rospedРоссийский педиатрический журнал имени М.Я. СтуденикинаM.Ya. Studenikin Russian Pediatric JournalФГАУ «НМИЦ здоровья детей» Минздрава России10.46563/1560-9561-2025-28-4-282-287rosped-1665Research ArticleОБЗОРЫREVIEWSИскусственный интеллект и нейронные сети в детской урологииArtificial intelligence and neural networks in pediatric urologyhttps://orcid.org/0000-0002-4038-1472ЗоркинСергей НиколаевичZorkinSergey N.zorkin@nczd.ruhttps://orcid.org/0000-0002-2809-1894БаязитовРимир РадиковичBayazitovRimir R.i@rbayazitov.ruhttps://orcid.org/0000-0001-8663-2698ГурскаяАлександра СергеевнаGurskayaAleksandra S.aldra_gur@mail.ruhttps://orcid.org/0000-0001-5098-2266ЕкимовскаяЕкатерина ВикторовнаEkimovskayaEkaterina V.ekimovskaia.ev@nczd.ruФГАУ «Национальный медицинский исследовательский центр здоровья детей» Минздрава РоссииNational Medical Research Center for Children’s Health202505092025284282287Copyright © Зоркин С.Н., Баязитов Р.Р., Гурская А.С., Екимовская Е.В., 20252025Зоркин С.Н., Баязитов Р.Р., Гурская А.С., Екимовская Е.В.Zorkin S.N., Bayazitov R.R., Gurskaya A.S., Ekimovskaya E.V.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://www.rosped.ru/jour/article/view/1665

Введение. Искусственный интеллект (ИИ) и нейронные сети являются мощными инструментами, которые могут анализировать большие объёмы данных, выявлять закономерности и делать прогнозы. Применяемые в диагностике урологических заболеваний у детей ультразвуковые исследования, рентгенография, сцинтиграфия и расчётные данные (степени, размеры, индексы) являются идеальным объектом для обучения алгоритмов компьютерного зрения с целью автоматического анализа и расчёта интересующих врача показателей. Предложены различные модели ИИ для прогнозирования исходов лечения, рисков осложнений, разработки персонализированной терапии. ИИ позволяет снижать нагрузку на медицинский персонал, поскольку автоматизирует рутинные задачи. Система поддержки принятия решений, возможности удалённого мониторинга за пациентами, виртуальные симуляторы, чат-боты и ассистенты — технологии, крайне востребованные в медицине. Однако есть и ряд ограничений применения ИИ. Необходимо помнить, что алгоритмы тестируют на идеально подготовленных массивах данных, тогда как в реальной практике врачи сталкиваются с неполной информацией, техническими артефактами и нетипичными случаями. Поэтому для успешной интеграции моделей ИИ в детскую урологию необходимо обеспечить высокое качество данных для машинного обучения, безопасность сбора и хранения персональных данных пациентов, соблюдение этических норм. Цель: провести анализ данных применения ИИ в детской урологии при диагностике пузырно-мочеточникового рефлюкса, гидронефроза, гипоспадии, клапана задней уретры. Проведён систематический поиск научных публикаций в базах данных PubMed, Scopus, Google Scholar, eLIBRARY.RU за 2018–2024 гг. В выборку включены клинические исследования (n ≥ 50), метаанализы, для систематических обзоров применяли PRISMA-методологию. Интеграция технологий ИИ в клиническую практику обладает большим потенциалом для решения клинических задач в детской урологии. Ограничениями для успешного внедрения остаются недостаточная надёжность существующих моделей и отсутствие адаптированных для клинического применения алгоритмов.

Introduction. Artificial intelligence (AI) and neural networks are powerful tools that can analyze large amounts of data, identify patterns, and make forecastings. Ultrasound, radiography, scintigraphy, and the quantitative indices (degrees, sizes, indices) used in the diagnosis of urological diseases in children are an ideal object for training computer vision algorithms for the purpose of automatic analysis and calculation of the indices of interest to the doctor. Various AI models have been proposed for predicting treatment outcomes, risks of complications, and developing personalized therapy. AI can reduce the workload on medical personnel by automating routine tasks. A decision support system, remote patient monitoring capabilities, virtual simulators, chatbots, and assistants are technologies that are in high demand among health workers. However, there is a number of limitations to the use of AI. It is important to remember that algorithms are tested on ideally prepared data sets, while in real practice, doctors are faced with incomplete information, technical artifacts, and atypical cases. Therefore, for the successful integration of AI models into pediatric urology, it is necessary to ensure high quality of data for machine learning, security of collection and storage of personal patient data, and compliance with ethical standards. Aim. To analyze the literature data on the use of AI in pediatric urology in the world and Russia in the diagnosis of vesicoureteral reflux, hydronephrosis, hypospadias, posterior urethral valve. A systematic search of scientific publications was conducted in the PubMed, Scopus, Google Scholar, eLibrary.ru databases for the period 2018–2024. The sample included clinical studies (n ≥ 50), meta-analyses, and PRISMA methodology was used for systematic reviews. The integration of AI technologies into clinical practice has great potential for solving clinical problems in pediatric urology. The limitations for successful implementation remain the insufficient reliability of existing models and the lack of algorithms adapted for the clinical use.

обзорискусственная нейронная сетьискусственный интеллектмашинное обучениедетская урологияliterature reviewartificial neural networkartificial intelligencemachine learningpediatric urologyReferencesChen J., Remulla D., Nguyen J.H., Dua A., Liu Y., Dasgupta P., et al. Current status of artificial intelligence applications in urology and their potential to influence clinical practice. BJU Int. 2019; 124(4): 567–77. https://doi.org/10.1111/bju.14852Chen J., Remulla D., Nguyen J.H., Dua A., Liu Y., Dasgupta P., et al. Current status of artificial intelligence applications in urology and their potential to influence clinical practice. BJU Int. 2019; 124(4): 567–77. https://doi.org/10.1111/bju.14852Scott Wang H.H., Vasdev R., Nelson C.P. Artificial intelligence in pediatric urology. Urol. Clin. North Am. 2024; 51(1): 91–103. https://doi.org/10.1016/j.ucl.2023.08.002Scott Wang H.H., Vasdev R., Nelson C.P. Artificial intelligence in pediatric urology. Urol. Clin. North Am. 2024; 51(1): 91–103. https://doi.org/10.1016/j.ucl.2023.08.002Cooper C.S. A potpourri of pediatric urology: the winds of change. J. Pediatr. Urol. 2025; 21(3): 793–5. https://doi.org/10.1016/j.jpurol.2025.04.020Cooper C.S. A potpourri of pediatric urology: the winds of change. J. Pediatr. Urol. 2025; 21(3): 793–5. https://doi.org/10.1016/j.jpurol.2025.04.020Khondker A., Kwong J.C.C., Malik S., Erdman L., Keefe D.T., Fernandez N., et al. The state of artificial intelligence in pediatric urology. Front. Urol. 2022; 2: 1024662. https://doi.org/10.3389/fruro.2022.1024662Khondker A., Kwong J.C.C., Malik S., Erdman L., Keefe D.T., Fernandez N., et al. The state of artificial intelligence in pediatric urology. Front. Urol. 2022; 2: 1024662. https://doi.org/10.3389/fruro.2022.1024662Lorenzo A.J., Rickard M., Braga L.H., Guo Y., Oliveria J.P. Predictive analytics and modeling employing machine learning technology: the next step in data sharing, analysis, and individualized counseling explored with a large, prospective prenatal hydronephrosis database. Urology. 2019; 123: 204–9. https://doi.org/10.1016/j.urology.2018.05.041Lorenzo A.J., Rickard M., Braga L.H., Guo Y., Oliveria J.P. Predictive analytics and modeling employing machine learning technology: the next step in data sharing, analysis, and individualized counseling explored with a large, prospective prenatal hydronephrosis database. Urology. 2019; 123: 204–9. https://doi.org/10.1016/j.urology.2018.05.041Дубров В.И., Сизонов В.В., Каганцов И.М., Негматова К.Н., Бондаренко С.Г. Прогнозирование результатов однократной эндоскопической коррекции пузырно-мочеточникового рефлюкса с использованием декстраномерагиалуроновой кислоты. Выбор оптимальной прогностической модели. Вестник урологии. 2021; 9(2): 45–55. https://doi.org/10.21886/2308-6424-2021-9-2-45-55 https://elibrary.ru/lwygjjДубров В.И., Сизонов В.В., Каганцов И.М., Негматова К.Н., Бондаренко С.Г. Прогнозирование результатов однократной эндоскопической коррекции пузырно-мочеточникового рефлюкса с использованием декстраномерагиалуроновой кислоты. Выбор оптимальной прогностической модели. Вестник урологии. 2021; 9(2): 45–55. https://doi.org/10.21886/2308-6424-2021-9-2-45-55 https://elibrary.ru/lwygjjEroglu Y., Yildirim K., Çinar A., Yildirim M. Diagnosis and grading of vesicoureteral reflux on voiding cystourethrography images in children using a deep hybrid model. Comput. Methods Programs Biomed. 2021; 210: 106369. https://doi.org/10.1016/j.cmpb.2021.106369Eroglu Y., Yildirim K., Çinar A., Yildirim M. Diagnosis and grading of vesicoureteral reflux on voiding cystourethrography images in children using a deep hybrid model. Comput. Methods Programs Biomed. 2021; 210: 106369. https://doi.org/10.1016/j.cmpb.2021.106369Smail L.C., Dhindsa K., Braga L.H., Becker S., Sonnadara R.R. Using deep learning algorithms to grade hydronephrosis severity: toward a clinical adjunct. Front. Pediatr. 2020; 8: 1. https://doi.org/10.3389/fped.2020.00001Smail L.C., Dhindsa K., Braga L.H., Becker S., Sonnadara R.R. Using deep learning algorithms to grade hydronephrosis severity: toward a clinical adjunct. Front. Pediatr. 2020; 8: 1. https://doi.org/10.3389/fped.2020.00001Blum E.S., Porras A.R., Biggs E., Tabrizi P.R., Sussman R.D., Sprague B.M., et al. Early detection of ureteropelvic junction obstruction using signal analysis and machine learning: a dynamic solution to a dynamic problem. J. Urol. 2018; 199(3): 847–52. https://doi.org/10.1016/j.juro.2017.09.147Blum E.S., Porras A.R., Biggs E., Tabrizi P.R., Sussman R.D., Sprague B.M., et al. Early detection of ureteropelvic junction obstruction using signal analysis and machine learning: a dynamic solution to a dynamic problem. J. Urol. 2018; 199(3): 847–52. https://doi.org/10.1016/j.juro.2017.09.147Abbas T.O., Abdel Moniem M., Khalil I.A., Abrar Hossain M.S., Chowdhury M.E.H. Deep learning based automated quantification of urethral plate characteristics using the plate objective scoring tool (POST). J. Pediatr. Urol. 2023; 19(4): 373.e1–9. https://doi.org/10.1016/j.jpurol.2023.03.033Abbas T.O., Abdel Moniem M., Khalil I.A., Abrar Hossain M.S., Chowdhury M.E.H. Deep learning based automated quantification of urethral plate characteristics using the plate objective scoring tool (POST). J. Pediatr. Urol. 2023; 19(4): 373.e1–9. https://doi.org/10.1016/j.jpurol.2023.03.033Abdovic S., Cuk M., Cekada N., Milosevic M., Geljic A., Fusic S., et al. Predicting posterior urethral obstruction in boys with lower urinary tract symptoms using deep artificial neural network. World J. Urol. 2019; 37(9): 1973–9. https://doi.org/10.1007/s00345-018-2588-9Abdovic S., Cuk M., Cekada N., Milosevic M., Geljic A., Fusic S., et al. Predicting posterior urethral obstruction in boys with lower urinary tract symptoms using deep artificial neural network. World J. Urol. 2019; 37(9): 1973–9. https://doi.org/10.1007/s00345-018-2588-9Kwong J.C., Khondker A., Kim J.K., Chua M., Keefe D.T., Dos Santos J., et al. Posterior Urethral Valves Outcomes Prediction (PUVOP): a machine learning tool to predict clinically relevant outcomes in boys with posterior urethral valves. Pediatr. Nephrol. 2022; 37(5): 1067–74. https://doi.org/10.1007/s00467-021-05321-3Kwong J.C., Khondker A., Kim J.K., Chua M., Keefe D.T., Dos Santos J., et al. Posterior Urethral Valves Outcomes Prediction (PUVOP): a machine learning tool to predict clinically relevant outcomes in boys with posterior urethral valves. Pediatr. Nephrol. 2022; 37(5): 1067–74. https://doi.org/10.1007/s00467-021-05321-3Bertsimas D., Li M., Estrada C., Nelson C., Scott Wang H.H. Selecting children with vesicoureteral reflux who are most likely to benefit from antibiotic prophylaxis: application of machine learning to RIVUR. J. Urol. 2021; 205(4): 1170–9. https://doi.org/10.1097/JU.0000000000001445Bertsimas D., Li M., Estrada C., Nelson C., Scott Wang H.H. Selecting children with vesicoureteral reflux who are most likely to benefit from antibiotic prophylaxis: application of machine learning to RIVUR. J. Urol. 2021; 205(4): 1170–9. https://doi.org/10.1097/JU.0000000000001445Щамхалова К.К., Меринов Д.С., Артемов А.В., Гурбанов Ш.Ш. Искусственный интеллект и нейронные сети в урологии. Экспериментальная и клиническая урология. 2023; 16(2): 32–7. https://doi.org/10.29188/2222-8543-2023-16-2-32-37 https://elibrary.ru/znnfhuЩамхалова К.К., Меринов Д.С., Артемов А.В., Гурбанов Ш.Ш. Искусственный интеллект и нейронные сети в урологии. Экспериментальная и клиническая урология. 2023; 16(2): 32–7. https://doi.org/10.29188/2222-8543-2023-16-2-32-37 https://elibrary.ru/znnfhuТимофеева Е.Ю., Азильгареева К.Р., Морозов А.О., Тараткин М.С., Еникеев Д.В. Использование искусственного интеллекта в диагностике, лечении и наблюдении за пациентами с раком почки. Вестник урологии. 2023; 11(3): 142–8. https://doi.org/10.21886/2308-6424-2023-11-3-142-148 https://elibrary.ru/kopikzТимофеева Е.Ю., Азильгареева К.Р., Морозов А.О., Тараткин М.С., Еникеев Д.В. Использование искусственного интеллекта в диагностике, лечении и наблюдении за пациентами с раком почки. Вестник урологии. 2023; 11(3): 142–8. https://doi.org/10.21886/2308-6424-2023-11-3-142-148 https://elibrary.ru/kopikzWen Y., Di H. Potential and risks of artificial intelligence models: Common in medicine practice and special in pediatric urology. J. Pediatr. Urol. 2023; 19(5): 666–7. https://doi.org/10.1016/j.jpurol.2023.06.005Wen Y., Di H. Potential and risks of artificial intelligence models: Common in medicine practice and special in pediatric urology. J. Pediatr. Urol. 2023; 19(5): 666–7. https://doi.org/10.1016/j.jpurol.2023.06.005Khondker A., Kwong J.C.C., Rickard M., Skreta M., Keefe D.T., Lorenzo A.J., et al. A machine learning-based approach for quantitative grading of vesicoureteral reflux from voiding cystourethrograms: Methods and proof of concept. J. Pediatr. Urol. 2022; 18(1): 78.e1–78.e7. https://doi.org/10.1016/j.jpurol.2021.10.009Khondker A., Kwong J.C.C., Rickard M., Skreta M., Keefe D.T., Lorenzo A.J., et al. A machine learning-based approach for quantitative grading of vesicoureteral reflux from voiding cystourethrograms: Methods and proof of concept. J. Pediatr. Urol. 2022; 18(1): 78.e1–78.e7. https://doi.org/10.1016/j.jpurol.2021.10.009Topol E.J. High-performance medicine: the convergence of human and artificial intelligence. Nat. Med. 2019; 25(1): 44–56. https://doi.org/10.1038/s41591-018-0300-7Topol E.J. High-performance medicine: the convergence of human and artificial intelligence. Nat. Med. 2019; 25(1): 44–56. https://doi.org/10.1038/s41591-018-0300-7Rajpurkar P., Chen E., Banerjee O., Topol E. AI in health and medicine. Nat. Med. 2022; 28(1): 31–8. https://doi.org/10.1038/s41591-021-01614-0Rajpurkar P., Chen E., Banerjee O., Topol E. AI in health and medicine. Nat. Med. 2022; 28(1): 31–8. https://doi.org/10.1038/s41591-021-01614-0Reis M., Reis F., Kunde W. Influence of believed AI involvement on the perception of digital medical advice. Nat. Med. 2024; 30(11): 3098–100. https://doi.org/10.1038/s41591-024-03180-7Reis M., Reis F., Kunde W. Influence of believed AI involvement on the perception of digital medical advice. Nat. Med. 2024; 30(11): 3098–100. https://doi.org/10.1038/s41591-024-03180-7Keskinoğlu A., Özgür S. The use of artificial neural networks for differential diagnosis between vesicoureteral reflux and urinary tract infection in children. J. Pediatr. Res. 2020; 7(3): 230–5. https://doi.org/10.4274/jpr.galenos.2019.24650Keskinoğlu A., Özgür S. The use of artificial neural networks for differential diagnosis between vesicoureteral reflux and urinary tract infection in children. J. Pediatr. Res. 2020; 7(3): 230–5. https://doi.org/10.4274/jpr.galenos.2019.24650Logvinenko T., Chow J.S., Nelson C.P. Predictive value of specific ultrasound findings when used as a screening test for abnormalities on VCUG. J. Pediatr. Urol. 2015; 11(4): 176.e1–7. https://doi.org/10.1016/j.jpurol.2015.03.006Logvinenko T., Chow J.S., Nelson C.P. Predictive value of specific ultrasound findings when used as a screening test for abnormalities on VCUG. J. Pediatr. Urol. 2015; 11(4): 176.e1–7. https://doi.org/10.1016/j.jpurol.2015.03.006Weaver J.K., Logan J., Broms R., Antony M., Rickard M., Erdman L., et al. Deep learning of renal scans in children with antenatal hydronephrosis. J. Pediatr. Urol. 2023; 19(5): 514.e1–7. https://doi.org/10.1016/j.jpurol.2022.12.017Weaver J.K., Logan J., Broms R., Antony M., Rickard M., Erdman L., et al. Deep learning of renal scans in children with antenatal hydronephrosis. J. Pediatr. Urol. 2023; 19(5): 514.e1–7. https://doi.org/10.1016/j.jpurol.2022.12.017Fernandez N., Lorenzo A.J., Rickard M., Chua M., Pippi-Salle J.L., Perez J., et al. Digital pattern recognition for the identification and classification of hypospadias using artificial intelligence vs experienced pediatric urologist. Urology. 2021; 147: 264–9. https://doi.org/10.1016/j.urology.2020.09.019Fernandez N., Lorenzo A.J., Rickard M., Chua M., Pippi-Salle J.L., Perez J., et al. Digital pattern recognition for the identification and classification of hypospadias using artificial intelligence vs experienced pediatric urologist. Urology. 2021; 147: 264–9. https://doi.org/10.1016/j.urology.2020.09.019Bertsimas D., Estrada C., Nelson C., Li M., Scott Wang H.H., Dunn J. Advanced analytics group of pediatric urology and ORC personalized medicine group. Targeted workup after initial febrile urinary tract infection: using a novel machine learning model to identify children most likely to benefit from voiding cystourethrogram. J. Urol. 2019; 202(1): 144–52. https://doi.org/10.1097/JU.0000000000000186Bertsimas D., Estrada C., Nelson C., Li M., Scott Wang H.H., Dunn J. Advanced analytics group of pediatric urology and ORC personalized medicine group. Targeted workup after initial febrile urinary tract infection: using a novel machine learning model to identify children most likely to benefit from voiding cystourethrogram. J. Urol. 2019; 202(1): 144–52. https://doi.org/10.1097/JU.0000000000000186Weaver J.K., Martin-Olenski M., Logan J., Broms R., Antony M., Van Batavia J., et al. Deep learning of videourodynamics to classify bladder dysfunction severity in patients with spina bifida. J. Urol. 2023; 209(5): 994–1003. https://doi.org/10.1097/JU.0000000000003267Weaver J.K., Martin-Olenski M., Logan J., Broms R., Antony M., Van Batavia J., et al. Deep learning of videourodynamics to classify bladder dysfunction severity in patients with spina bifida. J. Urol. 2023; 209(5): 994–1003. https://doi.org/10.1097/JU.0000000000003267Tsai M.C., Lu H.H., Chang Y.C., Huang Y.C., Fu L.S. Automatic screening of pediatric renal ultrasound abnormalities: deep learning and transfer learning approach. JMIR Med. Inform. 2022; 10(11): e40878. https://doi.org/10.2196/40878Tsai M.C., Lu H.H., Chang Y.C., Huang Y.C., Fu L.S. Automatic screening of pediatric renal ultrasound abnormalities: deep learning and transfer learning approach. JMIR Med. Inform. 2022; 10(11): e40878. https://doi.org/10.2196/40878McKinney S.M., Sieniek M., Godbole V., Godwin J., Antropova N., Ashrafian H., et al. International evaluation of an AI system for breast cancer screening. Nature. 2020; 577(7788): 89–94. https://doi.org/10.1038/s41586-019-1799-6McKinney S.M., Sieniek M., Godbole V., Godwin J., Antropova N., Ashrafian H., et al. International evaluation of an AI system for breast cancer screening. Nature. 2020; 577(7788): 89–94. https://doi.org/10.1038/s41586-019-1799-6

The authors declare that there are no conflicts of interest present.