• Publications
  • Influence
Overview of CLEF eHealth Task 1 - SpRadIE: A challenge on information extraction from Spanish Radiology Reports
TLDR
The challenge aims at providing a standard evaluation framework to contribute to the advancement in the field of clinical natural language processing in Spanish, and is the first public challenge for named entity recognition and hedge cue detection for radiology reports in Spanish.
Pathways to mental health care in Italy: Results from a multicenter study
TLDR
Although general practitioners and hospital doctors are still the main referral point for mental health care, a greater proportion of patients are first seen in private settings or directly reach mental health centers, compared to previous surveys conducted in Italy.
Annotation of Entities and Relations in Spanish Radiology Reports
TLDR
A manual annotation of radiology reports written in Spanish is performed and the corpus, the annotation schema, the annotated guidelines and further insight of the data are presented.
An Approach for Automatic Classification of Radiology Reports in Spanish
TLDR
This work presents an approach to classify RadLex, a lexicon of English radiology terms, and NLP techniques to identify the occurrence of pathological findings in radiology reports written in Spanish into two sets: those that indicate pathological findings and the ones that do not.
Overview of the CLEF eHealth Evaluation Lab 2021
TLDR
The resources created for these tasks and evaluation methodology adopted are described and the organizers have made data and tools associated with the lab tasks available for future research and development.
Automatic Detection of Negated Findings in Radiological Reports for Spanish Language: Methodology Based on Lexicon-Grammatical Information Processing
TLDR
Results show that there are minimal differences in favor of the algorithm developed using NooJ, but the quality and specificity of the data improves if lexical-grammatical information is added, and the methodology was compared with a Spanish version of NegEx.
Automatic Detection of Negated Findings with NooJ: First Results
TLDR
A methodology for the automatic detection of negated findings in radiological reports which takes into account semantic and syntactic descriptions, as well as morphological and Syntactic analysis rules is developed.
Creation of an Annotated Corpus of Spanish Radiology Reports
TLDR
This work provides some guidelines that could help other researchers to undertake similar tasks, and was conceived as an evaluation resource for named entity recognition and relation extraction algorithms, and as input for the use of supervised methods.