(C) PLOS One
This story was originally published by PLOS One and is unaltered.
 . . . . . . . . . .



Artificial intelligence and machine learning in mobile apps for mental health: A scoping review [1]

['Madison Milne-Ives', 'Centre For Health Technology', 'University Of Plymouth', 'Plymouth', 'United Kingdom', 'Emma Selby', 'Wysa', 'Wenlock Road', 'London', 'Becky Inkster']

Date: 2022-08 

Mental health conditions, such as anxiety and depression, can have significant negative impacts on a range of mental and physical wellbeing, social, and employment outcomes [ 1 , 2 ]. People with severe, long-term mental illness have an average of 15 years shorter life expectancies than the general population [ 3 ]. Worldwide, there is a high prevalence of mental health issues and conditions [ 4 ]; in the UK, approximately a quarter of the population is seeking mental health treatment [ 5 ]. Despite this, it is estimated that 75% of people who need mental health support do not receive it, resulting in costs to the UK economy of approximately £100 billion annually [ 3 , 6 ]. Globally, this cost exceeds US$1 trillion each year [ 7 ]. There is a clear need for improved means of identifying and supporting mental health conditions among the general population.

Rationale

Many mobile health apps have been developed and made available to the public to try and address this need [8]. Several systematic reviews have recently been published focusing on various aspects and outcomes of mental health apps [8–13]. Most of these systematic reviews found methodological issues (such as a lack of control or comparison groups or representative samples, and a high risk of bias) [9,10] and insufficient evidence of effectiveness of mental health apps for changing behaviours or improving clinical outcomes [9,11,13]. However, one meta-analysis of randomised controlled trials found a significant difference between app interventions and control conditions (but not face-to-face or computer interventions) on certain outcomes [12]. A recent review of meta-analyses also found evidence for small to medium effects of apps on quality of life and stress [8]. This suggests that there is potential for mobile apps to support mental health, although there is a need for further, high-quality research to provide evidence of effectiveness. Following standardised guidelines for study design and reporting (such as the CONSORT statement [14] and CONSORT-EHEALTH extension [15]) would improve the quality of evidence available and help determine in what contexts mental health apps could provide benefits.

Despite this need for more rigorous evaluation, mobile apps for mental health are widely available to the general public and new ones are being designed to include innovative technologies. A number of mobile apps for mental health are available in app stores that have incorporated artificial intelligence (AI) and machine learning (ML) technologies into their service [16–18]. AI refers to the simulation of human intelligence in machines whereas ML allows machines to learn from data without being explicitly programmed [19]. AI/ML techniques have been widely applied in healthcare to generate insights from massive amounts of data [20–22] and are increasingly being incorporated in mobile health apps [23].

None of the systematic reviews that were identified examined evidence for the use of AI in mobile apps for mental health. A search of PROSPERO for registered reviews using the keywords “mental health apps” AND “AI OR artificial intelligence OR machine learning OR chatbot” also found no records. Given the increasing use of artificial intelligence in mobile health apps, a scoping review is needed to provide an overview of the state of the literature and to summarise the strengths and weaknesses of the existing research [24]. An overview of the state of research on AI/ML-enabled mental health apps will help to inform directions for future research and provide an initial assessment of the potential of these apps.

[END]
---
[1] Url: https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0000079

Published and (C) by PLOS One
Content appears here under this condition or license: Creative Commons - Attribution BY 4.0.

via Magical.Fish Gopher News Feeds:
gopher://magical.fish/1/feeds/news/plosone/