Using Natural Language Processing and Machine Learning to classify the status of kidney allograft in Electronic Medical Records written in Spanish.

Journal: PloS one
PMID: 40338843

Abstract

INTRODUCTION: Accurate identification of graft loss in Electronic Medical Records of kidney transplant recipients is essential but challenging due to inconsistent and not mandatory International Classification of Diseases (ICD) codes. We developed and validated Natural Language Processing (NLP) and machine learning models to classify the status of kidney allografts in unstructured text in EMRs written in Spanish.

Authors

  • Andrea Garcia-Lopez
    PhD Program in Clinical Epidemiology, Department of Clinical Epidemiology and Biostatistics, Faculty of Medicine, Pontificia Universidad Javeriana, Bogotá, Colombia.
  • Juliana Cuervo-Rojas
    Department of Clinical Epidemiology and Biostatistics, Faculty of Medicine, Pontificia Universidad Javeriana, Bogotá, Colombia.
  • Juan Garcia-Lopez
    Department of Technology and Informatics, Colombiana de Trasplantes, Bogotá, Colombia.
  • Fernando Giron-Luque
    Department of Transplant Research, Colombiana de Trasplantes, Bogotá, Colombia.

Keywords

External Resources

Popular Topics
Recent Journals