Search

Background. Nowadays, with the digitalization of healthcare systems, huge amounts of clinical narratives are available. However, despite the wealth of information contained in them, interoperability and extraction of relevant information from documents remains a challenge. Objective. This work presents an approach towards automatically standardizing Spanish Electronic Discharge Summaries (EDS) following the HL7 Clinical Document Architecture. We address the task of section annotation in EDSs written in Spanish, experimenting with three different approaches, with the aim of boosting interoperability across healthcare systems and hospitals. Methods. The paper presents three different methods, ranging from a knowledge-based solution by means of manually constructed rules to supervised Machine Learning approaches, using state of the art algorithms like the Perceptron and transfer learning-based Neural Networks. Results. The paper presents a detailed evaluation of the three approaches on two different hospitals. Overall, the best system obtains a 93.03% F-score for section identification. It is worth mentioning that this result is not completely homogeneous over all section types and hospitals, showing that cross-hospital variability in certain sections is bigger than in others. Conclusions. As a main result, this work proves the feasibility of accurate automatic detection and standardization of section blocks in clinical narratives, opening the way to interoperability and secondary use of clinical data.

The aim of this paper is to present our approach (IxaMed) in the PharmacoNER 2019 task. The task consists of identifying chemical, drug, and gene/protein mentions from clinical case studies written in Spanish. The evaluation of the task is divided in two scenarios: one corresponding to the detection of named entities and one corresponding to the indexation of named entities that have been previously identified. In order to identify named entities we have made use of a Bi-LSTM with a CRF on top in combination with different types of word embeddings. We have achieved our best result (86.81 F-Score) combining pretrained word embeddings of Wikipedia and Electronic Health Records (50M words) with contextual string embeddings of Wikipedia and Electronic Health Records. On the other hand, for the indexation of the named entities we have used the Levenshtein distance obtaining a 85.34 F-Score as our best result.

Hizkuntzaren Prozesamenduan kokatzen den Dependentzia Uniber-tsalen proiektuaren helburua da hainbat hizkuntzatan sortu diren dependentzia-ereduan oinarritutako zuhaitz-bankuak etiketatze-eskema estandar berera egokitzea. Artikulu honetan, eredu horretara automatikoki egokitu den euskarazko zuhaitz-bankua aurkez-ten da; halaber, egokitzapen-lan hori nola gauzatu den deskribatzen da eta, azkenik, ho-rretan oinarrituta, azaltzen da zer antzekotasun eta zer desberdintasun diren jatorrizko zuhaitza-bankuaren eta Dependentzia Unibertsalen eredura egokitutako zuhaitz-ban-kuaren artean.; In the Natural Language Processing research area, the aim of the Uni-versal Dependencies project is to convert dependency based treebanks developed in different languages into the same standard tagging scheme. This article presents the automatic conversion of the previously existing Basque treebank into this universal tagging scheme. This work describes how the conversion process has been carried out and highlights the similarities and differences between the original Basque treebank and the Universal Dependency based version of it.

Natural Language Processing (NLP) is a field that joins computer science and linguistics in an attempt to mimic, artificially, human language understanding. This paper applied NLP in the medical domain. The trigger that motivated this research was an expert reading an article about a rare disease who was interested in finding related documents. Being aware of the fact that language boundaries often limit, unnecessarily, the amount of information found, the goal of our work is to retrieve information without bounding to translation methods. Semantic similarity approaches offer a framework to represent related words and sentences in a dense space. In this work, we turned to cross-lingual dense spaces to represent bilingual documents in a shared dense space. Our approach helped to retrieve both intra-and cross-lingual documents just resting upon a few parallel documents to infer the optimal mapping from. From the experimental results we learned that an important issue is to keep aligned the mapping space and the cross-lingual search space. The cosine similarity outperforms both Euclidean and Manhattan distance. The results obtained in our preliminary experiments suggest that, although there is room for improvement, our approach performs satisfactorily achieving a P@10 of 71.72 searching English documents and returning Spanish related documents and 70.80 in the opposite direction. Index Terms-Clinical text mining, Cross-lingual information-retrieval, Natural language processing