Conversational Agents in the Treatment of Mental Health Problems: Mixed-Method Systematic Review

Abstract

BackgroundThe use of conversational agent interventions (including chatbots and robots) in mental health is growing at a fast pace. Recent existing reviews have focused exclusively on a subset of embodied conversational agent interventions despite other modalities aiming to achieve the common goal of improved mental health.ObjectiveThis study aimed to review the use of conversational agent interventions in the treatment of mental health problems.MethodsWe performed a systematic search using relevant databases (MEDLINE, EMBASE, PsycINFO, Web of Science, and Cochrane library). Studies that reported on an autonomous conversational agent that simulated conversation and reported on a mental health outcome were included.ResultsA total of 13 studies were included in the review. Among them, 4 full-scale randomized controlled trials (RCTs) were included. The rest were feasibility, pilot RCTs and quasi-experimental studies. Interventions were diverse in design and targeted a range of mental health problems using a wide variety of therapeutic orientations. All included studies reported reductions in psychological distress postintervention. Furthermore, 5 controlled studies demonstrated significant reductions in psychological distress compared with inactive control groups. In addition, 3 controlled studies comparing interventions with active control groups failed to demonstrate superior effects. Broader utility in promoting well-being in nonclinical populations was unclear.ConclusionsThe efficacy and acceptability of conversational agent interventions for mental health problems are promising. However, a more robust experimental design is required to demonstrate efficacy and efficiency. A focus on streamlining interventions, demonstrating equivalence to other treatment modalities, and elucidating mechanisms of action has the potential to increase acceptance by users and clinicians and maximize reach.

Agents of change: Understanding the therapeutic processes associated with the helpfulness of therapy for mental health problems with relational agent MYLO

“…30,31 Notably, MYLO's therapeutic approach (curious questioning using MOL) is exclusively concerned with enabling the client to develop their own understanding of the problem to gain new insights and solutions, which is rather different to other relational agent interventions that have a greater focus on psychoeducation, advice giving, or teaching/learning new skills. [56][57][58] Our findings are also consistent with research indicating that maximizing the opportunity to talk freely is important for users, e.g., through enabling free text input and tailoring the session content or duration of sessions. 58 Repetitive, confusing or inappropriate questions, which highlighted MYLO's lack of understanding, were associated with a loss of faith in the MYLO intervention and were identified as unhelpful.…”

“…[56][57][58] Our findings are also consistent with research indicating that maximizing the opportunity to talk freely is important for users, e.g., through enabling free text input and tailoring the session content or duration of sessions. 58 Repetitive, confusing or inappropriate questions, which highlighted MYLO's lack of understanding, were associated with a loss of faith in the MYLO intervention and were identified as unhelpful. These themes are consistent with studies of other relational agent interventions [56][57][58][59][60][61] and are perhaps not unique to MYLO.…”

“…58 Repetitive, confusing or inappropriate questions, which highlighted MYLO's lack of understanding, were associated with a loss of faith in the MYLO intervention and were identified as unhelpful. These themes are consistent with studies of other relational agent interventions [56][57][58][59][60][61] and are perhaps not unique to MYLO. Furthermore, questions that elicited overwhelming or intense emotions were identified as unhelpful and appeared to be associated with disengagement from MYLO.…”

Improving Mental Health Services: A 50-Year Journey from Randomized Experiments to Artificial Intelligence and Precision Mental Health

“…They suggest that there is a great deal of clinical potential in using AI in this manner. In a review of the literature from 1946 to 2018 on conversational agents used in the treatment of mental health problems, Gaffney et al ( 2019 ) found only 13 qualifying studies out of an initial 30,853 with four being what they called full-scale RCTs. They concluded that the use of conversational agents was limited but growing.…”

Acceptability of an Embodied Conversational Agent for Type 2 Diabetes Self-Management Education and Support via a Smartphone App: Mixed Methods Study

“…Preliminary evidence suggests that ECAs are perceived to be less judgmental, less intimidating, and more likable than a human counterpart, resulting in participants feeling less guilty and more motivated by the interaction [ 13 , 14 , 17 , 18 ]. Collectively, this evidence suggests that ECAs may be effective in providing support for chronic disease management as they help to engage users by building a social and emotional relationship over time [ 9 , 18 , 20 ].…”