IOMED will participate in IberLEF as the organizing entity of an NLP task
The tech team has worked together with the HITZ research group to generate an annotated corpus of medical sections.
IOMED will participate in IberLEF as the organizing entity of an NLP (Natural Language Processing) task in the month of September.
At IOMED we believe that the current advanced state of clinical PCNL in Spanish presents an opportunity for the development of tools for the automatic identification of sections in clinical documents. For this reason, the tech team has worked together with the HITZ research group (Basque Center for Language Technology) to generate an annotated corpus of medical sections.
The task that will be carried out is novel, since it is the first time that it has been proposed for Spanish to detect and classify the parts of the text of a clinical document corresponding to each section.
The project, which will be presented at IberLEF, will consist of identifying seven sections that could appear in a given document. The sections chosen are adapted to the current specific needs and are: current illness, medical history, family history, examination, evolution, treatment and, finally, the section referred from/to which contains information about another hospital or service where treatment was given. part of the current disease.
From IOMED we anticipate that it will be of interest both for the wide potential set of research groups that work in medical NLP and for industrial companies, given that the current advanced state of clinical NLP for Spanish presents an opportunity for the development of this type. of tools that can provide a competitive advantage over other medical NLP systems.
