<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.3 20210610//EN" "JATS-journalpublishing1-3.dtd">
<article article-type="research-article" dtd-version="1.3" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xml:lang="ru"><front><journal-meta><journal-id journal-id-type="publisher-id">natszdrav</journal-id><journal-title-group><journal-title xml:lang="ru">Национальное здравоохранение</journal-title><trans-title-group xml:lang="en"><trans-title>National Health Care (Russia)</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2713-069X</issn><issn pub-type="epub">2713-0703</issn><publisher><publisher-name>Federal State Autonomous Educational Institution of Higher Education I.M. Sechenov First Moscow State Medical University of the Ministry of Health of the Russian Federation (Sechenov University)</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.47093/2713-069X.2025.6.4.55-63</article-id><article-id custom-type="elpub" pub-id-type="custom">natszdrav-538</article-id><article-categories><subj-group subj-group-type="heading"><subject>Research Article</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>ИНФОРМАТИЗАЦИЯ ЗДРАВООХРАНЕНИЯ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>INFORMATIZATION OF HEALTHCARE</subject></subj-group></article-categories><title-group><article-title>Использование методов машинного обучения для диагностики заболеваний на основе неструктурированных медицинских текстов</article-title><trans-title-group xml:lang="en"><trans-title>Disease diagnosis from unstructured medical texts using machine learning techniques</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-0513-8557</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Ермак</surname><given-names>А. Д.</given-names></name><name name-style="western" xml:lang="en"><surname>Ermak</surname><given-names>A. D.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Ермак Андрей Дмитриевич – аналитик данных направления искусственного интеллекта</p><p>наб. Варкауса, д. 17, г. Петрозаводск, 185910</p></bio><bio xml:lang="en"><p>Andrey D. Ermak – Data Analyst, Artificial Intelligence Division</p><p>Varkaus Embankment, 17, Petrozavodsk, 185910</p></bio><email xlink:type="simple">aermak@webiomed.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-5410-5890</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Макарова</surname><given-names>Е. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Makarova</surname><given-names>E. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Макарова Елена Андреевна – канд. техн. наук, руководитель направления искусственного интеллекта</p><p>наб. Варкауса, д. 17, г. Петрозаводск, 185910</p></bio><bio xml:lang="en"><p>Elena A. Makarova – Cand. of Sci. (Technical), Head of the Artificial Intelligence Division</p><p>Varkaus Embankment, 17, Petrozavodsk, 185910</p></bio><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0001-6898-8009</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Кафтанов</surname><given-names>А. Н.</given-names></name><name name-style="western" xml:lang="en"><surname>Kaftanov</surname><given-names>A. N.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Кафтанов Алексей Николаевич – канд. мед. наук, аналитик данных направления искусственного интеллекта</p><p>наб. Варкауса, д. 17, г. Петрозаводск, 185910</p></bio><bio xml:lang="en"><p>Aleksey N. Kaftanov – Cand. of Sci. (Medicine), Data Analyst, Artificial Intelligence Division</p><p>Varkaus Embankment, 17, Petrozavodsk, 185910</p></bio><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-8745-857X</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Гаврилов</surname><given-names>Д. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Gavrilov</surname><given-names>D. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Гаврилов Денис Владимирович – руководитель медицинского направления</p><p>наб. Варкауса, д. 17, г. Петрозаводск, 185910</p></bio><bio xml:lang="en"><p>Denis V. Gavrilov – Head of the Medical Division</p><p>Varkaus Embankment, 17, Petrozavodsk, 185910</p></bio><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-2350-977X</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Новицкий</surname><given-names>Р. Э.</given-names></name><name name-style="western" xml:lang="en"><surname>Novitsky</surname><given-names>R. E.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Новицкий Роман Эдвардович – генеральный директор</p><p>наб. Варкауса, д. 17, г. Петрозаводск, 185910</p></bio><bio xml:lang="en"><p>Roman E. Novitsky – general manager</p><p>Varkaus Embankment, 17, Petrozavodsk, 185910</p></bio><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Гусев</surname><given-names>А. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Gusev</surname><given-names>А. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Гусев Александр Владимирович – канд. техн. наук, старший научный сотрудник отдела научных основ организации здравоохранения</p><p>ул. Добролюбова, д. 11, г. Москва, 127254</p></bio><bio xml:lang="en"><p>Alexandr V. Gusev – Cand. of Sci. (Technical), Senior Research Fellow, Department of Scientific Foundations of Health Care Organization</p><p>Dobrolyubova str., 11, Moscow, 127254</p></bio><xref ref-type="aff" rid="aff-2"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>ООО «К-Скай»</institution><country>Россия</country></aff><aff xml:lang="en"><institution>K-SkAI LLC</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-2"><aff xml:lang="ru"><institution>ФГБУ «Центральный научно-исследовательский институт организации и информатизации здравоохранения» Министерства здравоохранения Российской Федерации</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Russian Research Institute of Health</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2025</year></pub-date><pub-date pub-type="epub"><day>16</day><month>01</month><year>2026</year></pub-date><volume>6</volume><issue>4</issue><fpage>55</fpage><lpage>63</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Ермак А.Д., Макарова Е.А., Кафтанов А.Н., Гаврилов Д.В., Новицкий Р.Э., Гусев А.В., 2026</copyright-statement><copyright-year>2026</copyright-year><copyright-holder xml:lang="ru">Ермак А.Д., Макарова Е.А., Кафтанов А.Н., Гаврилов Д.В., Новицкий Р.Э., Гусев А.В.</copyright-holder><copyright-holder xml:lang="en">Ermak A.D., Makarova E.A., Kaftanov A.N., Gavrilov D.V., Novitsky R.E., Gusev А.V.</copyright-holder><license xml:lang="ru" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>Данная работа распространяется под лицензией Creative Commons Attribution 4.0.</license-p></license><license xml:lang="en" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>This work is licensed under a Creative Commons Attribution 4.0 License.</license-p></license></permissions><self-uri xlink:href="https://www.natszdrav.ru/jour/article/view/538">https://www.natszdrav.ru/jour/article/view/538</self-uri><abstract><p>Современные методы машинного обучения открывают новые возможности для анализа медицинских текстов. Использование неструктурированных данных позволяет улучшить качество поддержки принятия врачебных решений и развивать персонализированные подходы к лечению пациентов.</p><sec><title>Цель исследования</title><p>Цель исследования: разработка оптимального алгоритма прогнозирования заболеваний с помощью мультиметочной классификации на основании медицинских текстов из отобранных случаев лечения пациентов.</p></sec><sec><title>Материалы и методы</title><p>Материалы и методы. В исследовании использовались анонимизированные электронные медицинские карты 387 590 пациентов. Для анализа текстовой информации применялись методы лемматизации и векторизации на основе предобученной модели FastText. Разработана мультиметочная модель классификации, предсказывающая 156 диагностических категорий, сгруппированных по основным группам заболеваний. Для построения моделей применялись нейросетевые архитектуры и ансамбли деревьев решений.</p></sec><sec><title>Результаты</title><p>Результаты. Предложенные модели показали высокую эффективность. Использование различных методов агрегации текстовых векторов позволило повысить качество прогнозирования. Модель продемонстрировала стабильность и клиническую интерпретируемость результатов, обеспечивая возможность применения в реальной медицинской практике.</p></sec><sec><title>Заключение</title><p>Заключение. Разработанный подход к анализу неструктурированных медицинских текстов с помощью методов машинного обучения является перспективным инструментом для поддержки диагностики заболеваний. Дальнейшие исследования направлены на улучшение интерпретируемости моделей и их адаптацию к различным клиническим источникам данных.</p></sec></abstract><trans-abstract xml:lang="en"><p>Modern machine learning methods open new opportunities for analyzing medical texts. The use of unstructured data enables improved clinical decision support and the development of personalized patient treatment approaches.</p><sec><title>The aim of the study</title><p>The aim of the study: to develop an optimal algorithm for disease prediction using multi-label classification based on medical texts from selected patient treatment cases.</p></sec><sec><title>Materials and methods</title><p>Materials and methods. The study utilized anonymized electronic medical records of 387 590 patients. Textual data were processed using lemmatization and vectorization based on a pretrained FastText model. A multi-label classification model was developed to predict 156 diagnostic categories grouped by major disease classes. Neural network architectures and decision tree ensembles were applied for model building.</p></sec><sec><title>Results</title><p>Results. The proposed models demonstrated high effectiveness. The use of various text vector aggregation methods improved prediction quality. The model showed stability and clinical interpretability, supporting its applicability in real-world medical practice.</p></sec><sec><title>Conclusion</title><p>Conclusion. The developed approach to analyzing unstructured medical texts using machine learning methods is a promising tool for disease diagnosis support. Further research will focus on improving model interpretability and adapting models to diverse clinical data sources.</p></sec></trans-abstract><kwd-group xml:lang="ru"><kwd>машинное обучение</kwd><kwd>неструктурированные данные</kwd><kwd>мультиметочная классификация</kwd><kwd>нейронные сети</kwd><kwd>персонализированная медицина</kwd></kwd-group><kwd-group xml:lang="en"><kwd>machine learning</kwd><kwd>unstructured data</kwd><kwd>multi-label classification</kwd><kwd>neural networks</kwd><kwd>personalized medicine</kwd></kwd-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Spasic I., Nenadic G. Clinical text data in machine learning: Systematic review. JMIR Medical Informatics. 2020; 8(3): e17984. https://doi.org/10.2196/17984. PMID: 32229465</mixed-citation><mixed-citation xml:lang="en">Spasic I., Nenadic G. Clinical text data in machine learning: Systematic review. JMIR Medical Informatics. 2020; 8(3): e17984. https://doi.org/10.2196/17984. PMID: 32229465</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Hossain E., Rana R., Higgins N., et al. Natural Language Processing in Electronic Health Records in relation to healthcare decision-making: A systematic review. Computers in Biology and Medicine. 2023; 155: 106649. https://doi.org/10.1016/j.compbiomed.2023.106649. PMID: 36805219</mixed-citation><mixed-citation xml:lang="en">Hossain E., Rana R., Higgins N., et al. Natural Language Processing in Electronic Health Records in relation to healthcare decision-making: A systematic review. Computers in Biology and Medicine. 2023; 155: 106649. https://doi.org/10.1016/j.compbiomed.2023.106649. PMID: 36805219</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Wu S., Roberts K., Datta S., et al. Deep learning in clinical natural language processing: A methodical review. Journal of the American Medical Informatics Association. 2020; 27(3): 457–470. https://doi.org/10.1093/jamia/ocz200. PMID: 31794016</mixed-citation><mixed-citation xml:lang="en">Wu S., Roberts K., Datta S., et al. Deep learning in clinical natural language processing: A methodical review. Journal of the American Medical Informatics Association. 2020; 27(3): 457–470. https://doi.org/10.1093/jamia/ocz200. PMID: 31794016</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Kesiku C.Y.Y., Chaves-Villota A., Garcia-Zapirain B. Natural Language Processing Techniques for Text Classification of Biomedical Documents: A Systematic Review. Information (Switzerland). 2022; 13(10): 499. https://doi.org/10.3390/info13100499.</mixed-citation><mixed-citation xml:lang="en">Kesiku C.Y.Y., Chaves-Villota A., Garcia-Zapirain B. Natural Language Processing Techniques for Text Classification of Biomedical Documents: A Systematic Review. Information (Switzerland). 2022; 13(10): 499. https://doi.org/10.3390/info13100499.</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Masud J.H.B., Kuo C.C., Yeh C.Y., et al. Applying Deep Learning Model to Predict Diagnosis Code of Medical Records. Diagnostics. 2023; 13(13): 2297. https://doi.org/10.3390/diagnostics13132297</mixed-citation><mixed-citation xml:lang="en">Masud J.H.B., Kuo C.C., Yeh C.Y., et al. Applying Deep Learning Model to Predict Diagnosis Code of Medical Records. Diagnostics. 2023; 13(13): 2297. https://doi.org/10.3390/diagnostics13132297</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Huang J., Osorio C., Sy L.W. An empirical evaluation of deep learning for ICD-9 code assignment using MIMIC-III clinical notes. Computers Methods and Programs in Biomedicine. 2019; 177: 141–153. https://doi.org/10.1016/j.cmpb.2019.05.024. PMID: 31319942</mixed-citation><mixed-citation xml:lang="en">Huang J., Osorio C., Sy L.W. An empirical evaluation of deep learning for ICD-9 code assignment using MIMIC-III clinical notes. Computers Methods and Programs in Biomedicine. 2019; 177: 141–153. https://doi.org/10.1016/j.cmpb.2019.05.024. PMID: 31319942</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Zeng M., Li M., Fei Z., et al. Automatic ICD-9 coding via deep transfer learning. Neurocomputing. 2019; 324: 43–50. https://doi.org/10.1016/j.neucom.2018.04.081</mixed-citation><mixed-citation xml:lang="en">Zeng M., Li M., Fei Z., et al. Automatic ICD-9 coding via deep transfer learning. Neurocomputing. 2019; 324: 43–50. https://doi.org/10.1016/j.neucom.2018.04.081</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Blanco A., Perez-de-Viñaspre O., Pérez A., et al. Boosting ICD multi-label classification of health records with contextual embeddings and label-granularity. Computers Methods and Programs in Biomedicine. 2020; 188: 105264. https://doi.org/10.1016/j.cmpb.2019.105264. PMID: 31851906</mixed-citation><mixed-citation xml:lang="en">Blanco A., Perez-de-Viñaspre O., Pérez A., et al. Boosting ICD multi-label classification of health records with contextual embeddings and label-granularity. Computers Methods and Programs in Biomedicine. 2020; 188: 105264. https://doi.org/10.1016/j.cmpb.2019.105264. PMID: 31851906</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Zhang K., Ma H., Zhao Y., et al. The Comparative Experimental Study of Multilabel Classification for Diagnosis Assistant Based on Chinese Obstetric EMRs. Journal of Healthcare Engineering. 2018; 2018: 7273451. https://doi.org/10.1155/2018/7273451. PMID: 29666671</mixed-citation><mixed-citation xml:lang="en">Zhang K., Ma H., Zhao Y., et al. The Comparative Experimental Study of Multilabel Classification for Diagnosis Assistant Based on Chinese Obstetric EMRs. Journal of Healthcare Engineering. 2018; 2018: 7273451. https://doi.org/10.1155/2018/7273451. PMID: 29666671</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Korobov M. Morphological analyzer and generator for Russian and Ukrainian languages. Communications in Computer and Information Science. Springer Verlag; 2015; 542: 320–332. https://doi.org/10.1007/978-3-319-26123-2_31</mixed-citation><mixed-citation xml:lang="en">Korobov M. Morphological analyzer and generator for Russian and Ukrainian languages. Communications in Computer and Information Science. Springer Verlag; 2015; 542: 320–332. https://doi.org/10.1007/978-3-319-26123-2_31</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Bergstra J., Bengio Y. Random Search for Hyper-Parameter Optimization. Journal of Machine Learning Research. 2012; 13: 281–305.</mixed-citation><mixed-citation xml:lang="en">Bergstra J., Bengio Y. Random Search for Hyper-Parameter Optimization. Journal of Machine Learning Research. 2012; 13: 281–305.</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Sokolova M., Lapalme G. A systematic analysis of performance measures for classification tasks. Information Processing and Management. 2009; 45(4): 427–437. https://doi.org/10.1016/j.ipm.2009.03.002</mixed-citation><mixed-citation xml:lang="en">Sokolova M., Lapalme G. A systematic analysis of performance measures for classification tasks. Information Processing and Management. 2009; 45(4): 427–437. https://doi.org/10.1016/j.ipm.2009.03.002</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Hinojosa Lee M.C., Braet J., Springael J. Performance Metrics for Multilabel Emotion Classification: Comparing Micro, Macro, and Weighted F1-Scores. Applied Sciences. 2024; 14(21): 9863. https://doi.org/10.3390/app14219863</mixed-citation><mixed-citation xml:lang="en">Hinojosa Lee M.C., Braet J., Springael J. Performance Metrics for Multilabel Emotion Classification: Comparing Micro, Macro, and Weighted F1-Scores. Applied Sciences. 2024; 14(21): 9863. https://doi.org/10.3390/app14219863</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Maltoudoglou L., Paisios A., Lenc L., et al. Well-calibrated confidence measures for multi-label text classification with a large number of labels. Pattern Recognition. 2022; 122: 108271. https://doi.org/10.1016/j.patcog.2021.108271</mixed-citation><mixed-citation xml:lang="en">Maltoudoglou L., Paisios A., Lenc L., et al. Well-calibrated confidence measures for multi-label text classification with a large number of labels. Pattern Recognition. 2022; 122: 108271. https://doi.org/10.1016/j.patcog.2021.108271</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Chawla N.V., Bowyer K.W., Hall L.O., et al. SMOTE: Synthetic Minority Over-sampling Technique. Journal of Artificial Intelligence Research. 2002; 16(1): 321–357. https://doi.org/10.1613/jair.953</mixed-citation><mixed-citation xml:lang="en">Chawla N.V., Bowyer K.W., Hall L.O., et al. SMOTE: Synthetic Minority Over-sampling Technique. Journal of Artificial Intelligence Research. 2002; 16(1): 321–357. https://doi.org/10.1613/jair.953</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">He H., Bai Y., Garcia E.A., et al. ADASYN: Adaptive synthetic sampling approach for imbalanced learning. Proceedings of the International Joint Conference on Neural Networks. 2008: 1322–1328. https://doi.org/10.1109/IJCNN.2008.4633969</mixed-citation><mixed-citation xml:lang="en">He H., Bai Y., Garcia E.A., et al. ADASYN: Adaptive synthetic sampling approach for imbalanced learning. Proceedings of the International Joint Conference on Neural Networks. 2008: 1322–1328. https://doi.org/10.1109/IJCNN.2008.4633969</mixed-citation></citation-alternatives></ref></ref-list><fn-group><fn fn-type="conflict"><p>The authors declare that there are no conflicts of interest present.</p></fn></fn-group></back></article>
