Open AccessImplant Term Extraction from Swedish Medical Records – Phase 1: Lessons Learned
Author(s) -
Oskar Jerdhaf,
Marina Santini,
Peter Lundberg,
Anette Karlsson,
Arne Jönsson
Publication year - 2021
Publication title -
linköping electronic conference proceedings
Language(s) - English
Resource type - Conference proceedings
eISSN - 1650-3740
pISSN - 1650-3686
DOI - 10.3384/ecp184173
Subject(s) - workflow , computer science , term (time) , identification (biology) , safer , domain (mathematical analysis) , metric (unit) , cluster analysis , implant , patient safety , artificial intelligence , data mining , natural language processing , database , medicine , health care , computer security , engineering , surgery , mathematical analysis , operations management , botany , physics , mathematics , quantum mechanics , economics , biology , economic growth
We present the case of automatic identification of “implant terms”. Implant terms are specialized terms that are important for domain experts (e.g. radiologists), but they are difficult to retrieve automatically because their presence is sparse. The need of an automatic identification of implant terms spurs from safety reasons because patients who have an implant may be at risk if they undergo Magnetic Resonance Imaging (MRI). At present, the workflow to verify whether a patient could be at risk of MRI side-effects is manual and laborious. We claim that this workflow can be sped up, streamlined and become safer by automatically sieving through patients’ medical records to ascertain if they have or have had an implant. To this aim we use BERT, a state-of-the-art deep learning algorithm based on pre-trained word embeddings and we create a model that outputs term clusters. We then assess the linguistic quality or term relatedness of individual term clusters using a simple intra-cluster metric that we call cleanliness. Results are promising.