<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE root>
<article 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" xmlns:ali="http://www.niso.org/schemas/ali/1.0/" article-type="research-article" dtd-version="1.2" xml:lang="en"><front><journal-meta><journal-id journal-id-type="publisher-id">Russian Journal of Pediatric Surgery, Anesthesia and Intensive Care</journal-id><journal-title-group><journal-title xml:lang="en">Russian Journal of Pediatric Surgery, Anesthesia and Intensive Care</journal-title><trans-title-group xml:lang="ru"><trans-title>Российский вестник детской хирургии, анестезиологии и реаниматологии</trans-title></trans-title-group></journal-title-group><issn publication-format="print">2219-4061</issn><issn publication-format="electronic">2587-6554</issn><publisher><publisher-name xml:lang="en">Eco-Vector</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="publisher-id">1911</article-id><article-id pub-id-type="doi">10.17816/psaic1911</article-id><article-id pub-id-type="edn">IFNZIM</article-id><article-categories><subj-group subj-group-type="toc-heading" xml:lang="en"><subject>Original Study Articles</subject></subj-group><subj-group subj-group-type="toc-heading" xml:lang="ru"><subject>Оригинальные исследования</subject></subj-group><subj-group subj-group-type="article-type"><subject>Research Article</subject></subj-group></article-categories><title-group><article-title xml:lang="en">Stratification of kidney damage severity in children with vesicoureteral reflux based on cluster analysis of imaging data</article-title><trans-title-group xml:lang="ru"><trans-title>Стратификация тяжести повреждения почек у детей с пузырно-мочеточниковым рефлюксом на основе кластерного анализа данных визуализации</trans-title></trans-title-group><trans-title-group xml:lang="zh"><trans-title>基于影像数据聚类分析的儿童膀胱输尿管反流肾损伤严重程度分层</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-2243-7073</contrib-id><contrib-id contrib-id-type="spin">9281-4273</contrib-id><name-alternatives><name xml:lang="en"><surname>Demidova</surname><given-names>Karmina N.</given-names></name><name xml:lang="ru"><surname>Демидова</surname><given-names>Кармина Насимджоновна</given-names></name><name xml:lang="zh"><surname>Demidova</surname><given-names>Karmina N.</given-names></name></name-alternatives><address><country country="RU">Russian Federation</country></address><bio xml:lang="en"><p>MD, Cand. Sci. (Medicine)</p></bio><bio xml:lang="ru"><p>канд. мед. наук</p></bio><bio xml:lang="zh"><p>MD, Cand. Sci. (Medicine)</p></bio><email>negmatova.karmina@mail.ru</email><xref ref-type="aff" rid="aff1"/></contrib><contrib contrib-type="author"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-3718-8911</contrib-id><contrib-id contrib-id-type="spin">6989-5041</contrib-id><name-alternatives><name xml:lang="en"><surname>Rostovskaya</surname><given-names>Vera V.</given-names></name><name xml:lang="ru"><surname>Ростовская</surname><given-names>Вера Васильевна</given-names></name><name xml:lang="zh"><surname>Rostovskaya</surname><given-names>Vera V.</given-names></name></name-alternatives><address><country country="RU">Russian Federation</country></address><bio xml:lang="en"><p>MD, Dr. Sci. (Medicine)</p></bio><bio xml:lang="ru"><p>д-р мед. наук</p></bio><bio xml:lang="zh"><p>MD, Dr. Sci. (Medicine)</p></bio><email>rostovskaya_vera@mail.ru</email><xref ref-type="aff" rid="aff1"/><xref ref-type="aff" rid="aff2"/></contrib><contrib contrib-type="author"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-5957-7037</contrib-id><contrib-id contrib-id-type="spin">7990-4317</contrib-id><name-alternatives><name xml:lang="en"><surname>Kuzovleva</surname><given-names>Galina I.</given-names></name><name xml:lang="ru"><surname>Кузовлева</surname><given-names>Галина Игоревна</given-names></name><name xml:lang="zh"><surname>Kuzovleva</surname><given-names>Galina I.</given-names></name></name-alternatives><address><country country="RU">Russian Federation</country></address><bio xml:lang="en"><p>MD, Cand. Sci. (Medicine)</p></bio><bio xml:lang="ru"><p>канд. мед. наук</p></bio><bio xml:lang="zh"><p>MD, Cand. Sci. (Medicine)</p></bio><email>dr.gala@mail.ru</email><xref ref-type="aff" rid="aff1"/><xref ref-type="aff" rid="aff2"/></contrib><contrib contrib-type="author"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-3251-6904</contrib-id><name-alternatives><name xml:lang="en"><surname>Starostina</surname><given-names>Irina E.</given-names></name><name xml:lang="ru"><surname>Старостина</surname><given-names>Ирина Евгеньевна</given-names></name><name xml:lang="zh"><surname>Starostina</surname><given-names>Irina E.</given-names></name></name-alternatives><address><country country="RU">Russian Federation</country></address><email>irinamadness1@gmail.com</email><xref ref-type="aff" rid="aff3"/></contrib></contrib-group><aff-alternatives id="aff1"><aff><institution xml:lang="en">I.M. Sechenov First Moscow State Medical University</institution></aff><aff><institution xml:lang="ru">Первый Московский государственный медицинский университет им. И.М. Сеченова</institution></aff><aff><institution xml:lang="zh">I.M. Sechenov First Moscow State Medical University</institution></aff></aff-alternatives><aff-alternatives id="aff2"><aff><institution xml:lang="en">Speransky Children’s Hospital No. 9</institution></aff><aff><institution xml:lang="ru">Детская городская клиническая больница № 9 им. Г.Н. Сперанского</institution></aff><aff><institution xml:lang="zh">Speransky Children’s Hospital No. 9</institution></aff></aff-alternatives><aff-alternatives id="aff3"><aff><institution xml:lang="en">DocMed Evidence-Based Medicine Clinic</institution></aff><aff><institution xml:lang="ru">Клиника доказательной медицины DocMed</institution></aff><aff><institution xml:lang="zh">DocMed Evidence-Based Medicine Clinic</institution></aff></aff-alternatives><pub-date date-type="pub" iso-8601-date="2026-05-02" publication-format="electronic"><day>02</day><month>05</month><year>2026</year></pub-date><volume>26</volume><issue>1</issue><issue-title xml:lang="en"/><issue-title xml:lang="ru"/><fpage>29</fpage><lpage>38</lpage><history><date date-type="received" iso-8601-date="2025-05-12"><day>12</day><month>05</month><year>2025</year></date><date date-type="accepted" iso-8601-date="2026-03-16"><day>16</day><month>03</month><year>2026</year></date></history><permissions><copyright-statement xml:lang="en">Copyright ©; 2026, Eco-Vector</copyright-statement><copyright-statement xml:lang="ru">Copyright ©; 2026, Эко-Вектор</copyright-statement><copyright-statement xml:lang="zh">Copyright ©; 2026,</copyright-statement><copyright-year>2026</copyright-year><copyright-holder xml:lang="en">Eco-Vector</copyright-holder><copyright-holder xml:lang="ru">Эко-Вектор</copyright-holder><license><ali:license_ref xmlns:ali="http://www.niso.org/schemas/ali/1.0/">https://creativecommons.org/licenses/by-nc-nd/4.0</ali:license_ref></license></permissions><self-uri xlink:href="https://rps-journal.ru/jour/article/view/1911">https://rps-journal.ru/jour/article/view/1911</self-uri><abstract xml:lang="en"><p><bold>BACKGROUND:<italic> </italic></bold>Vesicoureteral reflux is one of the most important risk factors for the development of urinary tract infections in children, leading to renal parenchymal injury. Assessment of the severity of vesicoureteral reflux based on imaging modalities does not always correlate with the reflux grade, which complicates the selection of patient management strategies.</p> <p><bold>AIM:</bold> The work aimed to evaluate the feasibility of using cluster analysis for stratification of the degree of structural and kidney function damage in children with vesicoureteral reflux based on imaging data.</p> <p><bold>METHODS:<italic> </italic></bold>The study included 101 patients (143 renal units) aged 1 month to 7 years. Renal imaging methods were used, including Doppler ultrasound, static renal scintigraphy, and excretory urography. Clustering of the diagnostic dataset was performed using the TwoStep cluster method (SPSS Statistics, version 23.0; IBM, USA), which allows for simultaneous analysis of quantitative and qualitative variables. The optimal number of clusters was determined using the silhouette coefficient.</p> <p><bold>RESULTS:</bold> Cluster analysis identified four clusters of renal units (RUs): cluster 1, with no changes in renal structure, hemodynamics, or function (34 RUs); cluster 2, with minor changes and early signs of nephrosclerosis (55 RUs); cluster 3, with moderate impairment (45 RUs); and cluster 4, with pronounced changes in the renal parenchyma (9 RUs). A trend toward an increase in the number of renal units in clusters 3 and 4 with increasing grade of vesicoureteral reflux was observed: at grades 1–2, clusters 1 and 2 predominated; at grade 3, clusters 2 and 3; and at grades 4–5, cluster 4 predominated.</p> <p><bold>CONCLUSION:</bold> Cluster analysis of imaging data enabled stratification of the severity of kidney damage in children with vesicoureteral reflux using a multidimensional analytical approach.</p></abstract><trans-abstract xml:lang="ru"><p><bold>Обоснование.</bold> Пузырно-мочеточниковый рефлюкс— один из наиболее значимых факторов риска развития инфекции мочевыводящих путей у детей, приводящей к повреждению почечной паренхимы. Оценка тяжести пузырно-мочеточникового рефлюкса по данным визуализационных методов не всегда коррелирует со степенью рефлюкса, что затрудняет выбор тактики ведения пациентов.</p> <p><bold>Цель исследования.</bold> Оценить возможность применения кластерного анализа для стратификации степени структурно-функционального повреждения почек у детей с пузырно-мочеточниковым рефлюксом на основе данных лучевых методов исследования.</p> <p><bold>Методы.</bold> В исследование включен 101 пациент (143 почечные единицы) в возрасте от 1 месяца до 7 лет. Использованы методы визуализации почек, включая ультразвуковое исследование с допплерографией, статическую нефросцинтиграфию и экскреторную урографию. Кластеризация совокупности диагностических данных выполнена методом TwoStep Cluster (двухэтапный кластерный анализ) (SPSS Statistics v23.0, IBM, США), обеспечивающим одновременный анализ количественных и качественных признаков. Оптимальное число кластеров определяли по силуэтному коэффициенту.</p> <p><bold>Результаты.</bold> В результате кластерного анализа выделены 4 кластера почечных единиц (ПЕ): первый — без изменений структуры, гемодинамики и функции почек (34 ПЕ), второй — с незначительными изменениями и начальными признаками нефросклероза (55 ПЕ), третий — с умеренными нарушениями (45 ПЕ), и четвертый — с выраженными изменениями почечной паренхимы (9 ПЕ). Отмечена тенденция увеличения числа ПЕ в 3-м и 4-м кластерах с возрастанием степени пузырно-мочеточникового рефлюкса: при I–II степени преобладали кластеры 1 и 2, при III — 2 и 3, при IV и V степенях — 4-й кластер.</p> <p><bold>Заключение.</bold> Применение кластерного анализа данных визуализации позволило стратифицировать степень тяжести повреждения почек при пузырно-мочеточниковом рефлюксе у детей с использованием многомерного аналитического подхода.</p></trans-abstract><trans-abstract xml:lang="zh"><p>论证。膀胱输尿管反流是导致儿童泌尿系统感染最重要的风险因素之一，可能引发肾实质损伤。 影像学方法对膀胱输尿管反流严重程度的评估，并不总能与反流程度完全吻合，这为患者治疗策略的选择带来了困难。</p> <p>目的。评估应用聚类分析法基于放射学检查数据对儿童膀胱输尿管反流所致肾脏结构功能损害程度进行分层的可行性。</p> <p>方法。该研究纳入了101名患者（143个肾脏单位），年龄范围从1个月至7岁。采用的肾脏影像学检查方法包括超声多普勒血流成像、静态肾闪烁扫描及排泄性尿路造影。诊断数据总体的聚类采用TwoStep Cluster（两步聚类分析）法（SPSS Statistics v23.0，IBM，美国）完成，该方法支持定量与定性特征的同时分析。通过轮廓系数确定最优簇数。</p> <p>结果。通过聚类分析共识别出4类肾单位（PE）：第一类为结构、血流动力学及肾功能均无异常者 （34个PE），第二类为存在轻微变化及早期肾硬化迹象者（55个PE），第三类为中度功能受损者 （45个PE），第四类为肾实质显著病变者（9个PE）。注意到一种趋势：随着膀胱输尿管反流程度的加重，第3和第4簇中PE数量增加：I-II度时以第1和第2簇为主，III度时以第2和第3簇为主，IV度和V度时则以第4簇为主。</p> <p>结论。通过采用多变量分析方法对可视化数据进行聚类分析，实现了对儿童膀胱输尿管反流所致肾脏损伤严重程度的分层评估。</p></trans-abstract><kwd-group xml:lang="en"><kwd>primary vesicoureteral reflux</kwd><kwd>kidney diseases</kwd><kwd>cluster analysis</kwd><kwd>stratification</kwd><kwd>children</kwd></kwd-group><kwd-group xml:lang="ru"><kwd>первичный пузырно-мочеточниковый рефлюкс</kwd><kwd>повреждение почек</kwd><kwd>кластерный анализ</kwd><kwd>стратификация</kwd><kwd>дети</kwd></kwd-group><kwd-group xml:lang="zh"><kwd>原发性膀胱输尿管反流</kwd><kwd>肾脏损伤</kwd><kwd>聚类分析</kwd><kwd>风险分层</kwd><kwd>儿童</kwd></kwd-group><funding-group/></article-meta></front><body></body><back><ref-list><ref id="B1"><label>1.</label><mixed-citation>Gnech M, ‘t Hoen L, Zachou A, et al. Update and summary of the European Association of Urology/European Society of Paediatric Urology paediatric guidelines on vesicoureteral reflux in children. Eur Urol. 2024;85(5):433–442. doi: 10.1016/j.eururo.2023.12.005</mixed-citation></ref><ref id="B2"><label>2.</label><mixed-citation>Morozova OL, Lakomova DY, Zakharova NB, et al. Reflux nephropathy in children: pathogenesis and prognosis. Part 1. Urologiia. 2021;(3):150–154. doi: 10.18565/urology.2021.3.150-154 EDN: BKXWTV</mixed-citation></ref><ref id="B3"><label>3.</label><mixed-citation>Andrioli V, Regacini R, Aguiar W. Primary Vesicoureteral reflux and chronic kidney disease in pediatric population. What we have learnt? Int Braz J Urol. 2020;46(2):262–268. doi: 10.1590/S1677-5538.IBJU.2020.02.02</mixed-citation></ref><ref id="B4"><label>4.</label><mixed-citation>Hewitt I, Montini G. Vesicoureteral reflux is it important to find? Pediatr Nephrol. 2021;36(4):1011–1017. doi: 10.1007/s00467-020-04573-9</mixed-citation></ref><ref id="B5"><label>5.</label><mixed-citation>Aboutaleb H, Abouelgreed TA, El-Hagrasi H, et al. Correlation of renal scarring to urinary tract infections and vesicoureteral reflux in children. Adv Urol. 2022:9697931. doi: 10.1155/2022/9697931</mixed-citation></ref><ref id="B6"><label>6.</label><mixed-citation>Woo LL. “Bottoms Up!”: A Toast to reexamining the debate of top-down vs bottom-up approach for the evaluation of febrile urinary tract infection. J Urol. 2021;206(5):1095–1096. doi: 10.1097/JU.0000000000002171</mixed-citation></ref><ref id="B7"><label>7.</label><mixed-citation>Simičić Majce A, Arapović A, Čapkun V, et al. The spectrum of parenchymal changes in kidneys affected by intrarenal reflux, diagnosed by contrast-enhanced voiding urosonography and DMSA scan. Front Pediatr. 2022;10:886112. doi: 10.3389/fped.2022.886112</mixed-citation></ref><ref id="B8"><label>8.</label><mixed-citation>Pavlov AY, Sabirzyanova ZR. Clinical interpretation of the results of radionuclide research methods in the evaluation of diseases of the urinary system in children (lecture). Bashkortostan Medical Journal. 2023;18(1):103–108. EDN: FEHSLN</mixed-citation></ref><ref id="B9"><label>9.</label><mixed-citation>Läckgren G, Cooper CS, Neveus T, Kirsch AJ. Management of vesicoureteral reflux: what have we learned over the last 20 years? Front Pediatr. 2021;9:650326. doi: 10.3389/fped.2021.650326</mixed-citation></ref><ref id="B10"><label>10.</label><mixed-citation>Marzuillo P, La Manna A, Palma PL, et al. Voiding cystourethrography for the pediatric nephrologist: clinical value, challenges, and areas of debate. Pediatr Nephrol. 2025;41:1278–1301. doi: 10.1007/s00467-025-06901-3</mixed-citation></ref><ref id="B11"><label>11.</label><mixed-citation>Morozova OL, Lakomova DY, Zakharova NB, et al. Reflux nephropathy in children: pathogenesis and prognosis. Part 2. Urologiia. 2021;(4):145–151. doi: 10.18565/urology.2021.4.145-151 EDN: KBLOVE</mixed-citation></ref><ref id="B12"><label>12.</label><mixed-citation>Valério FC, Lemos RD, de C Reis AL, et al. Biomarkers in vesicoureteral reflux: an overview. Biomark Med. 2020;14(8):683–696. doi: 10.2217/bmm-2019-0378</mixed-citation></ref><ref id="B13"><label>13.</label><mixed-citation>Mirkin BG. Cluster analysis methods for decision support: A review. Moscow: Publishing House of the National Research University “HSE”; 2011. 84 p. EDN: QUSUXH (In Russ.)</mixed-citation></ref><ref id="B14"><label>14.</label><mixed-citation>Alsova OK. Algorithms for clustering of a heterogeneous data on the example of solution of the medical task. In: SPIIRAS proceedings. Vol. 37. Saint Petersburg, 2014. P. 156–169. EDN: TELOKB</mixed-citation></ref><ref id="B15"><label>15.</label><mixed-citation>Lee J, Warner E, Shaikhouni S, et al. Clustering-based spatial analysis (CluSA) framework through graph neural network for chronic kidney disease prediction using histopathology images. Sci Rep. 2023;13:12701. doi: 10.1038/s41598-023-39591-8</mixed-citation></ref><ref id="B16"><label>16.</label><mixed-citation>Saito H, Yoshimura H, Tanaka K, et al. Predicting CKD progression using time series clustering and light gradient boosting machines. Sci Rep. 2024;14(1):1723. doi: 10.1038/s41598-024-52251-9</mixed-citation></ref><ref id="B17"><label>17.</label><mixed-citation>Cummins T, Merchant М, Rane M, et al. Urine biomarker analysis of pediatric nephrotic syndrome: FR-PO661. J Am Soc Nephrol. 2023;34(11S):584. doi: 10.1681/ASN.20233411S1584c</mixed-citation></ref><ref id="B18"><label>18.</label><mixed-citation>Sherman MA, Gunawardana A, Amirault JP, et al. Autoantibody cluster analysis in juvenile lupus nephritis. Clin Rheumatol. 2022;41(8):2375–2381. doi: 10.1007/s10067-022-06146-7</mixed-citation></ref><ref id="B19"><label>19.</label><mixed-citation>Schneider AJ, Grimes M, Lyon W, et al. Cluster analysis of men undergoing surgery for BPH/LUTS reveals prominent roles of both bladder outlet obstruction and diminished bladder contractility. PLoS ONE. 2021;16(5):0251721. doi: 10.1371/journal.pone.0251721</mixed-citation></ref><ref id="B20"><label>20.</label><mixed-citation>Andreev VP, Helmuth ME, Liu G, et al. Subtyping of common complex diseases and disorders by integrating heterogeneous data. Identifying clusters among women with lower urinary tract symptoms in the LURN study. PLoS One. 2022;17(6):0268547. doi: 10.1371/journal.pone.0268547</mixed-citation></ref><ref id="B21"><label>21.</label><mixed-citation>Nithya А, Appadurai А, Venkatadri N, et al. Кidney disease detection and segmentation using artificial neural network and multi-kernel k-means clustering for ultrasound images. Measurement. 2020;149:106952. doi: 10.1016/j.2019.106952</mixed-citation></ref><ref id="B22"><label>22.</label><mixed-citation>Chiglintsev KA, Zyryanov AV, Chiglintsev AYu. Cluster analysis of the main parameters of homeostasis with kidney injury. Urologiia. 2021;(4):25–29. doi: 10.18565/urology.2021.4.25-29 EDN: ACJPLA</mixed-citation></ref><ref id="B23"><label>23.</label><mixed-citation>Тzelves L, Feretzakis G, Kalles D, et al. Cluster analysis assessment in proposing a surgical technique for benign prostatic enlargement. Stud Health Technol Inform. 2022;295:466–469. doi: 10.3233/SHTI220766</mixed-citation></ref><ref id="B24"><label>24.</label><mixed-citation>Fazelinia H, Ding H, Taylor D, et al. Stratification of neurogenic bladder risk in spina bifida using the urinary peptidome. Am J Physiol Renal Physiol. 2024;326(2):241–248. doi: 10.1152/ajprenal.00267.2023</mixed-citation></ref><ref id="B25"><label>25.</label><mixed-citation>De Ruysscher C, Pien L, Tailly T, et al. Risk factors for recurrent urolithiasis in children. J Pediatr Urol. 2020;16(1):34.e1–34.e9. doi: 10.1016/j.jpurol.2019.09.021</mixed-citation></ref><ref id="B26"><label>26.</label><mixed-citation>Fernandez N, Maxwell A, Noonavath M, Shnorhavoriana M. Comprehensive multidisciplinary phenotyping of patients with hypospadias. A pilot study. J Pediatr Urol. 2023;19(4):397.e1–397.e7. doi: 10.1016/j.jpurol.2023.04.005</mixed-citation></ref><ref id="B27"><label>27.</label><mixed-citation>Patent RU No. 2270605/ 27.02.2006. Yatsyk SP, Zubovsky GA, Fomin DK. A method for assessing the viability of renal parenchyma. (In Russ.)</mixed-citation></ref><ref id="B28"><label>28.</label><mixed-citation>Bacher J, Wenzig K, Vogler M. SPSS TwoStep cluster — a first evaluation. University Erlangen-Nürnberg: Lehrstuhl für Soziologie; 2004.</mixed-citation></ref><ref id="B29"><label>29.</label><mixed-citation>Kent P, Jensen RK, Kongsted A. A comparison of three clustering methods for finding subgroups in MRI, SMS or clinical data: SPSS TwoStep cluster analysis, latent gold and SNOB. BMC Med Res Methodol. 2014;14:113. doi: 10.3386/1471-2288-14-113</mixed-citation></ref><ref id="B30"><label>30.</label><mixed-citation>Costea RM, Maniu I, Dobrota L, et al. Exploring inflammatory status in febrile seizures associated with urinary tract infections: A two-step cluster approach. Brain Sci. 2021;11(9):1168. doi: 10.3390/brainsci11091168</mixed-citation></ref><ref id="B31"><label>31.</label><mixed-citation>Preda I, Jodal U, Sixt R, et al. Normal dimercaptosuccinic acid scintigraphy makes voiding cystourethrography unnecessary after urinary tract infection. J Pediatr. 2007;151(6):581–584. doi: 10.1016/j.jpeds.2007.05.008</mixed-citation></ref><ref id="B32"><label>32.</label><mixed-citation>Herz DB. The top-down approach: an expanded methodology. J Urol. 2010;183(3):856–857. doi: 10.1016/j.juro.2009.12.062</mixed-citation></ref></ref-list></back></article>
