LLM-assisted multidisciplinary decision-making in lung cancer: efficacy of Gemini-2.5-Pro and GPT-5 in a real-world MDT setting.
7 affiliations
- 1Department of Radiology, Beijing Friendship Hospital, Capital Medical University, Beijing, 100050, China.
- 2Department of Radiation Oncology, Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical Sciences, Shandong, 250117, China.
- 3Department of Radiology, Beijing Friendship Hospital, Capital Medical University, Beijing, 100050, China. [email protected].
- 4Department of Radiology, Beijing Friendship Hospital, Capital Medical University, Beijing, 100050, China. [email protected].
- 5Department of Radiology, Beijing Friendship Hospital, Capital Medical University, Beijing, 100050, China. [email protected].
- 6Department of Health Data Science, School of Medical Technology, Capital Medical University, Beijing, 100069, China. [email protected].
- 7Precision and Intelligence Medical Imaging Lab, Beijing Friendship Hospital, Capital Medical University, Beijing, 100069, China. [email protected].
Abstract
Background
Multidisciplinary team (MDT) review is essential for individualized treatment planning in lung cancer, where decisions often require integration of staging, pathology, molecular findings, performance status, and multimodal treatment options. However, the effective implementation of MDT review remains constrained by limited specialist availability in resource-limited hospitals and by high patient volume, heavy physician workload, and tight clinical schedules in tertiary care centers. Large language models (LLMs) may support MDT workflows by synthesizing clinical information and generating preliminary treatment recommendations for clinician review. This study compared GPT-5 and Gemini-2.5-Pro with expert MDT recommendations in real-world lung cancer cases and evaluated how information completeness and input format influenced LLM-generated treatment recommendations.Methods
We conducted a head-to-head evaluation of GPT-5 and Gemini-2.5-Pro for lung-cancer multidisciplinary team decision support. For each of 150 consecutively collected cases, structured vignettes were entered using three information-completeness levels in both natural-language and isomorphic JavaScript Object Notation (JSON) formats. Each model produced a single-sentence recommendation. Outputs were compared with the expert multidisciplinary team plan, which was treated as a clinical reference standard for concordance analysis rather than an objective guideline-only gold standard, using predefined plan-level categories. To better quantify model performance, we applied keyword extraction and semantic matching to normalize both multidisciplinary team recommendations and model outputs into ten treatment categories with subsequent manual review and correction.Results
Stratifying by information level and format, Information Level III produced the best overall performance for Gemini-2.5-Pro under natural-language input, with F1 0.7603, accuracy 0.8647, precision 0.7031, and recall 0.8278. GPT-5 achieved its highest recall under Information Level III with JSON input (recall 0.9132), but this was accompanied by lower precision and F1. Under the same natural-language Information Level III, GPT-5 reached recall 0.8770 with F1 0.6826 and accuracy 0.7967.Conclusions
Gemini-2.5-Pro show promise as adjuncts to MDT decision-making in lung cancer, offering high agreement with expert plans under controlled conditions. With appropriate clinician oversight, LLM-based tools may help expand access to standardized, high-quality recommendations where specialist availability is limited.
Related
- Large Language Models as Decision Support in Breast Cancer Management: A Comparison with Multidisciplinary Team Decision-Making
- Impact of a Virtual Multidisciplinary Lymphoma Tumor Board on Clinical Decision-Making
- Lung Multidisciplinary Team Decision-Making Challenges in Perioperative NSCLC: Borderline Resectability and Discordant Responses Through the Lens of Real-World Scenarios
- Liquid Biopsy-Guided Surgical Decision-Making in Oligometastatic Non-Small Cell Lung Cancer: Toward Dynamic Risk Stratification in the Multidisciplinary Era
- Effect of guideline-assisted prompting on large language model performance in medication-related osteonecrosis of the jaw–related endodontic decision-making
BibTeX
@article{zhou2026llmassisted,
title = {{LLM-assisted multidisciplinary decision-making in lung cancer: efficacy of Gemini-2.5-Pro and GPT-5 in a real-world MDT setting.}},
author = {Zichun Zhou and Min Wang and Jia Li and Zhenchang Wang and Han Lv},
journal = {BMC medical informatics and decision making},
year = {2026},
month = jul,
doi = {10.1186/s12911-026-03723-7},
url = {https://europepmc.org/article/MED/42907951},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - LLM-assisted multidisciplinary decision-making in lung cancer: efficacy of Gemini-2.5-Pro and GPT-5 in a real-world MDT setting.
AU - Zichun Zhou
AU - Min Wang
AU - Jia Li
AU - Zhenchang Wang
AU - Han Lv
PY - 2026
DA - 2026/07/01
JO - BMC medical informatics and decision making
DO - 10.1186/s12911-026-03723-7
UR - https://europepmc.org/article/MED/42907951
AB - Background Multidisciplinary team (MDT) review is essential for individualized treatment planning in lung cancer, where decisions often require integration of staging, pathology, molecular findings, performance status, and multimodal treatment options. However, the effective implementation of MDT review remains constrained by limited specialist availability in resource-limited hospitals and by high patient volume, heavy physician workload, and tight clinical schedules in tertiary care centers. Large language models (LLMs) may support MDT workflows by synthesizing clinical information and generating preliminary treatment recommendations for clinician review. This study compared GPT-5 and Gemini-2.5-Pro with expert MDT recommendations in real-world lung cancer cases and evaluated how information completeness and input format influenced LLM-generated treatment recommendations.Methods We conducted a head-to-head evaluation of GPT-5 and Gemini-2.5-Pro for lung-cancer multidisciplinary team decision support. For each of 150 consecutively collected cases, structured vignettes were entered using three information-completeness levels in both natural-language and isomorphic JavaScript Object Notation (JSON) formats. Each model produced a single-sentence recommendation. Outputs were compared with the expert multidisciplinary team plan, which was treated as a clinical reference standard for concordance analysis rather than an objective guideline-only gold standard, using predefined plan-level categories. To better quantify model performance, we applied keyword extraction and semantic matching to normalize both multidisciplinary team recommendations and model outputs into ten treatment categories with subsequent manual review and correction.Results Stratifying by information level and format, Information Level III produced the best overall performance for Gemini-2.5-Pro under natural-language input, with F1 0.7603, accuracy 0.8647, precision 0.7031, and recall 0.8278. GPT-5 achieved its highest recall under Information Level III with JSON input (recall 0.9132), but this was accompanied by lower precision and F1. Under the same natural-language Information Level III, GPT-5 reached recall 0.8770 with F1 0.6826 and accuracy 0.7967.Conclusions Gemini-2.5-Pro show promise as adjuncts to MDT decision-making in lung cancer, offering high agreement with expert plans under controlled conditions. With appropriate clinician oversight, LLM-based tools may help expand access to standardized, high-quality recommendations where specialist availability is limited.
SN - 1472-6947
ER -