<?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">tiblj</journal-id><journal-title-group><journal-title xml:lang="ru">Туберкулез и болезни легких</journal-title><trans-title-group xml:lang="en"><trans-title>Tuberculosis and Lung Diseases</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2075-1230</issn><issn pub-type="epub">2542-1506</issn><publisher><publisher-name>Медицинские знания и технологии</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.21292/2075-1230-2021-99-11-27-34</article-id><article-id custom-type="elpub" pub-id-type="custom">tiblj-1586</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>ОРИГИНАЛЬНЫЕ СТАТЬИ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>ORIGINAL ARTICLES</subject></subj-group></article-categories><title-group><article-title>Машинное обучение в прогнозировании рецидивов у больных туберкулезом с множественной лекарственной устойчивостью</article-title><trans-title-group xml:lang="en"><trans-title>Machine Learning for Prediction of Relapses in Multiple Drug Resistant Tuberculosis Patients</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Аллилуев</surname><given-names>А. С.</given-names></name><name name-style="western" xml:lang="en"><surname>Аlliluev</surname><given-names>A. S.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Аллилуев Александр Сергеевич – заместитель главного врача по организационно-методической работе, Томский фтизиопульмонологический медицинский центр.</p><p>634009, г. Томск, ул. Розы Люксембург, д. 17.</p></bio><bio xml:lang="en"><p>Aleksandr S. Аlliluev – Deputy Head Physician on Reporting and Statistics, Tomsk Phthisiopulmonology Medical Center.</p><p>17, R. Luxemburg St., Tomsk, 634009.</p><p> </p></bio><email xlink:type="simple">alliluev233@gmail.com</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Филинюк</surname><given-names>О. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Filinyuk</surname><given-names>O. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Филинюк Ольга Владимировна – доктор медицинских наук, профессор, заведующая кафедрой фтизиатрии и пульмонологии.</p><p>634050, г. Томск, Московский тракт, д. 2.</p></bio><bio xml:lang="en"><p>Olga V. Filinyuk - Doctor of Medical Sciences, Professor, Head of Phthisiologyand Pulmonology Department.</p><p>2, Moskovsky Tr., Tomsk. 634050.</p><p> </p></bio><email xlink:type="simple">filinyuk.olga@yandex.ru</email><xref ref-type="aff" rid="aff-2"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Шнайдер</surname><given-names>Е. Е.</given-names></name><name name-style="western" xml:lang="en"><surname>Shnаyder</surname><given-names>E. E.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Шнайдер Екатерина Евгеньевна – врач-статистик организационно-методического отдела.</p><p>634009, г. Томск, ул. Розы Люксембург, д. 17.</p></bio><bio xml:lang="en"><p>Ekaterina E. Shnayder – Specialist of Statistics and Reporting Department.</p><p>17, R. Luxemburg St., Tomsk, 634009.</p></bio><email xlink:type="simple">nikolaevskaya.e.e@gmail.com</email><xref ref-type="aff" rid="aff-3"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Аксенов</surname><given-names>С. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Аksenov</surname><given-names>S. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Аксенов Сергей Владимирович – кандидат технических наук, Томский политехнический университет, Инженерная школа информационных технологий и робототехники, доцент отделения информационных технологий.</p><p>634034, г. Томск, ул. Советская, д. 84, корп. 3.</p></bio><bio xml:lang="en"><p>Sergey V. Аksenov - Candidate of Technical Sciences, Associate Professor of Computer Sciences Department, School of Computer Science &amp; Robotics, Tomsk Polytechnic University.</p><p>Build. 3, 84, Sovetskaya St., Tomsk, 634034.</p></bio><email xlink:type="simple">axyonov@tpu.ru</email><xref ref-type="aff" rid="aff-4"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>ФГБОУ ВО «Сибирский государственный медицинский университет МЗ РФ»; &#13;
ОГАУЗ «Томский фтизиопульмонологический медицинский центр»</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Siberian State Medical University; &#13;
Tomsk Phthisiopulmonology Medical Center</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-2"><aff xml:lang="ru"><institution>ФГБОУ ВО «Сибирский государственный медицинский университет МЗ РФ»</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Siberian State Medical University</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-3"><aff xml:lang="ru"><institution>ОГАУЗ «Томский фтизиопульмонологический медицинский центр»</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Tomsk Phthisiopulmonology Medical Center</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-4"><aff xml:lang="ru"><institution>ФГБОУ ВО «Сибирский государственный медицинский университет МЗ РФ»; &#13;
ФГАОУ ВО «Национальный исследовательский Томский политехнический университет»; &#13;
ФГАОУ ВО «Национальный исследовательский Томский государственный университет»</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Siberian State Medical University; &#13;
Tomsk Polytechnic University; &#13;
National Research Tomsk State University</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2021</year></pub-date><pub-date pub-type="epub"><day>27</day><month>11</month><year>2021</year></pub-date><volume>99</volume><issue>11</issue><fpage>27</fpage><lpage>34</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Аллилуев А.С., Филинюк О.В., Шнайдер Е.Е., Аксенов С.В., 2021</copyright-statement><copyright-year>2021</copyright-year><copyright-holder xml:lang="ru">Аллилуев А.С., Филинюк О.В., Шнайдер Е.Е., Аксенов С.В.</copyright-holder><copyright-holder xml:lang="en">Аlliluev A.S., Filinyuk O.V., Shnаyder E.E., Аksenov S.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.tibl-journal.com/jour/article/view/1586">https://www.tibl-journal.com/jour/article/view/1586</self-uri><abstract><sec><title>Цель исследования</title><p>Цель исследования: оценить возможность применения алгоритмов машинного обучения в прогнозировании рецидива у больных туберкулезом с множественной лекарственной устойчивостью (МЛУ-ТБ).</p></sec><sec><title>Материалы и методы</title><p>Материалы и методы. Проведен анализ клинико-эпидемиологических, возрастно-половых, социальных, медико-биологических параметров и особенностей химиотерапии у 346 излеченных пациентов с МЛУ-ТБ. При построении моделей прогнозирования использовались инструменты библиотеки scikit-learn Version 0.24.2 в интерактивной облачной среде работы с программным кодом Google Colaboratory.</p></sec><sec><title>Результаты</title><p>Результаты. Анализ характеристик моделей прогнозирования рецидивов у излеченных больных МЛУ-ТБ с помощью алгоритмов машинного обучения, включающих дерево решений, случайный лес, градиентный бустинг и логистическую регрессию, с использованием К-блочной стратифицированной проверки, выявил высокую чувствительность (0,74 ± 0,167; 0,91 ± 0,17; 0,91 ± 0,14; 0,91 ± 0,16 соответственно) и специфичность (0,97 ± 0,03; 0,98 ± 0,02; 0,98 ± 0,02; 0,98 ± 0,02 соответственно). Установлены пять основных предикторов развития рецидивов у излеченных больных МЛУ-ТБ: неоднократные курсы химиотерапии; длительность стажа туберкулеза; деструктивный процесс в легких; общий срок лечения менее 22 мес. и использование в схеме химиотерапии менее пяти эффективных противотуберкулезных препаратов.</p></sec></abstract><trans-abstract xml:lang="en"><p>The objective of the study: to evaluate the possibility of using machine learning algorithms for prediction of relapses in multiple drug resistant tuberculosis (MDR TB) patients.</p><sec><title>Subjects and Methods</title><p>Subjects and Methods. Сlinical, epidemiological, gender, sex, social, biomedical parameters and chemotherapy parameters were analyzed in 346 cured MDR TB patients. The tools of the scikit-learn library, Version 0.24.2 in the Google Colaboratory interactive cloud environment were used to build forecasting models.</p></sec><sec><title>Results</title><p>Results. Analysis of the characteristics of relapse prediction models in cured MDR TB patients using machine learning algorithms including decision tree, random forest, gradient boosting, and logistic regression using K-block stratified validation revealed high sensitivity (0.74 ± 0.167; 0.91 ± 0.17; 0.91 ± 0.14; 0.91 ± 0.16, respectively) and specificity (0.97 ± 0.03; 0.98 ± 0.02; 0.98 ± 0.02; 0.98 ± 0.02, respectively).</p><p>Five main predictors of relapse in cured MDR-TB patients were identified: repeated courses of chemotherapy; length of history of tuberculosis; destructive process in the lungs; total duration of treatment less than 22 months; and use of less than five effective anti-TB drugs in the regimen of chemotherapy.</p></sec></trans-abstract><kwd-group xml:lang="ru"><kwd>туберкулез</kwd><kwd>машинное обучение</kwd><kwd>множественная лекарственная устойчивость</kwd><kwd>рецидив</kwd><kwd>факторы риска</kwd><kwd>прогноз</kwd></kwd-group><kwd-group xml:lang="en"><kwd>tuberculosis</kwd><kwd>machine learning</kwd><kwd>multiple drug resistance</kwd><kwd>relapse</kwd><kwd>risk factors</kwd><kwd>forecast</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">Ghiasi M. M., Zendehboudi, S. Decision tree-based methodology to select a proper approach for wart treatment // Comp. Biol. Med. – 2019. – Vol. 4. – P. 400-409. DOI: 10.1016/j.compbiomed.2019.04.001. PMID: 31077954.</mixed-citation><mixed-citation xml:lang="en">Ghiasi M.M., Zendehboudi, S. Decision tree-based methodology to select a proper approach for wart treatment. Comp. Biol. Med., 2019, vol. 4, pp. 400-409. doi: 10.1016/j.compbiomed.2019.04.001. PMID: 31077954.</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Hou N., Li M., He L., Xie B., Wang L., Zhang R., Yu Y., Sun X., Pan Z., Wang K. Predicting 30-days mortality for MIMIC-III patients with sepsis-3: a machine learning approach using XGboost // J. Transl. Med. – 2020. ‒ Vol. 18, № 1. ‒ P. 462. DOI: 10.1186/s12967-020-02620-5. PMID: 33287854.</mixed-citation><mixed-citation xml:lang="en">Hou N., Li M., He L., Xie B., Wang L., Zhang R., Yu Y., Sun X., Pan Z., Wang K. Predicting 30-days mortality for MIMIC-III patients with sepsis-3: a machine learning approach using XGboost. J. Transl. Med., 2020, vol. 18, no. 1, pp. 462. doi: 10.1186/s12967-020-02620-5. PMID: 33287854.</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Inoue T., Ichikawa D., Ueno T., Cheong M., Inoue T., Whetstone W. D., Endo T., Nizuma K., Tominaga T. XGBoost, a machine learning method, predicts neurological recovery in patients with cervical spinal cord injury // Neurotrauma Reports. – 2020. – Vol. 1, № 1. ‒ P. 8-16. DOI:10.1089/neur.2020.0009.</mixed-citation><mixed-citation xml:lang="en">Inoue T., Ichikawa D., Ueno T., Cheong M., Inoue T., Whetstone W.D., Endo T., Nizuma K., Tominaga T. XGBoost, a machine learning method, predicts neurological recovery in patients with cervical spinal cord injury. Neurotrauma Reports, 2020, vol. 1, no. 1, pp. 8-16. doi:10.1089/neur.2020.0009.</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Ji C., Zou X., Hu Y., Liu S., Lyu L., Zheng X. XG-SF: An XGBoost classifier based on shapelet features for time series classification // Procedia Comp. Sci. – 2019. – Vol. 147. ‒ P. 24-28. DOI: 10.1016/j.procs.2019.01.179.</mixed-citation><mixed-citation xml:lang="en">Ji C., Zou X., Hu Y., Liu S., Lyu L., Zheng X. XG-SF: An XGBoost classifier based on shapelet features for time series classification. Procedia Comp. Sci., 2019, vol. 147, pp. 24-28. doi: 10.1016/j.procs.2019.01.179.</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Kouchaki S., Yang Y., Walker T. M., Walker S. A., Wilson D. J., Peto T., Crook D. W., CRyPTIC Consortium; Clifton D. A. Application of machine learning techniques to tuberculosis drug resistance analysis // Bioinformatics. – 2019. – Vol. 35, № 13. – Р. 2276-2282. DOI:10.1093/bioinformatics/bty949. PMID: 30462147.</mixed-citation><mixed-citation xml:lang="en">Kouchaki S., Yang Y., Walker T.M., Walker S.A., Wilson D.J., Peto T., Crook D.W., CRyPTIC Consortium; Clifton D. A. Application of machine learning techniques to tuberculosis drug resistance analysis. Bioinformatics, 2019, vol. 35, no. 13, pp. 2276-2282. doi:10.1093/bioinformatics/bty949. PMID: 30462147.</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Lakhani P., Sundaram B. Deep learning at chest radiography: automated classification of pulmonary tuberculosis by using convolutional neural networks // Radiology. – 2017. – Vol. 284, №. 2. – Р. 574-582. DOI: 10.1148/radiol.2017162326. PMID: 28436741.</mixed-citation><mixed-citation xml:lang="en">Lakhani P., Sundaram B. Deep learning at chest radiography: automated classification of pulmonary tuberculosis by using convolutional neural networks. Radiology, 2017, vol. 284, no. 2, pp. 574-582. doi: 10.1148/radiol.2017162326. PMID: 28436741.</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Lange C. et al. Management of patients with multidrug-resistant tuberculosis // Intern. J. Tuberc. Lung Dis. – 2019. – Vol. 23, № 6. – Р. 645-662. DOI: 10.5588/ijtld.18.0622. PMID: 31315696.</mixed-citation><mixed-citation xml:lang="en">Lange C. et al. Management of patients with multidrug-resistant tuberculosis. Intern. J. Tuberc. Lung Dis., 2019, vol. 23, no. 6, pp. 645-662. doi: 10.5588/ijtld.18.0622. PMID: 31315696.</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Pal K., Patel B. V. Data classification with k-fold cross validation and holdout accuracy estimation methods with 5 different machine learning techniques // Proceedings of the 2020 Fourth International Conference on Computing Methodologies and Communication (ICCMC) – 2020. pp. 83-87. DOI: 10.1109/ICCMC48092.2020.ICCMC-00016.</mixed-citation><mixed-citation xml:lang="en">Pal K., Patel B.V. Data classification with k-fold cross validation and holdout accuracy estimation methods with 5 different machine learning techniques. Proceedings of the 2020 Fourth International Conference on Computing Methodologies and Communication (ICCMC). 2020, pp. 83-87. doi: 10.1109/ICCMC48092.2020.ICCMC-00016.</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Rajkomar A., Dean J., Kohane I. Machine learning in medicine // N. Engl. J. Med. – 2019. – Vol. 380, № 14. – Р. 1347-1358.</mixed-citation><mixed-citation xml:lang="en">Rajkomar A., Dean J., Kohane I. Machine learning in medicine. N. Engl. J. Med., 2019, vol. 380, no. 14, pp. 1347-1358.</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Shi Yu, Wong W.-K., Goldin J. G., Brown M. S., Kim G. H. J. Prediction of progression in idiopathic pulmonary fibrosis using CT scans at baseline: a quantum particle swarm optimization ‒ random forest approach // Artif. Intellig. Med. ‒ 2019. – Vol. 100, № 7. – P. 101719. DOI: 10.1016/j.artmed.2019.101709. PMID: 31607341.</mixed-citation><mixed-citation xml:lang="en">Shi Yu, Wong W.K., Goldin J.G., Brown M.S., Kim G.H.J. Prediction of progression in idiopathic pulmonary fibrosis using CT scans at baseline: a quantum particle swarm optimization ‒ random forest approach. Artif. Intellig. Med., 2019, vol. 100, no. 7, pp. 101719. doi: 10.1016/j.artmed.2019.101709. PMID: 31607341.</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">World Health Organization. Tuberculosis surveillance and monitoring in Europe 2019: 2017 data. – 2019.</mixed-citation><mixed-citation xml:lang="en">World Health Organization. Tuberculosis surveillance and monitoring in Europe 2019: 2017 data. 2019.</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Yim J. J., Koh W. J. MDR-TB recurrence after successful treatment: additional studies using molecular genotyping are needed // Intern. J. Tuberc. Lung Dis. – 2015. – Vol. 19, №. 4. – Р. 371. DOI: 10.5588/ijtld.15.0117. PMID: 25859987.</mixed-citation><mixed-citation xml:lang="en">Yim J.J., Koh W.J. MDR-TB recurrence after successful treatment: additional studies using molecular genotyping are needed. Intern. J. Tuberc. Lung Dis., 2015, vol. 19, no. 4, pp. 371. doi: 10.5588/ijtld.15.0117. PMID: 25859987.</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Yoshiyama T., Morimoto K., Okumura M., Sasaki Y., Ogata H., Shiraishi Y., Kudou S. Long term outcome of multidrug-resistant TB patients in Fukujuji Hospital in Japan // Trans. Roy. Soc. Trop. Med. Hyg. – 2014. – Vol. 108, №. 9. – Р. 589-590. DOI: 10.1093/trstmh/tru080. PMID: 24902580.</mixed-citation><mixed-citation xml:lang="en">Yoshiyama T., Morimoto K., Okumura M., Sasaki Y., Ogata H., Shiraishi Y., Kudou S. Long term outcome of multidrug-resistant TB patients in Fukujuji Hospital in Japan. Trans. Roy. Soc. Trop. Med. Hyg., 2014, vol. 108, no. 9, pp. 589-590. doi: 10.1093/trstmh/tru080. PMID: 24902580.</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Zhao X., Liu Y., Zhang A., Gao B., Feng Q., Huang H., Zhu X., Sun X., Xu D. Logistic regression analyses of factors affecting fertility of intrauterine adhesions patients // Ann. Transl. Med. – 2020. ‒ Vol. 8, № 4. ‒ P. 49. DOI: 10.21037/atm.2019.11.115. PMID: 32175343.</mixed-citation><mixed-citation xml:lang="en">Zhao X., Liu Y., Zhang A., Gao B., Feng Q., Huang H., Zhu X., Sun X., Xu D. Logistic regression analyses of factors affecting fertility of intrauterine adhesions patients. Ann. Transl. Med., 2020, vol. 8, no. 4, pp. 49. doi: 10.21037/atm.2019.11.115. PMID: 32175343.</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Zumla A. et al. World Tuberculosis Day 2021 Theme – ‘The Clock is Ticking’ – and the world is running out of time to deliver the United Nations General Assembly commitments to End TB due to the COVID-19 pandemic // Intern. J. Infect. Dis. – 2021. DOI: 10.1016/j.ijid.2021.03.046. PMID: 33746094.</mixed-citation><mixed-citation xml:lang="en">Zumla A. et al. World Tuberculosis Day 2021 Theme – ‘The Clock is Ticking’ – and the world is running out of time to deliver the United Nations General Assembly commitments to End TB due to the COVID-19 pandemic. Intern. J. Infect. Dis., 2021. doi: 10.1016/j.ijid.2021.03.046. PMID: 33746094.</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>
