Development and Evaluation of a Retrieval-Augmented Generation (RAG) Chatbot Based on a Large Language Model for Transitional Health Information Provision in Patients with Ischemic Stroke

Status

Active, not recruiting

Phases

Phase 2Phase 3

Study type

Interventional

Source

CRIS

Registry ID

KCT0011776

Enrollment

Registered

2026-03-25

Start date

2026-04-01

Completion date

Unknown

Last updated

2026-03-30

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

Conditions

None listed

Interventions

Behavioral : The intervention group will receive instructions from a researcher on how to use the RAG-based chatbot at the time of discharge and will be allowed to use the chatbot freely for one month

Eligibility

Sex/Gender

All

Inclusion criteria

Inclusion criteria: ? A total of 70 patients who were hospitalized for ischemic stroke in the Department of Neurology at Kangwon National University Hospital and subsequently discharged (35 in the intervention group and 35 in the control group) ? Patients without cognitive impairment who are able to ask questions verbally using a retrieval-augmented generation (RAG)-based chatbot

Exclusion criteria

Exclusion criteria: ? If the participant does not provide consent to participate in the study ? If the participant withdraws consent and requests to discontinue participation in the study ? If the participant dies

Design outcomes

Primary

Measure	Time frame
Digital Health Literacy;Health Literacy;Self-efficacy	—

Secondary

Measure	Time frame
Anxiety and depression;Confidence in health care after discharge	—

Countries

Korea, Republic of

Contacts

Public ContactSu Kyoung Kim

Kangwon National University Hospital

tnrud5698@naver.com+82-33-250-8910

Outcome results