AI-driven multimodal tool to identify early cognitive problems in people with type 2 diabetes

The Application of an AI-driven Multimodal Predictive Model for Cognitive Impairment in Patients With Type 2 Diabetes Mellitus

This project will test whether an AI-based multimodal screening system can find early memory problems in people aged 40–75 with type 2 diabetes during a 3–5 year follow-up.

Quick facts

• Study type: Observational
• Enrollment: 5000 (estimated)
• Ages: 40 Years to 75 Years
• Sex: All
• Sponsor: Tongji Hospital (Academic / other)
• Locations: 21 sites (Enshi, Hubei and 20 other locations)
• Trial ID: NCT07128186 on ClinicalTrials.gov

What this trial studies

This observational cohort follows people with type 2 diabetes for 3–5 years using an AI-driven multimodal cognitive screening system to detect early mild cognitive impairment. Participants with normal cognition or mild cognitive impairment at baseline undergo regular cognitive testing and collection of metabolic indicators such as HbA1c and measures of glycemic variability. The AI model integrates multimodal data to predict cognitive decline and the study analyzes correlations between metabolic measures and cognitive changes over time. Exclusions include other diabetes types, education <6 years, recent acute metabolic events, and major neurological or psychiatric disorders that could affect cognition.

Who should consider this trial

Good fit: Ideal candidates are people aged 40–75 with type 2 diabetes who report memory complaints, have preserved basic activities of daily living, and score as cognitively normal or with mild cognitive impairment at baseline.

Not a fit: People with type 1 or gestational diabetes, less than 6 years of education, recent severe metabolic events, major neurological or psychiatric disorders, or advanced dementia are unlikely to benefit from this screening approach.

Why it matters

Potential benefit: If successful, the system could enable earlier detection of diabetes-related cognitive decline, allowing timelier interventions to help preserve daily function.

How similar studies have performed: Prior research using AI and multimodal biomarkers for early MCI detection has shown promise, but prospective long-term validation specifically in type 2 diabetes populations is limited.

Eligibility criteria

Inclusion Criteria:

Inclusion Criteria

1. Diagnosed with type 2 diabetes mellitus (T2DM).
2. Aged 40-75 years, with self-reported or informant-reported memory complaints.
3. Cognitive assessment scores consistent with either:

   * Cognitive Normal (CN) or
   * Mild Cognitive Impairment (MCI).
4. Preserved ability to perform basic activities of daily living (ADLs).
5. Memory-specific deficits only (e.g., partial forgetfulness), with intact other cognitive domains (e.g., reasoning, judgment, attention, and executive function).

Exclusion Criteria:

1. Other types of diabetes (e.g., type 1 diabetes, gestational diabetes).
2. Education level \<6 years.
3. Metabolic disorders that may affect cognition, including:

   * Acute carbohydrate metabolism events within 3 months (e.g., severe hypoglycemia, diabetic ketoacidosis, hyperglycemic hyperosmolar state).
   * Hypothyroidism or other endocrine disorders.
4. Neurological/psychiatric conditions that may impair cognition:

   * History of head trauma, depression, anxiety, delirium, severe pulmonary/renal disease, heart failure, or malignancy.
5. Substance abuse (past 2 years), including nicotine/alcohol dependence.
6. Recent medication use (within 1 month):

   * Anti-Parkinsonian drugs, antiepileptics, sedatives/hypnotics.
7. Cognitive-enhancing drugs (e.g., donepezil, memantine).
8. Inability to complete AI screening or follow-up due to:

   * Speech/hearing/visual impairments or other disabilities

Where this trial is running

Enshi, Hubei and 20 other locations

• Minda Hospital Affiliated to Hubei Minzu University — Enshi, Hubei, China (Recruiting)
• Huanggang Central Hospital — Huanggang, Hubei, China (Recruiting)
• Huangshi Central Hospital — Huangshi, Hubei, China (Recruiting)
• Jingzhou Central Hospital — Jingzhou, Hubei, China (Recruiting)
• Sinopharm Dongfeng General Hospital — Shiyan, Hubei, China (Not_yet_recruiting)
• Suizhou Central Hospital — Suizhou, Hubei, China (Not_yet_recruiting)
• Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology — Wuhan, Hubei, China (Recruiting)
• China Resources & WISCO General Hospital — Wuhan, Hubei, China (Recruiting)
• Hubei Provincial Hospital of Integrated Chinese & Western Medicine — Wuhan, Hubei, China (Recruiting)
• Tianyou Hospital Affiliated to Wuhan University of Science and Technology — Wuhan, Hubei, China (Not_yet_recruiting)
• Wuhan Central Hospital — Wuhan, Hubei, China (Recruiting)
• Wuhan Fifth Hospital — Wuhan, Hubei, China (Recruiting)
• Wuhan Fourth Hospital — Wuhan, Hubei, China (Recruiting)
• Xiangyang Central Hospital — Xiangyang, Hubei, China (Not_yet_recruiting)
• Xiangyang First People's Hospital — Xiangyang, Hubei, China (Recruiting)
• Xianning Central Hospital — Xianning, Hubei, China (Recruiting)
• Xiantao First People's Hospital — Xiantao, Hubei, China (Not_yet_recruiting)
• Xiaogan Central Hospital — Xiaogan, Hubei, China (Recruiting)
• Renhe Hospital Affiliated to China Three Gorges University — Yichang, Hubei, China (Recruiting)
• Sinopharm Gezhouba Central Hospital — Yichang, Hubei, China (Not_yet_recruiting)
• Yichang Central People's Hospital — Yichang, Hubei, China (Recruiting)

Study contacts

• Study coordinator: Prof. Yang, Doctor

Conditions Cognitive Dysfunction; mild cognitive impairment; type 2 diabetes mellitus; artificial intelligence-based multimodal cognitive screening system