AI language tools to help tumor care teams write MDT reports
Evaluating Large Language Models as Decision Support Agents in Pan-Cancer Tumor Boards: A Randomized Controlled Trial
We will test whether AI language tools can help junior cancer doctors write MDT diagnosis and treatment reports more accurately and faster.
Quick facts
| Phase | Not applicable |
|---|---|
| Study type | Interventional |
| Enrollment | 60 (estimated) |
| Ages | 25 Years to 33 Years |
| Sex | All |
| Sponsor | Sun Yat-Sen Memorial Hospital of Sun Yat-Sen University Academic / other |
| Drugs / interventions | radiation |
| Locations | 2 sites (Guangzhou, Guangdong and 1 other locations) |
| Trial ID | NCT07504367 on ClinicalTrials.gov |
What this trial studies
This open-label randomized controlled study randomizes 40 junior clinicians to either use a selected large language model (LLM) to assist in writing multidisciplinary team (MDT) reports or to write reports without LLM support. The project builds on benchmark testing that identified high-performing LLMs for clinical tasks and prospectively collects diagnostic and treatment information from 20 patient cases across five cancer types. Primary outcomes include accuracy of MDT diagnostic and treatment recommendations and time spent producing MDT reports. The study is conducted at a single center and focuses on real-world workflow integration for oncologists, surgeons, radiation oncologists, radiologists, and pathologists with 3–5 years’ experience.
Who should consider this trial
Good fit: Ideal participants are junior doctors (oncologists, surgeons, radiation oncologists, radiologists, or pathologists) aged about 25–33 with 3–5 years of clinical experience who can commit at least 10 hours and provide informed consent.
Not a fit: Patients whose care involves highly specialized or procedural decisions, or whose cases were already part of the study’s initial 20 cases, may not see direct benefit from this report-writing intervention.
Why it matters
Potential benefit: If successful, AI assistance could make MDT reports more accurate and faster, potentially improving treatment decisions for patients.
How similar studies have performed: Early studies and benchmarks show LLMs can help clinical summarization and reasoning, but randomized trials of LLM assistance in multidisciplinary tumor boards are limited and this application is relatively novel.
Eligibility criteria
Show full inclusion / exclusion criteria
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.
Where this trial is running
Guangzhou, Guangdong and 1 other locations
- Sun Yat-Sen Memorial Hospital of Sun Yat-Sen University — Guangzhou, Guangdong, China (Recruiting)
- Sun Yat-Sen Memorial Hospital of Sun Yat-Sen University — Guangzhou, Guangdong, China (Recruiting)
Study contacts
- Study coordinator: Yunfang Yu, PhD
- Email: yuyf9@mail.sysu.edu.cn
- Phone: +8613660238987
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.