Scholarlink

Manual labelling of pathology reports is a costly bottleneck for medical data analysis. We propose diverse unanimous ensembles, integrating Large Language Models (LLMs) like GPT-4o with complementary model architectures, for high-confidence automatic labelling of pathology reports, particularly addressing the challenge of labelled training data scarcity. This consensus method yields high precision on an automatically identifiable subset while simultaneously flagging ambiguous cases requiring expert review. Applying this to the public TCGA-Reports dataset, a GPT-4o and DistilBERT ensemble achieved \(95.5\%\) accuracy on the \(45.5\%\) subset representing a 23.1 percentage point increase over the baseline DistilBERT’s overall accuracy on the full dataset. This demonstrates potential for cost-effective data annotation by automatically labelling high-confidence subsets, thereby reserving human effort for ambiguous cases.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

High-Confidence Labelling of Pathology Reports Using LLM-Based Unanimous Ensembles with Limited Data

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Thomas Greatrix,
  • Frank C. Langbein,
  • Roger M. Whitaker,
  • Gualtiero B. Colombo,
  • Liam D. Turner

摘要

Manual labelling of pathology reports is a costly bottleneck for medical data analysis. We propose diverse unanimous ensembles, integrating Large Language Models (LLMs) like GPT-4o with complementary model architectures, for high-confidence automatic labelling of pathology reports, particularly addressing the challenge of labelled training data scarcity. This consensus method yields high precision on an automatically identifiable subset while simultaneously flagging ambiguous cases requiring expert review. Applying this to the public TCGA-Reports dataset, a GPT-4o and DistilBERT ensemble achieved \(95.5\%\) accuracy on the \(45.5\%\) subset representing a 23.1 percentage point increase over the baseline DistilBERT’s overall accuracy on the full dataset. This demonstrates potential for cost-effective data annotation by automatically labelling high-confidence subsets, thereby reserving human effort for ambiguous cases.