<?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">diaendo</journal-id><journal-title-group><journal-title xml:lang="ru">Сахарный диабет</journal-title><trans-title-group xml:lang="en"><trans-title>Diabetes mellitus</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2072-0351</issn><issn pub-type="epub">2072-0378</issn><publisher><publisher-name>Endocrinology research centre</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.14341/DM13111</article-id><article-id custom-type="elpub" pub-id-type="custom">diaendo-13111</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 исследования</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>Original Studies</subject></subj-group></article-categories><title-group><article-title>Прогнозирование времени в целевом диапазоне глюкозы с помощью экспериментального мобильного приложения при сахарном диабете 1 типа</article-title><trans-title-group xml:lang="en"><trans-title>Time in range prediction using the experimental mobile application in type 1 diabetes</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-2234-407X</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Русанов</surname><given-names>А. Н.</given-names></name><name name-style="western" xml:lang="en"><surname>Rusanov</surname><given-names>A. N.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Русанов Арсений Николаевич - ассистент кафедры эндокринологии.</p><p>410031, Саратов, улица Большая Горная, д. 43А</p></bio><bio xml:lang="en"><p>Arseniy N. Rusanov – MD.</p><p>43A Bolshaya Gornaya street, 410031 Saratov</p></bio><email xlink:type="simple">arseniyrusanov91@gmail.com</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0003-4280-6945</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Родионова</surname><given-names>Т. И.</given-names></name><name name-style="western" xml:lang="en"><surname>Rodionova</surname><given-names>T. I.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Родионова Татьяна Игоревна - д.м.н., профессор; ResearcherID: ABC-2921-2020; Scopus Author ID: 7004712772.</p><p>Саратов</p></bio><bio xml:lang="en"><p>Tatiana I. Rodionova - MD, PhD, Professor; ResearcherID: ABC-2921-2020; Scopus Author ID: 7004712772.</p><p>Saratov</p></bio><email xlink:type="simple">rodionova777@mail.ru</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Саратовский государственный медицинский университет им. В.И. Разумовского</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Saratov State Medical University named after V.I. Razumovsky</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2024</year></pub-date><pub-date pub-type="epub"><day>06</day><month>06</month><year>2024</year></pub-date><volume>27</volume><issue>2</issue><fpage>130</fpage><lpage>141</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Русанов А.Н., Родионова Т.И., 2024</copyright-statement><copyright-year>2024</copyright-year><copyright-holder xml:lang="ru">Русанов А.Н., Родионова Т.И.</copyright-holder><copyright-holder xml:lang="en">Rusanov A.N., Rodionova T.I.</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.dia-endojournals.ru/jour/article/view/13111">https://www.dia-endojournals.ru/jour/article/view/13111</self-uri><abstract><sec><title>ОБОСНОВАНИЕ</title><p>ОБОСНОВАНИЕ. Время в целевом диапазоне глюкозы (TIR) — перспективный показатель гликемического контроля, применяющийся при оценке непрерывного мониторинга глюкозы (НМГ) у пациентов с сахарным диабетом (СД). Актуальной проблемой остается оценка и прогнозирование данного параметра для пациентов, использующих самостоятельный мониторинг глюкозы крови (СМГК), с учетом недостаточной доступности НМГ для большинства пациентов с СД.</p></sec><sec><title>ЦЕЛЬ</title><p>ЦЕЛЬ. На основании данных экспериментального мобильного приложения разработать прогностическую модель времени в целевом диапазоне для пациентов с СД 1 типа (СД1).</p></sec><sec><title>МАТЕРИАЛЫ И МЕТОДЫ</title><p>МАТЕРИАЛЫ И МЕТОДЫ. Проведен анализ 1253 профилей профессионального НМГ пациентов с СД1. На основании включенных в исследование записей выполнен расчет TIR(НМГ), сгенерированы тренировочные модели 7-точечных профилей СМГК. Профили СМГК загружались в разработанное экспериментальное мобильное приложение, рассчитывающее стандартные параметры гликемического контроля. Данные были разделены на основную и тестовую выборки в соотношении 80 и 20%. Для основной выборки применены следующие методы разработки прогностических моделей: простая линейная регрессия (ПЛР), множественная линейная регрессия (МЛР), искусственная нейронная сеть (ИНС). Оценка эффективности разработанных моделей проводилась на тестовой выборке с расчетом средней абсолютной ошибки (MAE), квадратного корня из среднеквадратичной ошибки (RMSE).</p></sec><sec><title>РЕЗУЛЬТАТЫ</title><p>РЕЗУЛЬТАТЫ. В исследование включено 568 профилей НМГ. В основной группе (n=454) TIR составил 45 [33; 65]%, в тестовой группе (n=114) — 43 [33; 58]%. Наиболее значимыми предикторами TIR в регрессионных моделях являлись процент значений в целевом диапазоне (dTIR), p&lt;0,001; процент значений ниже целевого диапазона 1 уровня (dTBR1), p&lt;0,001; стандартное отклонение гликемии (SD), p=0,007. Коэффициент детерминации для ПЛР (предиктор: dTIR) — 0,844; для МЛР (предикторы: dTIR, dTBR1, SD) — 0,907. Разработаны модели ИНС по типу многослойный перцептрон с двумя и одним внутренним слоем нейронов, для которых RMSE на валидационной выборке составил 4,617 и 6,639% соответственно. Результаты анализа эффективности прогноза на тестовой выборке: dTIR: MAE — 6,82%, RMSE — 8,60%; модель ПЛР: MAE — 5,66%, RMSE — 7,34%; модель МЛР: MAE — 4,18%, RMSE — 5,28%; модель ИНС (2 слоя): MAE — 4,14%, RMSE — 5,19%; модель ИНС (1 слой): MAE — 4,44%, RMSE — 5,52%.</p></sec><sec><title>ЗАКЛЮЧЕНИЕ</title><p>ЗАКЛЮЧЕНИЕ. Наилучшую способность для прогноза TIR продемонстрировали ИНС с двумя внутренними слоями и МЛР. Требуются дальнейшие исследования с целью клинической валидации разработанных прогностических моделей.</p></sec></abstract><trans-abstract xml:lang="en"><sec><title>BACKGROUND</title><p>BACKGROUND: Time in range (TIR) is a promising indicator of glycemic control used for evaluation of continuous glucose monitoring (CGM) for patients with diabetes mellitus (DM). The current problem is the assessment and prediction of TIR for patients who use self-monitoring of blood glucose (SМBG) corresponding low CGM availability for the majority of diabetic patients.</p></sec><sec><title>AIM</title><p>AIM: To develop a predictive model of TIR for patients with T1DM based on data of the experimental mobile application.</p></sec><sec><title>MATERIALS AND METHODS</title><p>MATERIALS AND METHODS: An analysis of 1253 professional CGM profiles of patients with T1DM was performed. On the base of included records, TIR(CGM) was calculated and training models of 7-point SMBG profiles were generated. SMBG profiles’re loaded into the developed experimental mobile application that calculated standard glycemic control parameters. The dataset was divided into main and test samples (80 and 20%). For the main sample, the following methods’re used to develop predictive models: simple linear regression (SLR), multiple linear regression (MLR), artificial neural network (ANN). The effectiveness of the developed models was assessed on the test sample with the calculation of the mean absolute error (MAE), the root mean square error (RMSE).</p></sec><sec><title>RESULTS</title><p>RESULTS: The 568 CGM profiles’re included in the study. TIR in the main group (n=454) — 45 [33; 65]%, in the test group (n=114) — 43 [33; 58]%. The most significant predictors of the regression models were the derived TIR (dTIR), p&lt;0,001; derived time below range level 1 (dTBR1), p&lt;0,001; standard deviation of blood glucose (SD), p=0,007. Determination coefficient for SLR (predictor: dTIR) — 0,844; for MLR (predictors: dTIR, dTBR1, SD) — 0,907. ANN multilayer perceptron models with two and one hidden layers’re developed, with the RMSE on the validation set 4,617 and 6,639%, respectively. The results of the forecast efficiency on the test sample were: dTIR: MAE — 6,82%, RMSE — 8,60%; SLR: MAE — 5,66%, RMSE — 7,34%; MLR: MAE — 4,18%, RMSE — 5,28%; ANN (2 layers): MAE — 4,14%, RMSE — 5,19%; ANN (1 layer): MAE — 4,44%, RMSE — 5,52%.</p></sec><sec><title>CONCLUSION</title><p>CONCLUSION: ANN with two hidden layers and MLR demonstrated the best ability for TIR prediction. Further studies are required for clinical validation of developed prognostic models.</p></sec></trans-abstract><kwd-group xml:lang="ru"><kwd>время в целевом диапазоне глюкозы</kwd><kwd>мобильное здравоохранение</kwd><kwd>машинное обучение</kwd><kwd>искусственные нейронные сети</kwd></kwd-group><kwd-group xml:lang="en"><kwd>time in range</kwd><kwd>mHealth</kwd><kwd>machine learning</kwd><kwd>artificial neural networks</kwd></kwd-group><funding-group><funding-statement xml:lang="ru">Работа выполнена по инициативе авторов без привлечения финансирования</funding-statement></funding-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Battelino T, Danne T, Bergenstal RM, et al. Clinical Targets for Continuous Glucose Monitoring Data Interpretation: Recommendations From the International Consensus on Time in Range. Diabetes Care. 2019;42(8):1593-1603. https://doi.org/10.2337/dci19-0028</mixed-citation><mixed-citation xml:lang="en">Battelino T, Danne T, Bergenstal RM, et al. Clinical Targets for Continuous Glucose Monitoring Data Interpretation: Recommendations From the International Consensus on Time in Range. Diabetes Care. 2019;42(8):1593-1603. https://doi.org/10.2337/dci19-0028</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Суплотова Л.А., Судницына А.С., Романова Н.В., Шестакова М.В. Время нахождения в целевом диапазоне гликемии — инструмент оценки качества гликемического контроля при сахарном диабете // Сахарный диабет. — 2021. — Т. 24. — №3. — С. 282-290. https://doi.org/10.14341/DM12703</mixed-citation><mixed-citation xml:lang="en">Suplotova LA, Suditsyna AS, Romanova NV, Shestakova MV. Time in range is a tool for assessing the quality of glycemic control in diabetes. Diabetes Mellitus. 2021;24(3):282-290. https://doi.org/10.14341/DM12703</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Janapala RN, Jayaraj JS, Fathima N, et al. Continuous Glucose Monitoring Versus Self-monitoring of Blood Glucose in Type 2 Diabetes Mellitus: A Systematic Review with Meta-analysis. Cureus. 2019;11(9):e5634. https://doi.org/10.7759/cureus.5634</mixed-citation><mixed-citation xml:lang="en">Janapala RN, Jayaraj JS, Fathima N, et al. Continuous Glucose Monitoring Versus Self-monitoring of Blood Glucose in Type 2 Diabetes Mellitus: A Systematic Review with Meta-analysis. Cureus. 2019;11(9):e5634. https://doi.org/10.7759/cureus.5634</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Shan R, Sarkar S, Martin SS. Digital health technology and mobile devices for the management of diabetes mellitus: state of the art. Diabetologia. 2019;62(6):877-887. https://doi.org/10.1007/s00125-019-4864-7</mixed-citation><mixed-citation xml:lang="en">Shan R, Sarkar S, Martin SS. Digital health technology and mobile devices for the management of diabetes mellitus: state of the art. Diabetologia. 2019;62(6):877-887. https://doi.org/10.1007/s00125-019-4864-7</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Bergenstal RM, Hachmann-Nielsen E, Kvist K, et al. Increased Derived Time in Range Is Associated with Reduced Risk of Major Adverse Cardiovascular Events, Severe Hypoglycemia, and Microvascular Events in Type 2 Diabetes: A Post Hoc Analysis of DEVOTE. Diabetes Technol Ther. 2023;25(6):378-383. https://doi.org/10.1089/dia.2022.0447</mixed-citation><mixed-citation xml:lang="en">Bergenstal RM, Hachmann-Nielsen E, Kvist K, et al. Increased Derived Time in Range Is Associated with Reduced Risk of Major Adverse Cardiovascular Events, Severe Hypoglycemia, and Microvascular Events in Type 2 Diabetes: A Post Hoc Analysis of DEVOTE. Diabetes Technol Ther. 2023;25(6):378-383. https://doi.org/10.1089/dia.2022.0447</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Sun R, Duan Y, Zhang Y, et al. Time in Range Estimation in Patients with Type 2 Diabetes is Improved by Incorporating Fasting and Postprandial Glucose Levels. Diabetes Ther. 2023;14(8):1373-1386. https://doi.org/10.1007/s13300-023-01432-2</mixed-citation><mixed-citation xml:lang="en">Sun R, Duan Y, Zhang Y, et al. Time in Range Estimation in Patients with Type 2 Diabetes is Improved by Incorporating Fasting and Postprandial Glucose Levels. Diabetes Ther. 2023;14(8):1373-1386. https://doi.org/10.1007/s13300-023-01432-2</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Beck RW, Bergenstal RM, Cheng P, et al. The Relationships Between Time in Range, Hyperglycemia Metrics, and HbA1c. J Diabetes Sci Technol. 2019;13(4):614-626. https://doi.org/10.1177/1932296818822496</mixed-citation><mixed-citation xml:lang="en">Beck RW, Bergenstal RM, Cheng P, et al. The Relationships Between Time in Range, Hyperglycemia Metrics, and HbA1c. J Diabetes Sci Technol. 2019;13(4):614-626. https://doi.org/10.1177/1932296818822496</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Климонтов В.В., Бериков В.Б., Сайк О.В. Искусственный интеллект в диабетологии // Сахарный диабет. — 2021. — Т. 24. — №2. — С. 156-166. https://doi.org/10.14341/DM12665</mixed-citation><mixed-citation xml:lang="en">Klimontov VV, Berikov VB, Saik OV. Artificial intelligence in diabetology. Diabetes Mellitus. 2021;24(2):156-166. https://doi.org/10.14341/DM12665</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Li K, Daniels J, Liu C, Herrero P, Georgiou P. Convolutional Recurrent Neural Networks for Glucose Prediction. IEEE J Biomed Health Inform. 2020;24(2):603-613. https://doi.org/10.1109/JBHI.2019.2908488</mixed-citation><mixed-citation xml:lang="en">Li K, Daniels J, Liu C, Herrero P, Georgiou P. Convolutional Recurrent Neural Networks for Glucose Prediction. IEEE J Biomed Health Inform. 2020;24(2):603-613. https://doi.org/10.1109/JBHI.2019.2908488</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Yapanis M, James S, Craig ME, O’Neal D, Ekinci EI. Complications of Diabetes and Metrics of Glycemic Management Derived From Continuous Glucose Monitoring. J Clin Endocrinol Metab. 2022;107(6):e2221-e2236. https://doi.org/10.1210/clinem/dgac034</mixed-citation><mixed-citation xml:lang="en">Yapanis M, James S, Craig ME, O’Neal D, Ekinci EI. Complications of Diabetes and Metrics of Glycemic Management Derived From Continuous Glucose Monitoring. J Clin Endocrinol Metab. 2022;107(6):e2221-e2236. https://doi.org/10.1210/clinem/dgac034</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Bergenstal RM, Beck RW, Close KL, et al. Glucose Management Indicator (GMI): A New Term for Estimating A1C From Continuous Glucose Monitoring. Diabetes Care. 2018;41(11):2275-2280. https://doi.org/10.2337/dc18-158</mixed-citation><mixed-citation xml:lang="en">Bergenstal RM, Beck RW, Close KL, et al. Glucose Management Indicator (GMI): A New Term for Estimating A1C From Continuous Glucose Monitoring. Diabetes Care. 2018;41(11):2275-2280. https://doi.org/10.2337/dc18-158</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>
