First Steps towards Building a Medical Lexicon for Spanish with Linguistic and Semantic Information

Abstract

We report the work-in-progress of collecting MedLexSp, an unified medical lexicon for the Spanish language, featuring terms and inflected word forms mapped to Unified Medical Language System (UMLS) Concept Unique Identifiers (CUIs), semantic types and groups. First, we leveraged a list of term lemmas and forms from a previous project, and mapped them to UMLS terms and CUIs. To enrich the lexicon, we used both domain-corpora (e.g. Summaries of Product Characteristics and MedlinePlus) and natural language processing techniques such as string distance methods or generation of syntactic variants of multi-word terms. We also added term variants by mapping their CUIs to missing items available in the Spanish versions of standard thesauri (e.g. Medical Subject Headings and World Health Organization Adverse Drug Reactions terminology). We enhanced the vocabulary coverage by gathering missing terms from resources such as the Anatomical Therapeutical Classification, the National Cancer Institute (NCI) Dictionary of Cancer Terms, Or-phaData, or the Nomenclátor de Prescripción for drug names. Part-of-Speech information is being included in the lexicon, and the current version amounts up to 76 454 lemmas and 203 043 inflected forms (including conjugated verbs, number and gender variants), corresponding to 30 647 UMLS CUIs. MedLexSp is distributed freely for research purposes.

Supporting the classification of patients in public hospitals in Chile by designing, deploying and validating a system based on natural language processing

“…In particular, for the clinical domain, several authors have explored combinations of general language, biomedical literature, and clinical corpora [ 32 – 34 ]. For the clinical Spanish language there is a lack of language resources, with the few corpora coming predominantly from Spain [ 18 , 35 , 36 ]. In the work presented here, we extrinsically tested the Spanish Billion Word Corpus Embeddings (computed over 2,024,959,560 tokens) [ 37 ], the Chilean Biomedical corpus (computed over 67,246,025 tokens) [ 38 ], and the general dataset described earlier (computed over 56,079,828 tokens), with the latest showing the best classification performance (see “ Results ” section).…”

Optimizing healthcare system by amalgamation of text processing and deep learning: a systematic review

“…Few authors have researched this issue and achieved good results. For example, Llanos LC (2019) [ 62 ] used hybrid NLP methods such as string distance methods or the generation of syntactic variants of standard thesauri in the Spanish language. The author expanded vocabulary coverage by gathering missing terms from various medical resources and matching term variants to missing items available in Spanish versions of the standard thesauri.…”

Procesamiento de lenguaje natural para texto clínico en español: el caso de las listas de espera en Chile

“…Actualmente, contamos con una fracción de 2.000 interconsultas médicas anotadas en el Corpus de Lista de Espera Chilena, cuyas entidades médicas fueron normalizadas de forma automatizada empleando el léxico MedLexSp 38 , 39 asignándole uno o múltiples códigos únicos de identificación a cada entidad. Este recurso estará disponible para su libre uso próximamente.…”