Application of regression analysis and classification trees in calculating additional population risk of ischemic heart disease

View or download the full article:

health-risk-analysis-2017-3-4.pdf

UDC:

616.1:57.087

DOI:

10.21668/health.risk/2017.3.04.eng

Authors:

S.A. Maksimov, D.P. Tsygankova, G.V. Artamonova

Organization:

Scientific Institution Research Institute for Complex Issues of Cardiovascular Diseases, 6 Sosnoviy blvd, Kemerovo, 650002, Russian Federation

Abstract:

Our research goal was to perform a comparative analysis of regression analysis application and tree classification appli-cation in calculating additional population risk on the example of ischemic heart diseases (IHD). Our research object was a random population sample comprising both male and female population aged 25-64 in Kemerovo region (1,628 people) within ESSE-RF multi-centered epidemiologic research. We considered the following IHD risk factors: lipid metabolism parameters, arterial hypertension, lifestyle factors, psychoemotional peculiarities, and social parameters. IHD occurrence was assessed as per sum of 3 epidemiologic criteria: on the basis of ECG changes coding as per Minnesota code, Rose questionnaire, and car-diac infarction in case history. We calculated additional population IHD risk determined by risk factors as per unified original algorithms, but with various statistic analysis techniques: logistic regression analysis and classification trees.

We built up mathematic models for IHD probability as per risk factors, with predictive significance equal to 83.8% for logistic regression analysis and to 71.9% for classification trees. The applied statistical analysis techniques show different contributions made by risk factors into IHD prevalence which results from absence of correlation between them.

IBD risk additional to population one and determined by risk factors as per both statistical analysis techniques in sex-age groups changed from negative values in age groups younger than 45 to positive values in older people. Increase in addi-tional IHD risk in aged groups as per both techniques was practically linear with slight deviations. Difference in additional population risk calculated as per two statistical analysis techniques was insignificant and as a rule it didn't exceed 1.5%. Consequently, both techniques give similar results and can be equally used in calculating IHD population risk.

Keywords:

regression analysis, risk factor, ischemic heart disease, population risk, predictive models, statistical analysis techniques

Maksimov S.A., Tsygankova D.P., Artamonova G.V. Application of regression analysis and classification trees in calculating additional population risk of ischemic eart disease. Health Risk Analysis, 2017, no. 3, pp. 31–39. DOI: 10.21668/health.risk/2017.3.04.eng

References:

Batyushin M.M. Modernizatsiya shkaly SCORE otsenki desyatiletnego riska serdechno-sosudistoi smertnosti [Modernization of 10-year cardiovascular death risk scale SCORE]. Rossiiskii kardiologicheskii zhurnal, 2005, no. 6, pp. 40–44. (in Russian).
Zykov M.V., Zykova D.S., Kashtalap V.V., Pecherina T.B., Barbarash O.L. Znachimost' mul'tifokal'nogo ateroskleroza dlya modifikatsii shkaly otdalennogo riska smertnosti GRACE u bol'nykh ostrym koronarnym sin-dromom s pod"emom segmenta ST [The prognostic value of peripheral arteries diseases in patients with st-segment elevation myocardial infarction]. Ateroskleroz, 2012, vol. 8, no. 1, pp. 14–20 (in Russian).
Kontsevaya A.V., Suvorova E.I., Khudyakov M.B. Ekonomicheskaya effektivnost' renal'noy denervatsii u patsientov s rezistentnoy arterial'noy gipertoniey: rezul'taty markovskogo modelirovaniya [Economic eificiency of renal denervation in patients with resistant hypertension: results of markov modeling]. Kardiologiya, 2014, vol. 54, no. 1, pp. 41–47 (in Russian).
Kontsevaya A.V., Shal'nova S.A. Populyatsionnye modeli prognozirovaniya serdechno-sosudistogo riska: tselesoobraznost' modelirovaniya i analiticheskiy obzor sushchestvuyushchikh modeley[Population models of cardiovascular risk prediction: expedience of modeling and analytic review of current models]. Kardiovaskulyarnaya terapiya i profilaktika, 2015, vol. 14, no. 6, pp. 54–58 (in Russian).
Maksimov S.A., Indukaeva E.V., Artamonova G.V. Integral'naya otsenka riska ishemicheskoy bolezni serdtsa v epidemiologicheskikh issledovaniyakh (ESSE-RF v Kemerovskoy oblasti). Soobshchenie I: vozrastno-polovye determinant [Integral assessment of coronary heart disease risk in the epidemiological studies (ESSE-RF in the Kemerovo Region). Communication 1: Age and sex determinants]. Profilakticheskaya meditsina, 2015, vol.18, no. 6, pp. 34–39 (in Russian).
Maksimov S.A., Skripchenko A.E., Artamonova G.V. Integral'naya otsenka faktorov riska pro-fessional'noy obuslovlennosti arterial'noy gipertenzii [Integral assessment of work-related arterial hypertension risk factors]. Rossiyskiy kardiologicheskiy zhurnal, 2015, vol.120, no. 4, pp. 38–42 (in Russian).
Maksimov S.A., Tabakaev M.V., Artamonova G.V. Integral'naya otsenka riska ishemicheskoy bolezni serdtsa v epidemiologicheskikh issledovaniyakh (ESSE-RF v Kemerovskoy oblasti). Soobshchenie II: sotsial'no-ekonomicheskie determinant [Integral assessment of coronary heart disease risk in the epidemiological studies (ES-SE-RF in the Kemerovo Region). Communication 1I: Socioeconomic determinants]. Profilakticheskaya meditsina, 2016, vol.19, no. 1, pp. 24–29 (in Russian).
Mamedov M.N., Chepurina N.A. Summarnyi serdechno-sosudistyi risk: ot teorii k praktike: posobie dlya vrachei [Total cardio-vascular risk: from theory to practice: a manual for physicians]. In: R.G. Oganov, ed. Mos-cow, 2007, 23 p. (in Russian).
Boytsov S.A, Vatolina M.A., Samorodskaya I.V., Barbarash O.L., Ovcharenko O.A., Kondrikova N.V. Mnenie vrachey o roli otdel'nykh faktorov smertnosti ot bolezney sistemy krovoobrashcheniya v regionakh Ros-siyskoy Federatsii [Medical care practitioners' opinion on the role of specific factors contributing to the mortality from circulatory system disease in the regions of the Russian Federation]. Kompleksnye problemy serdechno-sosudistykh zabolevaniy, 2015, no. 4, pp. 53–60 (in Russian).
Oganov R.G., Shal'nova S.A., Kalinina A.M., Deev A.D., Glazachev O.S., Gusev E.I., Belyaeva I.A., Su-darev A.M. Novyy sposob otsenki individual'nogo serdechno-sosudistogo summarnogo riska dlya naseleniya Rossii [The novel method of assessment of individual total cardiovascular risk for the population of Russia]. Kardiologiya, 2008, vol. 48, no. 5, pp. 87–91 (in Russian).
Assmann G. Assessment of cardiovascular risk – PROCAM and new algorithms. Biomed. Tech. (Berl), 2005, vol. 50, no. 7–8, pp. 227–232.
Vanuzzo D., Pilotto L., Mirolo R., Pirelli S. Cardiovascular risk and cardiometabolic risk: an epidemio-logical evaluation. G. Ital. Cardiol. (Rome), 2008, vol. 9, no.4, pp. 6S–17S.
Gorenoi V., Hagen A. Overview of risk – estimation tools for primary prevention of cardiovascular dis-eases in European populations. Cent. Eur. J. Public. Health., 2015, vol. 23, no.2, pp. 91–99.
Berger J.S., Jordan C.O., Lloyd-Jones D., Blumenthal R.S. Screening for cardiovascular risk in asympto-matic patients. J. Am. Coll. Cardiol., 2010, vol. 55, no.12, pp. 1169–1177.
Kahn R., Robertson R.M., Smith R., Eddy D. The impact of prevention on reducing the burden of cardio-vascular disease. Circulation, 2008, vol. 118, pp. 576–585.