Evaluating the effectiveness of large language models (LLM)-based health consultation models in improving patient experience and hospital operational efficiency

Status

Recruiting

Phases

Early Phase 1

Study type

Interventional

Source

ChiCTR

Registry ID

ChiCTR2400094159

Enrollment

Unknown

Registered

2024-12-17

Start date

2025-02-08

Completion date

Unknown

Last updated

2025-06-16

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

Conditions

None listed

Interventions

Group A:Patients initially interacted with the AI consultation model via mobile phone with the guidance of a medical assistant before their physician consultation. A referral report generated from the

Group B:Patients initially interacted with the AI consultation model via mobile phone before their physician consultation. A referral report generated from the AI consultation is provided to the physi

Group C:The patient directly consults with the doctor.

Eligibility

Sex/Gender

All

Age

20 Years to 80 Years

Inclusion criteria

Inclusion criteria: 1. Patients with disease consultation needs in emergency and outpatient departments; 2. Aged 20-80 years old.

Exclusion criteria

Exclusion criteria: 1. Patients with high-risk risks and mental health problems are not suitable for AI health consultation.

Design outcomes

Primary

Measure	Time frame
Consultation duration;Care coordination;Ease of communication;	—

Secondary

Measure	Time frame
Physician attentiveness ;Interpersonal regard;Patient satisfaction;Future acceptability;Physician documentation practices;No.of patients per shift;	—

Countries

China

Contacts

Public ContactLibing Ma

Affiliated Hospital of Guilin Medical University

malibing1984@163.com+86 135 1773 7750

Outcome results