Toward Expert-Level Medical Reasoning in Large Language Models

Status

Active, not recruiting

Phases

Phase 2Phase 3

Study type

Interventional

Source

TCTR

Registry ID

TCTR20261006006

Enrollment

571

Registered

2026-10-06

Start date

2026-10-05

Completion date

Unknown

Last updated

2026-10-05

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

Conditions

None listed

Interventions

Implementation of an AI-powered conversational agent for preliminary patient screening and clinical triage

Experimental Other

AI Chatbot

Eligibility

Sex/Gender

All

Age

18 Years to No maximum

Inclusion criteria

Inclusion criteria: 1. Research participants/volunteers aged 18 years and older 2. Patients receiving care at the Siriraj Hospital, Bangkok 3. Patients who voluntarily agree to use the chatbot application

Exclusion criteria

Exclusion criteria: 1. Unstable conditions requiring immediate medical intervention, such as unconsciousness, severe confusion, respiratory distress, hemodynamic instability, severe massive bleeding, or active resuscitation 2. Psychiatric emergencies that impact communication, such as suicidal ideation/self-harm, severe psychosis, or risk of harm to others 3. Inability to provide informed consent or a failure to understand chatbot limitations, such as acute confusion, severe cognitive impairment, language barriers, etc.

Design outcomes

Primary

Measure	Time frame
Model Performance Analysis 1 day after enrolling the study Concordance analysis, Classification evaluation Metrics	—

Secondary

Measure	Time frame
Participant Satisfaction 1 day after enrolling the study Median, IQR, and %Frequency of 5-point Likert scale	—

Countries

Thailand

Contacts

Public ContactThananya Boonyasirinant

Faculty of Medicine Siriraj Hospital

thananya.boo@mahidol.ac.th024196102

Outcome results