A clinical trials corpus annotated with UMLS entities to enhance the access to evidence-based medicine

BMC Medical Informatics and Decision Making

Adrián Capllonch-Carrión¹  Antonio Moreno-Sandoval²  Leonardo Campillos-Llanos²  Ana Valverde-Mateos³ 

[1]Complejo Asistencial Hospital Benito Menni., C/Jardines 1, 28350, Ciempozuelos, Madrid, Spain

[2]Computational Linguistics Laboratory, Universidad Autónoma de Madrid, C/Francisco Tomás y Valiente 1. Cantoblanco Campus, 28049, Madrid, Spain

[3]Medical Terminology Unit, Spanish Royal Academy of Medicine., C/Arrieta 12, 28013, Madrid, Spain

关键词: Clinical Trials;    Evidence-Based Medicine;    Semantic Annotation;    Inter-Annotator Agreement;    Natural Language Processing;   

DOI  :  10.1186/s12911-021-01395-z

来源: Springer

【 摘 要 】

BackgroundThe large volume of medical literature makes it difficult for healthcare professionals to keep abreast of the latest studies that support Evidence-Based Medicine. Natural language processing enhances the access to relevant information, and gold standard corpora are required to improve systems. To contribute with a new dataset for this domain, we collected the Clinical Trials for Evidence-Based Medicine in Spanish (CT-EBM-SP) corpus.MethodsWe annotated 1200 texts about clinical trials with entities from the Unified Medical Language System semantic groups: anatomy (ANAT), pharmacological and chemical substances (CHEM), pathologies (DISO), and lab tests, diagnostic or therapeutic procedures (PROC). We doubly annotated 10% of the corpus and measured inter-annotator agreement (IAA) using F-measure. As use case, we run medical entity recognition experiments with neural network models.ResultsThis resource contains 500 abstracts of journal articles about clinical trials and 700 announcements of trial protocols (292 173 tokens). We annotated 46 699 entities (13.98% are nested entities). Regarding IAA agreement, we obtained an average F-measure of 85.65% (±4.79, strict match) and 93.94% (±3.31, relaxed match). In the use case experiments, we achieved recognition results ranging from 80.28% (±00.99) to 86.74% (±00.19) of average F-measure.ConclusionsOur results show that this resource is adequate for experiments with state-of-the-art approaches to biomedical named entity recognition. It is freely distributed at: http://www.lllf.uam.es/ESP/nlpmedterm_en.html. The methods are generalizable to other languages with similar available sources.

【 授权许可】

CC BY