Study of a PST-Trained Voice-Enabled Artificial Intelligence Counselor (SPEAC) for Adults With Emotional Distress (Phase 1)

NCT04524104 | Completed Results

• 2 other identifiers: 2020-09181R61MH119237-01A1
• Study Type: interventional
• Target: 63
• Locations: 1 country
• Sites: 2

Brief Summary

In the phase 1 of the SPEAC project the specific aims are to: (1) establish the functionality, usability, and treatment fidelity of Lumen using iterative, user-centered design, development, and formative evaluation; and (2) demonstrate feasibility, acceptability, and target engagement in a 2-arm pilot RCT. The aim 1 focuses on developing a voice-enabled, artificial intelligence (AI) virtual agent, named Lumen, trained in Problem Solving Therapy (PST) via an iPad-based application. The development of Lumen will employ iterative user-centered design-evaluation cycles. After the functionality, usability and treatment fidelity of Lumen are established, in the aim 2, we will conduct a 2-arm randomized clinical trial (RCT, Study 1) to pilot test Lumen.

Conditions

Depression; Anxiety

Outcome Measures

Primary Outcomes (4)

• Change in Activation of Left Amygdala From Baseline Functional Magnetic Resonance Scan at 16 Weeks

  Two neural targets defined a priori, specifically activation of the amygdala for nonconscious threat-related emotional reactivity and activation of the DLPFC for cognitive control will be assessed using fMRI. In the facial emotion viewing paradigm, facial expression stimuli are standardized black and white photographs of 8 identities (4 female, 4 male) with evoked expressions of threat-related emotions (fear, anger), sad-related emotions (sadness) and reward-related emotions (happiness), along with neutral. To assess amygdala activation for the negative affect circuit, our analysis focused on threatening faces only. Threat stimuli included a combination of fear and anger stimuli relative to neutral blocks. For the Go-NoGo paradigm, the 'Go' and 'NoGo' stimuli are presented for 500 ms each with an inter-stimulus interval of 750 ms. Higher score indicates higher activation of the amygdala and DLPFC.

  Baseline, 16 weeks

• Change in Activation of Right Amygdala From Baseline Functional Magnetic Resonance Scan at 16 Weeks

  Two neural targets defined a priori, specifically activation of the amygdala for nonconscious threat-related emotional reactivity and activation of the DLPFC for cognitive control will be assessed using fMRI. In the facial emotion viewing paradigm, facial expression stimuli are standardized black and white photographs of 8 identities (4 female, 4 male) with evoked expressions of threat-related emotions (fear, anger), sad-related emotions (sadness) and reward-related emotions (happiness), along with neutral. To assess amygdala activation for the negative affect circuit, our analysis focused on threatening faces only. Threat stimuli included a combination of fear and anger stimuli relative to neutral blocks. For the Go-NoGo paradigm, the 'Go' and 'NoGo' stimuli are presented for 500 ms each with an inter-stimulus interval of 750 ms. Higher score indicates higher activation of the amygdala and DLPFC.

  Baseline, 16 weeks

• Change in Activation of Left dlPFC From Baseline Functional Magnetic Resonance Scan at 16 Weeks

  Two neural targets defined a priori, specifically activation of the amygdala for nonconscious threat-related emotional reactivity and activation of the DLPFC for cognitive control will be assessed using fMRI. In the facial emotion viewing paradigm, facial expression stimuli are standardized black and white photographs of 8 identities (4 female, 4 male) with evoked expressions of threat-related emotions (fear, anger), sad-related emotions (sadness) and reward-related emotions (happiness), along with neutral. To assess amygdala activation for the negative affect circuit, our analysis focused on threatening faces only. Threat stimuli included a combination of fear and anger stimuli relative to neutral blocks. For the Go-NoGo paradigm, the 'Go' and 'NoGo' stimuli are presented for 500 ms each with an inter-stimulus interval of 750 ms. Higher score indicates higher activation of the amygdala and DLPFC.

  Baseline, 16 weeks

• Change in Activation of Right dlPFC From Baseline Functional Magnetic Resonance Scan at 16 Weeks

  Two neural targets defined a priori, specifically activation of the amygdala for nonconscious threat-related emotional reactivity and activation of the DLPFC for cognitive control will be assessed using fMRI. In the facial emotion viewing paradigm, facial expression stimuli are standardized black and white photographs of 8 identities (4 female, 4 male) with evoked expressions of threat-related emotions (fear, anger), sad-related emotions (sadness) and reward-related emotions (happiness), along with neutral. To assess amygdala activation for the negative affect circuit, our analysis focused on threatening faces only. Threat stimuli included a combination of fear and anger stimuli relative to neutral blocks. For the Go-NoGo paradigm, the 'Go' and 'NoGo' stimuli are presented for 500 ms each with an inter-stimulus interval of 750 ms. Higher score indicates higher activation of the amygdala and DLPFC.

  Baseline, 16 weeks

Secondary Outcomes (24)

• Change From Baseline Hospital Anxiety and Depression Scale (HADS) Depression Score at 16 Weeks

  Baseline, 16 weeks

• Change From Baseline Hospital Anxiety and Depression Scale (HADS) Anxiety Score at 16 Weeks

  Baseline, 16 weeks

• Change From Baseline Hospital Anxiety and Depression Scale (HADS) Total Score at 16 Weeks

  Baseline, 16 weeks

• Change From Baseline Social Problem-Solving Inventory-Revised: Short Form (SPSI-R:S) at 16 Weeks

  Baseline, 16 weeks

• Change From Baseline Dysfunctional Attitudes Scale (DAS) at 16 Weeks

  Baseline, 16 weeks

Study Arms (2)

Lumen treatment

EXPERIMENTAL

Participants will complete functional magnetic resonance imaging (fMRI) and self-report questionnaires at baseline and 16 weeks. Participant will receive an encrypted study iPad enabled with Lumen at baseline. They will complete 8 PST sessions beginning with 4 weekly and then 4 biweekly intervals (i.e., on weeks 1, 2, 3, 4, 6, 8, 10, 12) over 12 weeks on their assigned iPad. Participants will also complete naturalistic end-of-day assessments for 7 days every 2 weeks (on weeks 0, 2, 4, 6, 8, 10, 12, 16), that is, 8 time series. Additionally, participants will complete depressive and anxiety symptoms questionnaire and user experience surveys at all PST sessions.

Behavioral: Lumen Treatment

Waitlist Control

NO INTERVENTION

Participants will complete functional magnetic resonance imaging (fMRI) and self-report questionnaires at Baseline and 16 weeks. Participant will receive an encrypted study iPad at baseline. Participants will complete naturalistic end-of-day assessments for 7 days every 2 weeks (on weeks 0, 2, 4, 6, 8, 10, 12, 16), that is, 8 time series. Participants in the waitlist control arm will only complete assessments but will have the option to receive Lumen at the end of the study. The PST module on the study iPad will be disabled until their 16-week assessment is completed, at which time they will have the option to complete 8 PST sessions on their assigned iPads.

Interventions

Lumen Treatment BEHAVIORAL

the virtual AI agent, Lumen, via an iPad-based application. Each participant will receive a locked, encrypted study iPad installed with Lumen. They will complete 8 problem solving therapy (PST) sessions beginning with 4 weekly and then 4 biweekly intervals over 12 weeks on their assigned iPad.

Lumen treatment

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• years of age or older at study enrollment
• Emotional distress defined by elevated depressive (PHQ9 scores 10-19) and/or anxious symptoms (GAD7 scores 10-14)
• Willing and able to provide written informed consent and HIPAA authorization

You may not qualify if:

• Unable to speak, read, understand English for informed consent (grade 6 level)
• Current pharmacotherapy or psychotherapy (individual or professionally-led group therapy) for depression or anxiety
• Suicidal ideation per PHQ9 with active plan
• Bipolar or psychotic disorder, or current psychiatric treatment
• Weight ≥350 pounds due to brain scanner constraints, MRI contraindications, traumatic brain injuries, and tumor or any other known structural abnormality in the brain
• Severe medical condition (e.g., myocardial infarction or stroke or new cancer diagnosis in the past 6 months, end-stage organ failure, terminal illness) or residence in a long-term care facility
• Diagnosis of cancer (other than non-melanoma skin cancer) that is/was active or treated with radiation or chemotherapy within the past year
• Active alcohol or substance use disorder (including prescription drugs) based on the CAGE Questionnaire Adapted to Include Drugs (CAGE-AID)
• Cognitive impairment based on the Callahan 6-item screener
• Current or planned pregnancy or lactating (\<6 months postpartum)
• Family/household member of an already enrolled participant or of a study team member
• Plan to move out of the Chicagoland area during the study period
• Investigator discretion for clinical safety or protocol adherence reasons

Sponsors & Collaborators

• University of Illinois at Chicago: lead
• Penn State University: collaborator
• Washington University School of Medicine: collaborator
• Stanford University: collaborator
• National Institute of Mental Health (NIMH): collaborator

Study Sites (2)

Department of Medicine, Vitoux Program on Aging and Prevention

Chicago, Illinois, 60608, United States

Location

UIMC Advanced Imaging Center

Chicago, Illinois, 60612, United States

Location

Related Publications (1)

• Lv N, Kannampallil T, Xiao L, Ronneberg CR, Kumar V, Wittels NE, Ajilore OA, Smyth JM, Ma J. Association Between User Interaction and Treatment Response of a Voice-Based Coach for Treating Depression and Anxiety: Secondary Analysis of a Pilot Randomized Controlled Trial. JMIR Hum Factors. 2023 Nov 6;10:e49715. doi: 10.2196/49715.

  PMID: 37930781 DERIVED

MeSH Terms

Conditions

Depression; Anxiety Disorders

Condition Hierarchy (Ancestors)

Behavioral Symptoms; Behavior; Mental Disorders

Results Point of Contact

• Title: Nan Lv, PhD, Research Scientist
• Organization: Univeristy of Illinois, Chicago

lvn2017@uic.edu

312-802-1072

Study Officials

• Jun Ma, MD, PhD

  University of Illinois at Chicago

  PRINCIPAL INVESTIGATOR

Publication Agreements

• PI is Sponsor Employee: No
• Restrictive Agreement: No

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: DOUBLE
• Who Masked: INVESTIGATOR, OUTCOMES ASSESSOR
• Purpose: TREATMENT
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: MD, PhD, Beth and George Vitoux Professor of Medicine

Study Record Dates

• First Submitted: August 14, 2020
• First Posted: August 24, 2020
• Study Start: April 5, 2021
• Primary Completion: February 8, 2022
• Study Completion: March 5, 2022
• Last Updated: July 9, 2024
• Results First Posted: June 28, 2023

Record last verified: 2024-07

Locations

US (2)