Method for generating intelligent monitoring system for freezing of gait

A technology for intelligent monitoring and gait

Active Publication Date: 2018-07-24
SHANGHAI NINTH PEOPLES HOSPITAL AFFILIATED TO SHANGHAI JIAO TONG UNIV SCHOOL OF MEDICINE
View PDF8 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the laser walking aid device disclosed in the above-mentioned patent does not intelligently control the laser emission, and cannot monitor the occurrence of frozen gait of the patient
The device is manually turned on. Once it is turned on, the laser line is always on, which is likely to cause visual fatigue to the patient, weaken the patient's attention when walking, and cannot effectively improve the symptoms of FOG.
Because the occurrence of FOG is related to the environment and the situation, that is, FOG usually occurs in short-term or instantaneous situations such as patients starting, turning, narrow space, approaching the end point, and emotional tension, and FOG rarely occurs during the patient’s walking process, so there are reports in the literature , t

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method for generating intelligent monitoring system for freezing of gait
  • Method for generating intelligent monitoring system for freezing of gait
  • Method for generating intelligent monitoring system for freezing of gait

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0062] In this example, refer to figure 1 , including:

[0063] Step 1, Data Acquisition

[0064] Acquire the patient's three-axis acceleration data through a nine-axis sensor (including a three-axis accelerometer, a three-axis gyroscope, and a three-axis geomagnetic sensor), that is, the acceleration data of the X, Y, and Z axes, and the collected data is saved to the SD card by the microcontroller middle.

[0065] While collecting the acceleration data of the patient, the walking process of the patient is photographed synchronously.

[0066] Step 2, freeze gait offline recognition

[0067] The patient's acceleration data is imported from the SD card to the PC computer, and the developed frozen gait intelligent recognition algorithm is applied on the computer to identify and classify the patient's frozen gait. This step specifically includes:

[0068] 1) FOG encoding and label setting, constructing FOG encoding matrix

[0069] By observing the recorded images, determine...

Embodiment 2

[0110] In this embodiment, on the basis of Embodiment 1, step 2 also includes:

[0111] 4) Determination of sliding time window parameters (external parameters)

[0112] In part 2) of step 2, when extracting FOG features, the acceleration data is processed in each time window, and the sliding time window is set as an adjustable parameter. The larger the sliding time window, the higher the prediction accuracy, but it will be It brings a large system delay, so it is necessary to make a compromise adjustment to the parameter setting of the sliding time window to obtain a higher-precision FOG recognition result.

[0113] The present invention presets n incremental parameters for the sliding time window, and obtains the FOG recognition result under each sliding time window parameter by referring to the formula (4), and obtains the FOG prediction time series matrix y2.

[0114] According to Table 1, the confusion matrix of the two classifications was constructed, and the accuracy, ...

Embodiment 3

[0117] Different from Embodiment 1 or 2, in this embodiment, in the second) part of step 2, M patient data sets are selected, one is selected as a test set each time, and the remaining M-1 are used as a training set, which can be obtained The best general prediction model applicable to all patients can improve the generalization ability of the model and reduce the generalization error when validating new data.

[0118] The FOG prediction model obtained by the method of the present invention is transplanted to the microcontroller, and when the frozen gait of the patient is detected, that is, when the prediction output is 1, the microcontroller sends a control signal to the laser emitting system to turn on the laser light source. When the end of the frozen gait is detected immediately, the output of the FOG prediction model is -1, and the microcontroller sends a control signal to the laser light emitting system to turn off the laser light source.

[0119] After the actual test o...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention provides a method for generating an intelligent monitoring system for freezing of gait. The method comprises the steps that three-axis acceleration data is collected, an FOG prediction model is adopted for FOG and non-FOG characteristic recognition and classification according to the collected three-axis acceleration data, and the recognition precision of the FOG prediction model isverified; the verified FOG prediction model is transplanted to a micro-controller. According to the method, for the specific gait disorder disease of freezing of gait, an FOG intelligent recognition and classification algorithm is developed, the individual difference error caused when an acceleration set critical threshold value is judged in the prior art is overcome, and accordingly the FOG recognition accuracy is improved. According to the method, the recognition rate of freezing of gait is effectively increased, and the accuracy, sensitivity and specificity of FOG recognition on patients reach 88.6-95.2%, 83.7-93.1% and 90.2-97% respectively.

Description

technical field [0001] The invention relates to equipment in the field of intelligent medical assistance, in particular to a generation method of a wearable frozen gait intelligent monitoring system. Background technique [0002] Freezing of gait (FOG) is a common abnormal gait symptom in Parkinson's disease (PD). Cross-sectional studies have shown that 30%-60% of PD patients are accompanied by FOG. In other neurodegenerative diseases, such as multiple system atrophy and progressive supranuclear palsy, the incidence of FOG is higher than that of PD. FOG has the characteristics of sudden occurrence, short duration, situational triggering and unpredictable, which can easily cause patients to fall and seriously affect the quality of life of patients. However, in terms of the treatment of frozen gait, the effect of drugs on the symptoms of frozen gait is not ideal, and even for some patients, drugs can aggravate the symptoms of FOG. Therefore, exploring new methods for non-dru...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): A61B5/11A61H3/00
CPCA61B5/112A61B5/4082A61B5/6801A61H3/00
Inventor 顾冬云李波
Owner SHANGHAI NINTH PEOPLES HOSPITAL AFFILIATED TO SHANGHAI JIAO TONG UNIV SCHOOL OF MEDICINE
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap