AI4EU-CODE (Classify Oncology Diseases: Español) is a project for AI-driven automatic ICD10 diagnosis coding of oncology medical records in Spanish. It is funded by the European Union’s Horizon 2020 research and innovation programme as an AI4EU Solution for the challenge “Identification of Colon Cancer Risk Factors”.
Contact: Svetla Boytcheva
Project Overview
Inferring meaningful insights out of electronic health records (EHRs) is key to improving the quality of Healthcare, especially in Oncology. This is particularly applicable in text-based classification of patients’ discharge letters towards a specific medical coding standard such as the International Classification of Diseases, revision 10 (ICD-10), SNOMED CT, etc.
AI4EU-CODE’s main objective is to develop a method for automatic classification of clinical narratives in Spanish to ICD-10 codes. This facilitates the generation of a high quality annotated and validated EHR corpora for further use and training of diagnostic predictive algorithms that would help with the early detection of oncology conditions. The project applies state of the art deep learning models, which are adapted and fine-tuned for the specific task and type of textual content. These models have proven to be the best solutions for various medical tasks such as classification, named entity recognition, relation extraction and question answering.
An important aspect of the project is to provide multilingual support, ensuring the capability to classify Spanish clinical notes. AI4EU-CODE’s ambition is to propose a more general multilingual solution that can be easily fine-tuned for other European languages.
The resulting solution increases the efficiency and shortens the time that is needed for annotating diagnosis with ICD-10 codes. It is standards-based and interoperable, which makes it easy to integrate and use with hospital information systems and various systems used for medical research.
Sirma AI, trading as Ontotext, is part of Sirma Group Holding and provides a commercial suite of semantic technologies enabling better content management, knowledge discovery and semantic search.
Ontotext works on AI4EU-CODE for 6 months as an independent solution provider for thе AI4EU challenge “Identification of Colon Cancer Risk Factors”.
This project has received funding from the European Union’s Horizon 2020 research and innovation programme under Sub-grant Agreement AI4EU Open Call for Solutions No 825619.