Two papers accepted at International Conference


The papers from The ClinCode Project study how to automatically assign ICD-10 diagnosis codes to a discharge summary, and will be presented at the International RANLP Conference on Recent Advances in Natural Language Processing.

Illustration photo by Colourbox/Cherezov Kirill
Illustration photo by Colourbox/Cherezov Kirill

Computer-Assisted Clinical ICD-10 Coding will improve efficiency and quality in healthcare. The method will assist physicians and coders to assign IDC-10 codes, but also to validate previous manually assigned ICD-10 codes by hospital management and the health authorities.

The newly accepted papers study how to automatically assign ICD-10 diagnosis codes to a discharge summary, for Swedish and Spanish respectively. Usually, this time-consuming work is carried out manually by a physician or a coder. We use machine learning and specifically Deep AI Learning to perform this and already manually assign codes to discharges summaries.

  • Sonja Remmer, Anastasios Lamproudis and Hercules Dalianis
    “Multi-label Diagnosis Classification of Swedish Discharge Summaries – ICD-10 Code Assignment Using KB-BERT.”
  • Alberto Blanco, Sonja Remmer, Alicia Pérez, Hercules Dalianis and Arantza Casillas
    “On the contribution of per-ICD attention mechanisms to classify health records in languages with fewer resources than English.”

The first paper is made in collaboration with The Clinical Text Mining Group at the Department of Computer and Systems Sciences, Stockholm University, and the second paper with the HiTZ Center – Ixa, University of the Basque Country, Spain.

LINKS: