Thesaurus-based word embeddings for automated biomedical literature classification.

The special nature, volume and broadness of biomedical literature pose barriers for automated classification methods. On the other hand, manually indexing is time-consuming, costly and error prone. We argue that current word embedding algorithms can be efficiently used to support the task of biomedical text classification even in a multilabel setting, with many distinct labels. The ontology representation of Medical Subject Headings provides machine-readable labels and specifies the dimensionality of the problem space. Both deep- and shallow network approaches are implemented. Predictions are determined by the similarity between extracted features from contextualized representations of abstracts and headings. The addition of a separate classifier for transfer learning is also proposed and evaluated. Large datasets of biomedical citations are harvested for their metadata and used for training and testing. These automated approaches are still far from entirely substituting human experts, yet they can be useful as a mechanism for validation and recommendation. Dataset balancing, distributed processing and training parallelization in GPUs, all play an important part regarding the effectiveness and performance of proposed methods.

A comparative study of the origin, structure, and indexing language of the Persian and English keywords of articles indexed in the IranMedex database and their compliance with the Persian medical thesaurus and Medical Subject Headings.

INTRODUCTION: In the present era, thesauri as tools in indexing play an effective role in integrating retrieval preventing fragmentation as well as a multiplicity of terminologies and also in providing information content of documents. GOALS: This study aimed to investigate the keywords of articles indexed in IranMedex in terms of origin, structure and indexing situation and their Compliance with the Persian Medical Thesaurus and Medical Subject Headings (MeSH). MATERIALS AND METHODS: This study is an applied research, and a survey has been conducted. Statistical population includes 32,850 Persian articles which are indexed in the IranMedex during the years 1385-1391. 379 cases were selected as sample of the study. Data collection was done using a checklist. In analyzing the findings, the SPSS Software were used. FINDINGS: Although there was no significant difference in terms of indexing origin between the proportion of different types of the Persian and English keywords of articles indexed in the IranMedex, the compliance rates of the Persian and English keywords with the Persian medical thesaurus and MeSH were different in different years. In the meantime, the structure of keywords is leaning more towards phrase structure, and a single word structure and the majority of keywords are selected from the titles and abstracts. CONCLUSION: The authors' familiarity with the thesauri and controlled tools causes homogeneity in assigning keywords and also provides more precise, faster, and easier retrieval of the keywords. It's suggested that a mixture of natural and control languages to be used in this database in order to reach more comprehensive results.

Práctica Catalográfica en el DeCS

Por la imposibilidad de usar convenientemente el tesauro Descriptores en Ciencias de la Salud (DeCS) en la asignación de epígrafes durante el proceso de catalogación, se elabora un conjunto de instrucciones técnicas, encaminadas a posibilitar que los bibliotecarios del Sistema Nacional de Información de Ciencias Médicas puedan utilizarlo como epigrafiario, dado que, en su mayoría, éstos no disponen de sistemas automatizados para el procesamiento de la información, por lo que sustentan el procedimiento de búsqueda y recuperación en la ficha catalográfica. Se aborda la representación temática de los documentos mediante epígrafes y sus principios básicos, así como las reglas para la coordinación de epígrafes y subepígrafes y las restricciones para el empleo de algunos tipos de encabezamientos. Se recomienda la aplicación del anexo Práctica catalográfica en el DeCS, preparado sobre la base del Cataloging practices del MeSH anotado, como estrategia para eliminar las contradicciones generadas por la ausencia de disposiciones adecuadas para representar todos los aspectos abordados en los documentos, sujetos a la asignación de epígrafes y subepígrafes.

Due to the failure of using adequately the thesaurus «Descriptores en Ciencias de la Salud (DeCS)» in the assignment of epigraphs during the cataloging process, a number of technical instructions are drawn. These instructions enable the librarians from the National System of Medical Sciences Information to use it as a dictionary of epigraphs because most of them do not have automatic systems for the processing of information so that they support themselves in the search and recovery procedures on the cataloging index card. The subject representation of documents through epigraphs and its basic principles are discussed as well as the rules for the coordination of epigraphs and subepigraphs and the restrictions in using some of the types of subheadings. The implementation of the annex Práctica catalográfica en el DeCS, based upon the Cataloging Practices of MeSH is recommended as a strategy to eliminate the contradictions generated by the lack of appropiate dispositions to represent all the aspects discussed in the documents and submitted to the assignment of epigraphs and subepigraphs.