Mahalanobis distance-based cognitive disease rehabilitation cycle prediction method and system

Abstract

The invention relates to a cognitive disease rehabilitation cycle prediction method and system based on mahalanobis distance, and the method comprises the following steps: 1, selecting a sample set center length alpha in a historical sample data set of X types of cognitive diseases, the central length alpha of the sample set meets the condition that the sum of mahalanobis distances between the length alpha and other remaining lengths in the historical sample data set can be minimum; step 2, aiming at a target evaluation elder omega of the X-class cognitive disease, calculating a mahalanobis distance d (alpha, omega) from the target evaluation elder omega to a central elder alpha of the sample set; and step 3, according to the following mathematical expression (1), calculating the rehabilitation cycle Domega of the target evaluation elder omega.

Description

technical field [0001] The present invention relates to a method and a system for predicting the rehabilitation period of dementia based on Mahalanobis distance. Background technique [0002] With the development of human social well-being, the problem of population aging has gradually emerged. On the one hand, it brings greater development pressure to the elderly care industry, and on the other hand, it brings about the rehabilitation research of common cases in the aging population, such as dementia. There is a lot of mixed data. In recent years, with the rapid development of big data processing technology, some methods and ideas have been provided for this kind of data processing, and the existing big data processing solutions can be used to analyze and process this kind of data to a certain extent. However, in the prior art, there are almost no data analysis models specifically for rehabilitation research such as dementia, which cannot reach the level of data analysis t...

AI Technical Summary

Problems solved by technology

However, in the existing technology, there is almost no data analysis model specifically for rehabilitation research such as dementia, which cannot reach the level of data analysis that provides reference value for rehabilitation programs

Moreover, in the traditional predictive statistical model based on Euclidean distance, for big data such as dementia, it cannot well reflect the differences between the elderly with dementia of different races, different physical conditions, and different mental states consistency or consistency, and even affected by different measurement scales, dimensions, and potential correlation variables, it is impossible to make appropriate mathematical expressions for new data outside the data sample set, so in the key dementia rehabilitation assessment, it cannot be separated from Estimates and judgments based on human subjective experience have affected the scientific and quantifiable progress of dementia rehabilitation work, resulting in redundant consumption of human resources in nursing work

Images