High social impact of stroke makes early detection of stroke risk factors crucial for its prevention. It is important to use the most efficient natural language processing (NLP) methods for automatic extraction of information about risk factors from the electronic health records (EHRs) to improve the quality of preventive medical care.The authors have developed methods to extract information about diseases and health status of patients based on manually created rules, statistical machine learning and deep learning to solve the problem of named entity recognition (NER) in clinical records. Comparative experimental studies of the developed methods were conducted on a marked-up corpus of clinical records. As a result, conclusions are made on the effectiveness of the developed methods.
Download PDF from the Proceeding of the Institute for Systems Analysis of the Russian Academy of Science website (in Russian): http://www.isa.ru/proceedings/images/documents/2021-71-4/93-101.pdf
Download PDF from eLibrary (in Russian, registration required): https://elibrary.ru/item.asp?id=47374239
Donitova V. V., Kireev D. A., Titova E. V., Akimova A. A. (2021) Natural language processing models for extraction of stroke risk factors from electronic health records // Proceeding of the Institute for Systems Analysis of the Russian Academy of Science, Vol. 71, № 4, pp. 93–101.