A Persian AI-Based CBT Chatbot and Voice Analysis System for Managing Perceived Stress

NCT07840469 | Not Yet Recruiting

• 1 other identifier: IR.ARI.MUI.REC.1405.161
• Study Type: interventional
• Target: 120
• Locations: 1 country
• Sites: 1

Brief Summary

This pilot randomized controlled trial aims to evaluate a Persian-language artificial intelligence (AI)-based cognitive behavioral therapy (CBT) chatbot designed to support adults in managing perceived stress. A total of 120 adults will be randomly assigned to one of three groups: an AI-based CBT chatbot intervention, active mental health educational content, or a waitlist control. The intervention period will last 14 days. The study will evaluate the feasibility, acceptability, safety, and preliminary effectiveness of the AI-based CBT chatbot for perceived stress management. As a separate research component, voice recordings will be collected from participants at baseline and at the end of the study. These recordings will be used solely as research data to train and evaluate an artificial intelligence model for stress detection. The voice-based model will not be used to guide, modify, personalize, or influence the study intervention, chatbot responses, participant allocation, or clinical decision-making during this trial.

Conditions

Psychological Stress; Perceived Stress

Keywords

Stress Management; Large Language Model; AI Chatbot; Digital Mental Health

Outcome Measures

Primary Outcomes (1)

• Change in Perceived Stress Scale-10 (PSS-10) Score

  Change in total Perceived Stress Scale-10 (PSS-10) score from baseline to Day 14. The PSS-10 is used to assess perceived stress, with higher scores indicating greater perceived stress. Changes in PSS-10 scores will be compared across the three study groups.

  Baseline and Day 14

Secondary Outcomes (2)

• Change in DASS-21 Stress Subscale Score

  Baseline and Day 14

• Number of Completed Intervention Sessions

  Throughout the 14-day intervention period

Study Arms (3)

AI-Based CBT Chatbot

EXPERIMENTAL

Participants assigned to this arm will receive an interactive Persian-language AI-based CBT chatbot intervention during the 14-day study period. The chatbot will provide structured CBT-based exercises and conversational support for stress management. The intervention will include psychoeducation, cognitive restructuring, coping strategies, behavioral techniques, and stress-management exercises. The chatbot will operate within predefined safety guardrails and crisis-management procedures.

Behavioral: Persian AI-Based CBT Chatbot

Active Mental Health Content

ACTIVE COMPARATOR

Participants assigned to this arm will receive structured, non-interactive mental health and stress-management content during the study period. The content will include psychoeducational material and general stress-management techniques but will not include adaptive or personalized conversational interaction with the AI-based CBT chatbot. The active comparator is intended to control for nonspecific intervention effects, including attention, expectancy, and exposure to mental health-related content. This is important because perceived stress may decrease simply as a result of receiving structured support and study-related attention. Including this arm allows the study to better distinguish the specific effects of the interactive AI-based CBT chatbot from improvements attributable to general attention and psychoeducational exposure.

Behavioral: Active Mental Health Content

Waitlist Control

NO INTERVENTION

Participants assigned to this arm will not receive an active psychological intervention during the 14-day study period. They will complete the scheduled study assessments and will remain subject to the study safety and referral procedures.

Interventions

Persian AI-Based CBT Chatbot BEHAVIORAL

A Persian-language artificial intelligence-based conversational intervention designed to provide structured support based on cognitive behavioral therapy principles for adults with mild to moderate perceived stress. The chatbot delivers interactive CBT-based exercises, including psychoeducation, identification and restructuring of maladaptive thoughts, coping strategies, behavioral techniques, and stress-management exercises. The intervention is delivered during a 14-day period and incorporates predefined safety guardrails and crisis-management procedures.

Also known as: AI-CBT Chatbot

AI-Based CBT Chatbot

Active Mental Health Content BEHAVIORAL

Structured, non-adaptive mental health and stress-management educational content provided during the study period. The content is designed to provide general psychoeducation and stress-management support without personalized AI-generated dialogue or adaptive CBT interaction.

Active Mental Health Content

Eligibility Criteria

• Age: 18 Years - 45 Years
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64)

You may qualify if:

• Age between 18 and 45 years
• Mild or moderate perceived stress based on the Perceived Stress Scale-10 (PSS-10) screening assessment
• Ability to use a smartphone
• Access to the internet during the study period
• Ability and willingness to provide electronic informed consent
• Willingness to participate in study assessments and complete the required study procedures

You may not qualify if:

• Severe perceived stress at the initial screening assessment
• Active suicidal ideation or risk of self-harm
• Acute psychological crisis requiring immediate professional intervention
• Active psychosis
• Active mania
• Severe substance use disorder
• Psychiatric hospitalization in recent months
• Initiation of a new psychiatric medication or change in the dose of a psychiatric medication within the previous four weeks
• Concurrent participation in intensive psychotherapy or another intensive psychological intervention
• Any mental health condition requiring immediate specialist evaluation or treatment

Sponsors & Collaborators

• University of Isfahan: collaborator
• Hamid Reza Marateb: lead
• Isfahan University of Medical Sciences: collaborator

Study Sites (1)

Isfahan University of Medical Sciences

Isfahan, Isfahan, Iran

Location

Related Publications (3)

• Naslund JA, Aschbrenner KA, Araya R, Marsch LA, Unutzer J, Patel V, Bartels SJ. Digital technology for treating and preventing mental disorders in low-income and middle-income countries: a narrative review of the literature. Lancet Psychiatry. 2017 Jun;4(6):486-500. doi: 10.1016/S2215-0366(17)30096-2. Epub 2017 Apr 19.

  PMID: 28433615 RESULT

• Schneiderman N, Ironson G, Siegel SD. Stress and health: psychological, behavioral, and biological determinants. Annu Rev Clin Psychol. 2005;1:607-28. doi: 10.1146/annurev.clinpsy.1.102803.144141.

  PMID: 17716101 RESULT

• Torous J, Bucci S, Bell IH, Kessing LV, Faurholt-Jepsen M, Whelan P, Carvalho AF, Keshavan M, Linardon J, Firth J. The growing field of digital psychiatry: current evidence and the future of apps, social media, chatbots, and virtual reality. World Psychiatry. 2021 Oct;20(3):318-335. doi: 10.1002/wps.20883.

  PMID: 34505369 RESULT

MeSH Terms

Conditions

Stress, Psychological

Condition Hierarchy (Ancestors)

Behavioral Symptoms; Behavior

Study Officials

• Mohammad Reza Sharbafchizadeh

  Behavioural Sciences Research Center & Department of Psychiatry, Khorshid Hospital, Isfahan University of Medical Sciences, Isfahan, Iran

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Hamid Reza Marateb, PhD

CONTACT

+98 913 318 8782; h.marateb@eng.ui.ac.ir

Ali Nadi, Bachelor

CONTACT

+989135674166; alinadi.med.ai@gmail.com

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: SINGLE
• Who Masked: OUTCOMES ASSESSOR
• Masking Details: articipants cannot be blinded because of the nature of the chatbot and active-content interventions. Investigators involved in intervention delivery may also be aware of group assignment
• Purpose: SUPPORTIVE CARE
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: SPONSOR INVESTIGATOR
• PI Title: Associate Professor of Biomedical engineering, University of Isfahan

Model Details: Participants will be randomly assigned in a 1:1:1 ratio to one of three parallel study groups: an AI-based CBT chatbot intervention, an active mental health content condition, or a waitlist control condition. Participants will remain in their assigned group throughout the 14-day study period and will not cross over between study conditions.

Study Record Dates

• First Submitted: September 18, 2026
• First Posted: September 25, 2026
• Study Start (Estimated): October 5, 2026
• Primary Completion (Estimated): February 1, 2027
• Study Completion (Estimated): February 1, 2027
• Last Updated: September 25, 2026

Record last verified: 2026-09

Data Sharing

• IPD Sharing: Will share

Locations

IR (1)