[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"trial:NCT07701668":3,"trial-entities:NCT07701668":102,"trial-summary:NCT07701668":106},{"id":4,"nct_id":4,"org_study_id":5,"brief_title":6,"official_title":7,"overall_status":8,"completion_date":9,"status_verified_date":10,"last_update_date":11,"start_date":12,"sponsor_name":13,"lead_sponsor_class":14,"has_dmc":15,"brief_summary":16,"detailed_description":17,"conditions":18,"keywords":21,"study_type":25,"primary_purpose":26,"phases":27,"enrollment_info":29,"interventions":32,"primary_outcomes":39,"secondary_outcomes":47,"sex":55,"minimum_age":56,"maximum_age":57,"healthy_volunteers":15,"eligibility_criteria":58,"std_ages":72,"locations":74,"central_contacts":93,"overall_officials":96,"references":100,"see_also_links":101},"NCT07701668","2026P000461","AI-CONECT: A Conversational AI for Early Dementia Prevention in Socially-Isolated Older Adults","AI-CONECT: A Conversational AI for Early Dementia Prevention in Socially-Isolated Older Adults Based on the Efficacy-Proven I-CONECT Study","NOT_YET_RECRUITING","2028-03-31","2026-07","2026-07-14","2026-07-30","Massachusetts General Hospital","OTHER",false,"This randomized controlled trial examines the mechanisms of conversational AI-based interventions for early dementia prevention in socially isolated older adults.","Social isolation is a well-established and modifiable risk factor for cognitive decline and dementia. The completed I-CONECT trial (NCT02871921) showed that frequent, one-to-one, semi-structured conversational engagement delivered remotely by trained human interviewers improved cognitive outcomes among socially isolated older adults with mild cognitive impairment. Two limitations have constrained translating that approach into a scalable preventive intervention: its reliance on trained human interviewers limits scalability, and the behavioral mechanisms responsible for its cognitive benefits remain incompletely understood.\n\nAI-CONECT addresses both limitations by delivering the conversational intervention through a conversational artificial intelligence (AI) voice chatbot rather than a human interviewer, and by testing a hypothesized behavioral mechanism: that the intervention increases participants' social self-efficacy (confidence in their ability to engage socially), which in turn increases real-world social engagement.",[19,20],"Mild Cognitive Impairment (MCI)","Social Isolation",[20,22,23,24,19],"Artificial Intelligence","AI-Chatbot","I-CONECT","INTERVENTIONAL","PREVENTION",[28],"NA",{"count":30,"type":31},80,"ESTIMATED",[33],{"type":34,"name":35,"description":36,"armGroupLabels":37},"BEHAVIORAL","AI-based conversational intervention","AI-based one-on-one semi-structured conversation for cognitive stimulation",[38],"AI-CONECT",[40,44],{"measure":41,"description":42,"timeFrame":43},"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",{"measure":45,"description":46,"timeFrame":43},"Time contacting friends or family","Change in weekly time contacting friends or family.",[48,52],{"measure":49,"description":50,"timeFrame":51},"Time out of home","Self-reported weekly time out of home (a proximate measure of social engagement by the participants).","From enrollment to the end of treatment at 8 weeks",{"measure":53,"description":54,"timeFrame":51},"Frequency of contacting friends","Self-reported weekly frequency of contacting friends.","ALL","75 Years",null,{"inclusion":59,"exclusion":67,"raw_text":71},[60,61,62,63,64,65,66],"Aged 75+","Clinical diagnosis of MCI, or MMSE ≥ 24 or MoCA ≥ 18 (i.e., early MCI)","Identified as socially isolated by at least one of the two criteria: (1)score ≤ 12 on the 6-item Lubben Social Network Scale (LSNS-6); (2) engages in conversations lasting 30 minutes or longer, no more than twice per week, per subject self-report","GDS-15 (15-item Geriatric Depression Scale) at\u002Fbelow 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.",[68,69,70],"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: Frequent use of high doses of analgesics; Use of sedative medications except for those used occasionally for sleep (≤2 per week); Use of unstable dosing of Cholinesterase inhibitors (need to be stable dosing for 2 months).","Inclusion Criteria:\n\n* Aged 75+\n* Clinical diagnosis of MCI, or MMSE ≥ 24 or MoCA ≥ 18 (i.e., early MCI)\n* Identified as socially isolated by at least one of the two criteria: (1)score ≤ 12 on the 6-item Lubben Social Network Scale (LSNS-6); (2) engages in conversations lasting 30 minutes or longer, no more than twice per week, per subject self-report\n* GDS-15 (15-item Geriatric Depression Scale) at\u002Fbelow 9 (not severely depressed).\n* 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.\n* Ability to understand the research consent form.\n* Ability to connect a tablet to the Internet.\n\nExclusion Criteria:\n\n* Diagnosed with dementia such as AD, ischemic vascular dementia, normal pressure hydrocephalus, or Parkinson's disease.\n* Schizophrenia, or other major psychiatric disorder defined by DSM-IV criteria.\n* Medications: Frequent use of high doses of analgesics; Use of sedative medications except for those used occasionally for sleep (≤2 per week); Use of unstable dosing of Cholinesterase inhibitors (need to be stable dosing for 2 months).",[73],"OLDER_ADULT",[75],{"facility":13,"city":76,"state":77,"zip":78,"country":79,"contacts":80,"geoPoint":90},"Boston","Massachusetts","02129","United States",[81,86],{"name":82,"role":83,"phone":84,"email":85},"Catherine Young","CONTACT","617-724-2428","cyoung@mgh.harvard.edu",{"name":87,"role":83,"phone":88,"email":89},"Junyuan Hong, PhD","517-668-5790","jhong28@mgh.harvard.edu",{"lat":91,"lon":92},42.35843,-71.05977,[94,95],{"name":82,"role":83,"phone":84,"email":85},{"name":87,"role":83,"phone":88,"email":89},[97],{"name":98,"affiliation":13,"role":99},"Hiroko H Dodge, PhD","PRINCIPAL_INVESTIGATOR",[],[],{"nct_id":4,"conditions":103,"biomarkers":105},[104],"Mild cognitive disorder",[],{"nct_id":4,"found":107,"summary":108,"prompt_version":118},true,{"design":109,"status":110,"heading":111,"summary":112,"follow_up":113,"word_count":114,"commitments":115,"compensation":116,"drugs_mentioned":117},"This is a randomized controlled trial, meaning participants will be assigned by chance to different groups. It plans to enroll 80 participants.","completed","AI-CONECT: Conversational AI for Early Dementia Prevention","This study is looking at whether an AI-based conversational intervention can help older adults who are socially isolated and have mild cognitive impairment (MCI). MCI means you have some memory or thinking problems, but they aren't severe enough to be dementia. The AI-based conversational intervention involves one-on-one conversations designed to stimulate your brain. Researchers want to see if this intervention can improve your confidence in social situations (social self-efficacy) and increase how often you contact friends or family. You might be able to join if you are 75 or older, have MCI, and are considered socially isolated. The study aims to enroll 80 participants, but its current status is unclear.","The study measures outcomes for 8 weeks after enrollment, until the end of the intervention.",110,"The primary endpoints are measured from enrollment to the end of the intervention at 8 weeks.","Not stated in the trial record.",[35],"v2"]