MISTIC: a novel approach for metastasis classification in Italian electronic health records using transformers.

Journal: BMC medical informatics and decision making
PMID: 40211241

Abstract

BACKGROUND: Analysis of Electronic Health Records (EHRs) is crucial in real-world evidence (RWE), especially in oncology, as it provides valuable insights into the complex nature of the disease. The implementation of advanced techniques for automated extraction of structured information from textual data potentially enables access to expert knowledge in highly specialized contexts. In this paper, we introduce MISTIC, a Natural Language Processing (NLP) approach to classify the presence or absence of metastasis in Italian EHRs, in the breast cancer domain.

Authors

  • Livia Lilli
    Fondazione Policlinico Universitario Agostino Gemelli IRCCS, Rome, Italy.
  • Mario Santoro
    Istituto per le Applicazioni del Calcolo "Mauro Picone", Italian National Research Council, Rome, Italy.
  • Valeria Masiello
    Fondazione Policlinico Universitario Agostino Gemelli IRCCS, Rome, Italy.
  • Stefano Patarnello
    Fondazione Policlinico Universitario A. Gemelli IRCCS, Rome, Italy.
  • Luca Tagliaferri
    Unit of Radiotherapy, Fondazione Policlinico Universitario A. Gemelli IRCCS, Rome, Italy.
  • Fabio Marazzi
    Fondazione Policlinico Universitario Agostino Gemelli IRCCS, Rome, Italy.
  • Nikola Dino Capocchiano
    Fondazione Policlinico Universitario Agostino Gemelli IRCCS, Rome, Italy.

Keywords

External Resources

Popular Topics
Recent Journals