CN117854711A - Pelvic floor muscle function triage method based on pelvic floor muscle strength triage model - Google Patents
Pelvic floor muscle function triage method based on pelvic floor muscle strength triage model Download PDFInfo
- Publication number
- CN117854711A CN117854711A CN202410071743.1A CN202410071743A CN117854711A CN 117854711 A CN117854711 A CN 117854711A CN 202410071743 A CN202410071743 A CN 202410071743A CN 117854711 A CN117854711 A CN 117854711A
- Authority
- CN
- China
- Prior art keywords
- pelvic floor
- floor muscle
- triage
- model
- muscle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 210000003903 pelvic floor Anatomy 0.000 title claims abstract description 204
- 210000003205 muscle Anatomy 0.000 title claims abstract description 201
- 238000000034 method Methods 0.000 title claims abstract description 38
- 230000004220 muscle function Effects 0.000 title claims abstract description 22
- 238000003745 diagnosis Methods 0.000 claims abstract description 28
- 230000003449 preventive effect Effects 0.000 claims abstract description 6
- 230000000007 visual effect Effects 0.000 claims abstract description 5
- 208000029549 Muscle injury Diseases 0.000 claims abstract description 3
- 238000012549 training Methods 0.000 claims description 26
- 210000003489 abdominal muscle Anatomy 0.000 claims description 19
- 230000000284 resting effect Effects 0.000 claims description 17
- 238000012360 testing method Methods 0.000 claims description 17
- 230000008602 contraction Effects 0.000 claims description 13
- 238000012795 verification Methods 0.000 claims description 8
- 238000011156 evaluation Methods 0.000 claims description 7
- 238000005457 optimization Methods 0.000 claims description 7
- 238000011119 multifactor regression analysis Methods 0.000 claims description 6
- 230000036977 tonic contraction Effects 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 4
- 238000003759 clinical diagnosis Methods 0.000 claims description 3
- 238000013135 deep learning Methods 0.000 claims description 3
- 238000013210 evaluation model Methods 0.000 claims description 3
- 230000001771 impaired effect Effects 0.000 claims description 3
- 230000035945 sensitivity Effects 0.000 claims description 3
- 208000001490 Dengue Diseases 0.000 claims 1
- 206010012310 Dengue fever Diseases 0.000 claims 1
- 208000025729 dengue disease Diseases 0.000 claims 1
- 230000003183 myoelectrical effect Effects 0.000 description 25
- 230000035935 pregnancy Effects 0.000 description 7
- 238000002567 electromyography Methods 0.000 description 6
- 238000001514 detection method Methods 0.000 description 5
- 230000004118 muscle contraction Effects 0.000 description 5
- 230000003274 myotonic effect Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 210000001087 myotubule Anatomy 0.000 description 3
- 230000000638 stimulation Effects 0.000 description 3
- 238000011282 treatment Methods 0.000 description 3
- 230000003187 abdominal effect Effects 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 2
- 230000004064 dysfunction Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000002560 therapeutic procedure Methods 0.000 description 2
- 208000034423 Delivery Diseases 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000037396 body weight Effects 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000013211 curve analysis Methods 0.000 description 1
- 230000013872 defecation Effects 0.000 description 1
- 230000006735 deficit Effects 0.000 description 1
- 238000002001 electrophysiology Methods 0.000 description 1
- 230000007831 electrophysiology Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000011337 individualized treatment Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 210000002414 leg Anatomy 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000027939 micturition Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000037191 muscle physiology Effects 0.000 description 1
- 230000036640 muscle relaxation Effects 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 230000001766 physiological effect Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 210000000664 rectum Anatomy 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000001568 sexual effect Effects 0.000 description 1
- 230000002459 sustained effect Effects 0.000 description 1
- 210000003371 toe Anatomy 0.000 description 1
- 238000011269 treatment regimen Methods 0.000 description 1
- 210000000689 upper leg Anatomy 0.000 description 1
- 210000003932 urinary bladder Anatomy 0.000 description 1
- 210000004291 uterus Anatomy 0.000 description 1
- 210000001215 vagina Anatomy 0.000 description 1
- 230000009677 vaginal delivery Effects 0.000 description 1
Landscapes
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention relates to the technical field of pelvic floor muscle diagnosis, in particular to a pelvic floor muscle function diagnosis method based on a pelvic floor muscle force diagnosis model. According to the pelvic floor muscle function triage method based on the pelvic floor muscle force triage model, clinical data of pelvic floor muscle groups are obtained; finding out corresponding scores in a visualized nomogram according to the pelvic floor muscle clinical data, and calculating total scores; finding out a corresponding pelvic floor muscle strength risk value in a visualized nomogram according to the total score; and evaluating the damage information of the pelvic floor muscle according to the risk value, thereby realizing visual diagnosis of the pelvic floor muscle, facilitating a clinician to visually evaluate the risk of the pelvic floor muscle damage more accurately, and further formulating an individualized preventive intervention scheme.
Description
Technical Field
The invention relates to the technical field of pelvic floor muscle diagnosis, in particular to a pelvic floor muscle function diagnosis method based on a pelvic floor muscle force diagnosis model.
Background
Pelvic floor muscles are pelvic floor muscle groups, which mainly maintain normal positions of pelvic organs such as uterus, bladder, rectum and the like, participate in urination and defecation, and maintain physiological activities such as vaginal tightness, sexual pleasure and the like. Research shows that more than 45% of married women and women who are bred have pelvic floor dysfunction in China. Pelvic floor muscle training is the first line treatment regimen for treating female pelvic floor dysfunction. However, the problem of pelvic floor muscles of each female is different, the initial muscle contraction ability and learning ability are different, some of the group I muscle fibers are poor in contraction ability, some of the group II muscle fibers are poor in contraction ability, and some of the group II muscle fibers are even indistinguishable from pelvic floor muscle contraction. The difference of initial pelvic floor muscle contraction capability leads to the difference of pelvic floor muscle training learning capability, and directly influences the clinical curative effect of female pelvic floor muscle training. Therefore, pelvic floor muscle rehabilitation cannot unify treatment standards and fixed training modes, and an individualized training mode and scheme must be formulated by timely adjusting the self condition of each puerpera and the effect in the rehabilitation process according to the individualized treatment principle. However, the existing pelvic floor muscle function assessment technology cannot provide enough data support for personalized training.
In the prior art, the testing of pelvic floor muscles is often evaluated using information from electromyographic signals. Electromyography (EMG) detection is a simple, noninvasive and easily accepted Electromyography detection activity by a subject, can be used for testing Electromyography signals in a large range of human bodies, including abdominal Electromyography signals, pelvic floor Electromyography signals and the like, and is helpful for reflecting changes in aspects of muscle physiology, biochemistry and the like in the exercise process.
However, the existing method for detecting pelvic floor muscles by adopting EMG mainly reflects the nerve-muscle electrophysiological function of the pelvic floor muscles, can not accurately judge the condition of pelvic floor muscle force, and the interpretation of the data is highly dependent on the professional level and clinical experience of doctors, so that the method is time-consuming.
Disclosure of Invention
The invention aims to at least solve one of the technical problems in the prior art and provides a pelvic floor muscle function diagnosis method based on a pelvic floor muscle force diagnosis model.
In order to achieve the above purpose, the technical scheme adopted by the invention is as follows: the pelvic floor muscle function triage method based on the pelvic floor muscle strength triage model comprises the following steps:
acquiring clinical data of pelvic floor muscles;
finding out corresponding scores in a visualized nomogram according to the pelvic floor muscle clinical data, and calculating total scores;
finding out a corresponding pelvic floor muscle strength risk value in a visualized nomogram according to the total score;
and evaluating the damage information of the pelvic floor muscle force according to the risk value.
Further, the method also comprises the steps of constructing a pelvic floor muscle strength triage model, and establishing a visual nomogram according to the pelvic floor muscle strength triage model.
Further, the construction of the model for sub-diagnosis of pelvic floor muscle strength comprises
Constructing a pelvic floor muscle force triage model I by utilizing multi-factor regression analysis, and evaluating through training, testing and in-group/out-group verification to obtain a relatively better model I;
and designing a pelvic floor muscle strength triage evaluation model II based on the computer integrated learning algorithm and the deep learning algorithm respectively, and obtaining a relatively better model II through training, testing and in-group/out-group check sum comparison evaluation.
Further, the method also comprises optimizing the model of the pelvic floor muscle force triage, and the optimization of the model of the pelvic floor muscle force triage comprises the following steps of
Establishing a pelvic floor muscle force central database and a local database;
respectively deploying pelvic floor muscle force triage models in the central database and the local database;
pre-training the pelvic floor muscle strength triage model by using initial data;
and (3) carrying out comprehensive training optimization on the pre-trained pelvic floor muscle strength triage model based on the federal learning architecture.
Further, optimizing the pelvic floor muscle force triage model further comprises performing staged evaluation verification on the pre-trained pelvic floor muscle force triage model based on the federal learning architecture.
Further, the optimization of the pelvic floor muscle force triage model further comprises a system for developing the pelvic floor muscle force triage model, wherein the system comprises one or more of an applet, an APP and a remote cloud system.
Further, the method also comprises the step of verifying the pelvic floor muscle strength triage model, wherein the step of verifying the pelvic floor muscle strength triage model comprises the step of calculating the pelvic floor muscle strength triage model through a clinical diagnosis test to judge muscle strength diagnosis.
Further, the determination of the muscle force diagnosis includes one or more of specificity, sensitivity, negative predictive value, positive accuracy, about log index.
Further, the pelvic floor muscle clinical data includes one or more of a pelvic floor muscle pre-resting average muscle potential, a pelvic floor muscle tonic contraction average muscle potential, a pelvic floor muscle post-resting average muscle potential, a abdominal muscle rapid contraction maximum average muscle potential, and an abdominal muscle tonic contraction average muscle potential.
Further, the method also comprises the step of formulating an individualized preventive intervention scheme according to the damaged information of the pelvic floor muscle force.
The invention has the beneficial effects that: as can be seen from the above description of the present invention, compared with the prior art, the pelvic floor muscle function diagnosis method based on the pelvic floor muscle force diagnosis model of the present invention obtains the clinical data of the pelvic floor muscle; finding out corresponding scores in a visualized nomogram according to the pelvic floor muscle clinical data, and calculating total scores; finding out a corresponding pelvic floor muscle strength risk value in a visualized nomogram according to the total score; and evaluating the damage information of the pelvic floor muscle according to the risk value, thereby realizing visual diagnosis of the pelvic floor muscle, facilitating a clinician to visually evaluate the risk of the pelvic floor muscle damage more accurately, and further formulating an individualized preventive intervention scheme.
Drawings
FIG. 1 is an alignment chart of a model of pelvic floor muscle force triage in a preferred embodiment of the invention;
FIG. 2 is a graph of calibration in accordance with a preferred embodiment of the present invention;
FIG. 3 is a graph illustrating decision graphs in a preferred embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the invention.
In the description of the present invention, it should be noted that, unless explicitly specified and limited otherwise, the terms "connected," "connected," and "connected" are to be construed broadly, and may be either fixedly connected, detachably connected, or integrally connected, for example; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
As shown in fig. 1, the pelvic floor muscle function triage method based on the pelvic floor muscle force triage model according to the preferred embodiment of the present invention comprises the following steps:
s1, acquiring clinical data of pelvic floor muscles;
the pelvic floor muscle clinical data comprise pelvic floor muscle anterior resting average muscle potential, pelvic floor muscle tonic contraction average muscle potential, pelvic floor muscle posterior resting average muscle potential, abdominal muscle rapid contraction maximum average muscle potential, abdominal muscle tonic contraction average muscle potential and the like;
s2, finding out corresponding scores in a visualized nomogram according to the pelvic floor muscle clinical data, and calculating total scores;
s3, finding out a corresponding pelvic floor muscle strength risk value in the visualized nomogram according to the total score;
s4, evaluating damage information of the pelvic floor muscle force according to the risk value;
and S5, formulating an individualized preventive intervention scheme according to the damaged information of the pelvic floor muscle force.
The method specifically comprises the following steps: and respectively finding out corresponding scores of the acquired data in the alignment chart, then calculating total scores, and finding out corresponding risk values according to the total scores, wherein the corresponding pelvic floor muscle force is damaged to be normal from 0.1 to 0.9.
Such as: assuming that the birth weight of a newborn is 3000g for a lying-in woman in 32 years, the obtained measurement values of the myoelectric potential of the pelvic floor surface are respectively: resting mean myoelectric potential before pelvic floor muscle 4 μv; (2) the average myoelectric potential of the myotonic contraction of the pelvic floor is 20 mu v; (3) resting mean myoelectric potential 3 μv after pelvic floor muscles; (4) the maximum average myoelectric potential of rapid contraction of abdominal muscles is 4 mu v; (5) the average myoelectric potential of the abdominal myotonic contraction is 10 mu v. The sum of the corresponding scores in the nomograms was 25+24+19+5+26=81, the corresponding pelvic floor muscle force group was 30%, and the pelvic floor muscle was considered to be impaired, suggesting receiving pelvic floor muscle-assisted magneto-electric stimulation therapy and biofeedback therapy.
Thus, according to the nomograms of the present invention, a clinician can conveniently, visually and more accurately assess the risk of pelvic floor muscle impairment to formulate an individualized preventive intervention regimen.
As a preferred embodiment of the invention, it may also have the following additional technical features: and S201, constructing a pelvic floor muscle strength triage model, and building a visual alignment chart according to the pelvic floor muscle strength triage model.
The construction of the model for sub-diagnosis of pelvic floor muscle strength comprises
Constructing a pelvic floor muscle force triage model I by utilizing multi-factor regression analysis, and evaluating through training, testing and in-group/out-group verification to obtain a relatively better model I;
and designing a pelvic floor muscle strength triage evaluation model II based on the computer integrated learning algorithm and the deep learning algorithm respectively, and obtaining a relatively better model II through training, testing and in-group/out-group check sum comparison evaluation.
In this embodiment, the method further includes S202, optimizing a model of sub-pelvic floor muscle strength, where the optimizing of the model of sub-pelvic floor muscle strength includes
Establishing a pelvic floor muscle force central database and a local database;
namely, a central database of pelvic floor muscle function triage is established, and local pelvic floor muscle data are respectively established by depending on a plurality of clinical centers;
respectively deploying pelvic floor muscle force triage models in the central database and the local database;
pre-training the pelvic floor muscle strength triage model by using initial data;
based on a federal learning architecture, comprehensively training and optimizing the pre-trained pelvic floor muscle force triage model, performing staged evaluation and verification on the pre-trained pelvic floor muscle force triage model, and developing a system of the pelvic floor muscle force triage model, wherein the system comprises one or more of an applet, an APP and a remote cloud system, so that the pelvic floor muscle force triage model is more perfect and accurate.
Namely, a central database of pelvic floor muscle function triage is established, and a local pelvic floor muscle database is respectively established by depending on a plurality of clinical centers; respectively deploying the plurality of pelvic floor muscle force triage models in a central database and a distributed clinical center; pre-training the diagnosis model by using initial data, and performing training optimization and staged evaluation verification on the global model by using a federal learning architecture. Finally, the optimal model is obtained, and an application system (comprising an applet, an APP and a remote cloud system) is developed
In this embodiment, the method further includes S203, verifying a pelvic floor muscle force diagnosis model, where verification of the pelvic floor muscle force diagnosis model includes calculating a determination of a muscle force diagnosis of the pelvic floor muscle force diagnosis model through a clinical diagnosis test, and the determination of the muscle force diagnosis includes specificity, sensitivity, negative predictive value, positive accuracy, about log index, and the like.
The following is a description of the construction of a model of pelvic floor muscle strength triage using multi-factor regression analysis. The method comprises the following steps:
a. acquiring clinical data of pelvic floor muscles;
namely, collecting 1722 clinical data of puerpera through single-birth delivery, including information such as pelvic floor muscle surface myoelectric potential value, pelvic floor muscle strength grading, pregnancy, birth times, delivery mode, body mass index (weight/height), neonate weight and the like;
wherein, obtain pelvic floor muscle strength grading: according to the improved oxford muscle strength grading system method, basin bottom muscle strength grading is judged by 1 basin bottom specialist with high annual resources (clinical specialist time >15 years) through vaginal fingering. Muscle strength is classified into 0-5 grades: grade 0, no shrinkage; grade 1, slightly jerky; grade 2, weak shrinkage, no counter force; grade 3, moderate shrinkage, slightly countered; grade 4, good shrinkage, resistance; grade 5, strong shrinkage and strong counter force.
Labeling the pelvic floor muscle strength result: the definition is that when the muscle strength grading of the pelvic floor muscles is more than or equal to 3 grades (3-5 grades) is a normal group of the pelvic floor muscle, and when the muscle strength grading of the pelvic floor muscles is less than or equal to 2 grades (0-2 grades) is a damaged group of the pelvic floor muscle. The pelvic floor muscle strength impaired group can not independently complete normal pelvic floor muscle contraction, clinically needs auxiliary treatment such as magnetic stimulation, electric stimulation, biofeedback and the like to strengthen the muscle strength, and the pelvic floor muscle strength normal group can directly train the pelvic floor muscle without clinical auxiliary treatment.
Obtaining a pelvic floor myoelectric potential value:
the pelvic floor muscle electrophysiology detection was performed using an MDLB2 multichannel pelvic floor muscle bioelectricity meter (Nanjing Mailan Co.). The patient adopts the supine position, the legs naturally straighten the toes to abduct, and the whole body is relaxed. A disposable vaginal electrode (MLD V1, nanjing Mailan medical science and technology Co., ltd.) was placed in the vagina of a patient, and simultaneously, a body surface electrode was attached to the abdominal muscle, and pelvic floor surface myoelectric signals and abdominal muscle participation were detected by using a pelvic floor surface myoelectric analysis system (MLD A2, nanjing Mailan medical science and technology Co., ltd.). During detection, the patient performs a series of pelvic floor muscle contraction and relaxation actions according to the voice prompt. During the contraction, the gluteus muscles, abdominal muscles and thigh adductor muscles should be relaxed as much as possible. The detection parameters include: (1) a pre-resting stage muscle level average; (2) Myoelectricity maximum, rise time and recovery time during the rapid contraction phase; (3) mean and variability of muscle level during the sustained contraction phase; (4) Muscle level mean value, variability and rear-front 10s ratio in endurance test stage; (5) mean and variability of muscle level at post-resting stage.
The data collected (in μv each) included: (1) resting average myopotential before pelvic floor muscles; (2) the pelvic floor muscle rapidly contracts to a maximum average myoelectric potential; (3) the pelvic floor muscle continuously contracts the average myoelectric potential; (4) pelvic floor muscle endurance contraction average myoelectric potential; (5) resting the average myopotential after pelvic floor muscles; (6) resting mean myopotential before abdominal muscle; (7) the abdominal muscles rapidly contract the maximum average myoelectric potential; (8) myotonic contractile average myoelectric potential of abdominal muscle; (9) abdominal muscle endurance contracts the average myoelectric potential; and the average myoelectric potential is rested after the abdominal muscles.
Pregnancy times: total number of pregnancies;
yield of: total production times of gestational age not less than 28 weeks;
delivery mode: vaginal delivery, caesarean delivery and obstetric forceps delivery assisting;
body mass index (BMI Body mass index) =body weight/height. The data collected included pre-pregnancy BMI, gestational growth BMI (= (weight at production-weight pre-pregnancy)/height), post-partum BMI;
neonatal weight: for example, the maximum weight value of the neonate is selected for the parturient. For example, a birth weight of 33 years old 2 children is 3200g and 3800g, respectively, and a birth weight of 3800g is taken from newborn.
b. Randomly dividing the acquired pelvic floor muscle clinical data into a Train training set and a Test set;
namely, classifying pelvic floor muscle strength as a dependent variable, taking a pelvic floor muscle potential value as an independent variable, and randomly dividing the pelvic floor muscle potential value (1722 cases) into a Train training set (1209 cases) and a Test set (513 cases) according to the ratio of 7:3 by adopting R language;
c. variable screening is carried out based on the Train training set and the lasso regression model, and influence factors related to the pelvic floor muscle strength damaged group are obtained;
variables that entered the lasso regression model include release (labor), age, BMIa (pre-pregnancy BMI), BMIb (time-of-birth BMI), BMIc (post-birth BMI), G (pregnancy), P (time-of-birth), iinfantwtmax (primary greater weight), beforeavg (pre-resting potential average), fastmax (fast-myopotential maximum), slow (slow-myopotential average), afteravg (post-resting potential average), beforavgpp (pre-resting potential average), fastmaxpp (fast-myopotential average), slofaavgpp (slow-myopotential average), afteravgpp (post-resting potential average), and 16 variables that may be related to pelvic floor muscle strength. Obtaining 5 influencing factors (see table 1) related to the pelvic floor muscle strength damaged group through multi-factor regression analysis, wherein the influencing factors are respectively (1) the resting average muscle potential before pelvic floor muscles; (2) the pelvic floor myotonic contracts the average myoelectric potential; (3) resting the average myopotential after pelvic floor muscles; (4) the abdominal muscles rapidly contract the maximum average myoelectric potential; (5) the abdominal muscles contract straight to average myoelectric potential.
And selecting an appropriate lambda value based on the Train training set and modeling, and calculating C-index (see Table 1);
table 1 multifactor regression analysis in training set
d. And establishing a pelvic floor muscle force triage model based on the pelvic floor muscle potential according to the influence factors.
Namely, according to the average resting myoelectric potential before pelvic floor muscles, the average resting myoelectric potential after pelvic floor muscles, the maximum average myoelectric potential after rapid contraction of abdominal muscles and the average myoelectric potential after abdominal muscles, a pelvic floor muscle force triage prediction model based on the pelvic floor myoelectric potential is established, and the model is visualized and toolized, such as an alignment chart of the pelvic floor muscle force triage model is established, as shown in figure 1.
e. And (3) verifying by using a Test set, and drawing one or more of an ROC curve, a correction curve and a decision curve DCA.
Randomly sampling the training set by adopting a bootstrap method, repeating 3000 times, performing 10-fold cross validation, wherein C-index (namely AUC) is 0.761, and displaying a model with medium accuracy;
(2) In the test set, the modeling C-index is 0.813 as well, and the display model has strong accuracy in the test set; simultaneously, a correction curve and a decision curve (decision curve analysis, DCA) are drawn to obtain the graphs of FIGS. 2-3.
The above additional technical features can be freely combined and superimposed by a person skilled in the art without conflict.
It will be understood that the invention has been described in terms of several embodiments, and that various changes and equivalents may be made to these features and embodiments by those skilled in the art without departing from the spirit and scope of the invention. In addition, many modifications may be made to adapt a particular situation or material to the teachings of the invention without departing from the essential scope thereof. Therefore, it is intended that the invention not be limited to the particular embodiment disclosed, but that the invention will include all embodiments falling within the scope of the appended claims.
Claims (10)
1. The pelvic floor muscle function triage method based on the pelvic floor muscle force triage model is characterized by comprising the following steps of:
acquiring clinical data of pelvic floor muscles;
finding out corresponding scores in a visualized nomogram according to the pelvic floor muscle clinical data, and calculating total scores;
finding out a corresponding pelvic floor muscle strength risk value in a visualized nomogram according to the total score;
and evaluating the information of the pelvic floor muscle damage according to the risk value.
2. The pelvic floor muscle function triage method based on the pelvic floor muscle force triage model according to claim 1, characterized by comprising the following steps: the method also comprises the steps of constructing a pelvic floor muscle strength triage model, and establishing a visual nomogram according to the pelvic floor muscle strength triage model.
3. The pelvic floor muscle function triage method based on the pelvic floor muscle force triage model according to claim 2, characterized by comprising the following steps: the construction of the pelvic floor muscle force diagnosis model comprises the following steps of
Constructing a pelvic floor muscle force triage model I by utilizing multi-factor regression analysis, and evaluating through training, testing and in-group/out-group verification to obtain a relatively better model I;
and designing pelvic floor muscle strength triage evaluation models II and III based on computer integrated learning and deep learning algorithms respectively, and obtaining relatively better models II and III through training, testing and in-group/out-group check sum comparison evaluation.
4. The pelvic floor muscle function triage method based on the pelvic floor muscle force triage model according to claim 1, characterized by comprising the following steps: the method also comprises the step of optimizing the pelvic floor muscle force triage model, wherein the step of optimizing the pelvic floor muscle force triage model comprises the following steps of
Establishing a pelvic floor muscle force central database and a local database;
respectively deploying pelvic floor muscle force triage models in the central database and the local database;
pre-training the pelvic floor muscle strength triage model by using initial data;
and (3) carrying out comprehensive training optimization on the pre-trained pelvic floor muscle strength triage model based on the federal learning architecture.
5. The pelvic floor muscle function triage method based on the pelvic floor muscle force triage model according to claim 4, wherein the method comprises the following steps of: the optimization of the pelvic floor muscle strength triage model further comprises the step of carrying out step evaluation verification on the pre-trained pelvic floor muscle strength triage model based on the federal learning architecture.
6. The pelvic floor muscle function triage method based on the pelvic floor muscle force triage model according to claim 4, wherein the method comprises the following steps of: the optimization of the pelvic floor muscle force triage model further comprises a system for developing the pelvic floor muscle force triage model, wherein the system comprises one or more of an applet, an APP and a remote cloud system.
7. The pelvic floor muscle function triage method based on the pelvic floor muscle force triage model according to claim 1, characterized by comprising the following steps: the method further comprises the step of verifying the pelvic floor muscle strength sub-diagnosis model, wherein the step of verifying the pelvic floor muscle strength sub-diagnosis model comprises the step of calculating the pelvic floor muscle strength sub-diagnosis model through a clinical diagnosis test to judge muscle strength diagnosis.
8. The pelvic floor muscle function triage method based on the pelvic floor muscle force triage model according to claim 7, characterized by comprising the following steps: the determination of the muscle strength diagnosis comprises one or more of specificity, sensitivity, negative predictive value, positive accuracy and about dengue index.
9. The pelvic floor muscle function triage method based on the pelvic floor muscle force triage model according to claim 1, characterized by comprising the following steps: the pelvic floor muscle clinical data comprises one or more of pelvic floor muscle anterior resting average muscle potential, pelvic floor muscle tonic contraction average muscle potential, pelvic floor muscle posterior resting average muscle potential, abdominal muscle rapid contraction maximum average muscle potential and abdominal muscle tonic contraction average muscle potential.
10. The pelvic floor muscle function triage method based on the pelvic floor muscle force triage model according to claim 1, characterized by comprising the following steps: also included is formulating a personalized preventive intervention regimen based on the impaired information of pelvic floor muscle force.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2023103024789 | 2023-03-27 | ||
| CN202310302478 | 2023-03-27 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117854711A true CN117854711A (en) | 2024-04-09 |
Family
ID=90530326
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410071743.1A Pending CN117854711A (en) | 2023-03-27 | 2024-01-18 | Pelvic floor muscle function triage method based on pelvic floor muscle strength triage model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117854711A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118121217A (en) * | 2024-05-08 | 2024-06-04 | 吉林大学 | Pelvic floor rehabilitation exercise assisting system and method based on artificial intelligence |
-
2024
- 2024-01-18 CN CN202410071743.1A patent/CN117854711A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118121217A (en) * | 2024-05-08 | 2024-06-04 | 吉林大学 | Pelvic floor rehabilitation exercise assisting system and method based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Woodley et al. | Pelvic floor muscle training for preventing and treating urinary and faecal incontinence in antenatal and postnatal women | |
| Hundley et al. | A comparison of perineometer to brink score for assessment of pelvic floor muscle strength | |
| Laycock et al. | Pelvic floor muscle assessment: the PERFECT scheme | |
| Resende et al. | Electromyographic evaluation of pelvic floor muscles in pregnant and nonpregnant women | |
| CN117854711A (en) | Pelvic floor muscle function triage method based on pelvic floor muscle strength triage model | |
| Koc et al. | Is cesarean section a real panacea to prevent pelvic organ disorders? | |
| CN117481670A (en) | Evaluation and training rehabilitation system based on pelvic floor myoelectricity | |
| Saltiel et al. | Terminology of pelvic floor muscle function in women with and without urinary incontinence: a systematic review | |
| Sillevis et al. | The management of plantar fasciitis with a musculoskeletal ultrasound imaging guided approach for instrument assisted soft tissue mobilization in a runner: a case report | |
| Thibault-Gagnon et al. | The temporal relationship between activity of the pelvic floor muscles and motion of selected urogenital landmarks in healthy nulliparous women | |
| Kadah et al. | Is there a difference in pelvic floor muscle tone between women with and without pelvic pain? A systematic review and meta-analysis | |
| Cryns et al. | Are there differences in abdominal muscle function in female singers with and without Voice disorders?-an observational study | |
| Soltandoost Nari et al. | Relationships between functional movement screen and pain, dynamic balance, and trunk muscle endurance in military personnel with non-specific chronic low back pain | |
| WO2024113521A1 (en) | Multi-modal data fusion method and device for pelvic floor function overall evaluation | |
| Bishop et al. | Effects of age, parity, and adherence on pelvic muscle response to exercise | |
| CN215305419U (en) | Basin bottom health management system based on intelligent closestool and intelligent closestool | |
| Bø | Overview of physical therapy for pelvic floor dysfunction | |
| Hong et al. | Artificial intelligence image–assisted knee ligament trauma repair efficacy analysis and postoperative femoral nerve block Analgesia effect research | |
| CN113425301A (en) | Closestool-based basin bottom health management system and management method and intelligent closestool | |
| Çalikoglu et al. | Pulmonary muscle strength, pulmonary function tests, and dyspnea in women with major depression | |
| Conlon | The relationship between the Functional Movement Screen™ and countermovement jump height | |
| Martínez Bustelo | Effect of perineal and abdominal exercises in the vesical displacement in postpartum women | |
| CN201955787U (en) | Subhealth status comprehensive evaluation tester | |
| Deshmukh et al. | Perineometer-An equipment used for measuring the strength of voluntary contractions of pelvic floor muscles-A Review | |
| RU2294140C2 (en) | Method for detecting psychological state |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |