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

NCT07318701NOT_YET_RECRUITINGNAINTERVENTIONAL

Summary

Key Facts

Lead Sponsor

Obstetrics & Gynecology Hospital of Fudan University

Enrollment

150

Start Date

2026-01-01

Completion Date

2026-06-30

Study Type

INTERVENTIONAL

Official Title

Multi-agent Large Language Models for Multidisciplinary Decision Support in Cervical Cancer During Pregnancy

Interventions

multi-disciplinary agents groupreal MDT groupjunor doctor groupjunor doctor group with aid of MDT agents

Conditions

Cervical Cancer

Eligibility

Sex

FEMALE

Inclusion Criteria:

1. Pathologically confirmed diagnosis of cervical cancer.
2. Confirmed intrauterine pregnancy status via ultrasound.
3. Patients receiving initial treatment.
4. Agreement to participate in the study with signed informed consent.

Exclusion Criteria:

1. Previous treatment received for cervical cancer during pregnancy.
2. Pathological pregnancy states (e.g., ectopic pregnancy).
3. Inability or unwillingness to provide signed informed consent.

Outcome Measures

Primary Outcomes

Accuracy of the MDT decision

scores, from 0 to 100, accuracy of the MDT decision according to evaluation indicators of each discipline

Time frame: immediately after the intervention

Secondary Outcomes

Consuming time

seconds, consuming time for generating MDT decisions from MDT agents/ real MDT team

Time frame: immediately after the intervention

Linked Papers

2023-11-21

Let's chat about cervical cancer: Assessing the accuracy of ChatGPT responses to cervical cancer questions

To quantify the accuracy of ChatGPT in answering commonly asked questions pertaining to cervical cancer prevention, diagnosis, treatment, and survivorship/quality-of-life (QOL). ChatGPT was queried with 64 questions adapted from professional society websites and the authors' clinical experiences. The answers were scored by two attending Gynecologic Oncologists according to the following scale: 1) correct and comprehensive, 2) correct but not comprehensive, 3) some correct, some incorrect, and 4) completely incorrect. Scoring discrepancies were resolved by additional reviewers as needed. The proportion of responses earning each score were calculated overall and within each question category. ChatGPT provided correct and comprehensive answers to 34 (53.1%) questions, correct but not comprehensive answers to 19 (29.7%) questions, partially incorrect answers to 10 (15.6%) questions, and completely incorrect answers to 1 (1.6%) question. Prevention and survivorship/QOL had the highest proportion of "correct" scores (scores of 1 or 2) at 22/24 (91.7%) and 15/16 (93.8%), respectively. ChatGPT performed less well in the treatment category, with 15/21 (71.4%) correct scores. It performed the worst in the diagnosis category with only 1/3 (33.3%) correct scores. ChatGPT accurately answers questions about cervical cancer prevention, survivorship, and QOL. It performs less accurately for cervical cancer diagnosis and treatment. Further development of this immensely popular large language model should include physician input before it can be utilized as a tool for Gynecologists or recommended as a patient resource for information on cervical cancer diagnosis and treatment.

Linked Investigators