CN114913977A

CN114913977A - Diabetic foot risk assessment method, device, equipment and storage medium

Info

Publication number: CN114913977A
Application number: CN202111586306.6A
Authority: CN
Inventors: 鲍民; 周蓬勃
Original assignee: Shengjing Hospital of China Medical University
Current assignee: Shengjing Hospital of China Medical University
Priority date: 2021-12-23
Filing date: 2021-12-23
Publication date: 2022-08-16

Abstract

The application discloses a diabetic foot risk assessment method, device, equipment and storage medium. The method comprises the following steps: acquiring physical sign data of a patient and a medical image of a focus position; inputting the sign data and the medical image into an evaluation model obtained by pre-training to obtain an evaluation value for representing the risk of the diabetic foot; and outputting decision information for executing target operation on the patient according to the size of the evaluation value. According to the method and the device, a quantitative evaluation basis of the diabetic foot risk is provided for medical staff through the evaluation model, the influence of human experience is reduced, and the accuracy of the diabetic foot risk evaluation is improved.

Description

Diabetic foot risk assessment method, device, equipment and storage medium

Technical Field

The application relates to the field of medical information intellectualization, in particular to a method, a device, equipment and a storage medium for evaluating the risk of a diabetic foot.

Background

Diabetic foot (diabetic foot) is one of the most severe and most costly chronic complications of diabetes, defined by the World Health Organization (WHO): the diabetic foot refers to the condition that the diabetic patient has lower limb infection, ulcer formation and/or deep tissue damage caused by combined neuropathy and peripheral vascular diseases with different degrees, and comprises toe diseases, callosity, tissue necrosis, skin damage, foot ulcer and musculoskeletal diseases. The most common of these is chronic ulcers, with the most serious outcome being amputation. The 15% of total diabetic patients who had or were suffering from foot ulcers or amputations during their lifetime.

The accurate evaluation of the risk level of the diabetic foot plays an important role in diagnosing the state of illness, judging prognosis, guiding treatment and achieving doctor-patient consensus. Foreign specialist doctors make diabetes foot grading systems such as Wagner grading, SAD grading, DEPA grading system, PEDIS grading system, DUSS system and the like in sequence, and domestic doctors also continue to use foreign grading systems.

However, the foreign diabetic foot grading system is too dependent on subjective experience, and medical staff are required to judge according to the subjective experience, so that the evaluation of the risk grade of the diabetic foot is inaccurate, and treatment is possibly delayed.

Disclosure of Invention

The embodiment of the application provides a diabetic foot risk assessment method, a diabetic foot risk assessment device, diabetic foot risk assessment equipment and a storage medium.

In a first aspect, there is provided a method for diabetic foot risk assessment, the method comprising:

acquiring physical sign data of a patient and a medical image of a focus position;

inputting the sign data and the medical image into an evaluation model obtained by pre-training to obtain an evaluation value for representing the risk of the diabetic foot;

and outputting decision information for executing target operation on the patient according to the size of the evaluation value.

Preferably, the inputting the physical sign data and the medical image into an evaluation model obtained by pre-training to obtain an evaluation value for representing the magnitude of the risk of the diabetic foot includes:

inputting the sign data into a first evaluation model obtained by pre-training to obtain a first output value and inputting the medical image into a second evaluation model obtained by pre-training to obtain a second output value;

and giving preset weights to the first output value and the second output value, and obtaining an estimated value for representing the magnitude of the diabetic foot risk by using a weighted summation method.

Preferably, the training method of the first evaluation model includes:

acquiring physical sign data of a patient from detection equipment, and preprocessing the physical sign data to obtain a training set and a test set;

training a preset neural network by using the training set to obtain each candidate learner;

and testing each candidate learner by using the test set, and taking the candidate learner with the highest accuracy as a first evaluation model.

Preferably, the vital sign data comprises: hemoglobin content, blood oxygen saturation, temperature of both lower extremities and foot position, dorsal artery pulsation, ankle blood pressure, foot neuroreflex intensity, and/or transcutaneous oxygen partial pressure.

Preferably, the training method of the second evaluation model includes:

acquiring a medical image of a focus position of a patient as an original sample set;

labeling the sample medical images in the original sample set to obtain each sample medical image and an execution result label corresponding to a target operation;

taking each sample medical image and the corresponding labeled execution result label as a training set, and training a preset deep learning model by using the training set;

and optimizing the deep learning model according to the matching result of the execution result obtained by training and the sample verification data until the matching rate of the execution result obtained by training and the sample verification data reaches a preset threshold value.

Preferably, the medical image of the lesion location comprises: vascular B-ultrasound, angiographic images, plantar infrared images, X-ray and/or MRI images.

In a second aspect, there is provided a diabetic foot risk assessment device, the device comprising:

the acquiring unit is used for acquiring the physical sign data of a patient and a medical image of a focus position;

the input unit is used for inputting the physical sign data and the medical image into an evaluation model obtained by pre-training to obtain an evaluation value for representing the diabetic foot risk of the patient;

and the output unit is used for outputting decision information for executing target operation on the patient according to the size of the evaluation value.

In a third aspect, a computer-readable storage medium is provided, in which a computer program is stored, the computer program being adapted to be loaded by a processor to perform the steps of the data processing method according to any of the embodiments above.

In a fourth aspect, a computer device is provided, the computer device comprising a processor and a memory, the memory storing a computer program therein, the processor being configured to execute the steps in the data processing method according to any of the above embodiments by calling the computer program stored in the memory.

In a fifth aspect, a computer program product is provided, comprising computer instructions which, when executed by a processor, implement the steps in the data processing method according to any of the embodiments above.

According to the embodiment of the application, after the physical sign data and the medical image of the patient are obtained, the data are input into the pre-trained evaluation model, the evaluation value output by the evaluation model can be obtained, and then medical staff can be helped to make a decision according to the value of the data. Because a quantitative evaluation basis of the diabetic foot risk is provided for medical staff through the evaluation model, the influence of human experience is reduced, and therefore, the accuracy of the diabetic foot risk evaluation is improved.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the description below are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a schematic flow chart of a method for evaluating a risk of a diabetic foot according to an embodiment of the present disclosure.

Fig. 2 is a schematic flowchart of a training method of a first evaluation model according to an embodiment of the present disclosure.

Fig. 3 is a flowchart illustrating a training method of a second evaluation model according to an embodiment of the present disclosure.

Fig. 4 is a schematic structural diagram of a device for evaluating a risk of a diabetic foot according to an embodiment of the present application.

Fig. 5 is a schematic structural diagram of a computer device according to an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

The method takes a Wager classification method which is commonly used clinically as an example, the method divides the clinical manifestations of the diabetic foot into 5 grades, wherein the 0 grade represents that the risk factor of foot ulcer is generated and no ulcer exists at present, the 1 grade represents that surface ulcer and clinical no infection exist, the 2 grade represents that deep ulcer and soft tissue inflammation are frequently combined and no abscess or bone infection exists, the 3 grade represents that deep ulcer and bone tissue lesion or no abscess exist, the 4 grade represents that limited gangrene, and the 5 grade represents that full-foot gangrene. As described above, the ischemia and infection of diabetic foot ulcer wounds are important indicators for determining the risk level of diabetic feet.

However, doctors usually judge wound infection and necrosis by visually observing the color and texture of granulation, slough and necrotic tissue in the wound area. Or the diabetic foot is judged to be ischemic by finding out the basis of weakening or disappearance of the dorsum of the foot, posterior tibial artery, or stenosis or occlusion of the artery visible by ultrasonic or arteriography of the lower limb artery. The evaluation result is judged mainly according to personal experience, is influenced by subjective factors such as knowledge level and experience of doctors to a great extent, and is strong in subjectivity and lacks of unified standards. Therefore, the objective risk assessment of diabetic foot becomes a problem to be solved urgently in the medical modernization development process.

The embodiment of the application provides a diabetic foot risk assessment method and device, computer equipment and a storage medium. Specifically, the method for evaluating the risk of diabetic foot according to the embodiment of the present application may be performed by an electronic device, where the electronic device may be a server.

Referring to fig. 1, fig. 1 is a schematic flow chart of a method for evaluating a risk of a diabetic foot according to an embodiment of the present application, where the method is applied to an electronic device, and the method includes:

step 100: acquiring the physical sign data of a patient and a medical image of the lesion position.

For example, a patient may be understood as a diabetic foot patient who needs to receive a diagnostic treatment, evaluate the risk level before treatment, or have performed surgery before treatment evaluation during the recovery period.

In some embodiments, the patient's vital sign data may include hemoglobin content, blood oxygen saturation, and further include temperature, dorsal artery pulsation, ankle blood pressure, reflection intensity of foot nerves, transcutaneous oxygen partial pressure, etc. of a lesion site, such as both lower limbs and foot site, and the medical image of the lesion site may include blood vessel B-ultrasound, angiographic image, plantar infrared image, or image for diagnosis by X-ray, MRI, etc.

Step 101: and inputting the sign data and the medical image into an evaluation model obtained by pre-training to obtain an evaluation value for representing the diabetic foot risk of the patient.

In the embodiment of the disclosure, each physical sign data and medical image of the patient may be input to an evaluation model obtained by pre-training, and the monitoring data and medical image of the patient are processed by the evaluation model, so as to obtain an output result of the evaluation model, where the output result may be a numerical value representing the degree or severity of the risk of the diabetic foot of the patient. Wherein the numerical value may be in the form of an integer, for example, 0, 1, 2, 3, 4, 5, etc., 0 or 1 representing low risk, 2 or 3 representing medium risk, 4 or 5 representing high risk, or a percentage, etc., for example, 20%, 60%, 80%, etc.

In the embodiment of the disclosure, the output prompt may be performed after the numerical value output by the evaluation model is obtained. The output prompting mode can be voice output or display output on a display screen.

Step 102: and outputting decision information for executing target operation on the patient according to the magnitude of the evaluation value.

In a specific application, the decision information may be determined according to a correspondence between the evaluation value and the decision information. Specifically, since the evaluation value represents the value of the risk of the diabetic foot of the patient, the surgical operation can be performed on the patient according to the risk, for example: the three pieces of decision information can be set, wherein the three pieces of decision information respectively suggest to execute the operation, further evaluate whether to execute the operation or not to suggest to execute the operation, and the plurality of pieces of decision information are set, so that the actual clinical requirements can be fully considered, and the risk that medical staff carry out the operation on a patient due to the fact that the medical staff excessively depend on the model result is avoided.

Taking three pieces of decision information as an example, evaluation values corresponding to the recommended surgical operation to be performed may be set to 5 and 4, a numerical value corresponding to whether the surgical operation is to be further evaluated to be performed is set to 3 or 2, and a numerical value interval corresponding to the recommended surgical operation not to be performed is set to 1 or 0, as an example. Therefore, if the value output by the evaluation model is 5, the output decision information is the suggestion of performing the surgical operation, and the medical staff can consider performing the surgical operation on the patient after seeing the decision information.

Further, the pre-trained evaluation model in the embodiment of the present disclosure includes a first evaluation model and a second evaluation model, where the input of the first evaluation model is sign data, and the input of the second evaluation model is a medical image of a lesion site. In this embodiment, the first output value of the first evaluation model and the second output value of the second evaluation model may be respectively given different weights, and then the final evaluation value is obtained by using a weighted summation method.

In order to train the first evaluation model, sample data corresponding to the target operation may be prepared, after the sample data corresponding to the target operation is obtained, the sample data may be divided into a training set and a test set according to a proportion, then each neural network model is trained by using the training set to obtain each candidate learner, then each candidate learner is tested by using the test set, the prediction accuracy of each candidate learner is tested, and then the candidate learner with the higher accuracy is selected as the first evaluation model.

The process of constructing the pre-trained first evaluation model is described in detail below with reference to specific examples.

Step 200: the method comprises the steps of obtaining sign data of a patient from detection equipment, preprocessing the sign data to obtain a training set and a testing set, wherein each sample in the training set comprises data corresponding to each feature and an execution result label corresponding to target operation.

The training set in this embodiment is a set composed of sample data obtained by preprocessing the vital sign data of the patient, the training set includes a plurality of sample data, each sample includes a plurality of different types of features, and since the vital sign data acquired from the detection device may include erroneous data or interference data, this embodiment may clean the interference data by removing an abnormal value, replacing a missing value, and the like, and then, by performing feature normalization and attribute construction on the vital sign data, add data classification to an attribute set, and finally label the classified data. Each sample in the training set includes various features including, but not limited to: hemoglobin content, blood oxygen saturation, temperature of both lower limbs and foot position, dorsal artery pulsation, ankle blood pressure, and foot nerve reflex intensity. The execution result tag corresponding to the target operation comprises the execution of the target operation, namely the operation, or the non-execution of the target operation, namely the non-operation.

Step 201: and training the preset neural network by using the training set to obtain each candidate learner.

It is understood that the predetermined neural network may be Naive Bayes (NB), Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), etc., and the embodiment is not limited in particular.

Step 202: and testing each candidate learner by using the test set, and taking the preset candidate learner with the highest accuracy as a first evaluation model.

It should be noted that, regardless of the subjective experience of the medical care personnel or the mode of evaluating the model, the accuracy of the determined decision information cannot be a hundred percent, and the accuracy is certain, and the accuracy can be continuously improved to be close to a hundred percent. Therefore, after the decision information for executing the target operation is output according to the value of the numerical value output by the evaluation model and the medical staff executes the target operation by referring to the decision information, the actual execution result for executing the target operation can be further obtained, and the physical sign data and the actual execution result are further used as new training samples for updating the evaluation model obtained by pre-training so as to improve the accuracy of model evaluation.

The construction process of the pre-trained second evaluation model is described in detail below with reference to specific examples.

Step 300: a medical image of the location of a lesion in a patient is acquired as an original sample set.

The medical image of the lesion position may be obtained based on historical data, including blood vessel B-ultrasound, angiographic image, plantar infrared image, diagnostic image by X-ray, MRI, or the like, or may be a picture reflecting the ischemia and infection of the foot ulcer wound of the patient.

In one embodiment, the medical image of the lesion position of the patient can be segmented by using the existing image segmentation method to obtain a plurality of regional images; taking a foot ulcer picture as an example, the positions and the number of the ulcers in the picture can be obtained by using an image segmentation method, and the positions and the number of the ulcers are used as the characteristics of a sample medical image for training a subsequent model.

Step 301: and labeling the sample medical images in the original sample set to obtain each sample medical image and an execution result label corresponding to the target operation.

Step 302: and taking each sample medical image and the corresponding labeled execution result label as a training set, and training the preset deep learning model by using the training set.

For example: the deep learning model may be a convolutional neural network model based on a CNN architecture.

Step 303: and continuously optimizing the deep learning model according to the matching result of the execution result obtained by training and the sample verification data until the matching rate of the execution result obtained by training and the sample verification data reaches a preset threshold value.

In this step, the labeled execution result label corresponding to the sample medical image is used as sample verification data, and the preset threshold is set to 70%, and the specific number can be set according to the actual situation.

Further, preset weights are given to the first output value output in the first evaluation model and the second output value output in the second evaluation model, and an evaluation value for representing the size of the diabetic foot risk of the patient is obtained by using a weighted summation method.

According to the diabetes foot risk assessment method provided by the embodiment, after the physical sign data and the medical image of the patient are acquired, the data are input into the pre-trained assessment model, so that the assessment value output by the assessment model can be obtained, and then medical staff can be helped to make a decision according to the magnitude of the numerical value. Because the quantitative evaluation basis of the diabetic foot risk is provided for the medical staff through the evaluation model, the influence of human experience is reduced, and therefore, the accuracy of the diabetic foot risk evaluation is improved.

In order to better implement the diabetic foot risk assessment method of the embodiment of the application, the embodiment of the application also provides a diabetic foot risk assessment device. Referring to fig. 4, fig. 4 is a schematic structural diagram of a device for evaluating a risk of a diabetic foot according to an embodiment of the present application. The diabetic foot risk assessment apparatus 400 may include:

an obtaining unit 401, configured to obtain physical sign data of a patient and a medical image of a lesion position;

an input unit 402, configured to input the physical sign data and the medical image into an evaluation model obtained through pre-training, so as to obtain an evaluation value for representing the diabetic foot risk of the patient;

an output unit 403, configured to output decision information for performing a target operation on the patient according to the magnitude of the evaluation value.

Optionally, the input unit 402 is further configured to input the vital sign data into a first evaluation model obtained through pre-training to obtain a first output value, and input the medical image into a second evaluation model obtained through pre-training to obtain a second output value;

further, the device further comprises an assignment unit, which is used for assigning preset weights to the first output value and the second output value, and obtaining an evaluation value for representing the magnitude of the diabetic foot risk by using a weighted summation method.

It should be noted that, for the functions of each module in the diabetic foot risk assessment apparatus 400 in the embodiment of the present application, reference may be made to the specific implementation manner of any embodiment in the foregoing method embodiments, and details are not described here again.

The respective units in the above-described data processing apparatus may be wholly or partially implemented by software, hardware, and a combination thereof. The units may be embedded in hardware or independent from a processor in the computer device, or may be stored in a memory in the computer device in software, so that the processor can call and execute operations corresponding to the units.

For example, the diabetes foot risk assessment device 400 may be integrated in a terminal having a memory and a processor mounted therein and having a computing capability, or the diabetes foot risk assessment device 400 may be the terminal. For example, the diabetes foot risk assessment device 400 may be integrated in a server having a memory and a processor and having an arithmetic capability, or the diabetes foot risk assessment device 400 may be a server. The terminal can be a smart phone, a tablet Computer, a notebook Computer, a smart television, a smart speaker, a wearable smart device, a Personal Computer (PC), and the like, and the terminal can further include a client, which can be a video client, a browser client, an instant messaging client, and the like. The server may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as cloud service, a cloud database, cloud computing, a cloud function, cloud storage, Network service, cloud communication, middleware service, domain name service, security service, Content Delivery Network (CDN), big data, an artificial intelligence platform, and the like.

Optionally, the present application further provides a computer device, which includes a memory and a processor, where the memory stores a computer program, and the processor implements the steps in the foregoing method embodiments when executing the computer program.

Fig. 5 is a schematic structural diagram of a computer device provided in an embodiment of the present application, and as shown in fig. 5, the computer device 500 may include: a communication interface 501, a memory 502, a processor 503, and a communication bus 504. The communication interface 501, the memory 502 and the processor 503 are communicated with each other through a communication bus 504. The communication interface 501 is used for the apparatus 500 to perform data communication with an external device. The memory 502 may be used to store software programs and modules, and the processor 503 may operate the software programs and modules stored in the memory 502, for example, the software programs of the corresponding operations in the foregoing method embodiments.

Alternatively, the processor 503 may call the software programs and modules stored in the memory 502 to perform the following operations:

acquiring physical sign data of a patient and a medical image of a focus position; inputting the sign data and the medical image into an evaluation model obtained by pre-training to obtain an evaluation value for representing the risk of the diabetic foot; and outputting decision information for executing target operation on the patient according to the size of the evaluation value.

Alternatively, the computer device 500 may be integrated in a terminal or a server having a memory and a processor installed therein and having an arithmetic capability, for example, or the computer device 500 may be the terminal or the server. The terminal can be a smart phone, a tablet computer, a notebook computer, a smart television, a smart sound box, a wearable smart device, a personal computer and the like. The server can be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, and can also be a cloud server for providing basic cloud computing services such as cloud service, a cloud database, cloud computing, cloud functions, cloud storage, network service, cloud communication, middleware service, domain name service, security service, CDN, big data and artificial intelligence platform and the like.

The present application also provides a computer-readable storage medium for storing a computer program. The computer readable storage medium can be applied to a computer device, and the computer program enables the computer device to execute the corresponding process in the method for evaluating the risk of diabetic foot in the embodiment of the present application, which is not described herein again for brevity.

The present application also provides a computer program product comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instruction from the computer-readable storage medium, and executes the computer instruction, so that the computer device executes the corresponding process in the diabetic foot risk assessment method in the embodiment of the present application, which is not described herein again for brevity.

It should be understood that the processor of the embodiments of the present application may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method embodiments may be performed by integrated logic circuits of hardware in a processor or instructions in the form of software. The Processor may be a general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, or discrete hardware components. The various methods, steps, and logic blocks disclosed in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present application may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software modules may be located in ram, flash, rom, prom, or eprom, registers, etc. as is well known in the art. The storage medium is located in a memory, and a processor reads information in the memory and completes the steps of the method in combination with hardware of the processor.

It will be appreciated that the memory in the embodiments of the subject application can be either volatile memory or nonvolatile memory, or can include both volatile and nonvolatile memory. The non-volatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), or a flash Memory. Volatile Memory can be Random Access Memory (RAM), which acts as external cache Memory. By way of example, but not limitation, many forms of RAM are available, such as Static random access memory (Static RAM, SRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic random access memory (Synchronous DRAM, SDRAM), Double Data Rate Synchronous Dynamic random access memory (DDR SDRAM), Enhanced Synchronous SDRAM (ESDRAM), Synchronous link SDRAM (SLDRAM), and Direct Rambus RAM (DR RAM). It should be noted that the memory of the systems and methods described herein is intended to comprise, without being limited to, these and any other suitable types of memory.

It should be understood that the above memories are exemplary but not limiting illustrations, for example, the memories in the embodiments of the present application may also be Static Random Access Memory (SRAM), dynamic random access memory (dynamic RAM, DRAM), Synchronous Dynamic Random Access Memory (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (enhanced SDRAM, ESDRAM), Synchronous Link DRAM (SLDRAM), Direct Rambus RAM (DR RAM), and the like. That is, the memory in the embodiments of the present application is intended to comprise, without being limited to, these and any other suitable types of memory.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

It can be clearly understood by those skilled in the art that, for convenience and simplicity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer or a server) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a U disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method for diabetic foot risk assessment, the method comprising:

inputting the sign data and the medical image into an evaluation model obtained by pre-training to obtain an evaluation value for representing the diabetic foot risk;

2. The method of claim 1, wherein the inputting the sign data and the medical image into a pre-trained evaluation model to obtain an evaluation value for representing the risk of the diabetic foot comprises:

and giving preset weights to the first output value and the second output value, and obtaining an evaluation value for representing the diabetes foot risk by using a weighted summation method.

3. The method of assessing diabetic foot risk according to claim 2, wherein the training of the first assessment model comprises:

4. The method of diabetic foot risk assessment according to claim 3, wherein the vital sign data comprises: hemoglobin content, blood oxygen saturation, temperature of both lower extremities and foot position, dorsal artery pulsation, ankle blood pressure, foot neuroreflex intensity, and/or transcutaneous oxygen partial pressure.

5. The method for diabetic foot risk assessment according to claim 2, wherein the training method of the second assessment model comprises:

and optimizing the deep learning model according to the matching result of the execution result obtained by training and the sample verification data until the matching rate of the execution result obtained by training and the sample verification data reaches a preset threshold value, so as to obtain the second evaluation model.

6. The method for diabetic foot risk assessment according to claim 5, wherein the medical image of the lesion location comprises: vascular B-ultrasound, angiographic images, plantar infrared images, X-ray and/or MRI images.

7. A diabetic foot risk assessment device, the device comprising:

8. A computer-readable storage medium, characterized in that it stores a computer program adapted to be loaded by a processor for performing the steps of the data processing method according to any one of claims 1-6.

9. Computer device, characterized in that it comprises a processor and a memory, in which a computer program is stored, which processor, by calling the computer program stored in the memory, is adapted to carry out the steps in the data processing method according to any of claims 1-6.

10. A computer program product comprising computer instructions, characterized in that said computer instructions, when executed by a processor, implement the steps in the data processing method of any of claims 1-6.