CN-121667729-B - Orthopedics operation postoperative rehabilitation auxiliary monitoring system based on artificial intelligence

CN121667729BCN 121667729 BCN121667729 BCN 121667729BCN-121667729-B

Abstract

The invention relates to the technical field of rehabilitation auxiliary monitoring, in particular to an artificial intelligence-based postoperative rehabilitation auxiliary monitoring system for orthopedic surgery, which comprises the steps of acquiring electrical signals driven by leg muscle groups of normal and abnormal legs under different training, determining initial abnormal performance according to the deviation of activation time and activation intensity of the two sides, analyzing by combining compensation conditions of different muscles, determining abnormal analysis indexes of each muscle, determining a functional performance change curve according to time sequence distribution of the abnormal analysis indexes of each muscle trained in different times, and performing rehabilitation auxiliary monitoring according to the functional change curves of all muscles. The invention can monitor the electric signal change of the muscle in real time, analyze the electric signal change through compensation characteristics, discover detail change, recovery trend and potential recovery problem in the recovery process in time, and obtain more accurate monitoring results.

Inventors

YU JIANGMING
YE XIAOJIAN
CHEN HAOJIE
XU RUIJUN
JIN CHEN

Assignees

上海市同仁医院

Dates

Publication Date: 20260512
Application Date: 20251223

Claims (8)

1. An artificial intelligence-based postoperative rehabilitation auxiliary monitoring system for orthopedic surgery, which is characterized by comprising: The acquisition module is used for acquiring electric signals driven by leg muscle group nerves of the normal side leg and the abnormal side leg under different training, and determining the activation time and activation intensity of the leg muscles at each position on each side from the electric signals; The performance analysis module is used for carrying out delay analysis according to the activation time of the electric signals of the muscles of the two sides, determining a time deviation coefficient, determining an intensity deviation coefficient according to the activation intensity difference of the electric signals of the muscles of the two sides, combining the time deviation coefficient and the intensity deviation coefficient, and determining the initial abnormal performance degree of the abnormal side leg, wherein the initial abnormal performance degree determination method comprises the steps of calculating the average value of the time deviation coefficient and the intensity deviation coefficient as the initial abnormal performance degree of the abnormal side leg; The compensation analysis module is used for determining other adjacent muscles of each muscle at the activation moment as analysis muscles according to the activation moment of different muscles of the abnormal side leg parts, carrying out compensation analysis in combination with the analysis of the abnormal performance degree of the muscles, determining abnormal compensation confusion degree, wherein the abnormal compensation confusion degree determination method comprises the steps of calculating the average value of the abnormal performance degrees of all analysis muscles, carrying out normalization processing on the opposite numbers of the average value to serve as the abnormal compensation confusion degree, and determining the abnormal analysis index of each muscle in combination with the initial abnormal performance degree and the abnormal compensation confusion degree; the monitoring module is used for determining a functional performance change curve according to the time sequence distribution of the abnormal analysis indexes of each muscle trained at different times, and carrying out artificial intelligent rehabilitation auxiliary monitoring according to the functional change curves of all the muscles.
2. The artificial intelligence based postoperative rehabilitation auxiliary monitoring system for orthopedic surgery according to claim 1, wherein the determining the time deviation coefficient according to the delay analysis of the activation time of the electric signals of the leg muscles comprises: determining the time interval between the activation time of each muscle electric signal and the activation time of the first muscle as the delay time of the corresponding muscle; taking the absolute value of the difference value of the delay time of the muscles at the same position of the abnormal side leg and the normal side leg as the time delay degree of the muscles at the corresponding position; And calculating the average value of the time delay degree of the muscles at each position of the abnormal side leg, and taking the normalization processing as a time deviation coefficient.
3. An artificial intelligence based postoperative rehabilitation aid monitoring system according to claim 1, wherein the determining of the intensity deviation coefficient from the difference in activation intensity of the electrical signals of the leg muscles on both sides comprises: taking the absolute value of the difference value of the activation intensity of the muscle electric signals at the same position as the intensity difference degree of the muscles at the corresponding position; and calculating the average value of the intensity difference degree of the muscles at each position of the abnormal side leg, and taking normalization processing as an intensity deviation coefficient.
4. The artificial intelligence based postoperative rehabilitation assistance monitoring system for orthopedic surgery according to claim 1, wherein the determining, according to activation time of different muscles of abnormal side leg, that other muscles adjacent to each muscle at the activation time are analysis muscles comprises: sequencing all muscles of the abnormal side leg according to the sequence of the activation time to obtain an activation sequence; on the activation sequence, the other two muscles closest to either muscle sequence were determined as analysis muscles.
5. The artificial intelligence based postoperative rehabilitation aid monitoring system for orthopedic surgery according to claim 1, wherein the determining of the abnormality analysis index of each muscle by combining the initial abnormality manifestation degree and the abnormality compensation confusion degree comprises: Linearly mapping the abnormal compensation confusion degree to the value range of [0.5,1.5] to obtain compensation weight; And calculating the product value of the initial abnormal expression degree and the compensation weight to be used as an abnormal analysis index.
6. The artificial intelligence based postoperative rehabilitation aid monitoring system for orthopedic surgery according to claim 1, wherein the determining the functional performance change curve according to the time sequence distribution of the abnormality analysis index of each muscle trained at different times comprises: sequencing according to the abnormal analysis indexes of each muscle in all training processes to obtain an abnormal analysis sequence; constructing a two-dimensional rectangular coordinate system by taking the times as the abscissa and the anomaly analysis index as the ordinate, and determining coordinate points of each element in the anomaly analysis sequence in the two-dimensional rectangular coordinate system; and performing curve fitting on all coordinate points based on a least square method to obtain a functional performance change curve.
7. The artificial intelligence based postoperative rehabilitation assistance monitoring system for orthopedic surgery according to claim 1, wherein the artificial intelligence based rehabilitation assistance monitoring according to the functional change curves of all muscles comprises: Screening to obtain target muscles to be monitored for key abnormality according to the fluctuation of the functional change curves of all muscles; Calculating the mean value of the abnormal analysis indexes of all target muscles trained at the current time, and taking the opposite number normalization processing of the mean value as the rehabilitation degree.
8. The artificial intelligence-based postoperative rehabilitation auxiliary monitoring system for orthopedic surgery according to claim 7, wherein the screening of target muscles to be monitored for key abnormalities according to fluctuation of functional change curves of all muscles comprises: performing straight line fitting on the functional change curves of all muscles to obtain a fitting straight line, and determining the slope of the fitting straight line; Calculating the numerical value average value of the ordinate of all coordinate points in the functional change curve to obtain an overall fluctuation coefficient; taking the product value of the integral fluctuation coefficient of any muscle and the slope value as a monitoring index through normalization treatment; And taking the muscle with the monitoring index larger than the preset index threshold as the target muscle.

Description

Orthopedics operation postoperative rehabilitation auxiliary monitoring system based on artificial intelligence Technical Field The invention relates to the technical field of rehabilitation auxiliary monitoring, in particular to an artificial intelligence-based postoperative rehabilitation auxiliary monitoring system for orthopedic surgery. Background The postoperative rehabilitation of the orthopedic surgery is taken as a process needing long-term monitoring and management, and is greatly promoted by the progress of AI technology, especially under the combination of intelligent hardware and big data analysis. In recent years, as the incidence of bone diseases increases year by year, especially the rehabilitation requirements after fracture, joint replacement and other operations increase. In the rehabilitation treatment process of orthopedics patients after operation, including physical therapy, pain management, muscle function recovery and the like, doctors and patients are helped to track the rehabilitation process better through corresponding rehabilitation monitoring on the patients, and the rehabilitation treatment scheme is adjusted. After a patient performs an orthopedic operation, due to the influence of factors such as operation wound (inflammation, swelling and pain), intra-articular structure change (such as proprioceptive change after ligament reconstruction), joint effusion and the like, the brain 'perceives' to be unstable or damaged to the joint, actively weakens muscle contraction to 'protect' the joint body, and accordingly reflectively inhibits nerve driving signals of muscles (such as quadriceps femoris) crossing the joint, and causes linkage signals of the muscles after operation to show disorder. The traditional rehabilitation monitoring means are also used for carrying out query type assessment on daily rehabilitation training, athletic performance and daily activities of patients, and most of the daily nurses or doctors are regular nurses and doctors, and lack of specific systematic quantitative analysis, so that the postoperative training and recovery performance condition of the patients cannot be fully mastered, and the rehabilitation monitoring means play a vital role in the rehabilitation process, but often cannot be fully considered and assessed. Therefore, detail changes, recovery trends, potential recovery problems and excessive training phenomena in the recovery process cannot be found in time, so that recovery monitoring analysis is not accurate enough. Disclosure of Invention In order to solve the technical problem that recovery abnormality can not be found in time in the related art, so that recovery monitoring analysis is not accurate enough, the invention provides an artificial intelligence-based postoperative recovery auxiliary monitoring system for orthopedic surgery, which adopts the following technical scheme: The invention provides an artificial intelligence-based postoperative rehabilitation auxiliary monitoring system for orthopedic surgery, which comprises: The acquisition module is used for acquiring electric signals driven by leg muscle group nerves of the normal side leg and the abnormal side leg under different training, and determining the activation time and activation intensity of the leg muscles at each position on each side from the electric signals; the performance analysis module is used for carrying out delay analysis according to the activation time of the electric signals of the leg muscles at two sides, determining a time deviation coefficient, determining an intensity deviation coefficient according to the activation intensity difference of the electric signals of the leg muscles at two sides, and determining the initial abnormal performance of the abnormal leg by combining the time deviation coefficient and the intensity deviation coefficient; The compensation analysis module is used for determining other adjacent muscles of each muscle at the activation time as analysis muscles according to the activation time of different muscles of the abnormal side leg, carrying out compensation analysis by combining the analysis muscle function abnormal expression degree to determine abnormal compensation confusion degree, and determining an abnormal analysis index of each muscle by combining the initial abnormal expression degree and the abnormal compensation confusion degree; the monitoring module is used for determining a functional performance change curve according to the time sequence distribution of the abnormal analysis indexes of each muscle trained at different times, and carrying out artificial intelligent rehabilitation auxiliary monitoring according to the functional change curves of all the muscles. Further, the step of performing delay analysis according to the activation time of the electric signals of the leg muscles at two sides to determine a time deviation coefficient comprises the following steps: determining the time interval between