CN115148363A

CN115148363A - Method, device, medium and electronic equipment for predicting depression risk of patient after stroke

Info

Publication number: CN115148363A
Application number: CN202210901279.5A
Authority: CN
Inventors: 朱遂强; 朱舟; 利国; 潘晨盛
Original assignee: Tongji Medical College of Huazhong University of Science and Technology
Current assignee: Tongji Medical College of Huazhong University of Science and Technology
Priority date: 2022-07-28
Filing date: 2022-07-28
Publication date: 2022-10-04

Abstract

The application relates to a method, a device, a medium and an electronic device for predicting depression risk of a post-stroke patient. The method comprises the following steps: acquiring a brain image and a depression function network standard map of a patient after stroke, wherein the depression function network standard map is used for representing a brain function network related to depression after stroke; calculating the network damage score of the patient after stroke according to the brain image and the depression function network standard map; obtaining a depression structural reconnection map, wherein the depression structural reconnection map is used for representing brain reconnection distribution conditions related to depression after stroke; calculating the structural reconnection score of the patient after stroke according to the brain image and the depression structural reconnection map; and inputting the network damage score, the structural loss connection score and clinical information data of the patient after the stroke into a prediction model, and determining the depression risk of the stroke patient after the stroke patient occurs for months through the prediction model. The method and the device can predict the depression risk according to the direct impact of the stroke focus on the brain network in the brain which is responsible for emotion regulation.

Description

Method, device, medium and electronic equipment for predicting depression risk of patient after stroke

Technical Field

The application relates to the technical field of medical treatment, in particular to a method, a device, a medium and electronic equipment for predicting depression risk of a patient after stroke.

Background

The incidence rate of post-stroke depression (PSD) is high, the clinical recognition rate is low, and the attention of clinicians and patients is often unavailable, so that the prognosis of the patients is seriously influenced. The existing prediction method pays attention to the influence of clinical factors and psychosocial factors on emotion, but neglects the direct impact of stroke focus on a brain network responsible for emotion regulation in the brain at the neurobiology level.

Based on this, those skilled in the art urgently need a method for predicting the risk of depression of a patient after stroke, and the risk of depression can be predicted to a certain extent according to the direct impact of the stroke focus on a brain network in the brain which is responsible for mood regulation.

Disclosure of Invention

The embodiment of the application provides a method, a device, a computer program product or a computer program, a computer readable medium and an electronic device for predicting the depression risk of a post-stroke patient, so that the depression risk can be predicted at least to a certain extent according to direct impact of stroke focuses on brain networks in the brain which are responsible for emotion regulation.

Other features and advantages of the present application will be apparent from the following detailed description, or may be learned by practice of the application.

According to an aspect of an embodiment of the present application, there is provided a method for predicting a risk of depression in a patient after stroke, the method including: acquiring a brain image and a depression function network standard map of a patient after stroke, wherein the depression function network standard map is used for representing a brain function network related to depression after stroke; calculating a network injury score of the post-stroke patient according to the brain image and the network standard map of depression function; obtaining a depression structural reconnection map, wherein the depression structural reconnection map is used for representing brain reconnection distribution conditions related to depression after stroke; calculating a structural reconnection score for the post-stroke patient from the brain image and the depressed structural reconnection map; inputting the network damage score, the structural loss of connection score and the post-stroke patient clinical information data into a predictive model, and determining the post-stroke patient depression risk through the predictive model.

In some embodiments of the present application, the acquiring an image of the brain of a post-stroke patient comprises: the method comprises the steps of obtaining an initial brain image of a patient after stroke, identifying a stroke focus area in the initial brain image, converting the initial brain image into a standard brain image format, and generating the brain image of the patient after stroke.

In some embodiments of the present application, based on the foregoing solution, the calculating the network impairment score of the post-stroke patient according to the brain image and the network standard map of depression function comprises: and calculating the network damage score of the post-stroke patient according to the overlapping degree of the stroke focus area of the brain image and the standard map of the depression function network.

In some embodiments of the present application, based on the foregoing, the calculating a structural reconnection score for the post-stroke patient from the brain image and the depressed structural reconnection map comprises: determining the brain structure connectionless range caused by the focus according to the stroke focus area of the brain image; calculating the structural misconnection score of the post-stroke patient according to the overlap degree of the partial structural misconnection range and the depressed structural misconnection map.

In some embodiments of the application, upon inputting the network impairment score, the structural loss of connection score, and the post-stroke patient clinical information data to a predictive model, the method further comprises: constructing an initial prediction model; obtaining a model training sample set, wherein the model training sample set comprises at least one network injury score, structural loss connection score, clinical information data and depression condition after illness of a patient after stroke; and based on the model training sample, performing model training based on a machine learning algorithm on the initial prediction model to obtain a prediction model.

In some embodiments of the present application, upon inputting the network impairment score, the structural loss of connection score, and the post-stroke patient clinical information data to a predictive model, the method further comprises: and acquiring the age, the sex, the disability degree after the stroke and the cognitive degree of the patient after the stroke, and taking the obtained degrees as clinical information data of the patient after the stroke.

In some embodiments of the present application, said determining the risk of depression of the post-stroke patient by the predictive model comprises: determining the probability of occurrence of post-stroke depression of the post-stroke patient through the prediction model, and determining the depression risk of the post-stroke patient through the probability of occurrence of post-stroke depression.

According to an aspect of an embodiment of the present application, there is provided a post-stroke patient depression risk prediction apparatus, the apparatus including: a first acquisition unit, which is used for acquiring a brain image of a post-stroke patient and a depression function network standard map, wherein the depression function network standard map is used for representing a brain function network related to post-stroke depression; a first calculation unit, configured to calculate a network impairment score of the post-stroke patient according to the brain image and the network standard map of depression function; a second obtaining unit, configured to obtain a depression structural reconnection map, the depression structural reconnection map being used to characterize a brain reconnection distribution associated with post-stroke depression; a second calculation unit for calculating a structural reconnection score of the post-stroke patient from the brain image and the depressed structural reconnection map; a determination unit for inputting the network impairment score, the structural loss of connection score and the post-stroke patient clinical information data into a predictive model, by which the post-stroke patient's risk of depression is determined.

According to an aspect of embodiments of the present application, there is provided a computer-readable storage medium having at least one program code stored therein, the at least one program code being loaded into and executed by a processor to implement the operations performed by the method for predicting post-stroke patient depression risk as described.

According to an aspect of embodiments herein, there is provided an electronic device comprising one or more processors and one or more memories having stored therein at least one program code, which is loaded and executed by the one or more processors to perform the operations performed by the method for predicting post-stroke patient depression risk as described.

Based on the scheme, the application has at least the following advantages or progresses:

in the technical scheme provided by some embodiments of the application, the network injury score and the structure loss connection score are respectively calculated by comparing the brain image of the patient after stroke with the standard network map of the depression function and the structure loss connection map of the depression, and then the depression risk of the patient after stroke is predicted by the prediction model, so that the risk information of the nerve anatomical layer and the traditional clinical-demographic factor can be integrated, and the performance and the popularization of the prediction model are further improved. Can also provide objective biological or image markers for the diagnosis of mental diseases, and has great clinical practice significance and innovation.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application.

It is obvious that the drawings in the following description are only some embodiments of the application, and that for a person skilled in the art, other drawings can be derived from them without inventive effort.

In the drawings:

fig. 1 shows a flow chart of a method of predicting a risk of depression in a patient after stroke according to one embodiment of the present application;

fig. 2 shows a network criteria map for depression function in an embodiment according to the application;

fig. 3 shows a flow chart of a method of predicting a risk of depression in a patient after stroke according to an embodiment of the present application;

FIG. 4 shows a simplified schematic diagram of a range of brain structure misconnection due to a determination of a lesion in an embodiment in accordance with the application;

FIG. 5 shows a map of depressive structure misconnection in one embodiment according to the application;

fig. 6 shows a flow chart of a method of predicting a risk of depression in a patient after stroke according to an embodiment of the present application;

FIG. 7 shows a software operating mechanism diagram in accordance with an embodiment of the present application;

fig. 8 shows a post-stroke patient depression risk prediction device according to an embodiment of the present application;

FIG. 9 illustrates a schematic structural diagram of a computer system suitable for use in implementing the electronic device of an embodiment of the present application.

Detailed Description

Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art.

Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the application. One skilled in the relevant art will recognize, however, that the subject matter of the present application can be practiced without one or more of the specific details, or with other methods, components, devices, steps, and so forth. In other instances, well-known methods, devices, implementations, or operations have not been shown or described in detail to avoid obscuring aspects of the application.

The block diagrams shown in the figures are functional entities only and do not necessarily correspond to physically separate entities. I.e. these functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor means and/or microcontroller means.

The flowcharts shown in the figures are illustrative only and do not necessarily include all of the contents and operations/steps, nor do they necessarily have to be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.

It should be noted that: reference herein to "a plurality" means two or more. "and/or" describe the association relationship of the associated objects, meaning that there may be three relationships, e.g., A and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.

The implementation details of the technical solution of the embodiment of the present application are set forth in detail below:

please refer to fig. 1.

Fig. 1 shows a flow chart of a method for predicting the risk of post-stroke depression of a patient according to an embodiment of the present application, which may comprise the steps S101-S105:

step S101, obtaining a brain image of a patient after stroke and a standard map of a depression function network, wherein the standard map of the depression function network is used for representing a brain function network related to depression after stroke.

And S102, calculating the network damage score of the patient after the stroke according to the brain image and the standard spectrum of the network of the depression function.

Step S103, obtaining a depression structure misconnection map, wherein the depression structure misconnection map is used for representing brain misconnection distribution conditions related to depression after stroke.

And step S104, calculating the structural reconnection score of the patient after the stroke according to the brain image and the depression structural reconnection map.

Step S105, inputting the network damage score, the structural loss connection score and the clinical information data of the post-stroke patient into a prediction model, and determining the depression risk of the post-stroke patient through the prediction model.

In the application, the brain image, the standard network map of the depression function and the connection map of the depression structure of the patient after stroke are compared, the network damage fraction and the connection fraction of the structure are respectively calculated, the depression risk of the patient after stroke is predicted through the prediction model, the risk information of the nerve anatomical layer can be integrated with the traditional clinical-demographic factor, and the performance and the popularization of the prediction model are further improved. And objective biological or image markers can be provided for the diagnosis of mental diseases, and the method has great clinical practice significance and innovation.

In the present application, the method of acquiring an image of the brain of a post-stroke patient comprises: the method comprises the steps of obtaining an initial brain image of a patient after stroke, identifying a stroke focus area in the initial brain image, converting the initial brain image into a standard brain image format, and generating the brain image of the patient after stroke.

In the application, the initial brain image of the patient after stroke can be an MRI or CT image, and in the practical application process, the MRI or CT image of the patient after stroke can be directly called through medical software in a hospital.

In the application, an image data management system (PACS) can be connected through a customized software interface, brain image data of a patient after stroke is automatically called and displayed, a doctor selects a required modality, for example, the patient who has caused the stroke due to cerebral infarction can use diffusion weighted imaging in a targeted manner, the patient who has caused the stroke due to cerebral hemorrhage can use CT flat scanning in a targeted manner, a semi-automatic algorithm is adopted to segment a stroke focus area, and in addition, the doctor can manually segment the focus area.

In the present application, the conversion of the initial brain image into a standard brain image format may be achieved by registering the initial brain to the international uniform MNI152 standard space.

In the present application, the method for calculating the network injury score of the post-stroke patient according to the brain image and the network standard atlas for depression function may comprise: and calculating the network damage score of the post-stroke patient according to the overlapping degree of the stroke focus area of the brain image and the standard map of the depression function network.

In the application, the depression function network standard map can be used for characterizing the brain connectionless distribution condition related to the post-stroke depression. For example, reference may be made to fig. 2, which fig. 2 shows a network criteria map for depression function in an embodiment according to the present application. As shown in fig. 2, the left dorsolateral prefrontal cortex (L-DLPFC) is taken as the center, and the brain area with positive T is shown as the

areas

201, 202, 203, 204 and 205, the functional activity is positively correlated with the L-DLPFC, most focuses of PSD patients are overlapped with the area with positive T, while the focus of non-depressed patients is overlapped with the area with positive T little or no.

In this application, the calculating the network impairment score of the post-stroke patient according to the brain image and the network standard atlas of depressive functions may include: and calculating the network damage score of the post-stroke patient according to the overlapping degree of the stroke focus area of the brain image and the standard map of the depression function network.

In the present application, brain images can be superimposed on a standard map of the network of depressed functions, and then the sum of the two overlapping T statistics is calculated as the network damage score of the patient after stroke.

Please refer to fig. 3-5.

Fig. 3 shows a flowchart of a method for predicting a risk of depression of a post-stroke patient according to an embodiment of the present application, the method for calculating a structural reconnection score of the post-stroke patient according to the brain image and the depression structural reconnection map may comprise steps S301-S302:

step S301, determining the brain structure connectionless range caused by focus according to the stroke focus area of the brain image.

Step S302, calculating the structural reconnection score of the post-stroke patient according to the overlap degree of the structural reconnection range and the depression structural reconnection map.

Fig. 4 shows a schematic diagram of determining a focal-induced brain structure misconnection range in accordance with an embodiment of the present application. As shown in fig. 4, in the graph a, a spatially normalized lesion may be superimposed on an open source structure connection map published by a human connection group plan as a reference, so as to obtain a structural connectionless range caused by the lesion. In graph B, a map of structural reconnection severity is shown, with the value for each voxel representing the percentage of fibers in the voxel that have become disconnected as a percentage of the total number of fibers in the voxel.

Fig. 5 shows a map of the loss of connection of depressed structures in one embodiment according to the application, as shown in fig. 5, the more white matter fibers in the 501-509 region are lost, the higher the risk and severity of post-stroke depression.

In the application, the brain structure connectionless range caused by the focus can be superimposed on the depression structure connectionless map, the high-risk regions of the brain structure connectionless range and the depression structure connectionless map, namely the superimposed degrees of the regions 501-509 in fig. 5, are judged, and the structural connectionless score of the patient after stroke is calculated.

Please refer to fig. 6.

Fig. 6 shows a flowchart of a method for predicting a post-stroke patient 'S depression risk, in which the network impairment score, the structural loss connection score and the post-stroke patient' S clinical information data are input to a prediction model, the method may further comprise steps S601-S603:

step S601, an initial prediction model is constructed.

Step S602, obtaining a model training sample set, wherein the model training sample set comprises at least one post-stroke patient network injury score, structural loss connection score, clinical information data and post-illness depression condition.

And step S603, based on the model training sample, carrying out model training based on a machine learning algorithm on the initial prediction model to obtain a prediction model.

In the application, because the aforesaid scheme can predict the depression risk of the patient after the stroke to some extent, but the situation of the patient is very diversified, and the model training needs to be carried out according to big data, so as to improve the accuracy, sensitivity and specificity of the prediction model.

In the application, because the time or degree of depression of the patient after stroke is different, different initial model parameters can be used for different training samples, the initial model modified by the parameters can more closely reflect the actual conditions of each training sample, and each training sample can also achieve normalization on the basis of a machine learning algorithm.

In the application, prospective multi-center queue data collected in the early stage can be relied on, the network damage score, the structural loss connection score, the clinical information data and the post-attack depression condition are used as prediction factors to train an initial prediction model after stroke, and a plurality of machine learning algorithms such as a support vector machine, a decision tree, an artificial neural network and ensemble learning can be adopted in the training process, and a model with the optimal performance is selected as a final model.

In this application, the network impairment score, the structural loss of connection score, and the post-stroke patient clinical information data are input to a predictive model, the method may further comprise: and acquiring the age, the sex, the disability degree after the stroke and the cognitive degree of the patient after the stroke, and taking the obtained degrees as clinical information data of the patient after the stroke.

In the present application, the method of determining the risk of depression of a patient after stroke by means of the predictive model comprises: determining the probability of occurrence of post-stroke depression of the post-stroke patient through the prediction model, and determining the depression risk of the post-stroke patient through the probability of occurrence of post-stroke depression.

In the present application, the risk of depression can be divided into three risk levels, low, medium and high risk.

Referring to fig. 7, fig. 7 shows a software operating mechanism diagram according to an embodiment of the present application. As shown in fig. 7, the technical method of the present application can be integrated into a one-stop software, and the operation mechanism of the software is as follows:

(1) The clinician enters a unique identification number (e.g., hospital admission number) for a particular patient at the software interface;

(2) The medical record system (HIS) is connected through a customized software interface, the basic clinical information data of the patient, such as age, sex and scale (disability degree after stroke, cognitive function and the like), are quickly extracted by adopting an artificial intelligent natural language processing algorithm, and the steps are automatically realized without the operation of a doctor;

(3) The system is connected with an image data management system (PACS) through a customized software interface, brain image data of a patient is automatically called and displayed, a doctor selects a required mode (cerebral infarction uses diffusion weighted imaging, cerebral hemorrhage uses CT flat scanning), software partitions a focus area in the brain image data by adopting a semi-automatic algorithm, and the software also has a focus manual partitioning function (manual partitioning is a gold standard for focus partitioning);

(4) Spatial normalization of lesions: the software automatically registers the initial brain image and the segmented lesion mask to an international unified MNI152 standard space;

(5) Calculating a network damage score: software superimposes the registered focus on a depression function network standard map, and the sum of T statistic of the overlapped part of the focus and the depression function network standard map is calculated to be the network injury score.

(6) Calculating the structural misconnection score: software superposes the brain image after registration on a human connection group plan-842 fiber connection map, and defines fibers cut off by the focus, namely the structure failure connection range caused by the focus; and superposing the range and the depression structure loss connection map, wherein the sum of Z statistics of the overlapped parts of the range and the depression structure loss connection map is the structure loss connection score.

(7) Risk prediction: the software integrates the functional network damage score, the structural loss connection score and the extracted clinical demographic information, the information is input into a machine learning model to calculate the occurrence risk of post-stroke depression, and a software interface displays the probability and the risk level of the post-stroke depression of the patient in the future.

(8) Doctors make clinical decisions according to the prediction results, and biological-psychological-social multi-level PSD prevention and treatment are given to high-risk people, and specific intervention strategies comprise psychotherapy, social support, antidepressant drugs, nerve regulation and the like.

An apparatus embodiment of the present application will be described with reference to the accompanying drawings.

Please refer to fig. 8.

Fig. 8 shows a post-stroke patient depression risk prediction device according to an embodiment of the application, the device 800 may comprise: a first acquisition unit 801, a first calculation unit 802, a second acquisition unit 803, a second calculation unit 804, and a determination unit 805.

The specific configuration of the apparatus 800 may be: a first acquiring unit 801, configured to acquire a brain image of a post-stroke patient and a standard map of a depression function network, where the standard map of the depression function network is used to characterize a brain function network related to post-stroke depression; a first calculating unit 802, configured to calculate a network impairment score of the post-stroke patient according to the brain image and the network standard map of depression function; a second obtaining unit 803, configured to obtain a depression stracture connectionless map, which is used to characterize the brain connectionless distribution associated with post-stroke depression; a second calculation unit 804 for calculating a structural reconnection score of the post-stroke patient from the brain image and the depressed structural reconnection map; a determination unit 805 configured to input the network impairment score, the structural loss of connection score and the post-stroke patient clinical information data into a predictive model, by which a risk of depression of the post-stroke patient is determined.

Please refer to fig. 9.

It should be noted that the computer system 900 of the electronic device shown in fig. 9 is only an example, and should not bring any limitation to the functions and the scope of the application of the embodiments.

As shown in fig. 9, the computer system 900 includes a Central Processing Unit (CPU) 901, which can execute various appropriate actions and processes, such as executing the method described in the above embodiments, according to a program stored in a Read-Only Memory (ROM) 902 or a program loaded from a storage portion 908 into a Random Access Memory (RAM) 903. In the RAM 903, various programs and data necessary for system operation are also stored. The CPU 901, ROM 902, and RAM 903 are connected to each other via a bus 904. An Input/Output (I/O) interface 905 is also connected to bus 904.

The following components are connected to the I/O interface 905: an input portion 906 including a keyboard, a mouse, and the like; an output section 907 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, a speaker, and the like; a storage portion 908 including a hard disk and the like; and a communication section 909 including a Network interface card such as a LAN (Local Area Network) card, a modem, or the like. The communication section 909 performs communication processing via a network such as the internet. The drive 910 is also connected to the I/O interface 905 as necessary. A removable medium 911 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 910 as necessary, so that a computer program read out therefrom is mounted into the storage section 908 as necessary.

In particular, according to embodiments of the application, the processes described above with reference to the flow diagrams may be implemented as computer software programs. For example, embodiments of the present application include a computer program product comprising a computer program embodied on a computer-readable medium, the computer program comprising program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication section 909 and/or installed from the removable medium 911. The computer program executes various functions defined in the system of the present application when executed by a Central Processing Unit (CPU) 901.

It should be noted that the computer readable medium shown in the embodiments of the present application may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a Read-Only Memory (ROM), an Erasable Programmable Read-Only Memory (EPROM), a flash Memory, an optical fiber, a portable Compact Disc Read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. Each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in the embodiments of the present application may be implemented by software or hardware, and the described units may also be disposed in a processor. Wherein the names of the elements do not in some way constitute a limitation on the elements themselves.

As another aspect, the present application also provides a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions to cause the computer device to execute the method for predicting the post-stroke depression risk of a patient as described in the above embodiments.

As another aspect, the present application also provides a computer-readable medium, which may be contained in the electronic device described in the above embodiments; or may exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs which, when executed by an electronic device, cause the electronic device to implement the method for predicting post-stroke patient depression risk described in the above embodiments.

It should be noted that although in the above detailed description several modules or units of the device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit, according to embodiments of the application. Conversely, the features and functions of one module or unit described above may be further divided into embodiments by a plurality of modules or units.

Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the embodiments of the present application.

Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the embodiments disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains.

It will be understood that the present application is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.

Claims

1. A method for predicting the risk of depression in a post-stroke patient, the method comprising:

acquiring a brain image and a depression function network standard map of a patient after stroke, wherein the depression function network standard map is used for representing a brain function network related to depression after stroke;

calculating a network injury score of the post-stroke patient according to the brain image and the network standard map of depression function;

obtaining a depression structural reconnection map, wherein the depression structural reconnection map is used for representing brain reconnection distribution conditions related to depression after stroke;

calculating a structural reconnection score for the post-stroke patient from the brain image and the depressed structural reconnection map;

inputting the network damage score, the structural loss of connection score and the post-stroke patient clinical information data into a predictive model, and determining the post-stroke patient depression risk through the predictive model.

2. The method of claim 1, wherein said acquiring an image of the brain of the post-stroke patient comprises:

the method comprises the steps of obtaining an initial brain image of a patient after stroke, identifying a stroke focus area in the initial brain image, converting the initial brain image into a standard brain image format, and generating the brain image of the patient after stroke.

3. The method of claim 2, wherein said calculating a network impairment score for said post-stroke patient from said brain image and said network standard map of depression function comprises:

and calculating the network damage score of the post-stroke patient according to the overlapping degree of the stroke focus area of the brain image and the standard map of the depression function network.

4. The method of claim 2, wherein said calculating a structural reconnection score for the post-stroke patient from the brain image and the depressed structural reconnection map comprises:

determining a brain structure reconnection range caused by a focus according to the stroke focus area of the brain image;

and calculating the structural loss connection score of the patient after the stroke according to the overlapping degree of the partial structural loss connection range and the depression structural loss connection map.

5. The method of claim 1, wherein upon inputting the network impairment score, the structural loss of connection score, and post-stroke patient clinical information data to a predictive model, the method further comprises:

constructing an initial prediction model;

obtaining a model training sample set, wherein the model training sample set comprises a network damage score, a structural loss connection score, clinical information data and a post-morbidity depression condition of at least one post-stroke patient;

and performing model training based on a machine learning algorithm on the initial prediction model based on the model training sample to obtain a prediction model.

6. The method of claim 1, wherein upon inputting the network impairment score, the structural loss of connection score, and post-stroke patient clinical information data to a predictive model, the method further comprises:

and acquiring the age, the sex, the disability degree after the stroke and the cognitive degree of the patient after the stroke as the clinical information data of the patient after the stroke.

7. The method of claim 1, wherein said determining a risk of depression of said post-stroke patient by said predictive model comprises:

determining the probability of occurrence of post-stroke depression of the post-stroke patient through the prediction model, and determining the depression risk of the post-stroke patient through the probability of occurrence of post-stroke depression.

8. An apparatus for predicting a post-stroke patient's risk of depression, the apparatus comprising:

a first acquisition unit, which is used for acquiring a brain image of a post-stroke patient and a depression function network standard map, wherein the depression function network standard map is used for representing a brain function network related to post-stroke depression;

a first calculation unit, configured to calculate a network impairment score of the post-stroke patient according to the brain image and the network standard map of depression function;

a second obtaining unit, configured to obtain a depression structural reconnection map, the depression structural reconnection map being used to characterize a brain reconnection distribution associated with post-stroke depression;

a second calculation unit for calculating a structural reconnection score of the post-stroke patient from the brain image and the depressed structural reconnection map;

a determination unit for inputting the network impairment score, the structural loss of connection score and the post-stroke patient clinical information data into a predictive model, by which the post-stroke patient's risk of depression is determined.

9. A computer-readable storage medium having at least one program code stored therein, the at least one program code being loaded and executed by a processor to perform the operations of the method for predicting post-stroke patient depression risk according to any one of claims 1 to 7.

10. An electronic device, comprising one or more processors and one or more memories having at least one program code stored therein, the at least one program code being loaded and executed by the one or more processors to perform the operations of the method for predicting post-stroke patient depression risk of any one of claims 1 to 7.