sibmedСибирский научный медицинский журналСибирский научный медицинский журнал2410-25122410-2520ИЦиГ СО РАН10.18699/SSMJ20230311sibmed-1112Research ArticleОРГАНИЗАЦИЯ ЗДРАВООХРАНЕНИЯ (закрыт с 20.03.26)HEALTHCARE MANAGEMENTФормирование набора больших данных для клинических исследований на примере аневризм сосудов головного мозгаEstablishing of big data clinical dataset in brain vessel aneurysm researchhttps://orcid.org/0000-0002-5499-9628КивелёвЮ. В.KivelevJu. V.

Кивелёв Юрий Владимирович, PhD

20520, Финляндия, Хямеентие, 11

Juri V. Kivelev, PhD

20520, Finland, Hämeentie, 11

129090, Moscow, Shchepkina str., 25

j.v.kivelev@gmail.comhttps://orcid.org/0000-0001-7013-6569СааренпяИ.SaarenpääI.

Сааренпя Илкка, PhD

20520, Финляндия, Хямеентие, 11

Ilkka Saarenpää, PhD

20520, Finland, Hämeentie, 11

ilkka.saarenpaa@tyks.fihttps://orcid.org/0000-0003-0789-8039КривошапкинА. Л.KrivoshapkinA. L.

Кривошапкин Алексей Леонидович, д.м.н., проф.

20520, Финляндия, Хямеентие, 11

129090, г. Москва, ул. Щепкина, 25

630055, г. Новосибирск, ул. Речкуновская, 15

Alexey L. Krivoshapkin, PhD, professor

129090, Moscow, Shchepkina str., 25

117198, Moscow, Miklukho-Maklaya str., 6

630055, Novosibirsk, Rechkunovskaya str., 15

alkr01@yandex.ruУниверситет ТуркуРоссияTurku University Hospital; European Medical CenterRussian FederationУниверситет ТуркуРоссияTurku University HospitalRussian FederationЕвропейский медицинский центр; Российский университет дружбы народов; НМИЦ имени академика Е.Н. Мешалкина Минздрава РоссииРоссияEuropean Medical Center; Peoples’ Friendship University of Russia (RUDN University); Meshalkin National Medical Research Center of Minzdrav of RussiaRussian Federation2023230620234338694Copyright © Кивелёв Ю.В., Сааренпя И., Кривошапкин А.Л., 20232023Кивелёв Ю.В., Сааренпя И., Кривошапкин А.Л.Kivelev J.V., Saarenpää I., Krivoshapkin A.L.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://sibmed.elpub.ru/jour/article/view/1112

Изменчивость и неоднородность цифровой медицинской информации требует разработки современных алгоритмов по структурированию массивов данных с целью их дальнейшей статистической обработки. Цель исследования – определить ход работы по созданию набора данных (НД) при исследовании аневризм сосудов головного мозга от этапа формирования технического задания до получения финального НД.Материал и методы. Процесс создания, обработки и анализа НД пациентов с аневризмами проводился на базе университетской клиники города Турку, Финляндия. В течение последних 20 лет клиника осуществляет медицинский документооборот в цифровом формате, что позволило создать на ее базе отдел хранения цифровых данных с целью максимального сохранения любой доступной цифровой информации. Автоматизированное получение данных пациентов проводилось дата-инженером с использованием языка программирования «R» на основании кодов Международной классификации болезней (МКБ-10).Результаты и их обсуждение. В период с января 2000 г. по май 2018 г. в ходе первичного получения данных выявлено 3850 пациентов. После независимой перекрестной проверки электронных историй болезни отсеяно 1218 (32 %) ложноположительных случаев. Данные по оставшимся пациентам были разделены на клинический и реанимационный блоки. Каждое событие, относящееся к конкретной временной дате в НД, определено как инфо-единица. Вся информация в обоих блоках структурирована в формате Excel и представлена в хронологическом порядке для каждого отдельного больного. В целом весь набор данных состоял из более чем 70 000 000 рядов инфо-единиц, выявленных у 2632 пациентов.Заключение. Автоматизированный поиск данных позволил создать многокомпонентный структурированный набор данных пациентов с аневризмами сосудов головного мозга. Выработанный алгоритм автоматизированного получения данных имел ограничение в отношении ложнопозитивных случаев, выявленных в 32 % случаев. Таким образом, анализ клинического материала, полученного с помощью цифровых алгоритмов, требует тщательной перекрестной проверки членами исследовательской группы.

Variability and heterogeneity of digital medical data requires establishing of modern algorithms which provide appropriate data processing. The aim of the study was to delineate the main steps in formation of a clinical dataset of patients with brain aneurysms from the stage of producing primary mining specifications to formation of a final version.Material and methods. Data collection, crosschecking of the cases and analyses of dataset has been carried out in Turku University Hospital. Within last two decades available medical data at our hospital have been stored in digital data lake thus allowing automatized data mining. In frame of our study, data mining was performed by a data scientist utilizing R software. Inclusion criteria were based on a set of diagnosis which were coded in medical charts according to international classification of diseases (ICD 10).Resutls and Discussion. Primary data mining identified 3850 patients with brain aneurysms treated at our hospital from January 2000 till May 2018. After independent manual crosschecking of medical charts of these patients, we found 1218 (32 %) cases, which had no aneurysm (false-positive). Data of remaining true aneurysm-cases were divided into clinical and intensive care unit subsets where every event linked to particular date of treatment was defined as an info-unit. All the data in both subsets were structured into separate Excel files and presented in chronological order for each particular patient. Altogether, dataset included 70 000 000 rows of info-units found in 2632 patients.Conclusions. Data mining allowed establishment of detailed clinical dataset of patients with brain aneurysms. Produced mining algorithm had limitation regarding false-positive cases (32 % patients). Based on that, we recommend manual crosschecking of automatically collected dataset before statistical analysis.

цифровизациямедицинские данныенабор данныхавтоматизированное получение данныхперекрестная проверка данныхdigitalizationmedical datadatasetminingcrosscheckingReferencesAue G., Biesdorf S., Henke N. How healthcare systems can become digital-health leaders. McKinsey and Company Healthcare Systems and Services. Available at: https://www.mckinsey.com/industries/healthcare/our-insights/how-healthcare-systems-canbecome-digital-health-leadersAue G., Biesdorf S., Henke N. How healthcare systems can become digital-health leaders. McKinsey and Company Healthcare Systems and Services. Available at: https://www.mckinsey.com/industries/healthcare/our-insights/how-healthcare-systems-canbecome-digital-health-leadersFaggella D. Where healthcare’s big data actually comes from. Available at: https://www.techemergence.com/where-healthcares-big-dataactually-comesfromFaggella D. Where healthcare’s big data actually comes from. Available at: https://www.techemergence.com/where-healthcares-big-dataactually-comesfromHuesch M., Mosher T. Using it or losing it? The case for data scientists inside health care. NEJM catalyst. Available at: https://catalyst.nejm.org/doi/full/10.1056/CAT.17.0493Huesch M., Mosher T. Using it or losing it? The case for data scientists inside health care. NEJM catalyst. Available at: https://catalyst.nejm.org/doi/full/10.1056/CAT.17.0493Gopal G., Suter-Crazzolara C., Toldo L., Eberhardt W. Digital transformation in healthcare - architectures of present and future information technologies. Clin. Chem. Lab. Med. 2019;57(3):328–335. doi: 10.1515/cclm-2018-0658Gopal G., Suter-Crazzolara C., Toldo L., Eberhardt W. Digital transformation in healthcare - architectures of present and future information technologies. Clin. Chem. Lab. Med. 2019;57(3):328–335. doi: 10.1515/cclm-2018-0658Backes D., Rinkel G., Greving J., Velthuis B., Murayama Y., Takao H., Ishibashi T., Igase M., ter-Brugge K., Agid R.,… Vergouwen M. ELAPSS score for prediction of risk of growth of unruptured intracranial aneurysms. Neurology. 2017;88(17):1600–1606. doi: 10.1212/WNL.0000000000003865Backes D., Rinkel G., Greving J., Velthuis B., Murayama Y., Takao H., Ishibashi T., Igase M., ter-Brugge K., Agid R.,… Vergouwen M. ELAPSS score for prediction of risk of growth of unruptured intracranial aneurysms. Neurology. 2017;88(17):1600–1606. doi: 10.1212/WNL.0000000000003865Chang K., Bai H., Zhou H., Su C., Bi W., Agbodza E., Kavouridis V., Senders J., Boaro A., Beers A., … Kalpathy-Cramer J. Residual convolutional neural network for the determination of IDH status in low- and high-grade gliomas from MR imaging. Clin. Cancer Res. 2018;24(5):1073–1081. doi: 10.1158/1078-0432.CCR-17-2236Chang K., Bai H., Zhou H., Su C., Bi W., Agbodza E., Kavouridis V., Senders J., Boaro A., Beers A., … Kalpathy-Cramer J. Residual convolutional neural network for the determination of IDH status in low- and high-grade gliomas from MR imaging. Clin. Cancer Res. 2018;24(5):1073–1081. doi: 10.1158/1078-0432.CCR-17-2236Malhotra A., Wu X., Forman H., Matouk C., Gandhi D., Sanelli P. Management of tiny unruptured intracranial aneurysms: a comparative effectiveness analysis. JAMA Neurol. 2018;75(1):27–34. doi: 10.1001/jamaneurol.2017.3232Malhotra A., Wu X., Forman H., Matouk C., Gandhi D., Sanelli P. Management of tiny unruptured intracranial aneurysms: a comparative effectiveness analysis. JAMA Neurol. 2018;75(1):27–34. doi: 10.1001/jamaneurol.2017.3232McKenna B. SAP banks on “intelligent enterprise” at Sapphire 2018. Available at: https://www.computerweekly.com/news/252442802/SAP-bankson-intelligent-enterprise-at-Sapphire-2018McKenna B. SAP banks on “intelligent enterprise” at Sapphire 2018. Available at: https://www.computerweekly.com/news/252442802/SAP-bankson-intelligent-enterprise-at-Sapphire-2018Quinn J.B. Strategic outsourcing: leveraging knowledge capabilities. MIT Sloan Management Review. Summer 1999. Available at: https://sloanreview.mit.edu/article/strategic-outsourcing-leveragingknowledge-capabilities/Quinn J.B. Strategic outsourcing: leveraging knowledge capabilities. MIT Sloan Management Review. Summer 1999. Available at: https://sloanreview.mit.edu/article/strategic-outsourcing-leveragingknowledge-capabilities/What is value-based healthcare? NEJM Catalyst. Available at: https://catalyst.nejm.org/doi/full/10.1056/CAT.17.0558What is value-based healthcare? NEJM Catalyst. Available at: https://catalyst.nejm.org/doi/full/10.1056/CAT.17.0558Shirer M., Daquilla M. IDC spending guide forecasts worldwide spending on cognitive and artificial intelligence systems to reach $57.6 Billion in 2021. IDC. Available at: https://www.idc.com/getdoc.jsp?containerId=prUS43095417Shirer M., Daquilla M. IDC spending guide forecasts worldwide spending on cognitive and artificial intelligence systems to reach $57.6 Billion in 2021. IDC. Available at: https://www.idc.com/getdoc.jsp?containerId=prUS43095417Laranjo L., Dunn A., Tong H., Kocaballi A., Chen J., Bashir R., Surian D., Gallego B., Magrabi F., Lau A., Coiera E. Conversational agents in healthcare: a systematic review. J. Am. Med. Inform. Assoc. 2018;25(9):1248–1258. doi: 10.1093/jamia/ocy072Laranjo L., Dunn A., Tong H., Kocaballi A., Chen J., Bashir R., Surian D., Gallego B., Magrabi F., Lau A., Coiera E. Conversational agents in healthcare: a systematic review. J. Am. Med. Inform. Assoc. 2018;25(9):1248–1258. doi: 10.1093/jamia/ocy072Perrin D. Lessons from the data: applying machine learning for clinical decision support. Vector medicine, Boston Children’s Hospital. Available at: https://vector.childrenshospital.org/2017/04/machinelearning-clinical-decision-support/Perrin D. Lessons from the data: applying machine learning for clinical decision support. Vector medicine, Boston Children’s Hospital. Available at: https://vector.childrenshospital.org/2017/04/machinelearning-clinical-decision-support/Rajkomar A., Dean J., Kohane I. Machine learning in medicine. N. Engl. J. Med. 2019;380(14):1347–1358. doi: 10.1056/NEJMra1814259Rajkomar A., Dean J., Kohane I. Machine learning in medicine. N. Engl. J. Med. 2019;380(14):1347–1358. doi: 10.1056/NEJMra1814259Madhavan R. Machine translation – 14 current applications and services. Available at: https://emerj.com/ai-sector-overviews/machine-translation-14-current-applications-and-services/Madhavan R. Machine translation – 14 current applications and services. Available at: https://emerj.com/ai-sector-overviews/machine-translation-14-current-applications-and-services/Gillies J.C., Baird A.G., Gillies E.M. Balancing proactive and reactive care. Occasional Paper in Royal College of General Practitioners. 1995;71(71):15–28.Gillies J.C., Baird A.G., Gillies E.M. Balancing proactive and reactive care. Occasional Paper in Royal College of General Practitioners. 1995;71(71):15–28.Aoe J., Fukuma R., Yanagisawa T., Harada T., Tanaka M., Kobayashi M., Inoue Y., Yamamoto S., Ohnishi Y., Kishima H. Automatic diagnosis of neurological diseases using MEG signals with a deep neural network. Sci. Rep. 2019;9(1):5057. doi: 10.1038/s41598-019-41500-xAoe J., Fukuma R., Yanagisawa T., Harada T., Tanaka M., Kobayashi M., Inoue Y., Yamamoto S., Ohnishi Y., Kishima H. Automatic diagnosis of neurological diseases using MEG signals with a deep neural network. Sci. Rep. 2019;9(1):5057. doi: 10.1038/s41598-019-41500-xSalimi Ashkezari S.F., Mut F., Slawski M., Cheng B., Yu A.K., White T.G., Woo H.H., Koch M.J., Amin-Hanjani S., Charbel F. T., … Cebral J.R. Prediction of bleb formation in intracranial aneurysms using machine learning models based on aneurysm hemodynamics, geometry, location, and patient population. J. Neurointerv. Surg. 2022;14(10):1002–1007. doi: 10.1136/neurintsurg-2021-017976Salimi Ashkezari S.F., Mut F., Slawski M., Cheng B., Yu A.K., White T.G., Woo H.H., Koch M.J., Amin-Hanjani S., Charbel F. T., … Cebral J.R. Prediction of bleb formation in intracranial aneurysms using machine learning models based on aneurysm hemodynamics, geometry, location, and patient population. J. Neurointerv. Surg. 2022;14(10):1002–1007. doi: 10.1136/neurintsurg-2021-017976Gulshan V., Peng L., Coram M., Stumpe M., Wu D., Narayanaswamy A., Venugopalan S., Widner K., Madams T., Cuadros J., … Webster D. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA. 2016;316(22):2402–2410. doi: 10.1001/jama.2016.17216Gulshan V., Peng L., Coram M., Stumpe M., Wu D., Narayanaswamy A., Venugopalan S., Widner K., Madams T., Cuadros J., … Webster D. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA. 2016;316(22):2402–2410. doi: 10.1001/jama.2016.17216Hitchcock E., Gibson W. A Review of the genetics of intracranial berry aneurysms and implications for genetic counseling. J. Genet. Couns. 2017;26(1):21–31. doi: 10.1007/s10897-016-0029-8Hitchcock E., Gibson W. A Review of the genetics of intracranial berry aneurysms and implications for genetic counseling. J. Genet. Couns. 2017;26(1):21–31. doi: 10.1007/s10897-016-0029-8Sing D., Metz L., Dudli S. Machine learningbased classification of 38 years of spine-related literature into 100 research topics. Spine. 2017;42(11):863–870. doi: 10.1097/BRS.0000000000002079Sing D., Metz L., Dudli S. Machine learningbased classification of 38 years of spine-related literature into 100 research topics. Spine. 2017;42(11):863–870. doi: 10.1097/BRS.0000000000002079Senders J., Arnaout O., Karhade A., Dasenbrock H., Gormley W., Broekman M., Smith T. Natural and artificial intelligence in neurosurgery: a systematic review. Neurosurgery. 2018;83(2):181–192. doi: 10.1093/neuros/nyx384Senders J., Arnaout O., Karhade A., Dasenbrock H., Gormley W., Broekman M., Smith T. Natural and artificial intelligence in neurosurgery: a systematic review. Neurosurgery. 2018;83(2):181–192. doi: 10.1093/neuros/nyx384

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