Resumen de TESTLINK en IberLEF 2023: Creación de relaciones entre análisis de laboratorio y mediciones clínicas y sus resultados

• Autores: Roberto Zanoli, Goutham Karunakaran, Begoña Altuna, Rodrigo Agerri Gascón , Lidia Salas, José Javier Saiz, Alberto Lavelli, Bernardo Magnini , Manuela Speranza
• Localización: Procesamiento del lenguaje natural, ISSN 1135-5948, Nº. 71, 2023, págs. 313-320
• Idioma: español
• Títulos paralelos:
  • Overview of TESTLINK at IberLEF 2023: Linking Results to Clinical Laboratory Tests and Measurements
• Enlaces
  • Texto completo
• Resumen
  • Multiple

    La tarea TESTLINK de IberLEF2023 se centra en la extracción de relaciones de casos clínicos en español y euskera. La tarea consiste en identificar resultados y medidas clínicas y relacionarlos con las pruebas y mediciones de las que se obtuvieron. Tres equipos han participado en la tarea y se han evaluado varios modelos (supervisados) de aprendizaje profundo. Curiosamente, ninguno de los equipos exploró el uso del aprendizaje few-shot. La evaluación muestra que el fine-tuning en el dominio y conjuntos de datos de entrenamiento más grandes mejoran los resultados. De hecho, el hecho de que los modelos supervisados superaran significativamente la baseline basada en el aprendizaje few-shot muestra el papel crucial que aún desempeña la disponibilidad de datos de entrenamiento anotados.

  • English

    The TESTLINK task conducted at IberLEF2023 focuses on relation extraction from clinical cases in Spanish and Basque. The task consists in identifying clinical results and measures and linking them to the tests and measurements from which they were obtained. Three teams took part in the task and various (supervised) deep learning models were evaluated; interestingly, none of the teams explored the use of few-shot learning. The evaluation shows that in-domain fine-tuning and larger training datasets improve the results. In fact, the fact that supervised models significantly outperformed the baseline based on few-shot learning shows the crucial role still played by the availability of annotated training data.

• Referencias bibliográficas
  • Agerri, R., I. San Vicente, J. A. Campos, A. Barrena, X. Saralegi, A. Soroa, and E. Agirre. 2020. Give your text representation models some...
  • Alfattni, G., N. Peek, and G. Nenadic. 2020. Extraction of temporal relations from clinical free text: A systematic review of current approaches....
  • Altuna, B., G. Karunakaran, A. Lavelli, B. Magnini, M. Speranza, and R. Zanoli. 2023. CLinkaRT at EVALITA 2023: Overview of the Task on Linking...
  • Carrino, C. P., J. Armengol-Estape, A. Gutierrez-Fandiño, J. Llop-Palao, M. P`amies, A. Gonzalez-Agirre, and M. Villegas. 2021. Biomedical...
  • Carrino, C. P., J. Llop, M. P`amies, A. Gutierrez-Fandiño, J. Armengol- Estape, J. Silveira-Ocampo, A. Valencia, A. Gonzalez-Agirre, and...
  • Cañete, J., G. Chaperon, R. Fuentes, J.-H. Ho, H. Kang, and J. Perez. 2020. Spanish Pre-Trained BERT Model and Evaluation Data. In PML4DC...
  • Hao, T., H. Liu, and C. Weng. 2016. Valx: A System for Extracting and Structuring Numeric Lab Test Comparison Statements from Text. Methods...
  • Jain, K. and V. Prajapati. 2021. NLP/Deep Learning Techniques in Healthcare for Decision Making. Primary Health Care, 11.
  • Jimenez-Zafra, S. M., F. Rangel, and M. Montes-y Gomez. 2023. Overview of IberLEF 2023: Natural Language Processing Challenges for Spanish...
  • Johnson, A. E., T. J. Pollard, L. Shen, L.- w. H. Lehman, M. Feng, M. Ghassemi, B. Moody, P. Szolovits, L. Anthony Celi, and R. G. Mark. 2016....
  • Magnini, B., B. Altuna, A. Lavelli, A.- L. Minard, M. Speranza, and R. Zanoli. 2022. European Clinical Case Corpus. In G. Rehm, editor, European...
  • Newman-Griffis, D., G. Divita, B. Desmet, A. Zirikly, C. P. Rose, and E. Fosler- Lussier. 2020. Ambiguity in medical concept normalization:...
  • Percha, B. 2021. Modern Clinical Text Mining: A Guide and Review. Annual Review of Biomedical Data Science, 4(1):165–187. PMID: 34465177.
  • Pustejovsky, J., J. M. Castaño, R. Ingria, R. Saurı, R. J. Gaizauskas, A. Setzer, G. Katz, and D. R. Radev. 2003. TimeML: Robust Specification...
  • Sankoh, O. and P. Byass. 2014. Causespecific mortality at INDEPTH Health and Demographic Surveillance System Sites in Africa and Asia: concluding...
  • Santiso, S., A. Perez, and A. Casillas. 2021. Adverse Drug Reaction extraction: Tolerance to entity recognition errors and subdomain variants....
  • Schweter, S. and A. Akbik. 2020. FLERT: Document-Level Features for Named Entity Recognition. CoRR, abs/2011.06993.
  • Styler, W. F., S. Bethard, S. Finan, M. Palmer, S. Pradhan, P. C. de Groen, B. Erickson, T. Miller, C. Lin, G. Savova, et al. 2014. Temporal...
  • Trigueros, O., A. Blanco, N. Lebeña, A. Casillas, and A. Perez. 2022. Explainable ICD multi-label classification of EHRs in Spanish with convolutional...