vitjВрач и информационные технологииMedical Doctor and Information Technologies1811-01932413-5208Pirogov National Medical and Surgical Center10.25881/18110193_2022_1_4vitj-133Research ArticleОБЗОРЫREVIEWSПрименение методов математического моделирования для прогнозирования осложнений гипертонической болезниApplication of mathematical modeling for prediction of complications of hypertensionТуценкоК. О.TutsenkoK. O.

Туценко К.О.

г. Красноярск

Tutsenko K.O.

Krasnoyarsk

kseniamkib@gmail.comНаркевичА. Н.NarkevichA. N.

Наркевич А.Н., д.м.н.

г. Красноярск

Narkevich A.N., Dr. Sci. (Medicine)

Krasnoyarsk

narkevichart@gmail.comРоссиевД. А.RossievD. A.

Россиев Д.А., д.м.н., профессор

г. Красноярск

Rossiev D.A., Dr. Sci. (Medicine), Professor

Krasnoyarsk

 

rossiev@mail.ruИпатюкО. В.IpatyukO. V.

Ипатюк О.В.

г. Красноярск

Ipatyuk O.V.

Krasnoyarsk

s.v.b.07@mail.ruАвдеевС. М.AvdeevS. M.

Авдеев С.М.

г. Красноярск

Avdeev S.M.

Krasnoyarsk

avdeev63@mail.ruФГБОУ ВО «Красноярский государственный медицинский университет им. проф. В.Ф. Войно-Ясенецкого»РоссияKrasnoyarsk State Medical University named after prof. V. F. Voino-Yasenetsky»Russian FederationУН «Пальмира»РоссияUN «Palmira»Russian FederationИП Авдеев Сергей МаксимовичРоссияIndividual entrepreneur Avdeev Sergey MaksimovichRussian Federation20220104202501411Copyright © Туценко К.О., Наркевич А.Н., Россиев Д.А., Ипатюк О.В., Авдеев С.М., 20252025Туценко К.О., Наркевич А.Н., Россиев Д.А., Ипатюк О.В., Авдеев С.М.Tutsenko K.O., Narkevich A.N., Rossiev D.A., Ipatyuk O.V., Avdeev S.M.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://www.vit-j.ru/jour/article/view/133

Гипертоническая болезнь является многофакторным заболеванием, при котором наблюдается повышение артериального давления. Избыточное давление может приводить к ишемической болезни сердца, инсульту, заболеваниям почек и другим патологиям. Частота осложнений гипертонической болезни во многом зависит от точности прогноза их развития. Врач, имея информацию о вероятности развития того или иного осложнения, может назначить пациенту соответствующую профилактику и снизить риск возникновения сердечно-сосудистого события. Для прогнозирования используются различные математические модели и компьютерные программы. Стандартные подходы к прогнозированию риска сердечно-сосудистых заболеваний имеют невысокую точность. В настоящее время всё чаще для подобных целей используются методы машинного обучения, которые имеют высокую прогностическую ценность для оценки риска развития осложнений гипертонической болезни. Данный обзор посвящён описанию многообразия методов, используемых для указанной цели.

Hypertension is a complex cardiovascular condition, defined as an abnormally high blood pressure. Such long-term and consistent increase in blood pressure could result in coronary heart disease, stroke, kidney damage and other serious debilitating conditions. Complication rate from hypertension depends on how well you can predict and prevent those complications, considering individual patient’s risks. Several mathematical models and computer algorithms that are currently used for these purposes have relatively low accuracy and prognostic value. Machine learning methods could be a next step in improving outcomes of patients with hypertension in terms of calculating their individual risk of complications and choosing rational therapeutic strategy based on that data. We performed a literature review to cover the topic of machine learning methods in the management of patients with hypertension.

гипертоническая болезньфакторы рискапрогнозирование осложнениймашинное обучениеоценка рискаhypertensionrisk factorsprediction of complicationsmachine learningrisk ratingReferencesИнформационный бюллетень Всемирной организации здравоохранения. C. 17–24. https://www.who.int/ru/news-room/fact-sheets/detail/hypertension/World Health Organization: 17–24. (In Russ). https://www.who.int/ru/news-room/fact-sheets/detail/hypertension/Искаков Е.Б. Распространенность факторов риска развития сердечно-сосудистых заболеваний // Медицина и экология. — 2017. — №3(84).Iskakov YeB. Prevalence of risk factors of cardiovascular diseases. Medicine and ecology. 2017; 3 Leonov V.P., Shneider V.E. An example of using logistic regression to calculate the prediction of the initial operational investigation (84). (In Russ).Леонов В.П., Шнейдер В.Э. Пример использования логистической регрессии для расчета прогноза исхода оперативного лечения. http://www.biometrica.tomsk.ru/biometrica.tomsk.ru/logit_7.htm.Leonov VP, Shneider VE. An example of using logistic regression to calculate the prediction of the initial operational investigation. (In Russ). http://www.biometrica.tomsk.ru/biometrica.tomsk.ru/logit_7.htm.Ардашев В.Н., Фурсов А.Н., Конев А.В. и др. Прогнозирование развития инфаркта миокарда у больных гипертонической болезнью // Российский кардиологический журнал. — 2004. — №2. — С.11-15.Ardashev VN, Fursov AN, Konev AV, et al. Prognosing of myocardial infarction outcome in arterial hypertension patients. Russian Journal of Cardiology. 2004; 2: 11-15. (In Russ).Суспицына И.Н., Сукманова И.А. Факторы риска и прогнозирование развития инфаркта миокарда у мужчин различных возрастных групп // Российский кардиологический журнал. — 2016. — №8(136). С. 58–63.Suspitsina IN, Sukmanova IA. Risk factors and prediction of miocardial infarction in males of different age. Russian Journal of Cardiology. 2016; 8(136): 58–63. (In Russ).Голощапов-Аксёнов Р.С. Информативность факторов риска в прогнозировании инфаркта миокарда // Здравоохранение Российской Федерации. — 2019. — Т.63. — №2. – С. 60–65.Goloshchapov-Aksenov RS. Informativity of risk factors in forecasting myocardial infarction. Health care of the Russian Federation. 2019; 63(2): 60–65. (In Russ).Яскевич Р.А. Применение методов математического моделирования в прогнозе тяжести клинического течения артериальной гипертонии у мужчин // Современные проблемы науки и образования. — 2016. — №6. — С.62.Yaskevich RA. Application of methods of mathematical modeling in the prediction of severity of clinical course of arterial hypertension in men. Modern Problems of Science and Education. 2016; 6: 62. (In Russ).Kawai T, Ohishi M, Ito N, et al. Alteration of vascular function is an important factor in the correlation between visit-to-visit blood pressure variability and cardiovascular disease. Journal of Hypertension. 2013; 31: 1387-1395.Kawai T, Ohishi M, Ito N, et al. Alteration of vascular function is an important factor in the correlation between visit-to-visit blood pressure variability and cardiovascular disease. Journal of Hypertension. 2013; 31: 1387-1395.Chi X, Wang X, Guo Z, et al. Relationships between blood pressure variability and silent cerebral infarction in patients with primary hypertension. Artery Research. 2018; 24: 40-46.Chi X, Wang X, Guo Z, et al. Relationships between blood pressure variability and silent cerebral infarction in patients with primary hypertension. Artery Research. 2018; 24: 40-46.Tao Y, Xu J, Song B, Xie X, et al. Short-term blood pressure variability and long-term blood pressure variability: which one is a reliable predictor for recurrent stroke. Journal of Human Hypertension. 2017; 31(9): 568-573.Tao Y, Xu J, Song B, Xie X, et al. Short-term blood pressure variability and long-term blood pressure variability: which one is a reliable predictor for recurrent stroke. Journal of Human Hypertension. 2017; 31(9): 568-573.Palatini P, Saladini F, Mos L, et al. Short-term blood pressure variability outweighs average 24-h blood pressure in the prediction of cardiovascular events in hypertension of the young. Journal of Human Hypertension. 2019; 37(7: 1419-1426.Palatini P, Saladini F, Mos L, et al. Short-term blood pressure variability outweighs average 24-h blood pressure in the prediction of cardiovascular events in hypertension of the young. Journal of Human Hypertension. 2019; 37(7: 1419-1426.Mehlum MH, Liestøl K, Kjeldsen SE, et al. Blood pressure variability and risk of cardiovascular events and death in patients with hypertension and different baseline risks. European Heart Journal. 2018; 39(24): 2243-2251.Mehlum MH, Liestøl K, Kjeldsen SE, et al. Blood pressure variability and risk of cardiovascular events and death in patients with hypertension and different baseline risks. European Heart Journal. 2018; 39(24): 2243-2251.Arashi H, Ogawa H, Yamaguchi J, Kawada-Watanabe E, Hagiwara N. Impact of visit-to-visit variability and systolic blood pressure control on subsequent outcomes in hypertensive patients with coronary artery disease (from the HIJ-CREATE substudy). American Journal of Cardiology. 2015; 116(2): 236-42.Arashi H, Ogawa H, Yamaguchi J, Kawada-Watanabe E, Hagiwara N. Impact of visit-to-visit variability and systolic blood pressure control on subsequent outcomes in hypertensive patients with coronary artery disease (from the HIJ-CREATE substudy). American Journal of Cardiology. 2015; 116(2): 236-42.Hansen TW, Thijs L, Li Y, Boggia J, et al. International Database on Ambulatory Blood Pressure in Relation to Cardiovascular Outcomes Investigators. Prognostic value of reading to-reading blood pressure variability over 24 h in 8938 subjects from 11 populations // Hypertension. 2010; 55: 10491057.Hansen TW, Thijs L, Li Y, Boggia J, et al. International Database on Ambulatory Blood Pressure in Relation to Cardiovascular Outcomes Investigators. Prognostic value of reading to-reading blood pressure variability over 24 h in 8938 subjects from 11 populations // Hypertension. 2010; 55: 10491057.Ayala Solares JR, Canoy D, Raimondi FED, et al. Long-Term Exposure to Elevated Systolic Blood Pressure in Predicting Incident Cardiovascular Disease: Evidence From Large-Scale Routine Electronic Health Records. Journal of the American Heart Association. 2019; 8(12): e012129.Ayala Solares JR, Canoy D, Raimondi FED, et al. Long-Term Exposure to Elevated Systolic Blood Pressure in Predicting Incident Cardiovascular Disease: Evidence From Large-Scale Routine Electronic Health Records. Journal of the American Heart Association. 2019; 8(12): e012129.Adamsson Eryd S, Gudbjörnsdottir S, Manhem K, et al. Blood pressure and complications in individuals with type 2 diabetes and no previous cardiovascular disease: national population based cohort study. British Medical Journal. 2016; 354: i4070.Adamsson Eryd S, Gudbjörnsdottir S, Manhem K, et al. Blood pressure and complications in individuals with type 2 diabetes and no previous cardiovascular disease: national population based cohort study. British Medical Journal. 2016; 354: i4070.Мартыненко А.М., Давыдова А.В. Изменения АДФ-агрегации тромбоцитов и фатальные осложнения у больных гипертонической болезнью // Международный студенческий научный вестник. — 2017. — №6. — С.1.Martynenko AM, Davydova AV. Changes of ADP-platelet aggregation and fatal complications in hypertensive patients. International student scientific bulletin. 2017; 6: 1. (In Russ).Huang S, Xie X, Sun Y, et al. Development of a nomogram that predicts the risk for coronary atherosclerotic heart disease. Aging. 2020; 12(10): 9427. – 39.Huang S, Xie X, Sun Y, et al. Development of a nomogram that predicts the risk for coronary atherosclerotic heart disease. Aging. 2020; 12(10): 9427. – 39.Ambale-Venkatesh B, Yang X, Wu CO, et al. Cardiovascular Event Prediction by Machine Learning: The Multi-Ethnic Study of Atherosclerosis. Circulation Research. 2017; 121(9): 1092-1101.Ambale-Venkatesh B, Yang X, Wu CO, et al. Cardiovascular Event Prediction by Machine Learning: The Multi-Ethnic Study of Atherosclerosis. Circulation Research. 2017; 121(9): 1092-1101.Weng SF, Reps J, Kai J, Garibaldi JM, Qureshi N. Can machine-learning improve cardiovascular risk prediction using routine clinical data? Public Library of Science One. 2017; 12(4): e0174944.Weng SF, Reps J, Kai J, Garibaldi JM, Qureshi N. Can machine-learning improve cardiovascular risk prediction using routine clinical data? Public Library of Science One. 2017; 12(4): e0174944.Dimopoulos AC, Nikolaidou M, Caballero FF, et al. Machine learning methodologies versus cardiovascular risk scores, in predicting disease risk. BMC Medical Research Methodology. 2018; 18(1): 179.Dimopoulos AC, Nikolaidou M, Caballero FF, et al. Machine learning methodologies versus cardiovascular risk scores, in predicting disease risk. BMC Medical Research Methodology. 2018; 18(1): 179.Groenhof TKJ, Rittersma ZH, Bots ML, Brandjes M, Jacobs JJL, Grobbee DE, et. al. A computerised decision support system for cardiovascular risk management ‘live’ in the electronic health record environment: development, validation and implementation-the Utrecht Cardiovascular Cohort Initiative. Netherlands Heart Journal. 2019; 27(9): 435-442.Groenhof TKJ, Rittersma ZH, Bots ML, Brandjes M, Jacobs JJL, Grobbee DE, et. al. A computerised decision support system for cardiovascular risk management ‘live’ in the electronic health record environment: development, validation and implementation-the Utrecht Cardiovascular Cohort Initiative. Netherlands Heart Journal. 2019; 27(9): 435-442.Du Z, Yang Y, Zheng J, et al. Accurate prediction of coronary heart disease for patients with hypertension from electronic health records with big data and machine-learning methods: model development and performance evaluation. Journal of Medical Internet Research Medical Informatics. 2020; 8(7): е17257.Du Z, Yang Y, Zheng J, et al. Accurate prediction of coronary heart disease for patients with hypertension from electronic health records with big data and machine-learning methods: model development and performance evaluation. Journal of Medical Internet Research Medical Informatics. 2020; 8(7): е17257.Mandair D, Tiwari P, Simon S, Colborn KL, Rosenberg MA. Prediction of incident myocardial infarction using machine learning applied to harmonized electronic health record data. BMC medical informatics and decision making. 2020; 20(1): 1-10.Mandair D, Tiwari P, Simon S, Colborn KL, Rosenberg MA. Prediction of incident myocardial infarction using machine learning applied to harmonized electronic health record data. BMC medical informatics and decision making. 2020; 20(1): 1-10.Wu Y, Fang Y. Stroke Prediction with Machine Learning Methods among Older Chinese. International Journal of Environmental Research and Public Health. 2020; 17(6): 1828.Wu Y, Fang Y. Stroke Prediction with Machine Learning Methods among Older Chinese. International Journal of Environmental Research and Public Health. 2020; 17(6): 1828.Мамаев А.Н., Кудлай Д.А. Статистические методы в медицине. // Практическая медицина. — 2021.Mamaev AN, Kudlay D.. Statistical methods in medicine. Practical medicine. 2021. (In Russ).Гусев А.В., Добриднюк С.Л. Искусственный интеллект в медицине и здравоохранении // Информационное общество. — 2017. — №4-5. — С.78-93.Gusev AV, Dobridniuk SL. Artificial intelligence in medicine and healthcare. Information Society. 2017; 4-5: 78–93. (In Russ).

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