Electronic health records (EHR) contain large volumes of unstructured text, requiring the application of Information Extraction (IE) technologies to enable clinical analysis. We present the open-source Medical Concept Annotation Toolkit (MedCAT) that provides: a) a novel self-supervised machine learning algorithm for extracting concepts using any concept vocabulary including UMLS/SNOMED-CT; b) a feature-rich annotation interface for customising and training IE models; and c) integrations to the broader CogStack ecosystem for vendor-agnostic health system deployment. We show improved performance in extracting UMLS concepts from open datasets (F1:0.448-0.738 vs 0.429-0.650). Further real-world validation demonstrates SNOMED-CT extraction at 3 large London hospitals with self-supervised training over ~8.8B words from ~17M clinical records and further fine-tuning with ~6K clinician annotated examples. We show strong transferability (F1 > 0.94) between hospitals, datasets, and concept types indicating cross-domain EHR-agnostic utility for accelerated clinical and research use cases.
@article{arxiv.2010.01165,
title = {Multi-domain Clinical Natural Language Processing with MedCAT: the Medical Concept Annotation Toolkit},
author = {Zeljko Kraljevic and Thomas Searle and Anthony Shek and Lukasz Roguski and Kawsar Noor and Daniel Bean and Aurelie Mascio and Leilei Zhu and Amos A Folarin and Angus Roberts and Rebecca Bendayan and Mark P Richardson and Robert Stewart and Anoop D Shah and Wai Keong Wong and Zina Ibrahim and James T Teo and Richard JB Dobson},
journal= {arXiv preprint arXiv:2010.01165},
year = {2021}
}