Journal of Digital Imaging

, Volume 32, Issue 1, pp 19–29 | Cite as

Automatic Detection of Negated Findings in Radiological Reports for Spanish Language: Methodology Based on Lexicon-Grammatical Information Processing

  • Walter KozaEmail author
  • Darío Filippo
  • Viviana Cotik
  • Vanesa Stricker
  • Mirian Muñoz
  • Ninoska Godoy
  • Natalia Rivas
  • Ricardo Martínez-Gamboa


We present a methodology for the automatic recognition of negated findings in radiological reports considering morphological, syntactic, and semantic information. In order to achieve this goal, a series of rules for processing lexical and syntactic information was elaborated. This required development of an electronic dictionary of medical terminology and informatics grammars. Pertinent information for the assembly of the specialized dictionary was extracted from the ontology SNOMED CT and a medical dictionary (RANM, 2012). Likewise, a general language dictionary was also included. Lexicon-Grammar (LG), proposed by Gross (1975; Cahiers de l’institut de linguistique de Louvain, 24. 23-41 1998), was used to set up the database, which allowed an exhaustive description of the argument structure of predicates projected by lexical units. Computational framework was carried out with NooJ, a free software developed by Silberztein (Silberztein and Noo 2018, 2016), which has various utilities for treating natural language, such as morphological and syntactic grammar, as well as dictionaries. This methodology was compared with a Spanish version of NegEx (Chapman et al. Journal of Biomedical Informatics, 34(5):301-310 2001; Stricker 2016). Results show that there are minimal differences in favor of the algorithm developed using NooJ, but the quality and specificity of the data improves if lexical-grammatical information is added.


Negated findings Automatic recognition Lexicon-grammar NooJ NegEx 


Funding Information

This research was supported by a grant from the Proyecto Fondecyt Regular 1171033, from the Comisión Nacional de Investigación Científica y Tecnológica (Conicyt), Chile.


  1. 1.
    López-Huertas, M., Torres, I. & Barité, M: Terminological representation of specialized areas in conceptual structures: the case of gender studie. Proceedings of the 8th International ISCO Conference, pp. 263-268, Londres: Ia C. McIlwaine, 2004.Google Scholar
  2. 2.
    Zeng Q, Goryachev S, Weiss S, Sordo M, Murphy S, Lazarus R: Extracting principal diagnosis, co-morbidity and smoking status for asthma research: evaluation of a natural language processing system. BMC medical informatics and decision making 6(1):1, 2006CrossRefGoogle Scholar
  3. 3.
    Chapman, W., Bridewell, W., Hanbury, P., Cooper, G. y Buchanan, B: A Simple Algorithm for Identifying Negated Findings and Diseases in Discharge Summaries. Journal of Biomedical Informatics, 34(5):301–310, 2001.Google Scholar
  4. 4.
    Stricker V: Detección de negaciones en informes radiológicos en español. Buenos Aires: Universidad de Buenos Aires, 2016Google Scholar
  5. 5.
    Lacson R, Andriole K, Prevedello L, Khorasani R: Information from Searching Content with an Ontology-Utilizing Toolkit (iSCOUT). Journal of Digit Imaging 25:512–519, 2012CrossRefGoogle Scholar
  6. 6.
    Cotik, V., Stricker, V., Vivaldi, J. Rodríguez, H: Syntactic methods for negation detection in radiology reports in Spanish. Proceedings of 15th Workshop on Biomedical Natural Language Processing, 156-165. Berlín: Association for Computational Linguistics, 2016.Google Scholar
  7. 7.
    RANM: Diccionario de términos médicos. Editorial Médica Panamericana: Buenos Aires, 2012Google Scholar
  8. 8.
    RAE: Diccionario de la lengua Española. Bogotá: Santillana, 2014.Google Scholar
  9. 9.
    Gross M: Méthodes en syntaxe. París: Hermann, 1975Google Scholar
  10. 10.
    Gross M: Lexique, grammaires et cumulativité. Cahiers de l’institut de linguistique de Louvain 24:23–41, 1998CrossRefGoogle Scholar
  11. 11.
    Silberztein, M: NooJ: A Linguistic Annotation System For Corpus Processing. Accesed 3 January 2018.
  12. 12.
    Silberztein M: Formalizing Natural Languages. ISTE: The NooJ approach. Londres, 2016CrossRefGoogle Scholar
  13. 13.
    Harkema H, Dowling J, Thornblade T, Chapman W: Con-Text: An Algorithm for Determining Negation, Experiencer, and Temporal Status from Clinical Reports. Journal of biomedical informatics 42(5):839–851, 2009CrossRefGoogle Scholar
  14. 14.
    Costumero, R., Lopez, F., Gonzalo-Martín, C., Millan, M. y Menasalvas, E: An Approach to Detect Negation on Medical Documents in Spanish. Brain Informatics and Health, 8609, 366-375, 2014.Google Scholar
  15. 15.
    Campillos Llanos, L., Martínez, P. y Segura-Berdman, I: A preliminary analysis of negation in a Spanish clinical records dataset, Actas del Taller de NEGación en español. NEGES-2017, 33-37. Murcia: Universidad de Murcia, 2017.Google Scholar
  16. 16.
    Wu As, Do Bh, Kim & Rubin, D: Evaluation of negation and uncertainty detection and its impact on precision and recall in search. J Digit Imaging 24(2):234–242, 2011Google Scholar
  17. 17.
    Nassif, H., Woods, R., Burnside, E., Ayvaci, M., Shavlik, J. & Page, D: Information extraction for clinical data mining: a mammography case study. Proc IEEE Internationa Conference Data Mining, 2009.Google Scholar
  18. 18.
    Nassif, H., Cunha, F., Moreira, I., Cruz-Correia, R., Sousa, E., Burnside, E. & Dutra, I: Extracting BI-RADS features from Portuguese Clinical Texts. Proceedings IEEE International Conference Bioinformatics Biomed, 2012.Google Scholar
  19. 19.
    Breast Imaging Reporting and Data System (BI-RADSTM). American College of Radiology; Reston, VA: 1998.Google Scholar
  20. 20.
    Elia, A., Monteleone, M. & Marano, F: From the concept of transformation in Harris and Chomsky to the Lexique-Grammaire of Maurice Gross. En Kasevich, V., Kleiner, Y. & Sériot, P. (Eds.) History of linguistics, 76-82, Amsterdam: John Benjamins, 2011.Google Scholar
  21. 21.
    Tolone, E: Conversión de las tablas del Léxico-Gramática del francés en el léxico LGLex. 2nd Argentinian Workshop on Natural Language Processing (WNLP’11), Córdoba, Argentina, 2012.Google Scholar
  22. 22.
    Koza, W. Traducción automática del conocimiento médico. Propuesta basada en explicitación y reglas transformacionales. Proyecto FONDECyT Regular 1171033. Comisión Nacional de Investigación Científica y Tecnológica (Conicyt), Chile.Google Scholar
  23. 23.
    Bonino R: Una propuesta para el tratamiento de los enclíticos en NooJ. Infosur Revista 7:31–40, 2015Google Scholar
  24. 24.
    Koza, W. Enumerative series in Spanish: Formalization and Automatic Detection. Commun Comput Inf Sci 667:121–131, 2017Google Scholar

Copyright information

© Society for Imaging Informatics in Medicine 2018

Authors and Affiliations

  1. 1.Instituto de Literatura y Ciencias del LenguajePontificia Universidad Católica de ValparaísoValparaísoChile
  2. 2.Hospital Pediátrico GarrahanBuenos AiresArgentina
  3. 3.Departamento de Ciencias de la Computación, FCEyNUniversidad de Buenos AiresBuenos AiresArgentina
  4. 4.Universidad Diego PortalesSantiagoChile

Personalised recommendations