Using Socratic Questioning to promote cognitive change and achieve depressive symptom reduction: Evidence of cognitive change as a mediator

Vittorio, Lisa; Murphy, Samuel T.; Braun, Justin D.; Strunk, Daniel R.

doi:10.1016/j.brat.2022.104035

Cited by 14 publications

(9 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…7,8 Building on recent advances relating to LLMs, our goal was to create and examine the feasibility of a generative AI tool that can complement traditional cognitive behavioral therapies (CBTs) by facilitating a core therapeutic intervention: Socratic dialogue. 9,10 Given current limitations of LLMs, 7 our tool "Socrates 2.0" was designed to ultimately be used in conjunction with a licensed clinician to make CBTs' out-of-session practice of evaluating one's thoughts more engaging compared to traditional worksheets. In this manuscript, we first describe our process of designing and completing initial testing of Socrates 2.0, a multi-agent tool built using LLMs.…”

Section: Methodmentioning

confidence: 99%

Mixed Method Feasibility Study Protocol for Socrates 2.0: A Novel Cognitive Behavioral Therapy-Based Generative AI Tool to Facilitate Socratic Dialogue (Preprint)

Held,

Pridgen,

Chen

et al. 2024

Preprint

View full text Add to dashboard Cite

BACKGROUND Digital mental health tools designed to augment traditional mental health treatments are becoming increasingly important due to a wide range of barriers to access, including a growing shortage of clinicians. Most existing tools use rule-based algorithms, often leading to unnatural-feeling interactions compared to human therapists. Large language models (LLMs) offer a solution for the development of more natural, engaging digital tools. In this manuscript, we detail the development of Socrates 2.0, which was designed to engage users in Socratic dialogue surrounding unrealistic or unhelpful beliefs, a core technique in cognitive behavioral therapies (CBTs). The multi-agent LLM-based tool features an AI therapist, 'Socrates', which receives automated feedback from an AI supervisor and an AI rater. The combination of multiple agents appeared to help address common LLM issues like looping and improved the overall dialogue experience. Initial user feedback from individuals with lived experiences of mental health problems as well as cognitive behavioral therapists has been positive. Moreover, tests in ~500 scenarios showed that Socrates 2.0 engaged in harmful responses in under 1% of cases, with the AI supervisor promptly correcting the dialogue each time. However, formal feasibility studies with potential end users are needed. OBJECTIVE This manuscript details a mixed method feasibility study of Socrates 2.0. METHODS Based on the initial data we devised a formal feasibility study of Socrates 2.0 to gather qualitative and quantitative data about users’ and clinicians’ experience of interacting with the tool. Using a mixed method approach, the goal is to gather feasibility and acceptability data from both 100 users and 50 clinicians to inform the eventual implementation of generative AI tools like Socrates 2.0 in mental health treatment. We designed this study to better understand how users and clinicians interact with the tool including the frequency, length and time of interactions, users’ satisfactions with the tool overall, as well as the quality of each dialogue and even individual responses, as well as ways in which the tool should be improved before it is used in efficacy trials. Descriptive and inferential analyses will be performed on data from validated usability measures. Thematic analysis will be performed on the qualitative data. RESULTS Recruitment will begin in February 2024 and is expected to conclude by February 2025. CONCLUSIONS The development of Socrates 2.0 and outlined feasibility study are important first steps in applying generative AI to mental health treatment delivery and lays the foundation for formal feasibility studies. CLINICALTRIAL N/A

show abstract

Section: Methodmentioning

confidence: 99%

Mixed Method Feasibility Study Protocol for Socrates 2.0: A Novel Cognitive Behavioral Therapy-Based Generative AI Tool to Facilitate Socratic Dialogue (Preprint)

Held,

Pridgen,

Chen

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Once patients learn to reliably identify their hot thoughts, the process of testing them with evidence (or putting them on trial) begins. Socratic questioning is a defining characteristic of cognitive therapy (J. S. DeRubeis et al, 2019) and is particularly critical at this stage of therapy (see Vittorio et al, 2022). Socratic questioning involves a series of related questions designed to help patients reach a more logical, objective conclusion about their inner experiences.…”

Section: Techniques To Work With Automatic Thoughtsmentioning

confidence: 99%

Negative thinking: Cognitive products and schema structures.

Dozois¹,

Beck²

2023

Treatment of Psychosocial Risk Factors in Depression.

View full text Add to dashboard Cite

The cognitive model of depression contends that maladaptive thinking and negative appraisals of life circumstances serve as important risk factors and that shifting cognition to be more evidence-based effectively disrupts the depressive process (Dozois et al., 2019). Most contemporary cognitive vulnerability models of depression have involved refinements and expansions of this basic conceptual framework (e.g.,

show abstract

“…To that end, there is a psychoeducational component on what “thoughts” are, how to recognise them and the effects they might have on us, covering the basics of the cognitive model developed by Aaron T. Beck [ 38 ]. The last part of the session will focus on Socratic questioning [ 39 ]. Session 5—The final session is aimed at revising any content of the previous sessions that was not clear to the family and providing a referral if necessary (e.g.…”

Section: Interventionsmentioning

confidence: 99%

Section: Interventionsmentioning

confidence: 99%

Brief internet-delivered cognitive-behavioural intervention for children and adolescents with symptoms of anxiety and depression during the COVID-19 pandemic: a randomised controlled trial protocol

Casella

Zuccolo

Sugaya

et al. 2022

Trials

View full text Add to dashboard Cite

Background The COVID-19 pandemic has had major impacts in many different spheres, including mental health. Children and adolescents are especially vulnerable because their central nervous system is still in development and they have fewer coping resources than do adults. Increases in the prevalence of depressive and anxiety symptomatology have been reported worldwide. However, access to mental health care is limited, especially for the paediatric population and in low- and middle-income countries. Therefore, we developed a brief internet-delivered cognitive-behavioural intervention for children and adolescents with symptoms of anxiety and depression. The aim of this proposed study is to test the efficacy of the intervention. Methods We will conduct a two-arm, parallel randomised controlled trial involving children and adolescents (8–11 and 12–17 years of age, respectively) with symptoms of anxiety, depression or both, according to the 25-item Revised Child Anxiety and Depression Scale (t-score > 70). A total of 280 participants will be randomised to the intervention group or the active control group, in a 1:1 ratio. Those in the intervention group will receive five weekly sessions of cognitive-behavioural therapy via teleconference. The sessions will focus on stress responses, family communication, diaphragmatic breathing, emotions, anger management, behavioural activation and cognitive restructuring. Participants in both groups will have access to 15 videos covering the same topics. Participant-guardian pairs will be expected to attend the sessions (intervention group), watch the videos (control group) or both (intervention group only). A blinded assessor will collect data on symptoms of anxiety, depression and irritability, at baseline, at the end of the intervention and 30 days thereafter. Adolescents with access to a smartphone will also be invited to participate in an ecological momentary assessment of emotional problems in the week before and the week after the intervention, as well as in passive data collection from existing smartphone sensors throughout the study. Discussion Internet-delivered interventions play a major role in increasing access to mental health care. A brief, manualised, internet-delivered intervention might help children and adolescents with anxiety or depressive symptomatology, even outside the context of the COVID-19 pandemic. Trial registration ClinicalTrials.gov NCT05139433. Registered prospectively in November 2021. Minor amendments made in July 2022.

show abstract

Using Socratic Questioning to promote cognitive change and achieve depressive symptom reduction: Evidence of cognitive change as a mediator

Cited by 14 publications

References 36 publications

Mixed Method Feasibility Study Protocol for Socrates 2.0: A Novel Cognitive Behavioral Therapy-Based Generative AI Tool to Facilitate Socratic Dialogue (Preprint)

Mixed Method Feasibility Study Protocol for Socrates 2.0: A Novel Cognitive Behavioral Therapy-Based Generative AI Tool to Facilitate Socratic Dialogue (Preprint)

Negative thinking: Cognitive products and schema structures.

Brief internet-delivered cognitive-behavioural intervention for children and adolescents with symptoms of anxiety and depression during the COVID-19 pandemic: a randomised controlled trial protocol

Contact Info

Product

Resources

About