Suchergebnisse

Mención Internacional en el título de doctor ; Nowadays, with the increasing use of several drugs for the treatment of one or more different diseases (polytherapy) in large populations, the risk for drugs combinations that have not been studied in pre-authorization clinical trials has increased. This provides a favourable setting for the occurrence of drug-drug interactions (DDIs), a common adverse drug reaction (ADR) representing an important risk to patients safety, and an increase in healthcare costs. Their early detection is, therefore, a main concern in the clinical setting. Although there are different databases supporting healthcare professionals in the detection of DDIs, the quality of these databases is very uneven, and the consistency of their content is limited. Furthermore, these databases do not scale well to the large and growing number of pharmacovigilance literature in recent years. In addition, large amounts of current and valuable information are hidden in published articles, scientific journals, books, and technical reports. Thus, the large number of DDI information sources has overwhelmed most healthcare professionals because it is not possible to remain up to date on everything published about DDIs. Computational methods can play a key role in the identification, explanation, and prediction of DDIs on a large scale, since they can be used to collect, analyze and manipulate large amounts of biological and pharmacological data. Natural language processing (NLP) techniques can be used to retrieve and extract DDI information from pharmacological texts, supporting researchers and healthcare professionals on the challenging task of searching DDI information among different and heterogeneous sources. However, these methods rely on the availability of specific resources providing the domain knowledge, such as databases, terminological vocabularies, corpora, ontologies, and so forth, which are necessary to address the Information Extraction (IE) tasks. In this thesis, we have developed two semantic resources for the DDI domain that make an important contribution to the research and development of IE systems for DDIs. We have reviewed and analyzed the existing corpora and ontologies relevant to this domain, based on their strengths and weaknesses, we have developed the DDI corpus and the ontology for drug-drug interactions (named DINTO). The DDI corpus has proven to fulfil the characteristics of a high-quality gold-standard, and has demonstrated its usefulness as a benchmark for the training and testing of different IE systems in the SemEval-2013 DDIExtraction shared task. Meanwhile, DINTO has been used and evaluated in two different applications. Firstly, it has been proven that the knowledge represented in the ontology can be used to infer DDIs and their different mechanisms. Secondly, we have provided a proof-of-concept of the contribution of DINTO to NLP, by providing the domain knowledge to be exploited by an IE pilot prototype. From these results, we believe that these two semantic resources will encourage further research into the application of computational methods to the early detection of DDIs. This work has been partially supported by the Regional Government of Madrid under the Research Network MA2VICMR [S2009/TIC-1542], by the Spanish Ministry of Education under the project MULTIMEDICA [TIN2010-20644-C03-01] and by the European Commission Seventh Framework Programme under TrendMiner project [FP7-ICT287863]. ; Hoy en día ha habido un notable aumento del número de pacientes polimedicados que reciben simultáneamente varios fármacos para el tratamiento de una o varias enfermedades. Esta situación proporciona el escenario ideal para la prescripción de combinaciones de fármacos que no han sido estudiadas previamente en ensayos clínicos, y puede dar lugar a un aumento de interacciones farmacológicas (DDIs por sus siglas en inglés). Las interacciones entre fármacos son un tipo de reacción adversa que supone no sólo un riesgo para los pacientes, sino también una importante causa de aumento del gasto sanitario. Por lo tanto, su detección temprana es crucial en la práctica clínica. En la actualidad existen diversos recursos y bases de datos que pueden ayudar a los profesionales sanitarios en la detección de posibles interacciones farmacológicas. Sin embargo, la calidad de su información varía considerablemente de unos a otros, y la consistencia de sus contenidos es limitada. Además, la actualización de estos recursos es difícil debido al aumento que ha experimentado la literatura farmacológica en los últimos años. De hecho, mucha información sobre DDIs se encuentra dispersa en artículos, revistas científicas, libros o informes técnicos, lo que ha hecho que la mayoría de los profesionales sanitarios se hayan visto abrumados al intentar mantenerse actualizados en el dominio de las interacciones farmacológicas. La ingeniería informática puede representar un papel fundamental en este campo permitiendo la identificación, explicación y predicción de DDIs, ya que puede ayudar a recopilar, analizar y manipular grandes cantidades de datos biológicos y farmacológicos. En concreto, las técnicas del procesamiento del lenguaje natural (PLN) pueden ayudar a recuperar y extraer información sobre DDIs de textos farmacológicos, ayudando a los investigadores y profesionales sanitarios en la complicada tarea de buscar esta información en diversas fuentes. Sin embargo, el desarrollo de estos métodos depende de la disponibilidad de recursos específicos que proporcionen el conocimiento del dominio, como bases de datos, vocabularios terminológicos, corpora u ontologías, entre otros, que son necesarios para desarrollar las tareas de extracción de información (EI). En el marco de esta tesis hemos desarrollado dos recursos semánticos en el dominio de las interacciones farmacológicas que suponen una importante contribución a la investigación y al desarrollo de sistemas de EI sobre DDIs. En primer lugar hemos revisado y analizado los corpora y ontologías existentes relevantes para el dominio y, en base a sus potenciales y limitaciones, hemos desarrollado el corpus DDI y la ontología para interacciones farmacológicas DINTO. El corpus DDI ha demostrado cumplir con las características de un estándar de oro de gran calidad, así como su utilidad para el entrenamiento y evaluación de distintos sistemas en la tarea de extracción de información SemEval-2013 DDIExtraction Task. Por su parte, DINTO ha sido utilizada y evaluada en dos aplicaciones diferentes. En primer lugar, hemos demostrado que esta ontología puede ser utilizada para inferir interacciones entre fármacos y los mecanismos por los que ocurren. En segundo lugar, hemos obtenido una primera prueba de concepto de la contribución de DINTO al área del PLN al proporcionar el conocimiento del dominio necesario para ser explotado por un prototipo de un sistema de EI. En vista de estos resultados, creemos que estos dos recursos semánticos pueden estimular la investigación en el desarrollo de métodos computaciones para la detección temprana de DDIs. Este trabajo ha sido financiado parcialmente por el Gobierno Regional de Madrid a través de la red de investigación MA2VICMR [S2009/TIC-1542], por el Ministerio de Educación Español, a través del proyecto MULTIMEDICA [TIN2010-20644-C03-01], y por el Séptimo Programa Macro de la Comisión Europea a través del proyecto TrendMiner [FP7-ICT287863]. ; This work has been partially supported by the Regional Government of Madrid under the Research Network MA2VICMR [S2009/TIC-1542], by the Spanish Ministry of Education under the project MULTIMEDICA [TIN2010-20644-C03-01] and by the European Commission Seventh Framework Programme under TrendMiner project [FP7-ICT287863]. ; Programa Oficial de Doctorado en Ciencia y Tecnología Informática ; Presidente: Asunción Gómez Pérez.- Secretario: María Belén Ruiz Mezcua.- Vocal: Mariana Neves

Proceedings of: International Workshop on Semantic Evaluation. SemEval-2013 : Semantic Evaluation Exercises. Took place in 2013 June, 14-15, in Atlanta, Georgia (USA). The event Web site in http://www.cs.york.ac.uk/semeval-2013/ ; The DDIExtraction 2013 task concerns the recognition of drugs and extraction of drugdrug interactions that appear in biomedical literature. We propose two subtasks for the DDIExtraction 2013 Shared Task challenge: 1) the recognition and classification of drug names and 2) the extraction and classification of their interactions. Both subtasks have been very successful in participation and results. There were 14 teams who submitted a total of 38 runs. The best result reported for the first subtask was F1 of 71.5% and 65.1% for the second one. ; This research work has been supported by the Regional Government of Madrid under the Research Network MA2VICMR (S2009/TIC-1542), by the Spanish Ministry of Education under the project MULTIMEDICA (TIN2010-20644-C03-01). ; Publicado

The poster at: The Sixth International Biocuration Conference (Biocuration 2013), took at April 7–10, 2013 in Churchill College, Cambridge, UK. The event web site in: http://www.ebi.ac.uk/biocuration2013/content/home ; Ontologies are useful tools in text miming reserach tasks as a source of specialized vocabulary of terms and relationships in a given domain. Furthermore, formal knowledge representation propvieded by ontologies can be applied for new knowledge inference, wich can be exploited for biomedical research purposes. Drug-drug interactions (DDIs) are common adverse drug ractions having an important impact on patient safety and healthcare cost. ; This work was supported by the Regional Government of Madrid under the Research Network MA2VICMR [S2009/TIC-1542], by the Spanish Ministry of Education under the project MULTIMEDICA [TIN2010-20644-C03-01]. ; Publicado

This works is at: 5th International Conference on Corpus Linguistics (CILC2013), took place 2013, March 14-16, in Alicante (Spain). Conference web site: http://web.ua.es/en/cilc2013/ ; Natural language processing of pharmacological texts includes recognition of drug names and extraction of relationships between them. To this purpose, pharmacological annotated corpora are required. These corpora are usually semantically annotated by domain experts. However, other linguistic aspects should be considered to ensure the quality and consistency of the annotation. This paper introduces several linguistic phenomena affecting the annotation of both drug named entities and drug-drug interaction relationships that arose during the annotation process of the DDI corpus. The detailed documentation of these issues and the decisions on them will improve the quality of the annotated corpus and its usefulness for other researchers or users ; This work was supported by the Regional Government of Madrid under the Research Network MA2VICMR [S2009/TIC-1542] and by the Spanish Ministry of Economy under the project MULTIMEDICA [TIN2010-20644- C03-01]. ; Publicado

Proceedings of: The 6th International Workshop on Semantic Web Applications and Tools for Life Sciences (SWAT4LS 2013). Took place 2013, December 11-12, in Edinburgh, UK. The evnt Web site http://www.swat4ls.org/workshops/edinburgh2013/ ; Drug-drug interactions form a significant risk group for adverse effects associ-ated with pharmaceutical treatment. These interactions are often reported in the literature, however, they are sparsely represented in machine-readable re-sources, such as online databases, thesauri or ontologies. These knowledge sources play a pivotal role in Natural Language Processing (NLP) systems since they provide a knowledge representation about the world or a particular do-main. While ontologies for drugs and their effects have proliferated in recent years, there is no ontology capable of describing and categorizing drug-drug in-teractions. Moreover, there is no artifact that represents all the possible mecha-nisms that can lead to a DDI. To fill this gap we propose DINTO, an ontology for drug-drug interactions and their mechanisms. In this paper we describe the classes, relationships and overall structure of DINTO. The ontology is free for use and available at https://code.google.com/p/dinto/ ; This work was supported by the Regional Government of Madrid under the Research Network MA2VICMR [S2009/TIC-1542], by the Spanish Ministry of Education under the project MULTIMEDICA [TIN2010-20644-C03-01] and by the European Commission Seventh Framework Programme under the project TrendMiner_Enlarged (EU FP7-ICT 612336). ; Publicado