A software pipeline for medical information extraction with large language models, open source and suitable for oncology
Top Cited Papers
Open Access
- 17 September 2025
- journal article
- review article
- Published by Springer Nature in npj Precision Oncology
- Vol. 9 (1) , 1-12
Abstract
In medical oncology, text data, such as clinical letters or procedure reports, is stored in an unstructured way, making quantitative analysis difficult. Manual review or structured information retrieval is time-consuming and costly, whereas Large Language Models (LLMs) offer new possibilities in natural language processing for structured Information Extraction (IE) from medical free text. This protocol describes a workflow (LLM-AIx) for extracting predefined clinical entities from unstructured oncology text using privacy-preserving LLMs. It addresses a key barrier in clinical research and care by enabling efficient information extraction to support decision-making and large-scale data analysis. It runs on local hospital infrastructure, eliminating the need to transfer patient data externally. We demonstrate its utility on 100 pathology reports from The Cancer Genome Atlas (TCGA) for TNM stage extraction. LLM-AIx requires no programming skills and offers a user-friendly interface for rapid, structured data extraction from clinical free text.Keywords
Funding Information
- European Union’s Horizon Europe and innovation programme (101079894)
- German Federal Ministry of Research, Technology and Space BMFTR (01EO2101)
This publication has 35 references indexed in Scilit:
- Natural language processing: state of the art, current trends and challengesMultimedia Tools and Applications, 2022
- Impact of ≥ 0.1-mm free resection margins on local intramural residual cancer after local excision of T1 colorectal cancerEndoscopy International Open, 2022
- Exploring the impact of cancer registry completeness on international cancer survival differences: a simulation studyBritish Journal of Cancer, 2020
- Endoscopic Recognition and Management Strategies for Malignant Colorectal Polyps: Recommendations of the US Multi-Society Task Force on Colorectal CancerGastrointestinal Endoscopy, 2020
- Should free-text data in electronic medical records be shared for research? A citizens’ jury study in the UKJournal of Medical Ethics, 2020
- Colorectal polypectomy and endoscopic mucosal resection (EMR): European Society of Gastrointestinal Endoscopy (ESGE) Clinical GuidelineEndoscopy, 2017
- Achieving Coordinated Care for Patients With Complex Cases of Cancer: A Multiteam System ApproachJournal of Oncology Practice, 2016
- Is omission of free text records a possible source of data loss and bias in Clinical Practice Research Datalink studies? A case–control studyBMJ Open, 2016
- Availability of Structured and Unstructured Clinical Data for Comparative Effectiveness Research and Quality Improvement: A Multi-Site AssessmenteGEMs (Generating Evidence & Methods to improve patient outcomes), 2014
- Mining electronic health records: towards better research applications and clinical careNature Reviews Genetics, 2012