Skip to content

Application of a Retrieval-Augmented Generation and Large Language Model–Based Intelligent Question-Answering System in Health Education for Patients With Type 2 Diabetes: A Randomized Controlled Trial

Application of a Retrieval-Augmented Generation and Large Language Model–Based Intelligent Question-Answering System in Health Education for Patients With Type 2 Diabetes: A Randomized Controlled Trial

Status
Active, not recruiting
Phases
Unknown
Study type
Interventional
Source
ChiCTR
Registry ID
ChiCTR2600126757
Enrollment
Unknown
Registered
2026-06-15
Start date
2026-06-17
Completion date
Unknown
Last updated
2026-06-22

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Type 2 diabetes

Interventions

Trial group:Introducing an intelligent question-and-answer system based on RAG and large language models to support health education in conventional settings
Control group:Conventional health education methods were employed, including verbal guidance and the distribution of printed materials.

Sponsors

Yueyang Central Hospital
Lead Sponsor

Eligibility

Sex/Gender
All
Age
18 Years to No maximum

Inclusion criteria

Inclusion criteria: 1. Aged 18 or over; 2. Meets the diagnostic criteria for type 2 diabetes set out in the 2024 edition of the *Chinese Guidelines for the Prevention and Treatment of Diabetes*; 3. This is a planned hospital admission with an expected length of stay of 7 days or more; 4. Possesses good vision, hearing and communication skills; 5. The patient or their primary carer is proficient in using a smartphone and WeChat.

Exclusion criteria

Exclusion criteria: 1. Patients with severe failure or end-stage disease of vital organs such as the heart, liver, kidneys, or brain; 2. Patients with psychiatric disorders such as schizophrenia or bipolar disorder, or those with cognitive impairment or dementia who are unable to cooperate in completing scale assessments and health education interventions; 3. Individuals with physical disabilities, visual impairments, or hearing impairments that prevent them from properly operating smartphones and WeChat; 4. Patients who experienced acute severe complications such as diabetic ketoacidosis or hyperosmolar hyperglycemic syndrome prior to enrollment; 5. Individuals who refuse to participate in this study or are unable to sign the informed consent form.

Design outcomes

Primary

MeasureTime frame
Blood sugar levels;The incidence of adverse events during hospitalization;Compliance in the use of intelligent question-answering systems;

Secondary

MeasureTime frame
Level of self-management behavior;

Countries

China

Contacts

Public ContactPeng Shuang

Yueyang Central Hospital

1037959011@qq.com+86 730 8892040

Outcome results

None listed

Source: ChiCTR (via WHO ICTRP) · Data processed: Jun 29, 2026