Linear Regression of Blood Pressure to Determine the Risk of Secondary Hypotension

M.V. Voitykova, R.V. Khursa


The blood pressure is the most accessible and important characteristic of cardiovascular system. In this paper, we presented a method for classification of medical blood pressure monitoring data by risk of hypotension, which based on the linear regression modeling of blood pressure parameters followed by the application of the support vector machine-based classifier. Machine learning algorithms to differentiate the signals have a high quality score (93 %). To train the classifier, we have calculated 4-dimensional vector of the features of blood pressure, whose coordinates are linear regression coefficients for the systolic, diastolic and pulse pressure. The best quality for the classification of medical blood pressure signals at risk of hypotension had models that used regression of systolic blood pressure by pulse pressure (or diastolic — by the pulse) as compared to the regression of systolic pressure by diastolic pressure.


Кушаковский М.С. Гипертоническая болезнь. — СПб.: Сотис, 1995. — 4-е изд. — 311 с.

Рашмер Р. Динамика сердечно-сосудистой системы: Пер. с англ. М.А. Безносовой, Т.Е. Кузнецовой; под ред. Г.И. Косицкого. — М.: Медицина, 1981. — 600 с.

Weiss A., Boaz M., Beloosesky Y. et al. // J. Gen. Intern. Med. — 2009. — V. 24(8). — P. 893-896.

Frederique T., Jacques B., Athanase B. et al. // J. Hypertens. — 2008. — V. 26(6). — P. 1072-1077.

Баевский Р.М. Прогнозирование состояний на грани нормы и патологии. — М.: Медицина, 1979. — 298 с.

Хурса Р.В., Чеботарев В.М. Гемодинамические детерминанты гомеостаза сердечно-сосудистой системы // Клиническая физиология кровообращения. — 2007. — № 4. — С. 71-77.

Хурса Р.В., Чеботарев В.М., Балышева В.М. Способ перманентного контроля индивидуального функционального состояния кровообращения: Патент BY № 4876.

Benetos A., Lacolley P. From 24-Hour Blood Pressure Measurements to Arterial Stiffness: A Valid Short Cut? // Hypertension. — 2006. — V. 47. — P. 327-328.

Li Y, Wang J.G., Dolan E. et al. // Hypertension. — 2006. — V. 47. — P. 359-364.

Dolan E., Thijs L., Li Y. et al. // Hypertension. — 2006. — V. 47. — P. 365-370.

Цыплаков А.А. Некоторые эконометрические методы. Метод максимального правдоподобия в эконометрии: Учебное пособие. — Новосибирск: ЭФ НГУ, 1997. — 126 с.

Moody G.B., Lehman L.H. // Computers in Cardiology. — 2009. — V. 36. — P. 541-544.

The MIMIC II Project database:

Vapnik V. Statistical learning theory. — Berlin: Springer, 1998.



  • There are currently no refbacks.

Copyright (c) 2016 HYPERTENSION

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.


© Publishing House Zaslavsky, 1997-2018


   Seo анализ сайта