Abstract. 

Paper is aimed to develop algorithm for searching statically significant dependencies on medical data of patients with sub-mild cognitive decline. Algorithms and methods of statistical processing and transformation of medical data of patients are considered. A method for identifying groups of indicators that have the greatest consistency and separation capacity for a priori groups of patients and a method for selecting key observations are proposed. Combinatorial canonical analysis is applied to find the most important risk factors for cognitive decline. Confirmed the results of previous studies on the closest relationship between cognitive decline and cardiovascular risk factors such as arterial hypertension or myocardial infarction in anamnesis

Keywords: 

dimension reduction, multivariate statistical methods, canonical analysis, cognitive decline.

PP. 34-43.

DOI 10.14357/20718632210204

 

References

1. Zakharov V.V., Yakhno N.N. Sindrom umerennykh kognitivnykh narusheniy v pozhilom vozraste – diagnostika i lechenie [Mild cognitive impairment syndrome in old age - diagnosis and treatment]. Rossiyskiy meditsinskiy zhurnal. 2004; 12(10): 573–576.

2. Amieva H., Le Goff M., Millet X., Orgogozo J.M., Pérès K., Barberger-Gateau P. et al. Prodromal Alzheimer’s disease: Successive emergence of the clinical symptoms. Ann. Neurol. 2008; 64(5): 492–8

3. Mitchell A.J., Beaumont H., Ferguson D., Yadegarfar M., Stubbs B. Risk of dementia and mild cognitive impairment in older people with subjective memory complaints: metaanalysis. Acta Psychiatr. Scand. 2014; 130(6): 439–51.

4. Lokshina A.B., Zakharov V.V. Legkie i umerennye kognitivnye rasstroystva pri distsirkulyatornoy entsefalopatii [Mild to moderate cognitive impairment in discirculatory encephalopathy]. Nevrologicheskiy zhurnal. 2006; 11(Pril. 1): 57–63.

5. Dubois B., Hampel H.J, Feldman H.H., Scheltens P., Aisen P., Andrien S. et al. Preclinical Alzheimer’s disease: Definition, natural history and diagnostic criteria. Alzheimers Dement. 2016; 12(3): 292–323.

6. Seo E.H., Kim H., Lee K.H., Choo I.H. Altered executive function in pre-mild cognitive impairment. J. Alzheimers Dis. 2016; 54(3): 933–40

7. Jessen F., Amariglio R.E., van Boxtel M., Breteler M., Ceccaldi M., Chételat G. et al. Subjective Cognitive Decline Initiative (SCD-I) Working Group. A conceptual framework for research on subjective cognitive decline in preclinical Alzheimer’s disease. Alzheimers Dement. 2014; 10(6): 844–52

8. Yakhno N.N., Zakharov V.V., Koberskaya N.N., Mkhitaryan E.A., Grishina D.A., Lokshina A.B., Savushkina I.Yu., Posokhov S.I. "Predumerennye" (sub"ektivnye i legkie) kognitivnye rasstroystva ["Sub mild" (subjective and light) cognitive disorders] // Nevrologicheskiy zhurnal. 2017. №4. Available at:

https://cyberleninka.ru/article/n/predumerennyesubektivnye-

i-lyogkie-kognitivnye-rasstroystva ((accessed: March 03 2021).

9. Ostroumova T.M., Parfenov V.A., Ostroumova O.D., Perepelova E. M., Perepelov V. A., Borisova E.V. Vozmozhnosti metoda beskontrastnoy magnitnorezonansnoy perfuzii dlya vyyavleniya rannego porazheniya golovnogo mozga pri essentsial'noy arterial'noy gipertenzii [Possibilities of the non-contrast magnetic resonance perfusion method for detecting early brain damage in essential arterial hypertension] // Nevrologiya, neyropsikhiatriya, psikhosomatika. 2018; 10 (1): 17–23.

10. Parfenov V.A., Ostroumova T. M., Perepelova E. M., Perepelov V. A., Kochetkov A. I., Ostroumova O.D. Perfuziya golovnogo mozga, kognitivnye funktsii i sosudistyy vozrast u patsientov srednego vozrasta s essentsial'noy arterial'noy gipertenziey [Brain perfusion, cognitive function and vascular age in middle-aged patients with essential arterial hypertension] Kardiologiya. 2018; 58(5): 23–31.

11. Koberskaya N.N., Yakhno N.N., Gridin V.N., Smirnov D.S. [The influence of cardiovascular risk factors on submoderate cognitive decline in middle age and old age.] Nevrologiya, neyropsikhiatriya, psikhosomatika. 2021;13(1):13-17. https://doi.org/10.14412/2074-2711-2021-1-13-17

12. Yakhno N.N., Gridin V.N., Smirnov D.S., Panishchev V.S., Parfenov V.A., Ostroumova T.M., Koberskaya N.N. Ctatisticheskaya obrabotka i metodika sokrashcheniya razmernosti prostranstva dannykh patsientov pri analize kognitivnykh narusheniy [Statistical processing and methods of dimension reduction of the medical data of patients with subjective and mild cognitive decline]. Informatsionnye tekhnologii. 2020; 26(9): 515-522

13. Brock, G., Pihur, V., Datta, S., & Datta, S. clValid: An R Package for Cluster Validation. Journal of Statistical Software, 2008;25(4): 1-22.

doi:http://dx.doi.org/10.18637/jss.v025.i04

14. Kendall, M.G. (1948) Rank correlation methods. London: Griffin.

15. Labintcev, E. Metriki v zadachakh mashinnogo obucheniya [Metrics in Machine Learning Problems]. May 12, 2017, Available at:

https://habr.com/ru/company/ods/blog/328372/, (accessed March 5 2021)

16. Marxer, R., & Purwins H. An F-Measure for Evaluation of Unsupervised Clustering with Non-Determined Number of Clusters. 2008. [Электронный ресурс] Режим доступа:

http://mtg.upf.edu/files/publications/unsuperf.pdf

17. Hotelling H. (1936). Relations between two sets of variables. Biometrika, 28, 321–327. doi: 10.1093/biomet/28.3-4.321.

18. González I., Déjean S. CCA: Canonical Correlation Analysis. Available at: https://cran.rproject.org/web/packages/CCA/index.html (accessed March 5 2021)

19. Yehia, Ahmed & Saleh, Mohamed & Ahmed, Abdul-Hadi. (2016). An Adjusted Correlation Coefficient for Canonical Correlation Analysis // Journal of Egyptian Statistical Society.