1. SISN
  2. All Volumes and Issues
  3. Volume 17, 2025
  4. Development of an Automated Natural Language Text Analysis System Using Transformers

Development of an Automated Natural Language Text Analysis System Using Transformers

SISN.
2025;
Volume 17
: pp. 366 - 381
https://doi.org/10.23939/sisn2025.17.366
Authors:
  1. Ihor Pasemko
  2. Yuriy Fedonyuk
1
Lviv Polytechnic National University, Department of Information Systems and Networks, Lviv, Ukraine
2
Volyn National University named after Lesya Ukrainka, Department of General Mathematics and Methods of Teaching Informatics, Lutsk, Ukraine

The article is dedicated to the study of the development of an automated medical text analysis system using modern artificial intelligence technologies and natural language processing. The current state and prospects for the development of automated medical text analysis are analyzed. The main methods and technologies used in this field, including machine learning, deep learning, and natural language processing, are examined. It has been found that existing systems have certain limitations in terms of accuracy and processing speed and do not sufficiently account for the specifics of medical terminology and context. This confirms the need to develop new approaches and tools that provide a higher level of automation and accuracy. Various methods and technologies have been employed, such as text tokenization, natural language processing, text classification and clustering, semantic analysis, and text generation. The developed system is capable of recognizing and classifying symptoms, establishing possible diagnoses, and providing treatment recommendations. Integration with electronic medical records ensures the relevance and completeness of the information, which is essential for medical practice. Special attention has been paid to ensuring user convenience, and an intuitive user interface has been developed. Testing of the developed system was conducted. The test results demonstrated a high level of accuracy and efficiency in analyzing medical texts. The system’s performance was evaluated using real medical data, confirming its practical value and applicability in medical practice. Some limitations and areas requiring further improvement were identified, particularly in processing complex medical terms and ambiguous words.

natural language text analysis
machine learning
natural language processing
clustering
  1. Aggarwal, C. C. (2018). Neural networks and deep learning. Springer.
  2. Aggarwal, C. C., & Zhai, C. (2018). Text data mining: A monograph. Springer.
  3. Chen, Y., Li, X., Tal, K., Wu, D., Xu, Y., & Zhao, X. (2021). Integrating NLP with structured EHR data for case- control analysis of heart failure: Framework development study. JMIR Medical Informatics, 9(5), e25385.DOI: https://doi.org/10.2196/25385
  4. Chollet, F. (2018). Deep learning with Python. Manning Publications.
  5. Collobert, R., Weston, J., Bottou, L., Karlen, M., K avukcuoglu, K., & Kuksa, P. (2011). Natural language processing (almost) from scratch. Journal of Machine Learning Research, 12, 2493-2537.
  6. Fomenko, S. P., & Shevchuk, M. O. (2019). NLP in medical informatics: Modern approaches. Medical Informatics and Engineering, 21(3), 22-29.
  7. Gabrieli, E.R., and Speth, D.J. (1990) Automated analysis of medical text I. Clue gathering.J. Med Systems 4, 71–91.
  8. Ivanchenko, O. V., & Tkachenko, Y. A. (2019). Automation of diagnostics based on textual descriptions in medical documents. Medical Informatics and Engineering, 15(4), 29-35.
  9. Jiang, M., Chen, Y., Liu, M., Rosenbloom, S. T., & Mani, S. (2019). Text mining for early identification of causal factors of medical conditions: An overview. Journal of Biomedical Informatics, 85, 39–50. https://doi.org/ 10.1016/j.jbi.2018.07.003
  10. Johnson, A. E. W., Pollard, T. J., Shen, L., Lehman, L. H., Feng, M., Ghassemi, M., Moody, B., Szolovits, P., Celi, L. A., & Mark, R. G. (2016). MIMIC-III, a freely accessible critical care database. Scientific Data, 3, 160035.
  11. Juratfsky, D., & Martin, J. H. (2022). Speech and language processing. Pearson.
  12. Kelleher, J. (2019). Deep learning. MIT Press.
  13. Kovalchuk, S. P., Ostapenko, L. I., & Kovtun, N. O. (2022). The use of artificial intelligence for medical data analysis in clinical practice. Ukrainian Journal of Computer Engineering and Technology, 30(1), 52–60. https://doi.org/10.15407/ujcet2022.01.052.
  14. Kozyr, O. L., Smirnov, I. A., & Levchenko, R. Y. (2021). Development of a symptom recognition system based on neural networks. Medical Informatics, 21(2), 65-72.
  15. Kyrylenko, R. S., & Yaremenko, T. O. (2020). Application of natural language processing for improving the quality of medical data. Journal of Medical Informatics, 22(5), 57-63.
  16. Lee, J., Yoon, W., Kim, S., Kim, D., Kim, S., So, C. H., & Kang, J. (2020). BioBERT: A pre-trained biomedical language representation model for biomedical text mining. Bioinformatics, 36(4), 1234–1240. https://doi. org/10.1093/bioinformatics/btz682.
  17. Li, I., Zhu, X., & Luo, Y. (2019). A survey of natural language processing methods for relation extraction from electronic health records. Journal of the American Medical Informatics Association, 26(4), 357–368. https://doi.org/10.1093/jamia/ocz043.
  18. Lisovyi, O. Y., Savchuk, T. I., & Pylypenko, A. A. (2020). Application of machine learning methods for medical text classification. Informatics, Management and Artificial Intelligence, 17(1), 43-49.
  19. Marchenko, I. P., Chernenko, L. O., & Dmytruk, V. O. (2019). Use of natural language processing methods for medical records analysis. Ukrainian Journal of Medical Informatics and Engineering, 17(2), 32-40.
  20. Marchenko, V. O., Tarasov, Y. I., & Petrenko, I. V. (2021). Diagnostic system based on medical records analysis. Ukrainian Journal of Medical Informatics and Engineering, 18(3), 28-34.
  21. Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient estimation of word representations in vector space.arXiv preprint, arXiv:1301.3781. https://arxiv.org/abs/1301.3781.
  22. Miroshnychenko, K. Y., & Romanenko, V. I. (2021). Data mining methods in medical texts: Modern approaches. Journal of Informatics and Cybernetics, 19(2), 22-28.
  23. Oliinyk, P. S., Parkhomenko, L. K., & Kulyk, D. V. (2022). Adaptation of natural language processing for medical texts in the Ukrainian language. Medical Informatics and Engineering, 15(1), 53-59.
  24. Panchal, R. (2015). Automated Healthcare System using Text Mining: A Survey. International Journal of Engineering Research And.
  25. Porterfield DS, Rojas-Smith L, Lewis M, et al. ( 2015) A Taxonomy of Integration Interventions Between Health Care and Public Health [Internet]. Research Triangle Park (NC): RTI Press. URL: https://www.ncbi.nlm. nih.gov/books/NBK532450/ doi: 10.3768/rtipress.2015.op.0023.1507
  26. Raj, P., & Vijayakumar, R. (2019). Natural language processing and computational linguistics: A practical guide to text analysis with Python, Gensim, spaCy, and Keras. Packt Publishing.
  27. Rajkomar, A., Dean, J., & Kohane, I. (2019). Machine learning in medicine. New England Journal of Medicine, 380, 1347–1358. https://doi.org/10.1056/NEJMra1814259.
  28. Raschka, S., & Mirjalili, V. (2017). Python machine learning. Packt Publishing.
  29. Romanenko, O. V., Shevchenko, T. A., & Ivashchenko, S. V. (2022). Symptom recognition using neural networks in medical records. Scientific Bulletin of the National University of Life and Environmental Sciences of Ukraine, 11(6), 32-41.
  30. Sidorenko, M. P., & Koval, H. O. (2021). A symptom recognition system for medical records. Medical Informatics and Engineering, 16(4), 67-73.
  31. Tarasenko, V. G., Zubchenko, S. P., & Orlov, K. L. (2020). Using NLP methods for processing medical texts in the Ukrainian language. Computer Science and Technology in Medicine, 19(3), 35-42.