Neural network analysis of the relationships of risk factors with a fatal event depending on prospective follow-up duration

Aim. To compare the significance of risk factors (RF) in neural network modeling of a fatal outcome for prospective follow-up periods of 10, 20, 30 and 40 years.

Material and methods. From the Russian Lipid Research Clinics Study of 1975-1982, 13263 men and 5691 women were included in the current follow-up until 2017. The end point was all-cause death. Sex, age, blood pressure, heart rate, body mass index, blood lipid levels, smoking and education status, hypertension and hypotension were analyzed. Artificial neural network simulators were used to build multivariate models.

Results. According to the sensitivity analysis, the significance of all input variables included in the models increases with follow-up duration extension. The minimum significance of studied risk factors is observed with a 10-year follow-up in women.

Conclusion. Neural network prediction of a fatal event using the studied risk factors reaches maximum information content by 30 years of prospective follow-up.

1. Vilkov VG, Shalnova SA. Rationale for the use of non-linear statistical methods in the analysis of relationships between risk factors and fatal events according to the data of long-term prospective observation in population of Russia and the United States of America. Russian Journal of Preventive Medicine. 2024; 27(11):34-9. (In Russ.) doi:10.17116/profmed20242711134.

2. Gorban' AN, Dunin-Barkovskij VL, Kirdin AN, et al. Neuroinformatics. Novosibirsk: Science, 1998:1-296. (In Russ.) ISBN: 5-02-031410-2.

3. Shalnova SA, Deev AD, Shestov DB. Prognostic assessment of epidemiological characteristics of ischemic heart disease. Kardiologiia. 1997;9:49-54. (In Russ.)

4. Lapin VV. Arterial hypotension. In: Cardiology: a guide for physicians in 2 vol. Ed. Perepech NB, Ryabov SI. SPb.: SpecLit, 2008; 1:442-60. (In Russ.) ISBN: 978-5-299-00346-8.

5. Vilkov VG, Balanova YuA, Kapustina AV, et al. Hypotension and survival: diagnostic criteria in Russian and United States population. Russian Journal of Cardiology. 2021;26(5):4365. (In Russ.) doi:10.15829/1560-4071-2021-4365.

6. Neural networks: STATISTICA Neural Networks. M.: Goryachaya liniya-Telekom, 2001:1-182. (In Russ.) ISBN: 5-93517-015-9.

7. Borovikov V. STATISTICA: The art of analyzing data on a computer. For professionals. SPb.: Piter, 2001:601-640. (In Russ.) ISBN: 5-318-00302-8.

8. Buhl A, Zofel P. The art of information processing. Statistical data analysis and recovery of hidden patterns. SPb.:OOO "DiaSoftYuP", 2002:1-608. (In Russ.) ISBN: 5-93772-014-8.

9. Kannel WB, McGee D, Gordon T. A general cardiovascular risk profile: The Framingham study. Am J Cardiol. 1976;38(1):46-51. doi:10.1016/0002-9149(76)90061-8.

10. Pocock SJ, McCormack V, Gueyffier F, et al. A score for predic­ting risk of death from cardiovascular disease in adults with raised blood pressure, based on individual patient data from randomised controlled trials. Br Med J. 2001;323:75-81. doi:10.1136/bmj.323.7304.75.

11. Shalnova SA, Oganov RG, Deev AD. Assessment and management of total cardiovascular disease risk in Russian population. Cardiovascular Therapy and Prevention. 2004;3(4):4-11. (In Russ.)

12. Shalnova SA, Deev AD, Oganov RG, et al. Pulse rate and cardiovascular mortality of men and women in Russia. Results of epi­demiological studies. Kardiologiia. 2005;45(10):45-50. (In Russ.)

13. Shalnova SA, Imaeva AE, Kapustina AV, et al. Mortality in 55 years and older population and its relation with ischemic heart disease, traditional risk factors and inflammation markers: the results of prospective cohort study. Russian Journal of Cardiology. 2016;21(6):15-9. (In Russ.) doi:10.15829/1560-4071-2016-6-15-19.

14. Visseren FLJ, Mach F, Smulders YM, et al. 2021 ESC Guidelines on cardiovascular disease prevention in clinical practice. Eur Heart J. 2021;42(34):3227-337. doi:10.1093/eurheartj/ehab484.

15. Boshuizen HC, Izaks GJ, van Buuren S, et al. Blood pressure and mortality in elderly people aged 85 and older: community based stu­dy. BMJ. 1998;316(7147):1780-4. doi:10.1136/bmj.316.7147.1780.

16. Ohkubo T, Imai Y, Tsuji I, et al. Reference values for 24-hour am­bu­latory blood pressure monitoring based on a prognostic criterion: the Ohasama Study. Hypertension. 1998;32(2):255-9. doi:10.1161/01.hyp.32.2.255.