Search

A medical lexicon of 14013 pairs of technical word forms and the corresponding simpli-fied synonym or definition. It is aimed at automatic text simplification in Spanish. A subset of the lexicon (4642 term entries) was also normalized to Unified Medical Language System (UMLS) concept unique identifiers (CUIs). Note that the number of inflected forms was reduced after revision by experts, with regard to the version used in the published article (Campillos-Llanos et al. 2024). This dataset was collected in the CLARA-MeD project, with the goal of simplifying medical texts in the Spanish language and reduce the language barrier to patient's informed decision making. In particular, the project aims at developing linguistic resources for automatic medical term simplification in Spanish; and conducting experiments in automatic text simplification.

This dataset contains 1200 manually simplified sentences (144 019 tokens) from clinical trials in Spanish. A total of 1040 announcements from the European Clinical Trials Register (EudraCT) were analyzed to select sentences with ambiguities or exceeding 25 words. Simplification criteria were devised in an annotation guideline, which is released publicly along the dataset., This resource was collected in the CLARA-MeD project, with the goal of simplifying medical texts in the Spanish language and reduce the language barrier to patient's informed decision making. In particular, the project aims at developing linguistic resources for automatic medical term simplification in Spanish; and conducting experiments in automatic text simplification.

[EN] We introduce a dataset with 1200 manually simplified sentences (144 019 tokens) from clinical trials in Spanish. A total of 1040 announcements from the European Clinical Trials Register (EudraCT) were analyzed to select sentences with ambiguities or exceeding 25 words. Simplification criteria were devised in an annotation guideline, which is released publicly along with the dataset. We obtained two versions: syntactically simplified sentences, and sentences with syntactic and lexical simplification. We report a quantitative, a qualitative and a human evaluation, in which three independent evaluators assessed the grammaticality/fluency, semantic adequacy and overall simplification. Results show that the resource is suitable for advancing research on automatic simplification of medical texts., [ES] We introduce a dataset with 1200 manually simplified sentences (144 019 tokens) from clinical trials in Spanish. A total of 1040 announcements from the European Clinical Trials Register (EudraCT) were analyzed to select sentences with ambiguities or exceeding 25 words. Simplification criteria were devised in an annotation guideline, which is released publicly along with the dataset. We obtained two versions: syntactically simplified sentences, and sentences with syntactic and lexical simplification. We report a quantitative, a qualitative and a human evaluation, in which three independent evaluators assessed the grammaticality/fluency, semantic adequacy and overall simplification. Results show that the resource is suitable for advancing research on automatic simplification of medical texts.

Patients can not always completely understand medical documents given the myriad of technical terms they contain. Automatic text simplification techniques can help, but they must guarantee that the content is transmitted rigorously and not creating wrong information. In this work, we tested: 1) lexicon-based simplification approaches, using a Spanish lexicon of technical and laymen terms collected for this task (SimpMedLexSp); 2) deep-learning (DL) based methods, with BART-based and prompt-learning-based models; and 3) a combination of both techniques. As a test set, we used 5000 parallel (technical and laymen) sentence pairs: 3800 manually aligned sentences from the CLARA-MeD corpus; and 1200 sentences from clinical trials simplified by linguists. We conducted a quantitative evaluation with standard measures (BLEU, ROUGE and SARI) and a human evaluation, in which eleven subjects scored the simplification output of several methods. In our experiments, the lexicon improved the quantitative results when combined with the DL models. The simplified sentences using only the lexicon were assessed with the highest scores regarding semantic adequacy; however, their fluency needs to be improved. The prompt-method had similar ratings in this aspect and in simplification. We make available the models and the data to reproduce our results.

1. El día 11 de mayo de 2023 tuvo lugar en el Salón de Actos del CCHS un evento convocado por Isabel Díaz, Vicepresidenta Adjunta de Internacionalización y Cooperación del CSIC. El acto tenía un doble objetivo: (a) informar a todos los investigadores y técnicos de Humanidades y Ciencias Sociales del CSIC sobre DARIAH y CLARIN, las dos grandes infraestructuras europeas en HHDD y CCSS en las que próximamente se integrará España, y (b) ofrecer un escaparate de algunos de los proyectos en Humanidades Digitales y Ciencias Sociales que actualmente se están desarrollando en el CSIC. EL acto fue coordinado por Daniel Riaño Rufilanchas (científico titular del ILC) y estuvo presidido por Marina Villegas (directora del CCHS), 2. Después de un largo periodo de preparación, a mediados de 2023 finalmente se habían perfilado suficientemente los instrumentos legales que permiten la integración de nuestro país en estas dos ERICs, de las que de forma casi inexplicable estábamos ausentes. CLARIN (Common Language Resources and Technology Infrastructure) comenzó a funcionar con 9 países miembros en 2012 y en 2016 recibió el status de landmark en el European Research Infrastructures Roadmap. Se describe como una infraestructura digital que ofrece datos, herramientas y servicios para sostener la investigación basada en recursos lingüísticos. De forma semejante DARIAH (Digital Research Infrastructure for the Arts and Humanities) entró en el ESFRI Roadmap en 2006 y se estableció como ERIC 2014. En 2016 obtuvo también el estatus de Landmark y fue oficialmente ungido como pan-European hub of scientific excellence. De forma genérica DARIAH describe su misión como la de impulsar y dar apoyo a la investigación y la enseñanza dirigida a las artes y las Humanidades (en un sentido extenso) basada en recursos digitales. Orgánicamente se describe DARIAH como una red de personas, expertizaje, información, conocimiento, contenido, métodos, herramientas y tecnologías de sus países miembros. Isabel Díaz comentó los retos y oportunidades que suponía para el CSIC su participación destacada en ambas infraeestructuras, y la necesidad de conseguir la implicación activa de un número suficiente de investigadores y técnicos. Daniel Riaño resumió algunas de las características de la organización y funcionamiento de ambos ERICS, y qué forma iba tomando la participación de los nodos españoles en ella. En la primera parte del acto participó igualmente Emilio Cano, investigador del CENIM y coordinador Nacional de E-RIHS, quien explicó su experiencia en la incorporación de España a tal infraestructura., 3. En la segunda parte del acto se llevó a cabo la presentación, por parte de 35 investigadores de casi todos los institutos del CSIC dedicados a las HHDD y las CCSS, de unos 50 proyectos actualmente en curso o recién finalizados dentro de estas especialidades que dedican una especial atención a las herramientas o los desarrollos digitales. Fueron presentaciones de solo cinco minutos cada una, la mayoría de carácter presencial, en las que con un estilo directo y dinámico los investigadores y técnicos ofrecieron un resumen de su proyecto y los recursos tecnológicos implicados en ellos. Sin llegar a ser un panel exhaustivo de todos los proyectos en marcha con tales características en todos los centros e institutos del CSIC, se trata de un impresionante escaparate de la actividad que nuestra institución viene llevando a cabo para la aplicación de las más recientes técnicas, recursos, estándares y procedimientos tecnológicos a la investigación en Humanidades y Ciencias Sociales.

[Background] Medical lexicons enable the natural language processing (NLP) of health texts. Lexicons gather terms and concepts from thesauri and ontologies, and linguistic data for part-of-speech (PoS) tagging, lemmatization or natural language generation. To date, there is no such type of resource for Spanish., [Construction and content] This article describes an unified medical lexicon for Medical Natural Language Processing in Spanish. MedLexSp includes terms and inflected word forms with PoS information and Unified Medical Language System® (UMLS) semantic types, groups and Concept Unique Identifiers (CUIs). To create it, we used NLP techniques and domain corpora (e.g. MedlinePlus). We also collected terms from the Dictionary of Medical Terms from the Spanish Royal Academy of Medicine, the Medical Subject Headings (MeSH), the Systematized Nomenclature of Medicine - Clinical Terms (SNOMED-CT), the Medical Dictionary for Regulatory Activities Terminology (MedDRA), the International Classification of Diseases vs. 10, the Anatomical Therapeutic Chemical Classification, the National Cancer Institute (NCI) Dictionary, the Online Mendelian Inheritance in Man (OMIM) and OrphaData. Terms related to COVID-19 were assembled by applying a similarity-based approach with word embeddings trained on a large corpus. MedLexSp includes 100 887 lemmas, 302 543 inflected forms (conjugated verbs, and number/gender variants), and 42 958 UMLS CUIs. We report two use cases of MedLexSp. First, applying the lexicon to pre-annotate a corpus of 1200 texts related to clinical trials. Second, PoS tagging and lemmatizing texts about clinical cases. MedLexSp improved the scores for PoS tagging and lemmatization compared to the default Spacy and Stanza python libraries., [Conclusions] The lexicon is distributed in a delimiter-separated value file; an XML file with the Lexical Markup Framework; a lemmatizer module for the Spacy and Stanza libraries; and complementary Lexical Record (LR) files. The embeddings and code to extract COVID-19 terms, and the Spacy and Stanza lemmatizers enriched with medical terms are provided in a public repository.

MedLexSp is an unified medical lexicon for Medical Natural Language Processing in Spanish. It includes terms and inflected word forms with part-of-speech information and Unified Medical Language System (UMLS) semantic types, groups and Concept Unique Identifiers (CUIs). To create it, we used Natural Language Processing techniques and domain corpora (e.g. MedlinePlus). We also collected terms from the Dictionary of Medical Terms from the Spanish Royal Academy of Medicine, the Medical Subject Headings (MeSH), the Systematized Nomenclature of Medicine – Clinical Terms (SNOMED-CT), the Medical Dictionary for Regulatory Activities Terminology (MedDRA), the International Classification of Diseases vs 10, the Anatomical Therapeutical Classification, the National Cancer Institute (NCI) Dictionary, the Online Mendelian Inheritance in Man (OMIM) and OrphaData. Terms related to COVID-19 were assembled by applying a similarity-based approach with word embeddings trained on a large corpus. This dataset was collected during the NLPMedTerm project and the CLARA-MeD project, with the goal of creating a lexical resource for medical text processing in the Spanish language., MedLexSp is an unified medical lexicon for Medical Natural Language Processing in Spanish. It includes 100 887 lemmas, 302 543 inflected forms (conjugated verbs, and number/gender variants), and 42 958 Unified Medical Language System (UMLS) Concept Unique Identifiers (CUIs)., Spain, Latin America and United States of America (data from MedlinePlus Spanish and the Spanish version of the National Cancer Institute Dictionary of Medical Terms).

MedLexSp is an unified medical lexicon for Medical Natural Language Processing in Spanish. It includes terms and inflected word forms with part-of-speech information and Unified Medical Language System (UMLS) semantic types, groups and Concept Unique Identifiers (CUIs). To create it, we used Natural Language Processing techniques and domain corpora (e.g. MedlinePlus). We also collected terms from the Dictionary of Medical Terms from the Spanish Royal Academy of Medicine, the Medical Subject Headings (MeSH), the Systematized Nomenclature of Medicine – Clinical Terms (SNOMED-CT), the Medical Dictionary for Regulatory Activities Terminology (MedDRA), the International Classification of Diseases vs 10, the Anatomical Therapeutical Classification, the National Cancer Institute (NCI) Dictionary, the Online Mendelian Inheritance in Man (OMIM) and OrphaData. Terms related to COVID-19 were assembled by applying a similarity-based approach with word embeddings trained on a large corpus. This dataset was collected during the NLPMedTerm project and the CLARA-MeD project, with the goal of creating a lexical resource for medical text processing in the Spanish language., MedLexSp is an unified medical lexicon for Medical Natural Language Processing in Spanish. It includes 100 887 lemmas, 302 543 inflected forms (conjugated verbs, and number/gender variants), and 42 958 Unified Medical Language System (UMLS) Concept Unique Identifiers (CUIs)., Spain, Latin America and United States of America (data from MedlinePlus Spanish and the Spanish version of the National Cancer Institute Dictionary of Medical Terms).

A collection of 24 298 pairs of professional and simplified texts (>96 million tokens) for automatic medical text simplification in Spanish. A parallel corpus with a subset of 3800 sentence pairs of professional and laymen variants (149 862 tokens) is released as a benchmark for medical text simplification. This dataset was collected in the CLARA-MeD project, with the goal of simplifying medical texts in the Spanish language and reducing the language barrier to patient's informed decision making. In particular, the project aims at developing linguistic resources for automatic medical term simplification in Spanish; and conducting experiments in automatic text simplification.

A collection of 1200 texts (292 173 tokens) about clinical trials studies and clinical trials announcements in Spanish: - 500 abstracts from journals published under a Creative Commons license, e.g. available in PubMed or the Scientific Electronic Library Online (SciELO). - 700 clinical trials announcements published in the European Clinical Trials Register and Repositorio Español de Estudios Clínicos. Texts were annotated 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). 46 699 entities were annotated (13.98% are nested entities). 10% of the corpus was doubly annotated, and inter-annotator agreement (IAA) achieved a mean F-measure of 85.65% (±4.79, strict match) and a mean F-measure of 93.94% (±3.31, relaxed match).

[Background] The 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., [Methods] We 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., [Results] This 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., [Conclusions] Our 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.

Virtual patient software allows health professionals to practise their skills by interacting with tools simulating clinical scenarios. A natural language dialogue system can provide natural interaction for medical history-taking. However, the large number of concepts and terms in the medical domain makes the creation of such a system a demanding task. We designed a dialogue system that stands out from current research by its ability to handle a wide variety of medical specialties and clinical cases. To address the task, we designed a patient record model, a knowledge model for the task and a termino-ontological model that hosts structured thesauri with linguistic, terminological and ontological knowledge. We used a frame- and rule-based approach and terminology-rich resources to handle the medical dialogue. This work focuses on the termino-ontological model, the challenges involved and how the system manages resources for the French language. We adopted a comprehensive approach to collect terms and ontological knowledge, and dictionaries of affixes, synonyms and derivational variants. Resources include domain lists containing over 161,000 terms, and dictionaries with over 959,000 word/concept entries. We assessed our approach by having 71 participants (39medical doctors and 32 non-medical evaluators) interact with the system and use 35 cases from 18 specialities. We conducted a quantitative evaluation of all components by analysing interaction logs (11,834 turns). Natural language understanding achieved an F-measure of 95.8%. Dialogue management provided on average 74.3 (±9.5)% of correct answers. We performed a qualitative evaluation by collecting 171 five-point Likert scale questionnaires. All evaluated aspects obtained mean scores above the Likert mid-scale point. We analysed the vocabulary coverage with regard to unseen cases: the system covered 97.8% of their terms. Evaluations showed that the system achieved high vocabulary coverage on unseen cases and was ass