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