Personalized AI-Driven Models in Cognitive Behavioral Therapy for Anxiety

SCH: Personalized AI-Driven Models for Supporting User Engagement and Adherence in Health Interventions: Validation in Cognitive Behavioral Therapy for Anxiety

Untreated anxiety undermines long-term physical and emotional wellbeing, especially among college students, with rates worsening since the onset of the COVID-19 pandemic. Cognitive Behavioral Therapy (CBT) is the leading evidence-based intervention for anxiety, but many students fail to complete exercises between CBT sessions, reducing its effectiveness. Socially assistive robots (SARs) help promote adherence to home-based practice in the context of elder care, social skill learning, and physical therapy, but it is unknown how SARs can enhance CBT. The specific objective of this research is to develop personalized CBT SARs that can support CBT compliance for college students with anxiety. To meet the goals of the proposed work, these studies will determine how SAR personalization based on implicit and explicit feedback can help promote greater CBT compliance and anxiety reduction outcomes for students.

Study Overview

• Status: Recruiting
• Conditions: Generalized Anxiety Disorder (GAD)
• Intervention / Treatment: Behavioral: Control CBT SAR for 6 weeks; Behavioral: Explicit CBT SAR Personalization for 6 weeks; Behavioral: Implicit CBT SAR Personalization for 6 weeks

Detailed Description

The investigators will conduct a Phase 1 parallel intervention study with random assignment. The investigators will randomly assign consented college students reporting anxiety symptoms to one of two 6-week Cognitive Behavioral Therapy (CBT) exercise conditions that were validated in our preliminary studies. The participant will be randomly assigned to a condition (personalized versus not personalized socially assistive robot (SAR) CBT) and will be informed of their condition by the investigators when the participant is ready to start their home practice with the SAR CBT companion. During the initial baseline in-home visit, participants will be provided with a SAR and instructions for how to complete their SAR CBT exercises daily for 6 weeks. During the 6-week home-based study period that follows the baseline visit, the participant will be reminded daily to complete a CBT exercise with their SAR. The investigators will be the point of contact via phone or email for all participants who need assistance (e.g., with SAR/software issues).

The investigators will evaluate personalized re-engagement strategies derived from implicit feedback from individuals with clinically elevated anxiety. This will be done through an in-home between-subjects user study involving 60 student participants who will be randomly assigned to either a control condition without re-engagement feedback or a personalized feedback condition with personalized re-engagement feedback. Quantitative behavioral and subjective metrics will be compared between the conditions to assess the impact of personalized feedback on feelings of relatedness with the robot, intrinsic motivation, engagement, and adherence, guided by self-determination theory. The study aims to determine whether personalized re-engagement feedback enhances the intrinsic motivation, engagement, and adherence when using the SAR companion to deliver CBT concepts to individuals with clinically elevated anxiety.

The second aim is to evaluate the personalization of robot attributes based on explicit user feedback in individuals with clinically elevated anxiety. This will be done through an in-home between-subjects user study where 60 participants are randomly assigned to either a control condition without the capability to personalize the robot's attributes or a personalization condition where the participant can modify the robot's attributes at the start of the study and between CBT sessions. This study aims to determine whether granting users the ability to choose the robot's attributes will lead to higher levels of intrinsic motivation, engagement, and adherence during interaction with the SAR companion.

• Study Type: Interventional
• Enrollment (Estimated): 140
• Phase: Not Applicable

Contacts and Locations

Study Locations

• United States
  • California
    • Los Angeles, California, United States, 90089
      • Recruiting
      • University of Southern California
      • Contact: Lydia Ignatova; Phone Number: 714-855-7076; Email: lignatov@usc.edu
      • Contact: Emily Weiss; Phone Number: 402-237-2492; Email: emilymwe@usc.edu
      • Principal Investigator: Maja Matarić, PhD

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

Description

Inclusion Criteria:

• Are 18 years of age or older
• Are university students
• Are able to communicate in English
• Have corrected-to-normal vision and hearing
• Consent to have audio/video/interaction data recorded as part of the study
• Have a GAD-7 (Generalized Anxiety Disorder-7 item) score of 5 or greater, indicating mild to elevated levels of self-reported symptoms of anxiety
• Have a lower than minimal level of suicidality risk as measured by the Columbia Suicide Severity Rating Scale (C-SSRS) during screening ("NO" responses to items 3, 4, 5, and 6 on C-SSRS)
• Having access to home WiFi

Exclusion Criteria:

• Are less than 18 years of age
• Are not university students
• Are not able to communicate in English
• Do not have corrected-to-normal vision and hearing
• Do not consent to have audio/video/interaction data recorded as part of the study
• Have a GAD-7 (Generalized Anxiety Disorder-7 item) score of 4 or lower.
• Higher than a minimal level of suicidality risk as measured by the Columbia Suicide Severity Rating Scale (C-SSRS) during screening ("YES" responses to items 3, 4, 5, or 6 on C-SSRS)
• Don't have access to home WiFi

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Basic Science
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: None (Open Label)

Number of Arms

3

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: Explicit CBT SAR Personalization for 6 weeks; College student participants with clinically elevated anxiety will engage in 6 weeks of in-home CBT daily exercises with an explicitly personalized CBT SAR in the participants' homes. Each participant will receive personalized re-engagement feedback delivered by the SAR will be based on explicit user feedback regarding the participant's subjective preferences related to the robot attributes and engagement features.	Behavioral: Explicit CBT SAR Personalization for 6 weeks; College student participants with clinically elevated anxiety will engage in 6 weeks of in-home CBT daily exercises with an explicitly personalized CBT SAR in the participants' homes. Participants will receive personalized re-engagement feedback delivered by the SAR will be based on explicit user feedback regarding their subjective preferences related to the robot attributes and engagement features.
Experimental: Implicit CBT SAR Personalization for 6 weeks; College student participants with clinically elevated anxiety will engage in 6 weeks of in-home CBI daily exercises with an implicitly personalized CBT SAR in the participants' homes. The personalized re-engagement feedback provided by the SAR will be based on machine learning methods applied to implicit visual and auditory cues.	Behavioral: Implicit CBT SAR Personalization for 6 weeks; College student participants with clinically elevated anxiety will engage in 6 weeks of in-home CBI daily exercises with an implicitly personalized CBT SAR in the participants' homes. The personalized re-engagement feedback provided by the SAR will be based on machine learning methods applied to implicit visual and auditory cues.
Placebo Comparator: Control CBT SAR for 6 weeks; College student participants with clinically elevated anxiety will engage in 6 weeks of in-home CBT daily exercises with a non-personalized CBT SAR in the participants' homes. Participants will not have the capability to personalize the robot's attributes, and this condition will be a control baseline comparison group for the personalized intervention conditions described above.	Behavioral: Control CBT SAR for 6 weeks; College student participants with clinically elevated anxiety will engage in 6 weeks of in-home CBT daily exercises with a non-personalized CBT SAR. Participants will not have the capability to personalize the robot's attributes, and this condition will be a control baseline comparison group for the personalized intervention conditions described above.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Number of user-spoken words during interactions with SAR	Using transcriptions of the interactions, the investigators will count the number of words uttered by the participant.	During each session, through study completion, approximately 6 weeks.
Overall length of interaction sessions	Using the interaction data from the robot interface, the investigators will collect the time that the participant started the interaction with the robot and the time that the interaction ended.	Through the duration of the study, approximately 6 weeks.
Number of days participants complete CBT exercises (adherence)	Using the interaction data from the robot interface, the investigators will collect the number of days that the participant interacts with the system at least once during the day	Through study completion, approximately 6 weeks.
Outcomes Questionnaire-45.2	The total reported symptom distress value from the symptom distress subscale. Question scale (0-4). A higher total score indicates higher distress overall, and higher scores for question subsets indicate worse outcomes for symptom distress, interpersonal relations, and social role.	Once in weeks 1, 3, 6 of the study.
Modified Working Alliance Inventory-Short Revised	Repeated daily measure for assessing the quality of the relationship with the SAR companion. Question scale (1-5). Higher scores indicate stronger alliance.	Once in weeks 2, 4, 6 of study.
Sustem Usability Scale	The total reported usability score for evaluating participant perception of SAR companion's usability. Question responses scale from strongly agree to strongly disagree. Responses should not indicate trends in participant outcomes, but should instead help the investigators understand participants' perception of the system.	Once on Week 2 Day 4 and Week 6 Day 4.
Semi-structured interview	Focus group interviews with the investigators and participants will be used to process for collecting qualitative feedback and insights. The investigators will use this data to perform thematic analysis of participant responses while using the system.	One interview for 30 minutes - 120 minutes at the end of the 6 week study.

Other Outcome Measures

Outcome Measure	Measure Description	Time Frame
GAD-7 Questionnaire	Screening measure for identifying students with elevated levels of anxiety. Question scale (0-3). A higher total score indicates higher levels of anxiety.	Once in weeks 2, 4, 6 of the study.

Collaborators and Investigators

• Sponsor: University of Southern California
• Collaborators: National Institute of Mental Health (NIMH)

Study record dates

Study Major Dates

• Study Start (Actual): March 30, 2026
• Primary Completion (Estimated): August 1, 2028
• Study Completion (Estimated): August 1, 2028

Study Registration Dates

• First Submitted: February 18, 2026
• First Submitted That Met QC Criteria: February 18, 2026
• First Posted (Actual): February 24, 2026

Study Record Updates

• Last Update Posted (Actual): May 4, 2026
• Last Update Submitted That Met QC Criteria: April 28, 2026
• Last Verified: February 1, 2026

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Mental Disorders; Anxiety Disorders; Generalized Anxiety Disorder
• Other Study ID Numbers: R01MH139134-At-Home; R01MH139134 (U.S. NIH Grant/Contract)

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No