Assessment system and assessment method for predicting falling risk of senile sarcopenia patient

Abstract

The invention relates to a risk assessment system for predicting falling of a senile sarcopenia patient. The risk assessment system involves a walking stick, a radio detection device, a tremor frequency sensor, a first pressure detection sensor, a telescopic rod, a walking head and a microprocessor. According to the risk assessment system for predicting falling of the senile sarcopenia patient, a control part of the system is arranged in the walking stick used by the elderly when the elderly walks, pressure, muscle tremor frequency and human body image data are collected and wirelessly transmitted, finally a comprehensive falling risk assessment function is formed, whether the elderly falls down or is about to fall down is judged through a value of the risk assessment function, and when it is predicted that the elderly is about to fall down, a sound-light alarm is given out; and therefore, compared with an existing prediction method or prediction system adopting a single detection mode, the risk assessment system has the following advantages that the prediction accuracy and precision can be obviously improved, and rapid prediction and prevention can be realized.

Description

technical field [0001] The invention relates to the technical field of medical detection, in particular to a risk assessment system and assessment method for predicting falls of elderly patients with sarcopenia. Background technique [0002] The elderly often fall due to osteoporosis, rheumatism, arthritis, and sarcopenia. Falls can easily cause severe damage or even fracture to the already fragile bones. Among them, falls caused by sarcopenia are an important threat to the health of the elderly. Factors, as the muscle strength of the elderly deteriorates, the balance and reaction ability weaken, and the risk of falling will increase accordingly. By pre-evaluating the walking quality of the elderly, it is possible to guide their walking behavior and carry out active and effective interventions, which can greatly reduce the occurrence of falls and reduce the hazards of falls. Developing corresponding intervention measures according to the risk of falls of the elderly can effe...

AI Technical Summary

Problems solved by technology

But sometimes, the elderly fall because of non-skeletal diseases such as labor pains caused by rheumatoid arthritis, high blood pressure, hypoglycemia, and muscle tremors caused by sarcopenia. At this time, the elderly may fall due to these emergencies. However, such emergencies are often not detected by a single sensor

[0004] The method of judging by the sensor on the human body wearable device is generally: installing a camera in a place where the elderly are active frequently to obtain surveillance video data, and cutting out a human body image containing at least human joints from each frame of image in the surveillance video data, And process the human body image into a predetermined standard size human body image to be recognized, based on the pre-trained human body pose estimation network model, obtain the joint coordinate data in the human body image to be recognized, and based on the joint coordinate data of continuous multi-frame images, evaluate The risk of falling of the elderly is based on the machine learning model to obtain the body posture to evaluate the risk of falling. Although the image judgment method can reduce the use of detection sensors to a certain extent and reduce the impact of wearing devices on the lives of the elderly, image detection is only used for Fall risk assessment when judging that the elderly have large body movements, but the elderly usually seldom have large body movements before falling due to sarcopenia. Therefore, pure image judgment or judgment by sensors on wearable devices , it is difficult to accurately predict whether elderly patients with sarcopenia will fall

Images