Статья

Association of Cardiovascular Events and Blood Pressure and Serum Lipoprotein Indicators Based on Functional Data Analysis as a Personalized Approach to the Diagnosis

N. Plekhova, V. Nevzorova, T. Brodskay, K. Shakhgeldyan, B. Geltser, L. Priseko, I. Chernenko, K. Grunberg,
2020

The development of trends and practice-oriented approaches to personalized programs for the diagnosis and correction depending on the clinical and phenotypic variants of the person is relevant. A software application was created for data mining from respondent profiles in a semi-automatic mode; libraries with data preprocessing were analyzed. The anthropometric measurements and serum lipoprotein spectrum of 2131 volunteers (average age 45.75 ± 11.7 years) were studied. To estimate the association of blood pressure and cardiovascular events markers was carried out by means of multivariate analysis of data by the methods of selection and classification significant signs. The machine learning was used to predict cardiovascular events. Depends on gender there was found the significant difference in atherogenic index of plasma (AIP) (F < 0.05). In young women (20–30 y.o.), the lipoproteins did not correlate with the presence of hypertension, whereas for older women the statistically significant markers were higher, such as cholesterol (CH, F = 0.03), low-density lipoproteins (LDL, F = 0.03) and AIP (F = 0.02). In men for identifying the risk of hypertension developing lipoproteins should be considered depending on age. Accuracy of the risk recognition for the cardiovascular disease (CVD) model was more than 89% with an average confidence of the model in each forecasted case of 90%. The markers for diagnosing the risk of CVD, the following indicators can be used according to their degree of significance: AIP, CH and LDL. Thus, the data obtained indicate the importance of risk factor phenotyping using anthropometric markers and biochemical profile for determining their significance in the top 17 predictors of CVD. The machine learning provides CVD prediction according to standard risk assessments.

Цитирование

Похожие публикации

Источник

Версии

  • 1. Version of Record от 2020-01-01

Метаданные

Об авторах
  • N. Plekhova
    Pacific State Medical University, Institute of Chemistry FEB RAS
  • V. Nevzorova
    Pacific State Medical University, Institute of Chemistry FEB RAS
  • T. Brodskay
    Pacific State Medical University
  • K. Shakhgeldyan
    Vladivostok State University of Economics and Service, Far Eastern Federal University
  • B. Geltser
    Vladivostok State University of Economics and Service, Far Eastern Federal University
  • L. Priseko
    Pacific State Medical University
  • I. Chernenko
    Pacific State Medical University
  • K. Grunberg
    Pacific State Medical University
Название журнала
  • Advances in Intelligent Systems and Computing
Том
  • 1295
Страницы
  • 278-293
Финансирующая организация
  • Russian Foundation for Basic Research
Номер гранта
  • 19-29-01077
Тип документа
  • journal article
Тип лицензии Creative Commons
  • CC BY
Правовой статус документа
  • Свободная лицензия
Источник
  • scopus