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

Plain English Summary

Large Language Models Assist in Tumor MDT is a Not Applicable clinical trial sponsored by Sun Yat-Sen Memorial Hospital of Sun Yat-Sen University studying Lung Cancer, Breast Cancer, Colorectal Cancer, Stomach Cancer, Liver Cancer. This study tests if Artificial Intelligence (AI) tools can help doctors write reports for cancer patient treatment plans more accurately and efficiently. It is for junior doctors specializing in cancer care, including oncologists, surgeons, radiologists, and pathologists. Doctors will either use an AI tool to help write reports or use traditional methods, and their work will be reviewed by experts. The alternative is using current methods for gathering information and writing these complex reports. The trial aims to enroll 60 participants.

Official 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.

Who Can Participate

Here is what you need to know about eligibility for this trial. Junior doctors with a valid medical license can join. Doctors with 3-5 years of experience in oncology, surgery, radiation oncology, radiology, or pathology are eligible. Participants must be between 25 and 33 years old and available for at least 10 hours during the study. You cannot join if you have already been involved in the treatment of the specific patient cases being reviewed in this study. This trial is studying Lung Cancer, Breast Cancer, Colorectal Cancer, Stomach Cancer, Liver Cancer, so participants generally need a confirmed diagnosis. The trial is currently accepting new participants.

What They're Measuring

The main goal is to see if the AI-assisted reports are better overall, meaning the AI helps doctors create more thorough and accurate treatment plans for cancer patients. The specific primary outcome measures are: The overall score of the MDT report (Up to 4 weeks, complete the writing of medical opinions for all cases (n=20).). These endpoints are how researchers determine whether the treatment is effective and will form the basis of any future regulatory submissions.

About This Phase

This study does not have a traditional clinical phase designation. It may be an observational study that follows patients without intervening in their care, an expanded access or compassionate use program, or other non-interventional research. These studies contribute valuable data about disease progression, treatment patterns, and patient outcomes.

Why This Trial Matters

This trial matters because it explores how AI can improve the quality and speed of multidisciplinary team discussions for cancer treatment, addressing limitations in current medical resources and acce This research targets Lung Cancer, Breast Cancer, Colorectal Cancer, Stomach Cancer, Liver Cancer, where improved treatment options are needed.

Investor Insight

This trial signals a growing interest in AI's role in healthcare, potentially improving efficiency in complex medical decision-making for a large market of cancer patients.

Is This Trial Right for Me?

Ask your doctor how AI is being used in your cancer care and if it's part of a study. If you are a doctor in the study, you will use an AI tool to help draft reports for cancer cases, and your work will be compared to doctors using traditional methods. The study involves writing reports for 20 cancer cases over about 4 weeks. This trial is currently recruiting participants. The trial is being conducted at 2 sites. Always discuss clinical trial participation with your healthcare provider before making any decisions. This information is for educational purposes only and is not medical advice.

AI-generated analysis for educational purposes only. This is not medical advice. Discuss clinical trial participation with your doctor. Data sourced from ClinicalTrials.gov.

Study Design

• Study Type: INTERVENTIONAL
• Allocation: RANDOMIZED
• Model: PARALLEL
• Masking: SINGLE
• Enrollment: 60 participants

Interventions

• OTHER: LLM 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 traditiona

Primary Outcomes

• The overall score of the MDT report (Up to 4 weeks, complete the writing of medical opinions for all cases (n=20).)

Secondary Outcomes

• The radiation oncology score of the MDT report (Up to 4 weeks, complete the writing of medical opinions for all cases (n=20).)
• The medical oncology score of the MDT report (Up to 4 weeks, complete the writing of medical opinions for all cases (n=20).)
• The pathology score of the MDT report (Up to 4 weeks, complete the writing of medical opinions for all cases (n=20).)
• The radiology score of the MDT report (Up to 4 weeks, complete the writing of medical opinions for all cases (n=20).)
• The time consumption in writing an MDT report (Up to 4 weeks, complete the writing of medical opinions for all cases (n=20).)

Full Eligibility 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.

Trial Locations

• Sun Yat-Sen Memorial Hospital of Sun Yat-Sen University, Guangzhou, Guangdong, China
• Sun Yat-Sen Memorial Hospital of Sun Yat-Sen University, Guangzhou, Guangdong, China

Frequently Asked Questions

Related Conditions

• Lung Cancer
• Breast Cancer
• Colorectal Cancer
• Stomach Cancer
• Liver Cancer
• Oncology
• Medical Decision Support
• Artificial Intelligence in Medicine
• Clinical Report Writing
• Multidisciplinary Team Meetings

More Lung Cancer Trials

View all Lung Cancer clinical trials