AI-CONECT: A Conversational AI for Early Dementia Prevention in Socially-Isolated Older Adults

NCT07701668 | Not Yet Recruiting

• 1 other identifier: 2026P000461
• Study Type: interventional
• Target: 80
• Locations: 1 country
• Sites: 1

Brief Summary

This randomized controlled trial examines the mechanisms of conversational AI-based interventions for early dementia prevention in socially isolated older adults.

Conditions

Mild Cognitive Impairment (MCI); Social Isolation

Keywords

Social Isolation; Artificial Intelligence; AI-Chatbot; I-CONECT; Mild Cognitive Impairment (MCI)

Outcome Measures

Primary Outcomes (2)

• Social Self-Efficacy

  Participants' self-efficacy on social interactions using an instrument adapted from the Exercise Self-Efficacy Scale (EXSE, by McAuley, 1993). The scale comprises three items of confidence: interacting with others regularly, engaging with others when feeling less connected, and engaging others in conversations. The three items are adapted to social interaction in person and using technology (e.g., video calls), respectively. Each item is rated from 0 (not at all confident) to 10 (completely confident). A mean score is computed across the six items (range 0-10), with higher scores indicating greater social self-efficacy.

  From enrollment to the end of intervention at 8 weeks

• Time contacting friends or family

  Change in weekly time contacting friends or family.

  From enrollment to the end of the intervention at 8 weeks, using weekly data

Secondary Outcomes (2)

• Time out of home

  From enrollment to the end of treatment at 8 weeks

• Frequency of contacting friends

  From enrollment to the end of treatment at 8 weeks

Other Outcomes (2)

• Exploratory outcome: Social isolation score

  From baseline to week 8

• Exploratory outcome: Changes in the 3-item UCLA Loneliness Scale (UCLA-3)

  From baseline to week 8

Study Arms (2)

AI-CONECT

EXPERIMENTAL

Participants will receive four 15- to 30-minute conversations per week with the AI agent and a weekly 10- to15-minute survey call with a human interviewer.

Behavioral: AI-based conversational intervention

Control

NO INTERVENTION

Participants will receive a weekly 10- to 15-minute survey call with a human interviewer.

Interventions

AI-based conversational intervention BEHAVIORAL

AI-based one-on-one semi-structured conversation for cognitive stimulation

AI-CONECT

Eligibility Criteria

• Age: 75 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Older Adult (65+)

You may qualify if:

• Aged 75+
• Clinical diagnosis of MCI (any subtype) or, when a clinical diagnosis is unavailable, a Telephone-MoCA (T-MoCA) score of 15-17.
• Identified as socially isolated, defined as meeting both of the following self-reported criteria: (a) lives alone in one's own residence, and (b) engages in conversations lasting 30 minutes or longer no more than twice per week.
• GDS-15 (15-item Geriatric Depression Scale) at/below 9 (not severely depressed).
• Social self-efficacy mean ≤ 8 (on the 0-10 scale) across the 6-item Social Self-Efficacy Scale at screening, indicating low confidence in social interaction.
• Ability to understand the research consent form.
• Ability to connect a tablet to the Internet.

You may not qualify if:

• Diagnosed with dementia such as AD, ischemic vascular dementia, normal pressure hydrocephalus, or Parkinson's disease.
• Schizophrenia, or other major psychiatric disorder defined by DSM-IV criteria.
• Medications: (a) Frequent use of high doses of analgesics; Use of sedative medications except for those used occasionally for sleep (≤2 per week); (b) Use of unstable dosing of Cholinesterase inhibitors (need to be stable dosing for 2 months); (c) AD disease modifying monoclonal antibody treatment e.g., aducanumab or lecanemab (completed the treatment is allowed)

Sponsors & Collaborators

• Arizona State University: collaborator
• Massachusetts General Hospital: lead

Study Sites (1)

Massachusetts General Hospital

Boston, Massachusetts, 02129, United States

Location

MeSH Terms

Conditions

Cognitive Dysfunction; Social Isolation

Condition Hierarchy (Ancestors)

Cognition Disorders; Neurocognitive Disorders; Mental Disorders; Social Behavior; Behavior

Study Officials

• Hiroko H Dodge, PhD

  Massachusetts General Hospital

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Catherine Young

CONTACT

617-724-2428; cyoung@mgh.harvard.edu

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: SINGLE
• Who Masked: OUTCOMES ASSESSOR
• Purpose: PREVENTION
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Professor, Harvard Medical School

Study Record Dates

• First Submitted: February 19, 2026
• First Posted: July 14, 2026
• Study Start: October 1, 2026
• Primary Completion (Estimated): May 30, 2028
• Study Completion (Estimated): September 30, 2028
• Last Updated: August 25, 2026

Record last verified: 2026-08

Data Sharing

• IPD Sharing: Will share
• Shared Documents: ANALYTIC CODE
• Time Frame: De-identified data and related materials are available upon request; the current protocol does not specify a fixed availability start or end date. Availability and retention follow Mass General Brigham and NIH record-retention requirements.
• Access Criteria: Requests are reviewed by the study team. Sharing occurs only under an executed Data Use Agreement (DUA) or equivalent research agreement approved by the Mass General Brigham Contracting Office, is limited to de-identified (except audio recording as described above) or aggregated data for the analyses described in the protocol, and contractually prohibits re-identification and onward sharing. Data are transferred only via Mass General Brigham-approved secure, encrypted methods.

Locations

US (1)