Best system for ICD-10 (International Classification of diseases) coding in French, Italian and Hungarian at CLEF eHealth 2018

Hospital systems routinely assign disease codes (ICD10 codes) to medical records. The challenge stands on treating natural and non-standard language in which doctors express their diagnoses. We presented our system to the CLEF 2018 eHealth Evaluation Task 1 on Multilingual Information Extraction - ICD10 coding. This benchmark addresses information extraction in written text with focus on several languages, specifically Hungarian, Italian and French. The goal is to automatically assign ICD10 codes to diagnostic terms of death certificates. In total, fourteen teams participated: 14 teams submitted runs for the French dataset, 5 submitted runs for the Hungarian dataset and 6 for the Italian dataset. For death certificate coding, the highest performance was 0.838 F-measure for French, 0.9627 for Hungarian and 0.9524 for Italian.