% were negative about the embedding of AI in mHealth apps. This is in line with qualitative findings, where young people displayed rather positive attitudes towards AI and its integration into mHealth apps. Participants reported pragmatic attitudes towards data sharing and safety practices, implying openness to share data if it adds value for users and if the data request is not too intimate, however demanded transparency of data usage and control over personalization. Experts perceived AI-informed mHealth apps as a complementary solution to on–site delivered interventions in future health promotion among young people. Experts emphasized opportunities in regard with low-threshold access through the use of smartphones, and the chance to reach young people in risk situations. Conclusions The findings of this exploratory study highlight the importance of further participatory development of training components prior to implementation of a digital mHealth training in routine practice of mental health promotion and prevention. Our results may help to guide developments based on stakeholders’ first recommendations for an AI-informed mHealth app.

Health Care Professionals’ Views on the Use of Passive Sensing, AI, and Machine Learning in Mental Health Care: Systematic Review With Meta-Synthesis

“…Further suggestions were made as to how passive sensing and AI could be useful in therapeutic work, such as guiding productive discussions [ 33 ], setting treatment goals, delivering low-intensity support [ 3 ], tracking the efficacy of brief interventions [ 23 ], and encouraging ongoing engagement and regular self-reflection [ 38 ]. Furthermore, discussions were conducted about how AI’s ability to process, connect, and make conclusions from large amounts of data could be used to risk-stratify service users according to their personal factors and needs [ 36 ] and support identification and awareness of early warning signs, thus reducing the risk of relapse of mental health difficulties [ 32 - 34 , 37 ]. As clinicians have access to these data, it was also felt that they could identify when to intervene [ 38 ], which may further reduce a service user’s risk of deterioration in mental health [ 10 ].…”

“…It was highlighted that technology is now readily available, and this was reported as a benefit to using passive sensing and AI in mental health practice as it may improve service user access to mental health care [ 34 ]. However, not all mental health services have sufficient access to technology [ 37 ] because of factors such as cost and the lack of the necessary infrastructure to support digital tools [ 3 ]. For example, participants reported that in India, most hospitals do not have access to the internet [ 35 ], and service users do not always have access to smartphones [ 23 ].…”

“…To ensure ease of use, suggestions were made, such as including relevant stakeholders in the development of such technologies and related systems to ensure that they use accessible language [ 37 ] and presenting the data in a simple way that is easy to understand [ 3 ]:…”

“…It was suggested that passive sensing and AI could facilitate “knowledge transfer” and empower service users to understand how their actions, feelings, and thoughts are intertwined [ 37 ]. By increasing insight into mental health, self-monitoring allows service users to respond to symptoms and take action themselves [ 10 ].…”

Assessing the role of artificial intelligence in the mental healthcare of teachers and students

“…Conventional psychiatry will be much improved by the predictive AI-based technique that can identify probable chronic psychopathology early enough (Cosic 2022). Go ¨tzl et al (Go ¨tzl et al 2022) have conducted a study on the perspectives of end-users about the utilization of mobile mental health (mHealth) applications with the integration of artificial intelligence for their mental well-being. According to survey findings, 60% of young people regularly employ 1-2 mHealth applications, and more than two-thirds of them have familiarity with them.…”