Large Language Models Assist in Tumor MDT

Evaluating Large Language Models as Decision Support Agents in Pan-Cancer Tumor Boards: A Randomized Controlled Trial

Status

Recruiting

Phases

Unknown

Study type

Interventional

Source

ClinicalTrials.gov

Registry ID

NCT07504367

Enrollment

Registered

2026-03-31

Start date

2026-01-01

Completion date

2026-12-31

Last updated

2026-03-31

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

Conditions

Breast Cancer, Colorectal Cancer, Liver Cancer, Lung Cancer, Stomach Cancer

Brief summary

Multidisciplinary teams (MDTs) represent the gold standard for personalized tumor treatment, but they are limited by medical resources and accessibility Limitation. Although large language models (LLMs) have shown promise in medical reasoning, their multidisciplinary practicality in pan-cancer MDTs has not been fully explored. In the early stage of this project, LLMs with high clinical application efficacy were identified through benchmark tests, and an open-label randomized controlled study (RCT) was conducted based on these LLMs. The research aims to explore whether AI-assisted assistance can enhance the accuracy and writing efficiency of MDT diagnosis and treatment reports. This study intends to prospectively collect the diagnosis and treatment information of 20 patients and MDT diagnosis and treatment information. It is planned to recruit 40 junior doctors. Doctors in the intervention group will use LLM to assist in the writing of MDT reports, while doctors in the control group will use traditional information retrieval methods for the writing of MDT reports. Three clinical experts ultimately used a standardized Likert scale to conduct comprehensive and multidisciplinary scoring of the MDT reports of the intervention group and the control group. This study quantitatively compared the diagnosis and treatment quality and efficiency of the MDT AI-assisted model and the traditional model to verify the application potential of large language models in assisting tumor diagnosis and treatment.

Interventions

OTHERLLM assists in MDT report writing

This study was a prospective RCT, and the intervention content was an auxiliary tool for writing MDT reports. The intervention group used LLM to assist in the writing of MDT reports. The prescribed MDT medical records (excluding diagnosis and treatment opinions) were input into the LLM, and the output content could be used as a reference for the MDT report. Finally, the MDT diagnosis and treatment opinions were written under the personal judgment of the doctors. The control group used traditional information retrieval methods (such as Google, literature, and textbooks) to write MDT diagnosis and treatment opinions.

Study design

Allocation

RANDOMIZED

Intervention model

PARALLEL

Primary purpose

TREATMENT

Masking

SINGLE (Outcomes Assessor)

Eligibility

Sex/Gender

ALL

Age

25 Years to 33 Years

Healthy volunteers

Yes

Inclusion criteria

* A junior doctor with a practicing physician qualification certificate. * Oncologists, surgeons, radiation oncologists, radiologists and pathologists with 3 to 5 years of clinical experience. * Age: 25 to 33 years old, gender not limited. * During the research period, one can participate for no less than 10 hours. * Agree to participate in this research and sign the informed consent form.

Exclusion criteria

* Have participated in the previous diagnosis and treatment of any one of the 20 cases included in the study.

Design outcomes

Primary

Measure	Time frame	Description
The overall score of the MDT report	Up to 4 weeks, complete the writing of medical opinions for all cases (n=20).	Clinical experts comprehensively evaluated the diagnosis and treatment opinions of different departments in the MDT report, and used the standardized Likert scale to comprehensively score the MDT reports of the intervention group and the control group (1 to 5 points, the higher the better).

Secondary

Measure	Time frame	Description
The radiation oncology score of the MDT report	Up to 4 weeks, complete the writing of medical opinions for all cases (n=20).	Clinical experts used a standardized Likert scale to score the radiotherapy department's diagnosis and treatment opinions reported by the MDT in the intervention group and the control group (1 to 5 points, the higher the better).
The medical oncology score of the MDT report	Up to 4 weeks, complete the writing of medical opinions for all cases (n=20).	Clinical experts used the standardized Likert scale to score the medical oncology diagnosis and treatment opinions reported by the MDT in the intervention group and the control group (1 to 5 points, the higher the better).
The pathology score of the MDT report	Up to 4 weeks, complete the writing of medical opinions for all cases (n=20).	Clinical experts used the standardized Likert scale to score the pathological diagnosis and treatment opinions reported by the MDT in the intervention group and the control group (1 to 5 points, the higher the better).
The radiology score of the MDT report	Up to 4 weeks, complete the writing of medical opinions for all cases (n=20).	Clinical experts used a standardized Likert scale to score the radiology diagnosis and treatment opinions reported by the MDT in the intervention group and the control group (1 to 5 points, the higher the better).
The time consumption in writing an MDT report	Up to 4 weeks, complete the writing of medical opinions for all cases (n=20).	The intervention group and the control group completed the MDT report for each case at all times (unit: hours).

Countries

China

Contacts

CONTACTYunfang Yu, PhD

yuyf9@mail.sysu.edu.cn+8613660238987

CONTACTHerui Yao, PhD

yaoherui@mail.sysu.edu.cn+8613500018020

STUDY_CHAIRYunfang Yu, PhD

Sun Yat-Sen Memorial Hospital of Sun Yat-Sen University

STUDY_DIRECTORHerui Yao, PhD