Method for predicting fall risk of elderly person

Abstract

The invention discloses a method for predicting fall risk of elderly people. The method comprises the following steps: dividing a plantar pressure area into a hallux area, a second-fifth toe area, a forefoot area, a middle foot area and a heel area; dividing a support phase into an initial contact section, an initial metatarsal bone grounding section, an initial forefoot flat section, a heel off-ground section and a final contact section; then, based on the plantar pressure areas and the supporting phase, carrying out plantar pressure testing on a subject by using a Footscan plantar pressure flat plate testing system so as to obtain pressure change curves of the different plantar pressure areas in all supporting phase periods; constructing a deep neural network model by using a convolutional neural network and a recurrent neural network, training the prediction model, and selecting an optimal prediction model as a foot pressure prediction model; and finally, inputting the pressure change curves into the foot pressure prediction model to obtain a prediction value. The method has the characteristics of high data measurement precision, various characteristic indexes and good prediction accuracy.

Description

technical field [0001] The invention relates to the field of behavior recognition and judgment, in particular to a method for predicting the fall risk of the elderly. Background technique [0002] Walking is the most basic and natural form of exercise completed by the coordination and cooperation of various organs and muscles of the human body. Walking ability is the basic guarantee for the elderly to carry out independent activities and realize self-care. The main executive unit of human walking is the lower limbs, and 28 of the bones involved in the movement of the lower limbs come from the feet. Therefore, the plantar pressure during walking contains a wealth of gait information, which is often used to study the abnormal gait of special populations, such as the elderly, and then evaluate the risk of falls in the process of walking in real time, so as to prevent falls for the elderly. and interventions to provide theoretical support and practical guidance. [0003] At pr...

AI Technical Summary

Problems solved by technology

[0004] However, this prediction method can only select a discrete and single feature index as a detection factor during feature selection, which is not enough to summarize the entire gait or balance process, resulting in low prediction accuracy; and the selection of feature extraction and subsequent classifiers depends on In many studies, the processes are independent of each other, and the features and classifiers cannot be optimized at the same time according to the classification results, resulting in the problems of low detection efficiency and poor generalization ability of instrument detection methods

In addition, the data obtained by using the plantar pressure test platform has the characteristics of high latitude, high variability, multivariate, time dependence and nonlinearity, which further increases the difficulty of analyzing the prediction results

Therefore, the existing methods for predicting the risk of falls in the elderly have the problems of low data measurement accuracy, single characteristic index and poor prediction accuracy.

Images