Document-level adverse drug reaction event extraction on electronic health records in Spanish

  1. Sara Santiso
  2. Arantza Casillas
  3. Alicia Pérez
  4. Maite Oronoz
  5. Koldo Gojenola
Revista:
Procesamiento del lenguaje natural

ISSN: 1135-5948

Año de publicación: 2016

Número: 56

Páginas: 49-56

Tipo: Artículo

Otras publicaciones en: Procesamiento del lenguaje natural

Objetivos de desarrollo sostenible

Resumen

Presentamos un sistema de extracción de Reacciones Adversas a Medicamentos (RAMs) para Informes Médicos Electrónicos escritos en español. El objetivo del sistema es asistir a expertos en farmacia cuando tienen que decidir si un paciente padece o no una o más RAMs. El núcleo del sistema es un modelo predictivo inferido de un corpus etiquetado manualmente, que cuenta con características semánticas y sintácticas. Este modelo es capaz de extraer RAMs de parejas enfermedad-medicamento en un informe dado. Finalmente, las RAMs extraídas automáticamente son post-procesadas usando un heurístico para presentar la información de una forma compacta. Esta fase ofrece los medicamentos y enfermedades del documento con su frecuencia, y también une las parejas relacionadas como RAMs. En resumen, el sistema no sólo presenta las RAMs en el texto sino que también da información concisa a petición de los expertos en farmacia (los usuarios potenciales del sistema).

Referencias bibliográficas

  • Aramaki, E., Y. Miura, M. Tonoike, T. Ohkuma, H. Masuichi, K. Waki, and K. Ohe. 2010. Extraction of adverse drug effects from clinical records. In Proceedings of Medinfo, pages 739—743.
  • Bretonnel, K. and D. Demmer-Fushman. 2014. Biomedical Natural Language Processing, volume 11. John Benjamins Publishing Company.
  • Cohen, K.B. and D. Demner-Fushman. 2014. Biomedical Natural Language Processing. Natural Language Processing. John Benjamins Publishing Company.
  • de la Peña, S., I. Segura-Bedmar, P. Mart́ınez, and J.L. Mart́ınezFernández. 2014. ADR Spanish tool: a tool for extracting adverse drug reactions and indications. Procesamiento del Lenguaje Natural, 53:177–180.
  • Deléger, L., C. Grouin, and P. Zweigenbaum. 2010. Extracting medical information from narrative patient records: the case of medication-related information. JAMIA, 17:555–558.
  • Friedman, N., D. Geiger, and M. Goldszmidt. 1997. Bayesian network classifiers. Machine Learning, 29(2-3):131–163.
  • Gojenola, K., M. Oronoz, A. Pérez, and A. Casillas. 2014. IxaMed: Applying freeling and a perceptron sequential tagger at the shared task on analyzing clinical texts. In International Workshop on Semantic Evaluation (SemEval-2014), Task: Analysis of Clinical Text, pages 361–365.
  • Grigonyte, G., M. Kvist, S. Velupillai, and M. Wirén. 2014. Improving readability of swedish electronic health records through lexical simplification: First results. In Proceedings of the 3rd Workshop on Predicting and Improving Text Readability for Target Reader Populations (PITR), pages 74–83, April.
  • Gurulingappa, H., J. Fluck, M. HofmannApitius, and L. Toldo. 2011. Identification of adverse drug event assertive sentences in medical case reports. In Knowledge Discovery in Health Care and Medicine, pages 16–27.
  • Hall, M., E. Frank, G. Holmes, B. Pfahringer, P. Reutemann, and I. Witten. 2009. The WEKA data mining software: An update. SIGKDD Explorations, 11(1):10–18.
  • Japkowicz, N. and S. Stephen. 2002. The class imbalance problem: A systematic study. Intelligent data analysis, 6(5):429– 449.
  • Karlsson, S., J. Zhao, L. Asker, and H. Boström. 2013. Predicting adverse drug events by analyzing electronic patient records. In Proceedings of 14th Conference on Artificial Intelligence in Medicine, pages 125–129.
  • Kubat, M. and S. Matwin. 1997. Addressing the curse of imbalanced training sets: one-sided selection. In ICML, volume 97, pages 179–186. Nashville, USA.
  • Laippala, V., F. Ginter, S. Pyysalo, and T. Salakoski. 2009. Towards automated processing of clinical finnish: Sublanguage analysis and a rule-based parser. International journal of medical informatics, 78:e7–e12.
  • Li, Q., L. Deléger, T. Lingren, H. Zhai, M. Kaiser, L. Stoutenborough, A.G. Jegga, K.B. Cohen, and I. Solti. 2013. Mining fda drug labels for medical conditions. BMC Med. Inf. & Decision Making, 13:53.
  • Mollineda, R.A., R. Alejo, and J.M. Sotoca. 2007. The class imbalance problem in pattern classification and learning. In II Congreso Español de Informática (CEDI 2007). ISBN, pages 978–84. Citeseer.
  • Oronoz, M., A. Casillas, K. Gojenola, and A. Pérez. 2013. Automatic annotation of medical records in Spanish with disease, drug and substance names. Lecture Notes in Computer Science, 8259:536–547.
  • Oronoz, M., K. Gojenola, A. Pérez, A. Dı́az de Ilarraza, and A. Casillas. 2015. On the creation of a clinical gold standard corpus in Spanish: Mining adverse drug reactions. Journal of Biomedical Informatics, 56:318 – 332.
  • Segura-Bedmar, I., P. Mart́ınez, R. Revert, and J. Moreno-Schneider. 2015. Exploring spanish health social media for detecting drug effects. BMC medical informatics and decision making, 15(Suppl 2):S6.
  • Sohn, S., JP. Kocher, C. Chute, and G. Savova. 2011. Drug side effect extraction from clinical narratives of psychiatry and psychology patients. JAMIA, 18:144– 149.
  • Wang, X., G. Hripcsak, M. Markatou, and C. Friedman. 2009. Active computerized pharmacovigilance using natural language processing, statistics, and electronic health records: a feasibility study. JAMIA, 16:328–337.