الملخص
Molecular tumor boards integrate genomic findings, clinical context, and therapeutic evidence to support precision oncology. As AI enters this workflow, a key safety challenge is distinguishing truly unsupported recommendations from evidence-supported options that still require oncologist review because of incomplete information, poor ECOG performance status, or other clinical caveats. We introduce OpenMTB-Audit, an open-source benchmark of 500 synthetic non-small cell lung cancer cases spanning five adversarial error categories and four safety labels: Supported, Partially Supported, Unsupported, and Insufficient Information. Across eight large language model configurations, we identify pervasive over-refusal: all LLM configurations failed to retain the Partially Supported label in 83.3-100% of true Partially Supported cases, achieving high aggregate safety scores through label collapse rather than clinically calibrated reasoning. To address this limitation, we developed MTB-AuditAgent, a deterministic seven-module framework separating evidence verification, missing-information detection, safety classification, and abstention. It reduces over-refusal to 6.7% and achieves 91.2% accuracy (95% CI: 88.6-93.6%). A two-oncologist annotation study found disagreement concentrated at the boundary between information sufficiency and treatment optimization, underscoring the need to preserve clinically meaningful distinctions.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Ashrafi, N., Luo, J., Frumm, S. M., & Daneshjou, R. (2026). OpenMTB-Audit: Exposing Over-Refusal and Clinical Expert Perspectives in LLM-Based Molecular Tumor Board Safety Evaluation. https://omanscience.com/ar/articles/openmtb-audit-exposing-over-refusal-and-clinical-expert-perspectives-in-llm-based-molecular-tumor-board-safety-evaluation
MLA 9
Ashrafi, Negin, et al. "OpenMTB-Audit: Exposing Over-Refusal and Clinical Expert Perspectives in LLM-Based Molecular Tumor Board Safety Evaluation." https://omanscience.com/ar/articles/openmtb-audit-exposing-over-refusal-and-clinical-expert-perspectives-in-llm-based-molecular-tumor-board-safety-evaluation.
شيكاغو (المؤلف–التاريخ)
Ashrafi, Negin, Jia Luo, Stacey M. Frumm, and Roxana Daneshjou. 2026. "OpenMTB-Audit: Exposing Over-Refusal and Clinical Expert Perspectives in LLM-Based Molecular Tumor Board Safety Evaluation." https://omanscience.com/ar/articles/openmtb-audit-exposing-over-refusal-and-clinical-expert-perspectives-in-llm-based-molecular-tumor-board-safety-evaluation.
هارفارد
Ashrafi, N., Luo, J., Frumm, S. M. and Daneshjou, R. (2026) 'OpenMTB-Audit: Exposing Over-Refusal and Clinical Expert Perspectives in LLM-Based Molecular Tumor Board Safety Evaluation', Available at: https://omanscience.com/ar/articles/openmtb-audit-exposing-over-refusal-and-clinical-expert-perspectives-in-llm-based-molecular-tumor-board-safety-evaluation.
فانكوفر
Ashrafi N, Luo J, Frumm SM, Daneshjou R. OpenMTB-Audit: Exposing Over-Refusal and Clinical Expert Perspectives in LLM-Based Molecular Tumor Board Safety Evaluation. https://omanscience.com/ar/articles/openmtb-audit-exposing-over-refusal-and-clinical-expert-perspectives-in-llm-based-molecular-tumor-board-safety-evaluation
IEEE
N. Ashrafi, J. Luo, S. M. Frumm, and R. Daneshjou, "OpenMTB-Audit: Exposing Over-Refusal and Clinical Expert Perspectives in LLM-Based Molecular Tumor Board Safety Evaluation," https://omanscience.com/ar/articles/openmtb-audit-exposing-over-refusal-and-clinical-expert-perspectives-in-llm-based-molecular-tumor-board-safety-evaluation.