IHC-LLMiner: Automated extraction of tumour immunohistochemical profiles from PubMed abstracts using large language models

TL;DR

IHC-LLMiner presents a scalable, LLM-based pipeline to automatically extract immunohistochemical tumour profiles from PubMed abstracts, combining abstract collection, strict include/exclude classification, and structured extraction of tumour-marker data with UMLS normalisation. The Gemma-2 finetuned model leads abstract classification with 91.5% accuracy and 91.4 F1, while LoRA-finetuned Gemma-2 best extracts IHC-tumour profiles at 63.3% Correct, outperforming baselines and showing strong concordance with PathologyOutlines data. The approach yields a large, structured IHC-tumour landscape across 50 markers, enabling automated knowledge-base construction and potential gap-filling in existing resources, albeit with limitations from annotation size and the need for broader normalisation. Overall, IHC-LLMiner demonstrates the practical viability of integrating domain-specific and generative NLP for large-scale biomedical data mining, balancing performance and cost to support cancer research and clinical decision-support applications.

Abstract

Immunohistochemistry (IHC) is essential in diagnostic pathology and biomedical research, offering critical insights into protein expression and tumour biology. This study presents an automated pipeline, IHC-LLMiner, for extracting IHC-tumour profiles from PubMed abstracts, leveraging advanced biomedical text mining. There are two subtasks: abstract classification (include/exclude as relevant) and IHC-tumour profile extraction on relevant included abstracts. The best-performing model, "Gemma-2 finetuned", achieved 91.5% accuracy and an F1 score of 91.4, outperforming GPT4-O by 9.5% accuracy with 5.9 times faster inference time. From an initial dataset of 107,759 abstracts identified for 50 immunohistochemical markers, the classification task identified 30,481 relevant abstracts (Include) using the Gemma-2 finetuned model. For IHC-tumour profile extraction, the Gemma-2 finetuned model achieved the best performance with 63.3% Correct outputs. Extracted IHC-tumour profiles (tumour types and markers) were normalised to Unified Medical Language System (UMLS) concepts to ensure consistency and facilitate IHC-tumour profile landscape analysis. The extracted IHC-tumour profiles demonstrated excellent concordance with available online summary data and provided considerable added value in terms of both missing IHC-tumour profiles and quantitative assessments. Our proposed LLM based pipeline provides a practical solution for large-scale IHC-tumour profile data mining, enhancing the accessibility and utility of such data for research and clinical applications as well as enabling the generation of quantitative and structured data to support cancer-specific knowledge base development. Models and training datasets are available at https://github.com/knowlab/IHC-LLMiner.

Figures (2)

• Figure 1: Overview of IHC-LLMiner: Automated extraction of Immunohistochemical profiles using LLMs.
• Figure 2: Example of immunohistochemical-tumour profile extraction results from different models for PMID: 21691200.