O. Ferrández

Manuel García-Vega, Miguel A. García-Cumbreras L. Alfonso Ureña-López, José M. Perea-Ortega, F. Javier Ariza-López University of Jaén {mgarcia,magc,laurena,jmperea,fjariza }@ujaen.es Oscar Ferrández, Antonio Toral, Zornitsa Kozareva Elisa Noguera, Andrés ...

The aim of GeoCLEF 2005 is to retrieve relevant documents by using geographic tags [2]. Nowadays, the fast development of Geographic Information Systems (GIS) involves the need of Geographic Information Retrieval Systems (GIR) that help GIS systems to obtain ...

Abstract. This paper describes the participation of a combined ap-proach in GeoCLEF-2006. We have participated in Monolingual English Task and we present joint work of the three groups or teams belonging to the project R2D2 4 with a new system, ...

As more and more electronic clinical information is becoming easier to access for secondary uses such as clinical research, approaches that enable faster and more collaborative research while protecting patient privacy and confidentiality are becoming more important. Clinical text de-identification offers such advantages but is typically a tedious manual process. Automated Natural Language Processing (NLP) methods can alleviate this process, but their impact on subsequent uses of the automatically de-identified clinical narratives has only barely been investigated. In the context of a larger project to develop and investigate automated text de-identification for Veterans Health Administration (VHA) clinical notes, we studied the impact of automated text de-identification on clinical information in a stepwise manner. Our approach started with a high-level assessment of clinical notes informativeness and formatting, and ended with a detailed study of the overlap of select clinical information types and Protected Health Information (PHI). To investigate the informativeness (i.e., document type information, select clinical data types, and interpretation or conclusion) of VHA clinical notes, we used five different existing text de-identification systems. The informativeness was only minimally altered by these systems while formatting was only modified by one system. To examine the impact of de-identification on clinical information extraction, we compared counts of SNOMED-CT concepts found by an open source information extraction application in the original (i.e., not de-identified) version of a corpus of VHA clinical notes, and in the same corpus after de-identification. Only about 1.2-3% less SNOMED-CT concepts were found in de-identified versions of our corpus, and many of these concepts were PHI that was erroneously identified as clinical information. To study this impact in more details and assess how generalizable our findings were, we examined the overlap between select clinical information annotated in the 2010 i2b2 NLP challenge corpus and automatic PHI annotations from our best-of-breed VHA clinical text de-identification system (nicknamed 'BoB'). Overall, only 0.81% of the clinical information exactly overlapped with PHI, and 1.78% partly overlapped. We conclude that automated text de-identification's impact on clinical information is small, but not negligible, and that improved clinical acronyms and eponyms disambiguation could significantly reduce this impact.

In this paper, we present an evaluation of the hybrid best-of-breed automated VHA (Veteran's Health Administration) clinical text de-identification system, nicknamed BoB, developed within the VHA Consortium for Healthcare Informatics Research. We also evaluate two available machine learning-based text de-identifications systems: MIST and HIDE. Two different clinical corpora were used for this evaluation: a manually annotated VHA corpus, and the 2006 i2b2 de-identification challenge corpus. These experiments focus on the generalizability and portability of the classification models across different document sources. BoB demonstrated good recall (92.6%), satisfactorily prioritizing patient privacy, and also achieved competitive precision (83.6%) for preserving subsequent document interpretability. MIST and HIDE reached very competitive results, in most cases with high precision (92.6% and 93.6%), although recall was sometimes lower than desired for the most sensitive PHI categories.

Using a publicly available corpus of clinical texts called MTSamples originally created to train medical coders and transcriptionists we applied de-identification annotation guidelines and schema developed by the Consortium for Healthcare Informatics Research (CHIR). We assess the feasibility of a Best of Breed (BOB) de- identification tool to reduce workload associated with building a de-identification annotation layer on this corpus. We also report prevalence estimates, inter-annotator agreement metrics and F1-measures for annotators and the BOB tool.

This paper presents an improvement in the temporal expression (TE) recognition phase of a knowledge based system at a multilingual level. For this purpose, the combination of different approaches applied to the recognition of temporal expressions are studied. In this work, for the recognition task, a knowledge based system that recognizes temporal expressions and had been automatically extended to other

Este artículo presenta la extensión automática del sistema TERSEO a otras lenguas combinada con el uso de técnicas basadas en Aprendizaje Automático (AA). En concreto, en este artículo se trabaja en el reconocimiento de expresiones temporales para el italiano y se han probado dos técnicas diferentes de AA: un modelo de Máxima Entropía y modelos ocultos de Markov. Cada sistema ha sido evaluado tanto de manera independiente como de manera combinada con la finalidad de analizar si el sistema combinado mejora los resultados de los sistemas independientes sin incrementar el número de expresiones erróneas en el mismo porcentaje. El sistema TERSEO fue combinado previamente con técnicas de AA para el inglés, obteniendo en ese caso buenos resultados. En este artículo, la combinación del reconocimiento de TERSEO con el reconocimiento del sistema de AA ha sido evaluada para el italiano. La combinación de TERSEO con diferentes técnicas de AA ha sido evaluada obteniendo resultados satisfactorios...