AI-Assisted 4-Week Psychodynamic Therapy and Cognitive Behavioral Therapy Via Smartphone for Social Anxiety: A Randomized Pilot Study (STePS-Ai) (STePS-Ai)

April 9, 2026 updated by: Stockholm University

Smartphone-Based Treatments for Social Anxiety With Artificial Intelligence Support: A Three-Arm Randomized Controlled Pilot Study Comparing Psychodynamic Therapy, Cognitive Behavioral Therapy, and Waitlist (STePS-Ai)

This pilot study compares two 4-week, smartphone-based treatments for social anxiety: one uses a psychodynamic therapy approach and the other uses a cognitive behavioral therapy approach. Both treatments are guided by an AI assistant rather than a human therapist. The AI assistant is programmed to support participants in reflecting on core therapeutic principles, much like a well-informed coach would.

Participants are randomly assigned to one of three groups: psychodynamic therapy with AI support, cognitive behavioral therapy with AI support, or a waitlist control. Those in the waitlist group can receive an active treatment after the 4-week waiting period. All participants complete weekly online questionnaires to monitor anxiety and any changes in mood or well-being.

Study Overview

Status

Active, not recruiting

Conditions

Intervention / Treatment

Detailed Description

This study builds upon earlier findings from the STePS project by investigating the feasibility and effectiveness of two brief, smartphone-delivered treatments for social anxiety, delivered entirely through an AI-guided platform. The study is a randomized, controlled pilot trial with three arms. Two intervention groups receive a 4-week treatment via smartphone: one group receives a psychodynamic therapy approach and the other receives a cognitive behavioral therapy approach. In both treatments, the AI assistant prompts reflection and engagement with the therapeutic material instead of a traditional therapist. The third group serves as a waitlist control, with participants given the option to choose one of the active treatments after the study period.

Study Type

Interventional

Enrollment (Estimated)

90

Phase

  • Not Applicable

Contacts and Locations

This section provides the contact details for those conducting the study, and information on where this study is being conducted.

Study Locations

  • Sweden
    • Stockholm County
      • Stockholm, Stockholm County, Sweden, 10691
        • Stockholm University

Participation Criteria

Researchers look for people who fit a certain description, called eligibility criteria. Some examples of these criteria are a person's general health condition or prior treatments.

Eligibility Criteria

Ages Eligible for Study

  • Adult
  • Older Adult

Accepts Healthy Volunteers

No

Description

  • Age 18 years or older
  • Score of 30 or higher on the Liebowitz Social Anxiety Scale-Self Report (LSAS-SR)
  • Access to a smartphone
  • Ability to read and write Swedish
  • Currently engaged in psychological treatment
  • Severe depression (Patient Health Questionnaire-9 score 20 or higher)
  • Use of medication for anxiety or depression if there have been changes within the past 30 days
  • Suicidality as assessed by the Columbia Suicide Severity Rating Scale (C-SSRS)

Study Plan

This section provides details of the study plan, including how the study is designed and what the study is measuring.

How is the study designed?

Design Details

  • Primary Purpose: Treatment
  • Allocation: Randomized
  • Interventional Model: Parallel Assignment
  • Masking: Single

Arms and Interventions

Participant Group / Arm
Intervention / Treatment
Experimental: Smartphone-based psychodynamic therapy with AI support
This arm features a 4-week smartphone-delivered psychodynamic therapy intervention guided by an AI assistant. Participants will access structured treatment modules that emphasize emotional awareness, reduction of avoidance behaviors, and enhancement of affect regulation in social contexts. The AI assistant provides real-time reflection prompts, motivational support, and automated feedback based on the established psychodynamic material, ensuring consistent engagement throughout the treatment period. Weekly assessments monitor symptom changes, with data collected to evaluate the intervention's effectiveness in reducing social anxiety.
Behavioral: Ai chatbot
This intervention uses an AI-enabled chatbot within a smartphone app to deliver psychotherapy modules. The chatbot guides participants through the modules by providing reflective prompts, motivational support and automated reminders to enhance engagement. All communication is encrypted to protect privacy.
Experimental: Smartphone-based cognitive behavior therapy with AI support
This arm features a 4-week smartphone-delivered cognitive behavioral therapy (CBT) intervention guided by an AI assistant. Participants will access structured treatment modules that focus on psychoeducation about anxiety, cognitive restructuring to challenge and modify unhelpful thoughts, behavioral exposure techniques, and behavioral experiments to reduce avoidance. The AI assistant provides real-time reflection prompts, task reminders, motivational support, and automated feedback based on established CBT protocols, ensuring consistent engagement throughout the treatment period. Weekly assessments will monitor symptom changes, with data collected to evaluate the intervention's effectiveness in reducing social anxiety.
Behavioral: Ai chatbot
This intervention uses an AI-enabled chatbot within a smartphone app to deliver psychotherapy modules. The chatbot guides participants through the modules by providing reflective prompts, motivational support and automated reminders to enhance engagement. All communication is encrypted to protect privacy.
No Intervention: Waitlist
This arm involves a waitlist control condition where participants do not receive an active intervention during the 4-week period. Instead, they complete the same weekly assessments used in the active treatment arms to monitor changes in social anxiety symptoms and overall well-being. After the study period, participants will be offered the option to choose one of the active treatment approaches if desired.

What is the study measuring?

Primary Outcome Measures

Outcome Measure
Measure Description
Time Frame
Social Phobia Inventory (SPIN)
Time Frame: Baseline (pre-randomization), weekly during the 4-week intervention, post-treatment at week 4, and 1-month follow-up
The Social Phobia Inventory (SPIN) is a 17-item self-report questionnaire that measures fear, avoidance and physiological symptoms of social anxiety. Each item is rated on a 5-point Likert scale (0 = "not at all" to 4 = "extremely"), yielding a total score range from 0 to 68. Higher scores indicate more severe social anxiety symptoms.
Baseline (pre-randomization), weekly during the 4-week intervention, post-treatment at week 4, and 1-month follow-up

Secondary Outcome Measures

Outcome Measure
Measure Description
Time Frame
Liebowitz Social Anxiety Scale Self-Report (LSAS-SR)
Time Frame: Baseline, 4 weeks, and 1 month
The Liebowitz Social Anxiety Scale Self-Report (LSAS-SR) is a 24-item self-report instrument measuring the severity of social anxiety by assessing fear and avoidance across 24 social and performance situations. Total scores range from 0 to 144, with higher scores indicating greater social anxiety severity. It supplements the primary Social Phobia Inventory (SPIN) measure by providing additional insight into the participants' subjective experience of social anxiety and functional impairment.
Baseline, 4 weeks, and 1 month
Patient Health Questionnaire-9 (PHQ-9)
Time Frame: Baseline, weekly during weeks 1 through 4 (Patient Health Questionnaire-2 short form), 4 weeks (full scale), and 1 month
The Patient Health Questionnaire-9 (PHQ-9) is a 9-item self-report measure assessing depressive symptom severity over the past two weeks. Total scores range from 0 to 27, with higher scores indicating more severe depressive symptoms. A 2-item short form (Patient Health Questionnaire-2) is administered weekly to monitor mood, while the full 9-item version is collected at baseline, 4 weeks, and 1 month. This measure captures any effects of the intervention on depressive symptoms alongside anxiety outcomes.
Baseline, weekly during weeks 1 through 4 (Patient Health Questionnaire-2 short form), 4 weeks (full scale), and 1 month
Generalized Anxiety Disorder-7 (GAD-7)
Time Frame: Baseline, weekly during weeks 1 through 4 (Generalized Anxiety Disorder-2 short form), 4 weeks (full scale), and 1 month
The Generalized Anxiety Disorder-7 (GAD-7) is a 7-item self-report scale assessing the severity of generalized anxiety symptoms over the past two weeks. Total scores range from 0 to 21, with higher scores indicating more severe anxiety. A 2-item short form (Generalized Anxiety Disorder-2) is administered weekly, while the full 7-item version is collected at baseline, 4 weeks, and 1 month. This measure evaluates treatment effects on overall anxiety alongside social anxiety symptoms.
Baseline, weekly during weeks 1 through 4 (Generalized Anxiety Disorder-2 short form), 4 weeks (full scale), and 1 month

Collaborators and Investigators

This is where you will find people and organizations involved with this study.

Sponsor

Stockholm University

Investigators

  • Principal Investigator: Per Carlbring, PhD, Stockholm University

Study record dates

These dates track the progress of study record and summary results submissions to ClinicalTrials.gov. Study records and reported results are reviewed by the National Library of Medicine (NLM) to make sure they meet specific quality control standards before being posted on the public website.

Study Major Dates

Study Start (Actual)

April 21, 2025

Primary Completion (Actual)

June 21, 2025

Study Completion (Estimated)

July 1, 2026

Study Registration Dates

First Submitted

May 13, 2025

First Submitted That Met QC Criteria

April 9, 2026

First Posted (Actual)

April 16, 2026

Study Record Updates

Last Update Posted (Actual)

April 16, 2026

Last Update Submitted That Met QC Criteria

April 9, 2026

Last Verified

April 1, 2026

More Information

Terms related to this study

Keywords

Additional Relevant MeSH Terms

Other Study ID Numbers

  • STePS-Ai

Plan for Individual participant data (IPD)

Plan to Share Individual Participant Data (IPD)?

YES

IPD Plan Description

The individual participant data (IPD) that will be shared (Figshare or OSF) include de-identified, participant-level data from all phases of the study. Specifically, this dataset will contain (limited) demographic information, screening results, baseline assessments, and all primary and secondary outcome measures as well as some treatment engagement data. Data will be stripped of any identifying information and aggregated where appropriate to ensure confidentiality and compliance with data protection regulations.

IPD Sharing Time Frame

Anticipated during 2025.

IPD Sharing Access Criteria

By visiting Figshare or OSF.

IPD Sharing Supporting Information Type

  • ANALYTIC_CODE

Drug and device information, study documents

Studies a U.S. FDA-regulated drug product

No

Studies a U.S. FDA-regulated device product

No

This information was retrieved directly from the website clinicaltrials.gov without any changes. If you have any requests to change, remove or update your study details, please contact register@clinicaltrials.gov. As soon as a change is implemented on clinicaltrials.gov, this will be updated automatically on our website as well.

Clinical Trials on Social Anxiety Disorder (SAD)

Clinical Trials on Ai chatbot

Search Similar Trials

Sponsors and Collaborators

Medical Conditions

Drug Interventions

CROs by country

CROs in Japan

Conditions

Rare Diseases

Drug Interventions

Dietary Supplements

Sponsor/Collaborators

Locations

Subscribe