MedTrace Logo

Multi-agent LLMs for Decision Support in Cervical Cancer During Pregnancy

NCT07318701 · Status: NOT_YET_RECRUITING · Phase: NA · Type: INTERVENTIONAL · Enrollment: 150

Last updated 2026-01-06

No results posted yet for this study

Summary

The aim of this study is to develop an AI-assisted decision-making system based on multi-agent large language models and to evaluate its effectiveness and accuracy in the diagnosis and treatment of cervical cancer during pregnancy.

Conditions

Interventions

OTHER

multi-disciplinary agents group

generate diagnosis and treatment opinions for each case from multi-disciplinary agents

OTHER

real MDT group

generate diagnosis and treatment opinions for each case from a real MDT team inclduing senior physicians from relevant departments, including gynecologic oncology, pediatrics, obstetrics, medical oncology and radiation oncology.

OTHER

junor doctor group

generate diagnosis and treatment opinions for each case from junior doctor who are residents from relevant departments, including gynecologic oncology, pediatrics, obstetrics, medical oncology and radiation oncology.

OTHER

junor doctor group with aid of MDT agents

generate diagnosis and treatment opinions for each case from junior doctor who are residents from relevant departments, including gynecologic oncology, pediatrics, obstetrics, medical oncology and radiation oncology after referring to the results from MDT agent .

Sponsors & Collaborators

  • Obstetrics & Gynecology Hospital of Fudan University

    lead OTHER

Principal Investigators

  • Keqin Hua, Doctor · Gynecology and obstetrics hospital of fudan university

Study Design

Allocation
RANDOMIZED
Purpose
SUPPORTIVE_CARE
Masking
DOUBLE
Model
PARALLEL

Eligibility

Sex
FEMALE
Healthy Volunteers
No

Timeline & Regulatory

Start
2026-01-01
Primary Completion
2026-06-30
Completion
2026-10-30

More Related Trials

Entities

Diseases

Read the full study record

This page highlights key information. For complete eligibility criteria, study locations, investigator contacts, and the full protocol, visit the original record on ClinicalTrials.gov.

View NCT07318701 on ClinicalTrials.gov