CN117133402A - Method, device, equipment and readable storage medium for dynamically supervising patient rehabilitation - Google Patents
Method, device, equipment and readable storage medium for dynamically supervising patient rehabilitation Download PDFInfo
- Publication number
- CN117133402A CN117133402A CN202311112780.4A CN202311112780A CN117133402A CN 117133402 A CN117133402 A CN 117133402A CN 202311112780 A CN202311112780 A CN 202311112780A CN 117133402 A CN117133402 A CN 117133402A
- Authority
- CN
- China
- Prior art keywords
- rehabilitation
- patient
- sample
- terminal
- data
- 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
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000004458 analytical method Methods 0.000 claims abstract description 18
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 18
- 230000002980 postoperative effect Effects 0.000 claims abstract description 17
- 238000010801 machine learning Methods 0.000 claims abstract description 16
- 230000001105 regulatory effect Effects 0.000 claims abstract description 14
- 238000012790 confirmation Methods 0.000 claims abstract description 11
- 238000012549 training Methods 0.000 claims description 42
- 210000003205 muscle Anatomy 0.000 claims description 28
- 230000004927 fusion Effects 0.000 claims description 26
- 238000011084 recovery Methods 0.000 claims description 25
- 239000013598 vector Substances 0.000 claims description 24
- 238000004590 computer program Methods 0.000 claims description 23
- 238000011156 evaluation Methods 0.000 claims description 21
- 238000001356 surgical procedure Methods 0.000 claims description 19
- 230000006870 function Effects 0.000 claims description 17
- 230000003183 myoelectrical effect Effects 0.000 claims description 17
- 238000011282 treatment Methods 0.000 claims description 15
- 230000002159 abnormal effect Effects 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 10
- 239000011159 matrix material Substances 0.000 claims description 10
- 238000005457 optimization Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 9
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 5
- 230000037213 diet Effects 0.000 claims description 4
- 235000005911 diet Nutrition 0.000 claims description 4
- 239000003814 drug Substances 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 4
- 230000001276 controlling effect Effects 0.000 claims description 3
- 229940079593 drug Drugs 0.000 claims description 3
- 230000000694 effects Effects 0.000 description 7
- 230000006872 improvement Effects 0.000 description 7
- 238000012544 monitoring process Methods 0.000 description 7
- 230000008859 change Effects 0.000 description 5
- 238000001514 detection method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000002093 peripheral effect Effects 0.000 description 4
- 230000036541 health Effects 0.000 description 3
- 230000004118 muscle contraction Effects 0.000 description 3
- 230000004220 muscle function Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000001815 facial effect Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 208000010428 Muscle Weakness Diseases 0.000 description 1
- 206010028372 Muscular weakness Diseases 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 208000027744 congestion Diseases 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000008921 facial expression Effects 0.000 description 1
- 208000015181 infectious disease Diseases 0.000 description 1
- 230000036640 muscle relaxation Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000009323 psychological health Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000000638 stimulation Effects 0.000 description 1
- 238000011277 treatment modality Methods 0.000 description 1
- 230000029663 wound healing Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/30—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- Physical Education & Sports Medicine (AREA)
- Biophysics (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses a method, a device, equipment and a readable storage medium for dynamically supervising patient rehabilitation, wherein the method comprises the following steps: the body rehabilitation data of different body parts of the patient after the operation are collected and uploaded regularly are analyzed by utilizing an optimized machine learning algorithm, and the type of the rehabilitation degree of the operation of the patient in the current rehabilitation stage is obtained; according to the rehabilitation degree type of the patient, determining a physical quick rehabilitation strategy of the patient in a new rehabilitation stage, and sending the physical quick rehabilitation strategy to a terminal of the primary medical care for adjustment and confirmation; sending the regulated and confirmed physical quick rehabilitation strategy to a terminal of a patient for checking; the rehabilitation questionnaire reply information in the new rehabilitation stage uploaded by the patient terminal is analyzed, and the analysis result is sent to the terminal of the medical care responsibility. The invention can effectively monitor the postoperative rehabilitation condition of the patient and timely give out targeted rehabilitation suggestions.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a method, an apparatus, a device, and a readable storage medium for dynamically supervising patient rehabilitation.
Background
With the continuous development of medical technology, surgery has become a common treatment modality, but the rehabilitation after surgery directly affects the physical and psychological health of patients. Current supervision of patient postoperative rehabilitation relies mainly on subjective feedback from the patient and remote facial diagnosis to assess rehabilitation. However, the existing methods for monitoring the postoperative rehabilitation of patients mainly rely on subjective feedback and simple facial diagnosis of patients to evaluate rehabilitation conditions, so that the actual rehabilitation progress of the patients cannot be intuitively and comprehensively known. This results in difficult planning and adjustment of the rehabilitation, causing uncertainty in the rehabilitation effect; meanwhile, potential rehabilitation problems or complications cannot be found and treated in time; and also often does not provide personalized rehabilitation advice targeted to each patient's unique situation, while a general rehabilitation program cannot meet the specific needs and adaptation of different patients. Therefore, there is a need for a new approach to address these problems based on the drawbacks of the prior art of supervising the post-operative rehabilitation of patients.
Disclosure of Invention
The embodiment of the invention provides a method, a device, equipment and a readable storage medium for dynamically supervising patient rehabilitation, which effectively supervises postoperative rehabilitation conditions of patients and timely gives targeted rehabilitation suggestions to help the patients to recover more effectively and quickly.
An embodiment of the present invention provides a method for dynamically supervising patient rehabilitation, including:
the body rehabilitation data of different body parts of the patient after the operation are collected and uploaded regularly are analyzed by utilizing an optimized machine learning algorithm, and the type of the rehabilitation degree of the operation of the patient in the current rehabilitation stage is obtained; the body part includes a surgical site and includes at least one of: left side part and right side part of operation;
according to the rehabilitation degree type of the patient, determining a physical quick rehabilitation strategy of the patient in a new rehabilitation stage, and sending the physical quick rehabilitation strategy to a terminal of a primary medical care for adjustment and confirmation;
archiving and sending the regulated and confirmed body rapid rehabilitation strategy to a terminal of the patient for checking;
and analyzing the rehabilitation questionnaire reply information uploaded by the terminal of the patient in a new rehabilitation stage to obtain whether the patient carries out rehabilitation treatment according to the medical advice and whether the rehabilitation condition of the patient is abnormal, and sending the analysis result to the terminal of the medical care in charge.
As an improvement of the above solution, the method further includes:
and receiving satisfaction evaluation of the primary medical care uploaded by the terminal of the patient, archiving the satisfaction evaluation and transmitting the satisfaction evaluation to the terminal of the primary medical care.
As an improvement of the above scheme, the method for analyzing the physical rehabilitation data of different body parts of the patient after the surgery, which are collected and uploaded periodically, by using the optimized machine learning algorithm, obtains the type of the rehabilitation degree of the surgery of the patient in the current rehabilitation stage, and includes:
the acquired and uploaded body rehabilitation data of different body parts of the patient after the surgery are subjected to feature extraction; the physical rehabilitation data comprises: pain degree AR, muscle potential MS, and myoelectric frequency PD;
and inputting the extracted features into a trained SVM model for prediction to obtain the type of the rehabilitation degree of the operation of the patient in the current rehabilitation stage.
As an improvement of the above solution, the training process of the SVM model includes:
step a: acquiring sample rehabilitation data of similar operations of n patients and sample labels of the rehabilitation degree types of the similar operations corresponding to the sample rehabilitation data of each patient, and performing feature fusion calculation on the sample rehabilitation data of the patients according to a formula 1 to obtain sample data fusion features; the sample rehabilitation data comprises pain degree samples AR, muscle potential samples MS and myoelectricity frequency samples PD of different body parts of N parts of a patient after operation; 2.ltoreq.N.ltoreq.3, the body part including the surgical site and including at least one of: left side part and right side part of operation;
Z=w1×Σari+w2×Σmsi+w3×Σpdi+b, formula 1; w1, w2 and w3 are weights of corresponding parameters, b is a bias term, ARi represents a pain degree sample of the body part at the ith position of the patient, MSi represents a muscle potential sample of the body part at the ith position of the patient, and PDi represents a myoelectric frequency sample of the body part at the ith position of the patient; sigma represents the summation;
step b: combining each sample data fusion feature and a corresponding sample label in a training sample set to form a feature vector Zk, wherein the feature vector Zk is used as the training sample set, and the training sample set comprises n feature vectors Z1, Z2; for any two samples Zi and Zj, their similarity in feature space is calculated according to equation 2:
the number P (the number Zi, zj) =exp (-g x i Zi-Zj i 2), formula 2; where g is the decay rate parameter;
the similarity calculation result of each pair of samples in the training sample set is formed into a kernel matrix P, and the element P (i, j) of the kernel matrix P represents the similarity of the ith sample and the jth sample, so that feature conversion of sample data fusion features is realized and the feature conversion is mapped into a feature space with higher dimension;
step c: searching an optimal hyperplane in a feature space based on a kernel matrix P, so that the interval between positive and negative samples in the training sample set is maximized;
Step d: initializing Lagrangian multipliers alpha of all samples in the training sample set to be 0, and randomly selecting two multipliers alpha for optimization; in each iteration, selecting two multipliers alpha i and alpha j as multiplier pairs to be optimized according to a maximum step strategy; under the constraint condition of the objective function, fixing the values of other multipliers, and optimizing the selected multiplier pairs alpha i and alpha j so as to update the weights corresponding to the two multipliers; in each iteration, checking whether an optimization condition is met according to a KKT condition (Karush-Kuhn-Tucker), and if so, adjusting the threshold of the model according to the updated multiplier pair; according to a preset termination condition, the termination condition comprises that the maximum iteration number is reached or a certain convergence condition is met, and whether the iteration is terminated is determined; repeating the previous step flow in the step d until the termination condition is met, so as to gradually adjust the weight and the threshold corresponding to the multiplier, continuously optimizing the support vector and the corresponding weight in the SVM model by using the weight and the threshold corresponding to the multiplier, and finding out the optimal parameter combination for minimizing the objective function to obtain the optimal segmentation hyperplane;
wherein, the objective function is: minL (α) =Σα -1/2 Σ (Σα×α×yi×p (Zi, zj)), the constraint is: Σα×yi=0; 0< = α < = C; alpha is Lagrangian multiplier and is the weight value corresponding to each sample; yi refers to the label of the ith training sample and is used for representing the rehabilitation degree category of the ith sample; yj refers to the label of the jth training sample and is used for representing the rehabilitation degree category of the jth sample; yi and yj are 1 or-1, respectively representing two categories; p (Zi, zj) maps two samples Zi and Zj in the input feature space to the high-dimensional feature space and calculates their similarity; zi is the ith training sample in the input feature space and consists of a group of feature vectors; zj is the jth training sample in the input feature space, and also consists of a group of feature vectors; c is a regularization parameter used for controlling the complexity of the model;
Step e: and saving the calculated support vector and weight parameters as a trained SVM model.
As an improvement of the above solution, the feature extraction of the collected and uploaded physical rehabilitation data of different body parts after the surgery of the patient includes:
carrying out feature fusion calculation on the acquired and uploaded body rehabilitation data of different body parts of the patient after the operation according to a formula 3 to obtain data fusion features; the method comprises a pain degree sample AR ', a muscle potential sample MS ' and a myoelectric frequency sample PD ' of different body parts of a patient at N positions after operation; n is more than or equal to 2 and less than or equal to 3;
z '=w1×Σari' +w2×Σmsi '+w3×Σpdi' +b, formula 3; w1, w2 and w3 are weights of corresponding parameters, b is a bias term, ARi ' represents pain degree data of the i-th body part of the patient, MSi ' represents muscle potential data of the i-th body part of the patient, and PDi ' represents myoelectric frequency data of the i-th body part of the patient; Σ represents summation.
As an improvement to the above, said determining a physical rapid rehabilitation strategy for said patient at a new rehabilitation stage based on said type of rehabilitation level of said patient comprises:
Determining a physical quick recovery strategy of the patient in a new recovery stage according to the recovery degree type of the patient and based on a mapping relation between a preset recovery degree type and the physical quick recovery strategy; the physical rapid rehabilitation strategy comprises: rehabilitation measures, the treatment implementation time range of each rehabilitation measure; the rehabilitation measures comprise medicines required by rehabilitation, rehabilitation diet notes and rehabilitation exercise training schemes.
Another embodiment of the present invention correspondingly provides a device for dynamically supervising patient rehabilitation, which is applied to a cloud server, and includes:
the first analysis module is used for analyzing the acquired and uploaded physical rehabilitation data of different body parts of the patient after operation by using an optimized machine learning algorithm to obtain the type of the rehabilitation degree of the operation of the patient in the current rehabilitation stage; the body part includes a surgical site and includes at least one of: left side part and right side part of operation;
the optimization module is used for determining a physical quick rehabilitation strategy of the patient in a new rehabilitation stage according to the rehabilitation degree type of the patient and sending the physical quick rehabilitation strategy to a terminal of primary medical care for adjustment and confirmation;
The sending module is used for archiving the regulated and confirmed body rapid rehabilitation strategy and sending the regulated and confirmed body rapid rehabilitation strategy to the terminal of the patient for viewing;
and the second analysis module is used for analyzing the rehabilitation questionnaire reply information uploaded by the terminal of the patient in a new rehabilitation stage, analyzing whether the patient carries out rehabilitation treatment according to the medical advice or not and whether the rehabilitation condition of the patient is abnormal or not, and sending the analysis result to the terminal of the medical care in charge.
As an improvement of the above solution, the apparatus further comprises:
and the receiving module is used for receiving the satisfaction evaluation of the primary medical care uploaded by the terminal of the patient, archiving the satisfaction evaluation and transmitting the satisfaction evaluation to the terminal of the primary medical care.
Another embodiment of the present invention provides a device for dynamically supervising patient rehabilitation, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the method for dynamically supervising patient rehabilitation according to the above embodiment of the present invention when executing the computer program.
Another embodiment of the present invention provides a storage medium, where the computer readable storage medium includes a stored computer program, where when the computer program runs, the device where the computer readable storage medium is located is controlled to execute the method for dynamically supervising patient rehabilitation according to the embodiment of the present invention.
Compared with the prior art, one of the technical schemes has the following advantages:
the body rehabilitation data of different body parts of the patient after the operation, which are collected and uploaded regularly, are analyzed by utilizing an optimized machine learning algorithm to obtain the type of the rehabilitation degree of the operation of the patient in the current rehabilitation stage, so that the postoperative rehabilitation condition of the patient can be effectively monitored; meanwhile, according to the type of the rehabilitation degree of the patient, the physical rapid rehabilitation strategy of the patient in a new rehabilitation stage is determined and sent to a terminal of the primary medical care for adjustment and confirmation, so that a targeted rehabilitation suggestion is timely given according to the postoperative rehabilitation condition of the patient; archiving the regulated and confirmed body rapid rehabilitation strategy, and sending the regulated and confirmed body rapid rehabilitation strategy to a terminal of a patient for checking, so that the patient can know how to perform rapid rehabilitation treatment in the next stage in time; the rehabilitation questionnaire reply information uploaded by the terminal of the patient in a new rehabilitation stage is analyzed to obtain whether the patient carries out rehabilitation treatment according to the doctor's advice or not and whether the rehabilitation condition of the patient is abnormal or not, and the analysis result is sent to the terminal of the primary medical care, so that the primary medical care can timely know the rehabilitation condition of the patient, and the full-flow tracking of the rehabilitation condition of the patient is realized. Therefore, the application can effectively monitor the postoperative rehabilitation condition of the patient and timely give out targeted rehabilitation advice to help the patient to recover more effectively and quickly.
Drawings
FIG. 1 is a flow chart of a method for dynamically supervising patient rehabilitation according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a device for dynamically supervising patient rehabilitation according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an apparatus for dynamically supervising patient rehabilitation according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, a flow chart of a method for dynamically supervising patient rehabilitation according to an embodiment of the invention is shown. The method for dynamically supervising patient rehabilitation is applied to a cloud server and comprises the following steps of S10 to S13:
s10, analyzing physical rehabilitation data of different body parts of the patient after the surgery, which are acquired and uploaded regularly, by using an optimized machine learning algorithm to obtain the type of the rehabilitation degree of the surgery of the patient in the current rehabilitation stage; the body part includes a surgical site and includes at least one of: left side part and right side part of operation.
The patient can acquire regular physical rehabilitation data to any nearby medical point or community point with relevant physical physiological data detection equipment, regular physical detection is not needed to be performed to a hospital responsible for supervising patient rehabilitation, and the acquired physical rehabilitation data patient can be uploaded to the cloud server through the user terminal. Of course, the patient can purchase the relevant physical physiological data detection equipment at home, and the patient can upload the acquired physical rehabilitation data to the cloud server through the user terminal after the detection is completed. Wherein, when uploading relevant physical rehabilitation data, the operation type can be uploaded simultaneously. In addition, in order to improve the accuracy and comprehensiveness of the physical rehabilitation analysis, physical rehabilitation data acquisition may be performed on the surgical site and some peripheral sites of the surgery. For example, where the patient is undergoing a leg opening procedure, the body part where data is to be acquired may be: physical rehabilitation data of the leg opening surgery site and the peripheral site thereof, which can be used for evaluating rehabilitation.
The cloud server analyzes the physical rehabilitation data of different body parts of the patient after operation by using the optimized machine learning algorithm, so that the type of the rehabilitation degree of the operation of the patient in the current rehabilitation stage can be timely and accurately obtained.
S11, according to the rehabilitation degree type of the patient, determining a physical quick rehabilitation strategy of the patient in a new rehabilitation stage, and sending the physical quick rehabilitation strategy to a terminal of primary medical care for adjustment and confirmation.
Specifically, different physical quick rehabilitation strategies are formulated in advance according to different rehabilitation degree types, and the mapping relation between the two strategies is established in advance and stored. In this way, when the dynamic supervision of patient rehabilitation is performed, the physical rapid rehabilitation strategy of the patient in a new rehabilitation stage can be timely and pertinently determined according to the rehabilitation degree type of the patient and based on the mapping relation between the preset rehabilitation degree type and the physical rapid rehabilitation strategy; the physical rapid rehabilitation strategy comprises: rehabilitation measures, the time range of treatment implementation of each rehabilitation measure (i.e. which rehabilitation measure should be implemented in which time period and the duration of each implementation of the rehabilitation measure in the process); the rehabilitation measures include medicines required for rehabilitation, diet precautions for rehabilitation and rehabilitation exercise training schemes (such as what type of rehabilitation exercise needs to be done). For example, the rehabilitation degree type of the body parts such as legs, hands, heads, feet and the like can be several types such as complete rehabilitation, high rehabilitation, moderate rehabilitation, light rehabilitation and the like. If the rehabilitation is complete, the rehabilitation measures comprise no rehabilitation medicine, no rehabilitation attention diet items and no rehabilitation exercise training scheme.
In addition, in order to make the physical quick recovery strategy more reasonable, the physical quick recovery strategy determined by the system can be sent to the terminal of the medical care of responsibility for adjustment and confirmation.
And S12, archiving the regulated and confirmed body rapid rehabilitation strategy and sending to a terminal of the patient for viewing.
Wherein, through archiving the quick recovery tactics of health, be convenient for follow-up to the recovered whole journey of patient trace back and be convenient for find corresponding main responsibility and medical care to be convenient for can accurately find the problem and carry out accurate follow-up after the problem has occurred.
S13, analyzing the rehabilitation questionnaire reply information in the new rehabilitation stage uploaded by the terminal of the patient, obtaining whether the patient carries out rehabilitation treatment according to the medical advice or not and whether the rehabilitation condition of the patient is abnormal or not through analysis, and sending the analysis result to the terminal of the primary medical care.
The rehabilitation questionnaire can be a terminal which is pushed to a patient by a system at regular time according to the current rehabilitation stage, and can be sent to the patient for archiving by the medical care of responsibility in advance.
According to the method, the physical rehabilitation data of different body parts of the patient after the operation, which are collected and uploaded regularly, are analyzed by utilizing an optimized machine learning algorithm, so that the type of the rehabilitation degree of the operation of the patient in the current rehabilitation stage is obtained, and the postoperative rehabilitation condition of the patient can be effectively monitored; meanwhile, according to the type of the rehabilitation degree of the patient, the physical rapid rehabilitation strategy of the patient in a new rehabilitation stage is determined and sent to a terminal of the primary medical care for adjustment and confirmation, so that a targeted rehabilitation suggestion is timely given according to the postoperative rehabilitation condition of the patient; archiving the regulated and confirmed body rapid rehabilitation strategy, and sending the regulated and confirmed body rapid rehabilitation strategy to a terminal of a patient for checking, so that the patient can know how to perform rapid rehabilitation treatment in the next stage in time; the rehabilitation questionnaire reply information uploaded by the terminal of the patient in a new rehabilitation stage is analyzed to obtain whether the patient carries out rehabilitation treatment according to the doctor's advice or not and whether the rehabilitation condition of the patient is abnormal or not, and the analysis result is sent to the terminal of the primary medical care, so that the primary medical care can timely know the rehabilitation condition of the patient, and the full-flow tracking of the rehabilitation condition of the patient is realized. Therefore, the application can effectively monitor the postoperative rehabilitation condition of the patient and timely give out targeted rehabilitation advice to help the patient to recover more effectively and quickly.
In one embodiment, the method further comprises:
and receiving satisfaction evaluation of the primary medical care uploaded by the terminal of the patient, archiving the satisfaction evaluation and transmitting the satisfaction evaluation to the terminal of the primary medical care.
In this embodiment, the patient can evaluate the satisfaction of the primary care, and the cloud server sends the received satisfaction to the terminal of the primary care for checking, so that the primary care can know the evaluation of the patient on the patient, and if the primary care has a problem, the service working attitude and the service working mode of the patient can be adjusted and optimized in time, so that the user experience of the patient can be improved finally.
In one embodiment, the analyzing, by using the optimized machine learning algorithm, the physical rehabilitation data of different body parts of the patient after the surgery, which are collected and uploaded periodically, to obtain the type of rehabilitation degree of the surgery of the patient in the current rehabilitation stage includes:
the acquired and uploaded body rehabilitation data of different body parts of the patient after the surgery are subjected to feature extraction; the physical rehabilitation data comprises: pain degree AR, muscle potential MS, and myoelectric frequency PD;
and inputting the extracted features into a trained SVM model for prediction to obtain the type of the rehabilitation degree of the operation of the patient in the current rehabilitation stage.
In this example, the following three physical rehabilitation data were selected: pain degree AR, muscle potential MS and myoelectricity frequency PD can reflect the recovered condition of different health positions of patient's postoperative comparatively accurately and comprehensively. Wherein, pain degree AR: refers to the intensity or degree of pain perceived by the patient; pain levels are typically quantified within a standard evaluation, for example using a numerical scale (e.g., scale 0-10) or a facial expression scale (e.g., scale 5) or the like. The pain degree AR is one of important physiological indexes in the rehabilitation process of the patient after the operation, and can reflect the wound healing condition after the operation, the pain management effect and the overall rehabilitation condition of the patient. Muscle potential MS: refers to the change in potential difference between cells in muscle tissue. Muscle potentials can be generated by measuring muscle electrical signals to observe the response and activity state of the muscle under stimulation. It can provide information that is known about muscle contraction and relaxation, thereby assessing the patient's muscle function and rehabilitation progress. Myoelectric frequency PD: refers to the change in frequency of the electrical muscle signal as the muscle contracts. Normally, the myoelectric frequency at the time of muscle contraction is a value within a certain range. By monitoring myoelectric frequency, the intensity and coordination of muscle contraction in the patient's post-operative rehabilitation process can be known. The change in myoelectric frequency can be one of the important indicators for assessing patient rehabilitation progress and muscle function.
Specifically, the effect of patient recovery can be objectively assessed by monitoring the pain level, muscle potential and myoelectric frequency. The change of the parameters can reflect the recovery condition of the operation part, the pain management effect and the improvement degree of the muscle function, and the accurate assessment of the recovery effect is helpful for adjusting the recovery plan, finding problems in time and taking corresponding measures. Also, there may be differences in the need and progress of rehabilitation after surgery due to different patients. Therefore, by monitoring parameters such as pain degree, muscle potential, myoelectricity frequency and the like, a personalized rehabilitation scheme can be formulated according to the characteristics of each patient, and accurate evaluation of the parameters is helpful for determining the rehabilitation target and corresponding rehabilitation measures of the specific patient, so that the rehabilitation effect is improved. In addition, the monitoring of pain degree, muscle potential and myoelectricity frequency can observe the change of the patient in the rehabilitation process in real time; when abnormal conditions occur in these parameters, rehabilitation problems such as infection, congestion, muscle weakness and the like can be quickly found and treated, so that timely intervention can help avoid adverse consequences and promote the patient to recover health more quickly.
In one embodiment, the present application employs an optimized SVM machine learning algorithm in order to accurately analyze the type of patient recovery level of a patient's surgery of a type during the current recovery phase. The training process of the optimized SVM machine learning algorithm comprises the following steps:
Step a: acquiring sample rehabilitation data of similar operations of n patients and sample labels of the rehabilitation degree types of the similar operations corresponding to the sample rehabilitation data of each patient, and performing feature fusion calculation on the sample rehabilitation data of the patients according to a formula 1 to obtain sample data fusion features; the sample rehabilitation data comprises pain degree samples AR, muscle potential samples MS and myoelectricity frequency samples PD of different body parts of N parts of a patient after operation; 2.ltoreq.N.ltoreq.3, the body part including the surgical site and including at least one of: left side part and right side part of operation;
z=w1×Σari+w2×Σmsi+w3×Σpdi+b, formula 1; w1, w2 and w3 are weights of corresponding parameters, b is a bias term, ARi represents a pain degree sample of the body part at the ith position of the patient, MSi represents a muscle potential sample of the body part at the ith position of the patient, and PDi represents a myoelectric frequency sample of the body part at the ith position of the patient; sigma represents the summation;
step b: combining each sample data fusion feature and a corresponding sample label in a training sample set to form a feature vector Zk, wherein the feature vector Zk is used as the training sample set, and the training sample set comprises n feature vectors Z1, Z2; for any two samples Zi and Zj, their similarity in feature space is calculated according to equation 2:
The number P (the number Zi, zj) =exp (-g x i Zi-Zj i 2), formula 2; where g is the decay rate parameter;
the similarity calculation result of each pair of samples in the training sample set is formed into a kernel matrix P, and the element P (i, j) of the kernel matrix P represents the similarity of the ith sample and the jth sample, so that feature conversion of sample data fusion features is realized and the feature conversion is mapped into a feature space with higher dimension, and the classification is performed better;
step c: searching an optimal hyperplane based on a kernel matrix P in a feature space, so that the interval between positive and negative samples in the training sample set is maximized, and the accuracy of sample classification is maintained;
step d: initializing Lagrangian multipliers alpha of all samples in the training sample set to be 0, and randomly selecting two multipliers alpha for optimization; in each iteration, selecting two multipliers alpha i and alpha j as multiplier pairs to be optimized according to a maximum step strategy; under the constraint condition of the objective function, fixing the values of other multipliers, and optimizing the selected multiplier pairs alpha i and alpha j so as to update the weights corresponding to the two multipliers; in each iteration, checking whether an optimization condition is met according to a KKT condition (Karush-Kuhn-Tucker), and if so, adjusting the threshold of the model according to the updated multiplier pair; according to a preset termination condition, the termination condition comprises that the maximum iteration number is reached or a certain convergence condition is met, and whether the iteration is terminated is determined; repeating the previous step flow in the step d until the termination condition is met, so as to gradually adjust the weight and the threshold corresponding to the multiplier, continuously optimizing the support vector and the corresponding weight in the SVM model by using the weight and the threshold corresponding to the multiplier, and finding out the optimal parameter combination for minimizing the objective function to obtain the optimal segmentation hyperplane;
Wherein, the objective function is: minL (α) =Σα -1/2 Σ (Σα×α×yi×p (Zi, zj)), the constraint is: Σα×yi=0; 0< = α < = C; alpha is Lagrangian multiplier and is the weight value corresponding to each sample; yi refers to the label of the ith training sample and is used for representing the rehabilitation degree category of the ith sample; yj refers to the label of the jth training sample and is used for representing the rehabilitation degree category of the jth sample; yi and yj are 1 or-1, respectively representing two categories; p (Zi, zj) maps two samples Zi and Zj in the input feature space to the high-dimensional feature space and calculates their similarity; zi is the ith training sample in the input feature space and consists of a group of feature vectors; zj is the jth training sample in the input feature space, and also consists of a group of feature vectors; c is a regularization parameter used for controlling the complexity of the model;
step e: and saving the calculated support vector and weight parameters as a trained SVM model.
In the embodiment, the sample data fusion characteristics are carried out by adopting an optimized characteristic fusion algorithm, so that the characteristics of the physical rehabilitation data of the operation part or the peripheral part of the operation can be reasonably fused, and the extracted characteristics can more comprehensively reflect the physical rehabilitation condition of the patient after the operation; on the basis, sample classification can be well carried out by forming a feature vector Zk by combining each sample data fusion feature and a corresponding sample label in a training sample set and calculating the similarity of the feature vector Zk in a feature space, and meanwhile, a kernel matrix P is formed by the similarity calculation result of each pair of samples in the training sample set, and feature conversion of the sample data fusion feature is realized and mapped into a feature space with higher dimension, so that classification is better carried out; and the optimal hyperplane is found in the feature space, so that the interval between positive and negative samples in the training sample set is maximized, and the accuracy of sample classification is maintained; finally, through the sample parameter optimization process, proper support vectors and corresponding weights of the SVM model can be selected, so that an optimal segmentation hyperplane is obtained, and finally, the SVM model capable of accurately identifying the rehabilitation degree type according to fusion characteristics of three parameters, namely pain degree, muscle potential and myoelectricity frequency can be trained.
The objective function is obtained by summing the lagrange multipliers α of all training samples, wherein the similarity or distance between two samples is expressed by the product Σ (Σα×α×yi×p (Zi, zj)). By minimizing this objective function, an optimal set of alpha values can be solved to determine the segmentation hyperplane. The constraint Σα=0 represents the sum of the lagrangian multiplier α multiplied by the corresponding label yi to be 0, for ensuring that the classifier satisfies the KKT condition (Karush-Kuhn-tunerconditions). This condition ensures that there is a good relationship between the predicted value on each sample and the real label. 0< = α < = C is a range constraint of the value of the lagrangian multiplier α, ensuring that the value of α is between 0 and C, since α represents a weight value, it is necessary to take the value within positive and negative limits. In addition, the searching mode of searching an optimal hyperplane in the feature space can refer to the existing searching mode of the optimal hyperplane, and the feature is not described in detail herein.
In one embodiment, corresponding to the training process, the feature extraction of the collected and uploaded physical rehabilitation data of the different body parts of the patient after the surgery when the model is applied specifically includes:
Carrying out feature fusion calculation on the acquired and uploaded body rehabilitation data of different body parts of the patient after the operation according to a formula 3 to obtain data fusion features; the method comprises a pain degree sample AR ', a muscle potential sample MS ' and a myoelectric frequency sample PD ' of different body parts of a patient at N positions after operation; n is more than or equal to 2 and less than or equal to 3;
z '=w1×Σari' +w2×Σmsi '+w3×Σpdi' +b, formula 3; w1, w2 and w3 are weights of corresponding parameters, b is a bias term, ARi ' represents pain degree data of the i-th body part of the patient, MSi ' represents muscle potential data of the i-th body part of the patient, and PDi ' represents myoelectric frequency data of the i-th body part of the patient; Σ represents summation.
In the embodiment, the sample data fusion characteristics are carried out by adopting an optimized characteristic fusion algorithm, so that the characteristics of the physical rehabilitation data of the operation part or the peripheral part of the operation can be reasonably fused, and the extracted characteristics can more comprehensively reflect the physical rehabilitation condition of the patient after the operation; on the basis, the optimized SVM model can be utilized to more accurately identify the rehabilitation degree type according to the fusion characteristics of three parameters, namely the pain degree, the muscle potential and the myoelectricity frequency.
Referring to fig. 2, a schematic structural diagram of a device for dynamically supervising patient rehabilitation according to an embodiment of the present invention is provided. The device for dynamically supervising patient rehabilitation comprises:
the first analysis module 10 is configured to analyze the collected and uploaded physical rehabilitation data of different body parts of the patient after the operation by using an optimized machine learning algorithm, so as to obtain the type of rehabilitation degree of the operation of the patient in the current rehabilitation stage; the body part includes a surgical site and includes at least one of: left side part and right side part of operation;
an optimizing module 11, configured to determine a physical rapid rehabilitation strategy of the patient in a new rehabilitation stage according to the rehabilitation degree type of the patient, and send the strategy to a terminal of primary medical care for adjustment and confirmation;
a sending module 12, configured to archive and send the adjusted and confirmed body rapid rehabilitation strategy to a terminal of the patient for checking;
and the second analysis module 13 is used for analyzing the rehabilitation questionnaire reply information in the new rehabilitation stage uploaded by the terminal of the patient, analyzing whether the patient carries out rehabilitation treatment according to the medical order and whether the rehabilitation condition of the patient is abnormal, and sending the analysis result to the terminal of the medical care in responsibility.
In one embodiment, the apparatus further comprises:
and the receiving module is used for receiving the satisfaction evaluation of the primary medical care uploaded by the terminal of the patient, archiving the satisfaction evaluation and transmitting the satisfaction evaluation to the terminal of the primary medical care.
According to the method, the physical rehabilitation data of different body parts of the patient after the operation, which are collected and uploaded regularly, are analyzed by utilizing an optimized machine learning algorithm, so that the type of the rehabilitation degree of the operation of the patient in the current rehabilitation stage is obtained, and the postoperative rehabilitation condition of the patient can be effectively monitored; meanwhile, according to the type of the rehabilitation degree of the patient, the physical rapid rehabilitation strategy of the patient in a new rehabilitation stage is determined and sent to a terminal of the primary medical care for adjustment and confirmation, so that a targeted rehabilitation suggestion is timely given according to the postoperative rehabilitation condition of the patient; archiving the regulated and confirmed body rapid rehabilitation strategy, and sending the regulated and confirmed body rapid rehabilitation strategy to a terminal of a patient for checking, so that the patient can know how to perform rapid rehabilitation treatment in the next stage in time; the rehabilitation questionnaire reply information uploaded by the terminal of the patient in a new rehabilitation stage is analyzed to obtain whether the patient carries out rehabilitation treatment according to the doctor's advice or not and whether the rehabilitation condition of the patient is abnormal or not, and the analysis result is sent to the terminal of the primary medical care, so that the primary medical care can timely know the rehabilitation condition of the patient, and the full-flow tracking of the rehabilitation condition of the patient is realized. Therefore, the application can effectively monitor the postoperative rehabilitation condition of the patient and timely give out targeted rehabilitation advice to help the patient to recover more effectively and quickly.
It should be noted that other contents of the above-mentioned embodiment of the device for dynamically monitoring patient rehabilitation may also correspond to related contents of the above-mentioned embodiment of the method for dynamically monitoring patient rehabilitation, which are not described herein.
Referring to fig. 3, a schematic diagram of an apparatus for dynamically supervising patient rehabilitation according to an embodiment of the present invention is provided. The apparatus for dynamically supervising patient rehabilitation of this embodiment comprises: a processor 100, a memory 101, and a computer program stored in the memory 101 and executable on the processor 100, such as a program for dynamically supervising patient rehabilitation. The processor 100, when executing the computer program, implements the steps of the various method embodiments for dynamically supervising patient rehabilitation described above. Alternatively, the processor 100 may implement the functions of the modules/units in the above-described device embodiments when executing the computer program.
Illustratively, the computer program may be partitioned into one or more modules/units that are stored in the memory 101 and executed by the processor 100 to accomplish the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions for describing the execution of the computer program in the device for dynamically supervising patient rehabilitation.
The device for dynamically supervising patient rehabilitation can be a computing device such as a cloud server. The device for dynamically supervising patient rehabilitation may include, but is not limited to, a processor, a memory. It will be appreciated by those skilled in the art that the schematic is merely an example of a device for dynamically supervising patient rehabilitation and does not constitute a limitation of the device for dynamically supervising patient rehabilitation, and may include more or fewer components than shown, or may combine certain components, or different components, e.g. the device for dynamically supervising patient rehabilitation may further include input and output devices, network access devices, buses, etc.
The processor may be a central processing unit (Central Processing Unit, CPU), other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, which is a control center of the device for dynamically supervising patient rehabilitation, and various interfaces and lines are used to connect various parts of the whole device for dynamically supervising patient rehabilitation.
The memory may be used to store the computer program and/or modules, and the processor may implement various functions of the device for dynamically supervising patient rehabilitation by running or executing the computer program and/or modules stored in the memory and invoking data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data (such as audio data, phonebook, etc.) created according to the use of the handset, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart Media Card (SMC), secure Digital (SD) Card, flash Card (Flash Card), at least one disk storage device, flash memory device, or other volatile solid-state storage device.
Wherein the dynamically administered patient rehabilitation device integrated module/unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the present invention may implement all or part of the flow of the method of the above embodiment, or may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the computer program may implement the steps of each of the method embodiments described above. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth. It should be noted that the computer readable medium contains content that can be appropriately scaled according to the requirements of jurisdictions in which such content is subject to legislation and patent practice, such as in certain jurisdictions in which such content is subject to legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunication signals.
It should be noted that the above-described apparatus embodiments are merely illustrative, and the units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the drawings of the embodiment of the device provided by the invention, the connection relation between the modules represents that the modules have communication connection, and can be specifically implemented as one or more communication buses or signal lines. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
While the foregoing is directed to the preferred embodiments of the present invention, it will be appreciated by those skilled in the art that changes and modifications may be made without departing from the principles of the invention, such changes and modifications are also intended to be within the scope of the invention.
Claims (10)
1. A method for dynamically supervising patient rehabilitation, which is applied to a cloud server and comprises the following steps:
The body rehabilitation data of different body parts of the patient after the operation are collected and uploaded regularly are analyzed by utilizing an optimized machine learning algorithm, and the type of the rehabilitation degree of the operation of the patient in the current rehabilitation stage is obtained; the body part includes a surgical site and includes at least one of: left side part and right side part of operation;
according to the rehabilitation degree type of the patient, determining a physical quick rehabilitation strategy of the patient in a new rehabilitation stage, and sending the physical quick rehabilitation strategy to a terminal of a primary medical care for adjustment and confirmation;
archiving and sending the regulated and confirmed body rapid rehabilitation strategy to a terminal of the patient for checking;
and analyzing the rehabilitation questionnaire reply information uploaded by the terminal of the patient in a new rehabilitation stage to obtain whether the patient carries out rehabilitation treatment according to the medical advice and whether the rehabilitation condition of the patient is abnormal, and sending the analysis result to the terminal of the medical care in charge.
2. The method of dynamically supervising patient rehabilitation according to claim 1, wherein the method further comprises:
and receiving satisfaction evaluation of the primary medical care uploaded by the terminal of the patient, archiving the satisfaction evaluation and transmitting the satisfaction evaluation to the terminal of the primary medical care.
3. The method for dynamically supervising patient recovery according to claim 1, wherein the analyzing, by using the optimized machine learning algorithm, the physical recovery data of the different body parts of the patient after the type of surgery, which is periodically acquired and uploaded, to obtain the type of recovery degree of the type of surgery of the patient in the current recovery stage, includes:
the acquired and uploaded body rehabilitation data of different body parts of the patient after the surgery are subjected to feature extraction; the physical rehabilitation data comprises: pain degree AR, muscle potential MS, and myoelectric frequency PD;
and inputting the extracted features into a trained SVM model for prediction to obtain the type of the rehabilitation degree of the operation of the patient in the current rehabilitation stage.
4. A method of dynamically supervising patient rehabilitation according to claim 3, wherein the training process of the SVM model comprises:
step a: acquiring sample rehabilitation data of similar operations of n patients and sample labels of the rehabilitation degree types of the similar operations corresponding to the sample rehabilitation data of each patient, and performing feature fusion calculation on the sample rehabilitation data of the patients according to a formula 1 to obtain sample data fusion features; the sample rehabilitation data comprises pain degree samples AR, muscle potential samples MS and myoelectricity frequency samples PD of different body parts of N parts of a patient after operation; 2.ltoreq.N.ltoreq.3, the body part including the surgical site and including at least one of: left side part and right side part of operation;
Z=w1×Σari+w2×Σmsi+w3×Σpdi+b, formula 1; w1, w2 and w3 are weights of corresponding parameters, b is a bias term, ARi represents a pain degree sample of the body part at the ith position of the patient, MSi represents a muscle potential sample of the body part at the ith position of the patient, and PDi represents a myoelectric frequency sample of the body part at the ith position of the patient; sigma represents the summation;
step b: combining each sample data fusion feature and a corresponding sample label in a training sample set to form a feature vector Zk, wherein the feature vector Zk is used as the training sample set, and the training sample set comprises n feature vectors Z1, Z2; for any two samples Zi and Zj, their similarity in feature space is calculated according to equation 2:
the number P (the number Zi, zj) =exp (-g x i Zi-Zj i 2), formula 2; where g is the decay rate parameter;
the similarity calculation result of each pair of samples in the training sample set is formed into a kernel matrix P, and the element P (i, j) of the kernel matrix P represents the similarity of the ith sample and the jth sample, so that feature conversion of sample data fusion features is realized and the feature conversion is mapped into a feature space with higher dimension;
step c: searching an optimal hyperplane in a feature space based on a kernel matrix P, so that the interval between positive and negative samples in the training sample set is maximized;
Step d: initializing Lagrangian multipliers alpha of all samples in the training sample set to be 0, and randomly selecting two multipliers alpha for optimization; in each iteration, selecting two multipliers alpha i and alpha j as multiplier pairs to be optimized according to a maximum step strategy; under the constraint condition of the objective function, fixing the values of other multipliers, and optimizing the selected multiplier pairs alpha i and alpha j so as to update the weights corresponding to the two multipliers; in each iteration, checking whether an optimization condition is met according to a KKT condition (Karush-Kuhn-Tucker), and if so, adjusting the threshold of the model according to the updated multiplier pair; according to a preset termination condition, the termination condition comprises that the maximum iteration number is reached or a certain convergence condition is met, and whether the iteration is terminated is determined; repeating the previous step flow in the step d until the termination condition is met, so as to gradually adjust the weight and the threshold corresponding to the multiplier, continuously optimizing the support vector and the corresponding weight in the SVM model by using the weight and the threshold corresponding to the multiplier, and finding out the optimal parameter combination for minimizing the objective function to obtain the optimal segmentation hyperplane;
wherein, the objective function is: minL (α) =Σα -1/2 Σ (Σα×α×yi×p (Zi, zj)), the constraint is: Σα×yi=0; 0< = α < = C; alpha is Lagrangian multiplier and is the weight value corresponding to each sample; yi refers to the label of the ith training sample and is used for representing the rehabilitation degree category of the ith sample; yj refers to the label of the jth training sample and is used for representing the rehabilitation degree category of the jth sample; yi and yj are 1 or-1, respectively representing two categories; p (Zi, zj) maps two samples Zi and Zj in the input feature space to the high-dimensional feature space and calculates their similarity; zi is the ith training sample in the input feature space and consists of a group of feature vectors; zj is the jth training sample in the input feature space, and also consists of a group of feature vectors; c is a regularization parameter used for controlling the complexity of the model;
Step e: and saving the calculated support vector and weight parameters as a trained SVM model.
5. The method for dynamically supervising patient recovery according to claim 4, wherein the feature extraction of the acquired and uploaded physical recovery data of the patient-like post-operative different body parts comprises:
carrying out feature fusion calculation on the acquired and uploaded body rehabilitation data of different body parts of the patient after the operation according to a formula 3 to obtain data fusion features; the method comprises a pain degree sample AR ', a muscle potential sample MS ' and a myoelectric frequency sample PD ' of different body parts of a patient at N positions after operation; n is more than or equal to 2 and less than or equal to 3;
z '=w1×Σari' +w2×Σmsi '+w3×Σpdi' +b, formula 3; w1, w2 and w3 are weights of corresponding parameters, b is a bias term, ARi ' represents pain degree data of the i-th body part of the patient, MSi ' represents muscle potential data of the i-th body part of the patient, and PDi ' represents myoelectric frequency data of the i-th body part of the patient; Σ represents summation.
6. The method of dynamically supervising patient rehabilitation according to claim 1, wherein the determining a physical rapid rehabilitation strategy for the patient at a new rehabilitation stage based on the type of rehabilitation level for the patient comprises:
Determining a physical quick recovery strategy of the patient in a new recovery stage according to the recovery degree type of the patient and based on a mapping relation between a preset recovery degree type and the physical quick recovery strategy; the physical rapid rehabilitation strategy comprises: rehabilitation measures, the treatment implementation time range of each rehabilitation measure; the rehabilitation measures comprise medicines required by rehabilitation, rehabilitation diet notes and rehabilitation exercise training schemes.
7. The utility model provides a device of dynamic supervision patient rehabilitation which characterized in that is applied to in cloud server, includes:
the first analysis module is used for analyzing the acquired and uploaded physical rehabilitation data of different body parts of the patient after operation by using an optimized machine learning algorithm to obtain the type of the rehabilitation degree of the operation of the patient in the current rehabilitation stage; the body part includes a surgical site and includes at least one of: left side part and right side part of operation;
the optimization module is used for determining a physical quick rehabilitation strategy of the patient in a new rehabilitation stage according to the rehabilitation degree type of the patient and sending the physical quick rehabilitation strategy to a terminal of primary medical care for adjustment and confirmation;
The sending module is used for archiving the regulated and confirmed body rapid rehabilitation strategy and sending the regulated and confirmed body rapid rehabilitation strategy to the terminal of the patient for viewing;
and the second analysis module is used for analyzing the rehabilitation questionnaire reply information uploaded by the terminal of the patient in a new rehabilitation stage, analyzing whether the patient carries out rehabilitation treatment according to the medical advice or not and whether the rehabilitation condition of the patient is abnormal or not, and sending the analysis result to the terminal of the medical care in charge.
8. The apparatus for dynamically supervising patient rehabilitation according to claim 7, wherein the apparatus further comprises:
and the receiving module is used for receiving the satisfaction evaluation of the primary medical care uploaded by the terminal of the patient, archiving the satisfaction evaluation and transmitting the satisfaction evaluation to the terminal of the primary medical care.
9. An apparatus for dynamically supervising patient rehabilitation, comprising a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, the processor implementing the method for dynamically supervising patient rehabilitation according to any one of claims 1 to 6 when the computer program is executed.
10. A computer readable storage medium, characterized in that the computer readable storage medium comprises a stored computer program, wherein the computer program, when run, controls a device in which the computer readable storage medium is located to perform the method of dynamically supervising patient rehabilitation according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311112780.4A CN117133402A (en) | 2023-08-30 | 2023-08-30 | Method, device, equipment and readable storage medium for dynamically supervising patient rehabilitation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311112780.4A CN117133402A (en) | 2023-08-30 | 2023-08-30 | Method, device, equipment and readable storage medium for dynamically supervising patient rehabilitation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117133402A true CN117133402A (en) | 2023-11-28 |
Family
ID=88850561
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311112780.4A Pending CN117133402A (en) | 2023-08-30 | 2023-08-30 | Method, device, equipment and readable storage medium for dynamically supervising patient rehabilitation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117133402A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118116599A (en) * | 2024-04-28 | 2024-05-31 | 成都肛肠专科医院 | Rehabilitation management method and system applied to anorectal operation |
Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101127029A (en) * | 2007-08-24 | 2008-02-20 | 复旦大学 | Method for training SVM classifier in large scale data classification |
| CN104000586A (en) * | 2014-05-12 | 2014-08-27 | 燕山大学 | Stroke patient rehabilitation training system and method based on brain myoelectricity and virtual scene |
| CN107007284A (en) * | 2017-03-24 | 2017-08-04 | 北京动亮健康科技有限公司 | Dynamic monitoring and method for tracking and managing and system applied to chronic disease athletic rehabilitation |
| CN108985278A (en) * | 2018-08-24 | 2018-12-11 | 广东工业大学 | A kind of construction method of the gait function assessment models based on svm |
| CN110164524A (en) * | 2019-04-29 | 2019-08-23 | 北京国润健康医学投资有限公司 | A kind of hemiplegia patient training mission adaptive matching method and its system |
| CN111382636A (en) * | 2018-12-29 | 2020-07-07 | 西安思博探声生物科技有限公司 | Processing method, device, equipment and storage medium of knee joint movement signal |
| CN113707344A (en) * | 2021-08-30 | 2021-11-26 | 平安国际智慧城市科技股份有限公司 | AI-based patient rehabilitation tracking method, device, server and medium |
| CN114242203A (en) * | 2021-12-20 | 2022-03-25 | 广州医科大学附属第二医院 | Rehabilitation training management method and system |
| CN115547439A (en) * | 2022-09-20 | 2022-12-30 | 广西医科大学第一附属医院 | Patient follow-up tracking analysis device, method, system and medium |
| CN115588480A (en) * | 2022-10-11 | 2023-01-10 | 武汉拓思瑞医疗科技有限公司 | Orthopedics postoperative remote rehabilitation training method and system, server and storage medium |
| CN115602312A (en) * | 2022-09-26 | 2023-01-13 | 上海佳和健康管理有限公司（Cn） | Postoperative rehabilitation scheme generation method and device, electronic equipment and storage medium |
| CN115620890A (en) * | 2022-10-24 | 2023-01-17 | 华东医院 | Chest surgery patient postoperative remote monitoring and rehabilitation system based on digitization |
| CN115732058A (en) * | 2022-12-02 | 2023-03-03 | 北京复全健康科技有限公司 | Artificial intelligence-based automatic intervention and adjustment method and system for surgical rehabilitation |
| CN115841863A (en) * | 2022-11-29 | 2023-03-24 | 深圳联影智融医疗科技有限公司 | Rehabilitation training plan generation and rehabilitation training system |
| CN116130119A (en) * | 2023-02-27 | 2023-05-16 | 深圳市第二人民医院(深圳市转化医学研究院) | Breast cancer postoperative rehabilitation auxiliary management system |
| CN116230159A (en) * | 2022-10-26 | 2023-06-06 | 北京大学第三医院 | Knee joint movement injury rehabilitation method and system |
| CN116313159A (en) * | 2023-03-24 | 2023-06-23 | 众阳健康科技集团有限公司 | Full-flow supervision method and system for rehabilitation patients based on artificial intelligence |
| CN116386795A (en) * | 2023-03-02 | 2023-07-04 | 北大荒集团齐齐哈尔医院(北大荒集团齐齐哈尔妇幼保健院) | Obstetrical rehabilitation data management method and system |
-
2023
- 2023-08-30 CN CN202311112780.4A patent/CN117133402A/en active Pending
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101127029A (en) * | 2007-08-24 | 2008-02-20 | 复旦大学 | Method for training SVM classifier in large scale data classification |
| CN104000586A (en) * | 2014-05-12 | 2014-08-27 | 燕山大学 | Stroke patient rehabilitation training system and method based on brain myoelectricity and virtual scene |
| CN107007284A (en) * | 2017-03-24 | 2017-08-04 | 北京动亮健康科技有限公司 | Dynamic monitoring and method for tracking and managing and system applied to chronic disease athletic rehabilitation |
| CN108985278A (en) * | 2018-08-24 | 2018-12-11 | 广东工业大学 | A kind of construction method of the gait function assessment models based on svm |
| CN111382636A (en) * | 2018-12-29 | 2020-07-07 | 西安思博探声生物科技有限公司 | Processing method, device, equipment and storage medium of knee joint movement signal |
| CN110164524A (en) * | 2019-04-29 | 2019-08-23 | 北京国润健康医学投资有限公司 | A kind of hemiplegia patient training mission adaptive matching method and its system |
| CN113707344A (en) * | 2021-08-30 | 2021-11-26 | 平安国际智慧城市科技股份有限公司 | AI-based patient rehabilitation tracking method, device, server and medium |
| CN114242203A (en) * | 2021-12-20 | 2022-03-25 | 广州医科大学附属第二医院 | Rehabilitation training management method and system |
| CN115547439A (en) * | 2022-09-20 | 2022-12-30 | 广西医科大学第一附属医院 | Patient follow-up tracking analysis device, method, system and medium |
| CN115602312A (en) * | 2022-09-26 | 2023-01-13 | 上海佳和健康管理有限公司（Cn） | Postoperative rehabilitation scheme generation method and device, electronic equipment and storage medium |
| CN115588480A (en) * | 2022-10-11 | 2023-01-10 | 武汉拓思瑞医疗科技有限公司 | Orthopedics postoperative remote rehabilitation training method and system, server and storage medium |
| CN115620890A (en) * | 2022-10-24 | 2023-01-17 | 华东医院 | Chest surgery patient postoperative remote monitoring and rehabilitation system based on digitization |
| CN116230159A (en) * | 2022-10-26 | 2023-06-06 | 北京大学第三医院 | Knee joint movement injury rehabilitation method and system |
| CN115841863A (en) * | 2022-11-29 | 2023-03-24 | 深圳联影智融医疗科技有限公司 | Rehabilitation training plan generation and rehabilitation training system |
| CN115732058A (en) * | 2022-12-02 | 2023-03-03 | 北京复全健康科技有限公司 | Artificial intelligence-based automatic intervention and adjustment method and system for surgical rehabilitation |
| CN116130119A (en) * | 2023-02-27 | 2023-05-16 | 深圳市第二人民医院(深圳市转化医学研究院) | Breast cancer postoperative rehabilitation auxiliary management system |
| CN116386795A (en) * | 2023-03-02 | 2023-07-04 | 北大荒集团齐齐哈尔医院(北大荒集团齐齐哈尔妇幼保健院) | Obstetrical rehabilitation data management method and system |
| CN116313159A (en) * | 2023-03-24 | 2023-06-23 | 众阳健康科技集团有限公司 | Full-flow supervision method and system for rehabilitation patients based on artificial intelligence |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118116599A (en) * | 2024-04-28 | 2024-05-31 | 成都肛肠专科医院 | Rehabilitation management method and system applied to anorectal operation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11241188B2 (en) | System and methods for monitoring and improving cognitive flexibility | |
| RU2675345C1 (en) | Method for analysis and processing of data of elasticity determining device and elasticity determining device | |
| US20230157533A1 (en) | A computer-implemented system and method for assessing a level of activity of a disease or condition in a patient's eye | |
| CN112712882A (en) | Method and system for improving intensive care management level | |
| US20200074361A1 (en) | Performance measurement device, performance measurement method and performance measurement program | |
| WO2010129711A1 (en) | Devices, systems, and methods for evaluating vision and diagnosing and compensating impairment of vision | |
| Patel et al. | CNN-FEBAC: A framework for attention measurement of autistic individuals | |
| US11583214B2 (en) | Adaptive psychological assessment tool | |
| CN117133402A (en) | Method, device, equipment and readable storage medium for dynamically supervising patient rehabilitation | |
| US20200234824A1 (en) | Wound treatment recommendation system and wound treatment recommendation method | |
| CN114202772B (en) | Reference information generation system and method based on artificial intelligence and intelligent medical treatment | |
| US11955242B2 (en) | Method for automatic diagnosis of conditions of an object and a system for implementing the same | |
| US20210335491A1 (en) | Predictive adaptive intelligent diagnostics and treatment | |
| Zhao et al. | Motor function assessment of children with cerebral palsy using monocular video | |
| Meinel et al. | Tikhonov regularization enhances EEG-based spatial filtering for single trial regression | |
| CN113192603A (en) | Mental state assessment method and system based on big data | |
| CN113066531A (en) | Risk prediction method and device, computer equipment and storage medium | |
| Kalavacherla et al. | Learning from Machine Learning: advancing from static to dynamic facial function quantification | |
| US20220233130A1 (en) | Apparatus and process for measuring brain activity | |
| CN113362941B (en) | Disease condition monitoring method and system based on big data | |
| Rao et al. | Analysis of joints for tracking fitness and monitoring progress in physiotherapy | |
| CN116564540B (en) | Cornea shaping mirror parameter prediction method and system based on ensemble learning algorithm | |
| KR102442778B1 (en) | Server supporting and managing cognitive training and operating method of the server | |
| CN117462279A (en) | Decision-making method, device and equipment for auxiliary treatment of nerve function injury in operation | |
| Pinge et al. | mTanaaw: A System for Assessment and Analysis of Mental Health with Wearables |
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 |