Large Language Model Framework for Structured Biomarker Extraction and Triple-Negative Breast Cancer Identification From Pathology Reports: Development and Evaluation Study.
- 1School of Computer Science and Engineering, Vellore Institute of Technology, Vellore Campus, Tiruvalam Road, Katpadi, Vellore, Tamil Nadu, 632014, India, 91 9446171877.
- 2School of Bio Sciences and Technology, Vellore Institute of Technology, Vellore, Tamil Nadu, India.
- 3School of Advanced Sciences, Vellore Institute of Technology, Vellore, Tamil Nadu, India.
Abstract
Background
Triple-negative breast cancer (TNBC) is an aggressive molecular subtype of breast cancer that needs to be identified accurately from pathology reports to inform decision-making. Large language models (LLMs) have been reported to show great potential in the automatic extraction of important oncology information from unstructured medical text.Objective
We aimed to create and test an LLM-based approach for automatic biomarker extraction and TNBC subtype classification based on breast cancer pathology reports using prompt-engineering techniques.Methods
In total, 532 breast cancer pathology reports from The Cancer Genome Atlas (TCGA) were used. Our approach extracted structured oncology features, such as estrogen receptor status, progesterone receptor status, HER2 status, tumor size, tumor grade, and tumor histology, which were used to identify TNBC. We tested 4 frontier models: GPT-4o mini (released July 18, 2024), GPT-4.1 nano (released April 14, 2025), GPT-5 nano (released August 7, 2025), and Gemini 2.5 Flash-Lite.Results
The designed framework was able to extract relevant biomarkers and clinicopathological attributes from unstructured pathology reports and allowed for the automated identification of patients with TNBC. Gemini 2.5 Flash-Lite showed superior performance in the extraction of clinicopathological attributes. For all models investigated, chain-of-thought (CoT) prompting was shown to outperform other strategies, such as zero-shot and few-shot prompting, for both biomarker extraction and TNBC classification. GPT-4o mini using CoT prompts reported the highest performance for TNBC classification.Conclusions
Using prompt-engineering techniques based on LLMs proved to be an efficient method of translating unstructured breast cancer pathology reports into structured clinical information. Moreover, it can be used to accurately identify the TNBC subtype.
Related
- Structured information extraction from geoscientific literature with GeoExtractor
- A Knowledge Graph Framework for Linking Health Assessment Scales and Scientific Literature in Low-Annotation Settings: Development and Evaluation Study
- Large Language Models for Structured Information Extraction from German Histopathology Reports - Hepatocellular Carcinoma
- Development of a large language model clinical variable extraction pipeline for the study of lymphedema.
- Extraction, Structure–Activity Relationships, and Modification of Plant-Derived Polysaccharides: An Integrated Framework for Evidence-Based Method Selection and Bioactivity Optimization—A Review
BibTeX
@article{jain2026large,
title = {{Large Language Model Framework for Structured Biomarker Extraction and Triple-Negative Breast Cancer Identification From Pathology Reports: Development and Evaluation Study.}},
author = {Nirmit Jain and Trisha Annambhotla and Akshara Siddharthan and Harshini Kanala and Armaan Budhiraja and Manglam Goutam Sinha and Devyani Charan and Muzaffar Ahmad Dar and Trupti Patel and Biji C L},
journal = {JMIR formative research},
year = {2026},
month = oct,
doi = {10.2196/97117},
url = {https://europepmc.org/article/MED/42913472},
note = {CC BY},
}
RIS
TY - JOUR
TI - Large Language Model Framework for Structured Biomarker Extraction and Triple-Negative Breast Cancer Identification From Pathology Reports: Development and Evaluation Study.
AU - Nirmit Jain
AU - Trisha Annambhotla
AU - Akshara Siddharthan
AU - Harshini Kanala
AU - Armaan Budhiraja
AU - Manglam Goutam Sinha
AU - Devyani Charan
AU - Muzaffar Ahmad Dar
AU - Trupti Patel
AU - Biji C L
PY - 2026
DA - 2026/10/23
JO - JMIR formative research
DO - 10.2196/97117
UR - https://europepmc.org/article/MED/42913472
AB - Background Triple-negative breast cancer (TNBC) is an aggressive molecular subtype of breast cancer that needs to be identified accurately from pathology reports to inform decision-making. Large language models (LLMs) have been reported to show great potential in the automatic extraction of important oncology information from unstructured medical text.Objective We aimed to create and test an LLM-based approach for automatic biomarker extraction and TNBC subtype classification based on breast cancer pathology reports using prompt-engineering techniques.Methods In total, 532 breast cancer pathology reports from The Cancer Genome Atlas (TCGA) were used. Our approach extracted structured oncology features, such as estrogen receptor status, progesterone receptor status, HER2 status, tumor size, tumor grade, and tumor histology, which were used to identify TNBC. We tested 4 frontier models: GPT-4o mini (released July 18, 2024), GPT-4.1 nano (released April 14, 2025), GPT-5 nano (released August 7, 2025), and Gemini 2.5 Flash-Lite.Results The designed framework was able to extract relevant biomarkers and clinicopathological attributes from unstructured pathology reports and allowed for the automated identification of patients with TNBC. Gemini 2.5 Flash-Lite showed superior performance in the extraction of clinicopathological attributes. For all models investigated, chain-of-thought (CoT) prompting was shown to outperform other strategies, such as zero-shot and few-shot prompting, for both biomarker extraction and TNBC classification. GPT-4o mini using CoT prompts reported the highest performance for TNBC classification.Conclusions Using prompt-engineering techniques based on LLMs proved to be an efficient method of translating unstructured breast cancer pathology reports into structured clinical information. Moreover, it can be used to accurately identify the TNBC subtype.
SN - 2561-326X
ER -