Depression prediction method based on grey prediction model and related products

Abstract

The invention provides a depression prediction method of a grey prediction model and a related product. The depression prediction method comprises the following steps: acquiring a grey prediction model based on a grey system theory; acquiring multiple groups of historical diagnosis data and current diagnosis data of the target user; substituting multiple groups of historical diagnosis data and current diagnosis data of the target user into the grey prediction model, and calculating a prediction error of the grey prediction model; and in response to the prediction error meeting the preset requirement, predicting the future depression degree score of the target user according to the multiple groups of historical diagnosis data of the target user, the current diagnosis data of the target user and the gray prediction model. The method achieves the accurate prediction of the future depression degree change of the target user through the gray prediction model, and achieves the purpose of providing a diagnosis basis for the early intervention or the timely adjustment of the intervention method to achieve the optimal treatment effect.

Description

Technical Field

[0001] The present invention relates to the technical field of depression assessment, and in particular to a depression prediction method based on a grey prediction model and related products. Background Art

[0002] The "China Aging Development Report 2024: Mental Health Status of China's Elderly" report indicates that 23.76% of seniors in my country experience varying degrees of loneliness, with 4.75% reporting "often feeling lonely." Furthermore, 26.4% of seniors experience symptoms of depression, with 6.2% experiencing moderate to severe depression. Loneliness is a common psychological distress among the elderly, and long-term loneliness can lead to various physical and mental problems, including cognitive impairment, depression, sleep disorders, and cardiovascular disease.

[0003] Currently, the main clinical diagnostic methods for depression include: depression rating scale screening; electroencephalogram (EEG) assessment, functional magnetic resonance imaging (fMRI) assessment, electrocardiogram (ECG) assessment, and other technologies. Although these methods can diagnose depression, once depression develops, it requires long-term medication and psychological intervention, which is difficult and time-consuming to cure, resulting in significant losses to society and families. Therefore, using data mining technology to predict psychological states and intervene early is an urgent problem to be solved.

[0004] Due to the complexity of human cognition and the diversity of living environments, data patterns and influencing factors vary across different populations. Among related technologies, intelligent algorithms such as deep learning and machine learning require large amounts of training data to build effective depression prediction and assessment models. In the uncertain context of limited data and information, these technologies cannot effectively build effective depression prediction and assessment models. The advantage of gray system theory lies in its ability to establish predictive models, forecast development trends, make decisions, and effectively and rationally assess system control and status through data processing and phenomenon analysis within this uncertain context. Summary of the Invention

[0005] An object of the present invention is to provide a depression prediction method, computer-readable storage medium, computer program product and computer device based on a gray prediction model, so as to utilize gray system theory to construct an accurate prediction model for depression state, utilize the depression prediction model to evaluate the changes in the patient's depression level, and thus provide a diagnostic basis for early intervention or timely adjustment of intervention methods to achieve the best treatment effect.

[0006] Specifically, according to one aspect of the present invention, the present invention provides a depression prediction method based on a grey prediction model, comprising:

[0007] Obtaining a grey prediction model based on grey system theory, the grey prediction model being used to predict a future depression score of a sample user based on multiple sets of historical diagnostic data of the sample user, wherein the diagnostic data of the sample user includes a result of a depression assessment scale and a depression score obtained by the sample user during a diagnosis;

[0008] Acquiring multiple sets of historical diagnostic data and current diagnostic data of a target user; the diagnostic data of the target user includes the results of the depression assessment scale and the depression severity score obtained by the target user in a diagnosis;

[0009] Substituting multiple groups of historical diagnosis data and current diagnosis data of the target user into the grey prediction model, and calculating the prediction error of the grey prediction model;

[0010] In response to the prediction error meeting a preset requirement, the future depression level score of the target user is predicted based on the multiple groups of historical diagnosis data of the target user, the current diagnosis data of the target user, and the grey prediction model.

[0011] Optionally, the obtaining of a grey prediction model based on grey system theory includes:

[0012] Obtaining the depression assessment scale and the weight coefficient of each depression characteristic in the depression assessment scale;

[0013] Acquire multiple groups of historical diagnostic data of the sample users;

[0014] weighting the values ​​of the depression characteristics in the results of the depression assessment scale for each set of historical diagnostic data of the sample user according to the weight coefficients to obtain multiple sets of weighted historical diagnostic data of the sample user;

[0015] According to the multiple groups of weighted historical diagnostic data of the sample users, the grey prediction model based on the grey system theory is constructed.

[0016] Optionally, the step of obtaining the weight coefficient of each depression feature in the depression assessment scale includes:

[0017] Using the expert scoring method, invite multiple experts to weight the depression characteristics in the depression assessment table to obtain the corresponding initial weight coefficients. Wherein, i=1, 2, ..., n, i represents the serial number of each depressive feature, j=1, 2, ..., m, j represents the serial number of the expert;

[0018] The average initial weight coefficient of each depressive trait is obtained according to the following formula:

[0019]

[0020] in, The average initial weight coefficient representing the depression feature with sequence number i;

[0021] The average initial weight coefficient of each depression feature is normalized according to the following formula to obtain the weight coefficient of each depression feature:

[0022]

[0023] Among them, w i The weight coefficient of the depression feature with sequence number i is represented.

[0024] Optionally, obtaining multiple sets of historical diagnostic data of the sample users includes:

[0025] Obtaining results of the depression assessment scale for a plurality of sampled users, where the plurality of sampled users constitute the sample user, and the number of the sampled users is greater than the number of items of depression characteristics in the depression assessment scale;

[0026] Inviting multiple experts to score the depression level of each of the sampled users using an expert scoring method to obtain an initial depression level score corresponding to the result of the depression assessment scale of each of the sampled users;

[0027] The average of the initial depression level scores of each of the sampled users is used as the depression level score of the sampled user.

[0028] Optionally, constructing the grey prediction model based on the grey system theory according to the multiple groups of weighted historical diagnostic data of the sample users includes:

[0029] Obtain multiple sets of weighted historical diagnostic data of the sample users as training data set Y w , and expressed in matrix form:

[0030]

[0031] Among them, y w1,1 represents the depression severity score in the first set of weighted historical diagnostic data, y w1,2 represents the weighted value of the depression feature with sequence number 1 in the first group of weighted historical diagnostic data, y w1,n represents the weighted value of the depression feature numbered n-1 in the first group of weighted historical diagnostic data, y wm,1 represents the depression score in the mth group of weighted historical diagnostic data, y wm,2 represents the weighted value of the depression feature with sequence number 1 in the mth group of weighted historical diagnostic data, y wm,nrepresents the weighted value of the depression feature with sequence number n-1 in the mth group of weighted historical diagnostic data;

[0032] The training data set Y w The data of each column in is regarded as a sequence, and the data of each sequence is accumulated once to obtain an accumulated data set. And expressed in matrix form:

[0033]

[0034] Based on the grey system theory, we get

[0035]

[0036] Among them, k represents a cumulative data group The kth row in the matrix, a,b2,…,b h is the unknown coefficient,

[0037] Calculate the matrix of unknown coefficients using the least squares method The grey prediction model is obtained.

[0038] Optionally, the step of determining whether the prediction error meets the preset requirement includes:

[0039] Calculate the mean absolute error MAPE of the grey prediction model,

[0040]

[0041] in, represents the predicted value calculated by the grey prediction model;

[0042] Determining whether the mean absolute error is less than or equal to a preset error;

[0043] If it is less than or equal to the preset error, it is determined that the prediction error meets the preset requirement.

[0044] Optionally, the depressive characteristics include: age, gender, education level, sadness, insomnia, memory loss, suicidal impulses, suicidal behavior, economic pressure, self-image, childhood trauma, anxiety, weight change, hypochondria, substance dependence, chronic disease, life interests, physical disease, nightmares, pessimism, failure experiences, warm feelings from family or friends, interest in social activities, fatigue, mental work blockage, concentration level, pleasure, and residential area. Some or all of the characteristics.

[0045] According to another aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned depression prediction methods based on the grey prediction model are implemented.

[0046] According to another aspect of the present invention, a computer program product is provided, which includes a computer program. When the computer program is executed by a processor, the computer program implements the steps of any one of the above-mentioned depression prediction methods based on the grey prediction model.

[0047] According to another aspect of the present invention, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement any of the steps of the above-mentioned depression prediction method based on the grey prediction model.

[0048] The technical solution of the present invention, by establishing a grey prediction model based on a training data set of sample users and ensuring that the prediction error of the grey prediction model for the target user's historical diagnostic data meets preset requirements, realizes the use of the grey prediction model to accurately predict the future changes in the target user's depression level, thereby achieving the purpose of providing a diagnostic basis for early intervention or timely adjustment of intervention methods to achieve the best treatment effect.

[0049] Based on the following detailed description of specific embodiments of the present invention in conjunction with the accompanying drawings, those skilled in the art will become more aware of the above and other objects, advantages and features of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Hereinafter, some specific embodiments of the present invention will be described in detail in an exemplary and non-limiting manner with reference to the accompanying drawings. The same reference numerals in the accompanying drawings indicate the same or similar components or parts. It should be understood by those skilled in the art that these drawings are not necessarily drawn to scale. In the accompanying drawings:

[0051] Figure 1 is a schematic flow chart of a depression prediction method based on a grey prediction model according to an embodiment of the present invention;

[0052] Figure 2 is a schematic flow chart of constructing a grey prediction model in a depression prediction method according to an embodiment of the present invention;

[0053] Figure 3 is a schematic flow chart of obtaining weight coefficients of depression features in a depression prediction method according to an embodiment of the present invention;

[0054] Figure 4 is a schematic flow chart of obtaining depression scores of sampled users according to a depression prediction method according to another embodiment of the present invention;

[0055] Figure 5 is a schematic flow chart of obtaining a grey prediction model in a depression prediction method according to another embodiment of the present invention;

[0056] Figure 6 is a schematic flow chart of determining a preset error of a grey prediction model according to a depression prediction method according to another embodiment of the present invention;

[0057] Figure 7 is a schematic diagram of a computer program product according to one embodiment of the present invention;

[0058] Figure 8 is a schematic diagram of a computer-readable storage medium according to one embodiment of the present invention; and

[0059] Figure 9 is a schematic diagram of a computer device according to one embodiment of the present invention. DETAILED DESCRIPTION

[0060] Refer to the following Figures 1 to 9 To describe a depression prediction method and related products based on a grey prediction model according to an embodiment of the present invention. In the description of this embodiment, it should be understood that the terms "first" and "second" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, the features defined as "first" and "second" may explicitly or implicitly include at least one such feature, that is, include one or more such features. In the description of the present invention, the meaning of "multiple" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined. When a feature "includes or contains" one or some of the features it covers, unless otherwise specifically described, this indicates that other features are not excluded and may further include other features.

[0061] See also Figure 1 , Figure 1 FIG. 1 is a schematic flow chart of a depression prediction method using a grey prediction model according to an embodiment of the present invention. The method may generally include:

[0062] S100, obtaining a gray prediction model based on gray system theory, the gray prediction model being used to predict the future depression level score of the sample user based on multiple sets of historical diagnostic data of the sample user; the diagnostic data of the sample user including the results of a depression assessment scale and depression level score obtained by the sample user during a diagnosis;

[0063] S200, obtaining multiple sets of historical diagnostic data and current diagnostic data of a target user; the diagnostic data of the target user includes the results of a depression assessment scale and a depression severity score obtained by the target user in a diagnosis;

[0064] S300, substituting multiple sets of historical diagnosis data and current diagnosis data of the target user into the grey prediction model, and calculating the prediction error of the grey prediction model;

[0065] S400 , in response to the prediction error meeting a preset requirement, predicting the target user's future depression level score based on multiple groups of historical diagnosis data of the target user, the target user's current diagnosis data, and a grey prediction model.

[0066] In this embodiment, the sample user may be composed of multiple sample users, and the sample users may be selected from existing depression patients using statistical methods. For example, 50 sample users may be obtained to form the sample user group, so as to cover as many stages of depression development as possible (corresponding to their depression severity scores), thereby being able to comprehensively reflect the intrinsic relationship between the results of the depression assessment scale and the depression severity scores, and between different depression severity scores.

[0067] Depression assessment scales are a commonly used method for screening patients for depression. The results of depression assessment scales can reflect the depressive state of patients with depression. Depression assessment scales are usually in the form of questionnaires that include multiple depressive characteristics. For example, depressive characteristics are selected from aspects such as self-evaluation, psychological state, social support, physiological signs, and living environment. Depressive characteristics include but are not limited to: age, gender, education level, sadness, insomnia, memory loss, suicidal impulses, suicidal behavior, financial pressure, self-image, childhood trauma, anxiety, weight change, hypochondriasis, substance dependence, chronic disease, life interests, physical illness, nightmares, pessimism, experience of failure, warmth from family or friends, interest in social activities, fatigue, mental work blockage, concentration level, pleasure, and residential area, etc. Depressive characteristics are embedded in the questionnaire, and test-takers are asked to answer the questionnaire and obtain scores for each depressive characteristic. The results of the depression assessment scale are the scores for each depressive characteristic. After completing the depression assessment scale, each sampled user needs to use expert scoring to obtain his or her depression level score, and use the depression assessment scale results and corresponding depression level scores of each sampled user as a set of historical diagnostic data.

[0068] Next, multiple sets of historical diagnostic data of sample users can be used to form a training data set. For example, the training data set includes 50 sets of historical diagnostic data, and the depression assessment scale includes 28 depression features. Each depression feature can be represented by a numerical value. The results of each set of depression assessment scales can be expressed as:

[0069] X i =[x i,1 ,x i,2 …x i,28 ],

[0070] Among them, X irepresents the depression rating scale of group i, x i,1 represents the depression feature with sequence number 1 in the depression assessment table of group i, x i,2 represents the depression feature of number 2 in the depression assessment table of group i, and so on, x i,28 represents the depression feature of the 28th group in the depression assessment scale. The results of the 50 groups of depression assessment scales can be expressed as:

[0071]

[0072] Where X represents the set of results of 50 depression rating scales. In addition, the results of each depression rating scale X i Each corresponds to a depression score Y, then

[0073] Y=[y1,y2…y 50 ] T

[0074] Among them, y1 represents the depression severity score corresponding to the first group of depression assessment scales, y2 represents the depression severity score corresponding to the second group of depression assessment scales, and so on. In order to make the depression severity score Y represent the progression of depression, the depression severity scores can be arranged in ascending order, that is, in the matrix, from top to bottom, the depression severity scores are arranged in ascending order. X and Y i Can form a training data set Y, that is

[0075]

[0076] Next, we can build a grey prediction model based on the existing grey system theory, which will not be described here. The grey prediction model can predict the depression level scores corresponding to the next set of depression assessment scales based on the training data set Y, for example, y 51 .

[0077] After the gray prediction model is constructed, the depression score of the target user (i.e., the target patient) can be predicted based on the gray prediction model, thereby providing a diagnostic basis for early intervention or timely adjustment of intervention methods to achieve the best treatment effect. Specifically, multiple sets of historical diagnostic data of the target user can be obtained first. Each set of historical diagnostic data includes the results of the depression assessment scale and depression score obtained by the target user in a diagnosis. The more sets of historical diagnostic data, the better. In actual use, the target user should have no less than 3 sets of historical diagnostic data.

[0078] Next, it is necessary to verify whether the gray prediction model is applicable to the historical diagnostic data of the target user. Specifically, the historical diagnostic data of the target user is input into the gray prediction model, that is, a training data set Y based on the target user is formed, and then based on the existing gray system theory, the prediction error of the gray prediction model when applied to the target user is calculated. Specifically, the gray prediction model can be used to predict the historical depression score of the target user, and then the predicted historical depression score is compared with the actual historical depression score. For example, the mean absolute error is calculated. When the mean absolute error meets the preset requirements, such as being less than a certain preset value, it indicates that the gray prediction model is applicable to the target user, and the gray prediction model can be used to accurately predict the future changes in the target user's depression level, thereby providing a diagnostic basis for early intervention or timely adjustment of the intervention method to achieve the best treatment effect. If the prediction error does not meet the preset requirements, it is necessary to add the training data set Y of the target user to the training data set Y based on the sample user, perform the calculation again, and update the various parameters of the gray prediction model until the prediction error does not meet the preset requirements.

[0079] In this embodiment, by establishing a gray prediction model based on a training data set of sample users, and ensuring that the prediction error of the gray prediction model for the historical diagnostic data of the target user meets the preset requirements, the gray prediction model is used to accurately predict the future changes in the depression level of the target user, thereby achieving the purpose of providing a diagnostic basis for early intervention or timely adjustment of the intervention method to achieve the best treatment effect.

[0080] In some embodiments of the depression prediction method of the present invention, Figure 2 As shown, the grey prediction model based on grey system theory is obtained, including:

[0081] S111, obtaining a depression assessment scale and a weight coefficient of each depression characteristic in the depression assessment scale;

[0082] S113, obtaining multiple sets of historical diagnostic data of sample users;

[0083] S115, weighting the values ​​of each depression feature in the depression assessment scale results of each set of historical diagnostic data of the sample user according to each weight coefficient, to obtain multiple sets of weighted historical diagnostic data of the sample user;

[0084] S117, constructing a grey prediction model based on grey system theory according to multiple groups of weighted historical diagnostic data of sample users.

[0085] In this embodiment, by weighting the various depression characteristics in the depression assessment table, the training data set can more accurately reflect the depression status of the sample users, thereby improving the prediction accuracy of the gray prediction model. Specifically, the weight coefficients of the 28 depression characteristics in the depression assessment table can be scored by expert scoring, and 28 weight coefficients w i , where i represents the sequence number of each depressive trait, w i Represents the weight coefficient of the depressive feature item with sequence number i.

[0086] Next, the weight coefficient can be used to modify the training data set Y of the sample user to obtain the weighted training data set Y w :

[0087]

[0088] Furthermore, the above formula can also be expressed as follows based on the grey system theory:

[0089]

[0090] in, Indicates the depression level score in the first group of historical diagnostic data of sample users that have not been accumulated. Indicates the depression feature score of sequence number 1 in the first group of historical diagnostic data of the sample user that has not been accumulated. It represents the depression feature score of the sample user with sequence number 28 in the 50th group of historical diagnosis data for which no accumulation is performed, and so on.

[0091] After getting the weight training data set Y w Then, the grey prediction model can be constructed according to the existing grey system theory. Referring to the previous embodiment, the data at each position in the training data set Y is replaced with the weighted training data set Y. w The corresponding data in is sufficient and will not be elaborated here. Since the weight coefficient of depression characteristics is taken into account, this grey prediction model can more accurately predict the depression degree score corresponding to the next set of depression assessment scales.

[0092] In some embodiments of the depression prediction method of the present invention, Figure 3 As shown in FIG, the steps for obtaining the weight coefficients of each depression characteristic in the depression assessment table include:

[0093] S121, using the expert scoring method, invite multiple experts (for example, 20) to weight the depression characteristics in the depression assessment table to obtain the corresponding initial weight coefficients Where i = 1, 2, ..., 28, i represents the serial number of each depressive characteristic, j = 1, 2, ..., 20, j represents the serial number of the expert;

[0094] S123, according to the following formula, obtain the average initial weight coefficient of each depression feature:

[0095]

[0096] in, represents the average initial weight coefficient of the depression feature with sequence number i;

[0097] S125, normalizing the average initial weight coefficient of each depression feature according to the following formula to obtain the weight coefficient of each depression feature:

[0098]

[0099] Among them, w i Represents the weight coefficient of the depression feature with sequence number i.

[0100] In this embodiment, multiple experts are used to score and the average initial weight coefficient is obtained so that the weight training data set Y w It can more accurately reflect the depression state of the sampled users, thereby improving the accuracy of the grey prediction model.

[0101] In some embodiments of the depression prediction method of the present invention, Figure 4 As shown, the method of obtaining multiple sets of historical diagnostic data of sample users includes:

[0102] S131, obtaining results of a depression assessment scale for a plurality of sampled users, where the plurality of sampled users constitutes a sample user, and the number of sampled users is greater than the number of items of depression characteristics in the depression assessment scale;

[0103] S133, using an expert scoring method, inviting multiple experts (e.g., 20) to score the depression level of each sampled user, and obtaining an initial depression level score corresponding to the result of the depression assessment scale of each sampled user;

[0104] S135 , taking the average of the initial depression scores of each sampled user as the depression score of the sampled user.

[0105] In this embodiment, 20 experts are invited to score the depression level of each sampled user, and the average of the scores of the 20 experts is used as the depression level score Y = [y1, y2…y 50 ] T The final value of each data in the weight training data set Y w It can more accurately reflect the actual depression level of the sampled users and the depression development level of the sampled users, thereby improving the accuracy of the grey prediction model.

[0106] In some embodiments of the depression prediction method of the present invention, Figure 5 As shown, the grey prediction model based on grey system theory is constructed based on multiple groups of weighted historical diagnostic data of sample users, including:

[0107] S141, obtain multiple groups of weighted historical diagnostic data of sample users as training data group Y w , and expressed in matrix form:

[0108]

[0109] Among them, y w1,1 represents the depression score in the first group of weighted historical diagnostic data, y w1,2 represents the weighted value of the depression feature with sequence number 1 in the first group of weighted historical diagnostic data, y w1,29 represents the weighted value of the depression feature numbered 28 in the first group of weighted historical diagnostic data, y w50,1 represents the depression score in the 50th group of weighted historical diagnostic data, y w50,2 represents the weighted value of the depression feature with sequence number 1 in the 50th set of weighted historical diagnostic data, y w50,29 represents the weighted value of the depression feature numbered 28 in the 50th set of weighted historical diagnostic data;

[0110] S143, training data set Y w The data of each column in is regarded as a sequence, and the data of each sequence is accumulated once to obtain an accumulated data set. And expressed in matrix form:

[0111]

[0112] S145, based on the grey system theory, we get

[0113]

[0114] Among them, k represents a cumulative data group The kth row in the matrix, a,b2,…,b 29 is the undetermined coefficient,

[0115] S147, calculate the undetermined coefficient matrix using the least squares method Get the grey prediction model.

[0116] In this embodiment, the least squares method can be used to obtain the undetermined coefficient matrix The values ​​of the coefficients are:

[0117]

[0118] in,

[0119]

[0120] Next, there are

[0121]

[0122] Undetermined coefficient matrix The values ​​of each coefficient can reflect the training data set Y w The intrinsic correlation between the data in the model can accurately predict the future depression score.

[0123] In some embodiments of the depression prediction method of the present invention, Figure 6 As shown, the steps of determining whether the prediction error meets the preset requirements include:

[0124] S411, calculate the mean absolute error MAPE of the grey prediction model,

[0125]

[0126] in, represents the predicted value calculated by the grey prediction model, n represents the total number of depressive characteristics, and k represents the kth group in the historical diagnostic data;

[0127] S413, determining whether the mean absolute error is less than or equal to a preset error;

[0128] S415: If the error is less than or equal to the preset error, it is determined that the prediction error meets the preset requirement.

[0129] The mean absolute error can accurately reflect the prediction error of the gray prediction model. In this embodiment, the preset error can be set to 0.1. When the mean absolute error MAPE is less than or equal to 0.1, it indicates that the gray prediction model is suitable for the target user, and the gray prediction model can be used to accurately predict the changes in the target user's depression level in the future, thereby providing a diagnostic basis for early intervention or timely adjustment of the intervention method to achieve the best treatment effect. If the mean absolute error MAPE is greater than 0.1, it indicates that the prediction error does not meet the preset requirements, and it is necessary to add the training data set of the target user to the training data set based on the sample user, calculate again, and update the various parameters of the gray prediction model until the prediction error meets the preset requirements.

[0130] In some embodiments of the depression prediction method of the present invention, depression characteristics include: age, gender, education level, sadness, insomnia, memory loss, suicidal impulse, suicidal behavior, economic pressure, self-image, childhood trauma, anxiety, weight change, hypochondria, substance dependence, chronic disease, life interests, physical disease, nightmares, pessimism, failure experience, warm feelings from family or friends, interest in social activities, fatigue, mental work blockage, concentration level, pleasure, and residential area. Some or all of the characteristics.

[0131] In actual use, the system first scores the target user based on 28 depression characteristics, including self-evaluation, psychological state, social support, physiological signs, and living environment. Doctors then use their experience and the scale to determine the current depression state and use the mean absolute error of the grey prediction model to determine whether the grey prediction model needs to be recalibrated. If recalibration is not necessary, the system further assesses the patient's depression level based on the current diagnostic data and the grey prediction model's prediction of the next stage of depression. This is then used to evaluate the effectiveness of the current treatment plan, achieving efficient, personalized, and precise treatment. This system can be used to follow up depressed patients individually or be integrated into a depression treatment system to evaluate the effectiveness of treatment plans, resulting in significant social and economic benefits.

[0132] The flowchart provided in this embodiment is not intended to indicate that the operations of the method will be performed in any particular order, or that all operations of the method are included in all every case. In addition, the method may include additional operations. Within the scope of the technical ideas provided by the method of this embodiment, additional changes can be made to the above method.

[0133] It should be understood that in some embodiments, each part can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system.

[0134] The embodiment of the present invention further provides a computer program product 10 , a computer-readable storage medium 20 , and a computer device 30 . Figure 7 is a schematic diagram of a computer program product 10 according to one embodiment of the present invention, Figure 8 is a schematic diagram of a computer-readable storage medium 20 according to one embodiment of the present invention, Figure 9is a schematic diagram of a computer device 30 according to one embodiment of the present invention. A computer program product 10 includes a computer program 11. When executed by a processor 32, this computer program 11 implements the steps of any of the above-described depression prediction methods. A computer-readable storage medium 20 stores the computer program 11. When executed by the processor 32, this computer program 11 implements the steps of any of the above-described depression prediction methods. The computer device 30 may include a memory 31, a processor 32, and the computer program 11 stored in the memory 31 and executed by the processor 32.

[0135] The computer program 11 for performing the operations of the present invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, configuration data for an integrated circuit, or source code or object code written in any combination of one or more programming languages ​​and procedural programming languages. The computer program 11 may be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter case, the remote computer may be connected to the user's computer via any type of network (including a local area network (LAN) or a wide area network (WAN)), or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, to perform various aspects of the present invention, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may execute computer-readable program instructions by utilizing state information of the computer-readable program instructions to personalize the electronic circuit.

[0136] In the description of this embodiment, the computer program product 10 is a related product including the computer program 11 .

[0137] For the purposes of the description of this embodiment, the computer-readable storage medium 20 is a tangible device capable of retaining and storing the computer program 11, and can be any device that can contain, store, communicate, propagate, or transmit the computer program 11 for use by or in conjunction with an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable storage medium 20 include the following: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, and any suitable combination of the foregoing.

[0138] The computer device 30 can be, for example, a server, a desktop computer, a laptop computer, a tablet computer, or a smartphone. In some examples, the computer device 30 can be a cloud computing node. The computer device 30 can be described in the general context of computer system executable instructions (such as program modules) executed by a computer system. Generally, program modules can include routines, programs, object programs, components, logic, data structures, etc. that perform specific tasks or implement specific abstract data types. The computer device 30 can be implemented in a distributed cloud computing environment where remote processing devices linked via a communication network perform tasks. In a distributed cloud computing environment, program modules can be located on local or remote computing system storage media, including storage devices.

[0139] The computer device 30 may include a processor 32 adapted to execute stored instructions, and a memory 31 that provides temporary storage for the instructions during operation. The processor 32 may be a single-core processor, a multi-core processor, a computing cluster, or any number of other configurations. The memory 31 may include random access memory (RAM), read-only memory, flash memory, or any other suitable storage system.

[0140] The computer device 30 may also include a network adapter / interface and an input / output (I / O) interface. The I / O interface allows data to be input and output with external devices that can be connected to the computer device. The network adapter / interface can provide communication between the computer device and a network, which is generally shown as a communication network.

[0141] At this point, those skilled in the art will recognize that, although a number of exemplary embodiments of the present invention have been shown and described in detail herein, many other variations or modifications consistent with the principles of the present invention may be directly determined or derived from the disclosure of the present invention without departing from the spirit and scope of the present invention. Therefore, the scope of the present invention should be understood and deemed to cover all such other variations or modifications.

Claims

1. A depression prediction method based on a grey prediction model, characterized in that: include: Obtaining a grey prediction model based on grey system theory, the grey prediction model being used to predict a future depression score of a sample user based on multiple sets of historical diagnostic data of the sample user, wherein the diagnostic data of the sample user includes a result of a depression assessment scale and a depression score obtained by the sample user during a diagnosis; Acquiring multiple sets of historical diagnostic data and current diagnostic data of a target user; the diagnostic data of the target user includes the results of the depression assessment scale and the depression severity score obtained by the target user in a diagnosis; Substituting multiple groups of historical diagnosis data and current diagnosis data of the target user into the grey prediction model, and calculating the prediction error of the grey prediction model; In response to the prediction error meeting a preset requirement, the future depression level score of the target user is predicted based on the multiple groups of historical diagnosis data of the target user, the current diagnosis data of the target user, and the grey prediction model.

2. The depression prediction method according to claim 1, characterized in that The grey prediction model based on grey system theory is obtained, including: Obtaining the depression assessment scale and the weight coefficient of each depression characteristic in the depression assessment scale; Acquire multiple groups of historical diagnostic data of the sample users; weighting the values ​​of the depression characteristics in the results of the depression assessment scale for each set of historical diagnostic data of the sample user according to the weight coefficients to obtain multiple sets of weighted historical diagnostic data of the sample user; According to the multiple groups of weighted historical diagnostic data of the sample users, the grey prediction model based on the grey system theory is constructed.

3. The depression prediction method according to claim 2, characterized in that The step of obtaining the weight coefficient of each depression characteristic in the depression assessment table includes: Using the expert scoring method, invite multiple experts to weight the depression characteristics in the depression assessment table to obtain the corresponding initial weight coefficients. Wherein, i=1, 2, ..., n, i represents the serial number of each depressive feature, j=1, 2, ..., m, j represents the serial number of the expert; The average initial weight coefficient of each depressive trait is obtained according to the following formula: in, The average initial weight coefficient representing the depression feature with sequence number i; The average initial weight coefficient of each depression feature is normalized according to the following formula to obtain the weight coefficient of each depression feature: Among them, w i The weight coefficient of the depression feature with sequence number i is represented.

4. The depression prediction method according to claim 2, characterized in that The step of obtaining multiple sets of historical diagnostic data of the sample users includes: Obtaining results of the depression assessment scale for a plurality of sampled users, where the plurality of sampled users constitute the sample user, and the number of the sampled users is greater than the number of items of depression characteristics in the depression assessment scale; Inviting multiple experts to score the depression level of each of the sampled users using an expert scoring method to obtain an initial depression level score corresponding to the result of the depression assessment scale of each of the sampled users; The average of the initial depression level scores of each of the sampled users is used as the depression level score of the sampled user.

5. The depression prediction method according to claim 2, characterized in that The grey prediction model based on the grey system theory is constructed according to the multiple groups of weighted historical diagnostic data of the sample users, including: Obtain multiple sets of weighted historical diagnostic data of the sample users as training data set Y w , and expressed in matrix form: Among them, y w1,1 represents the depression severity score in the first set of weighted historical diagnostic data, y w1,2 represents the weighted value of the depression feature with sequence number 1 in the first group of weighted historical diagnostic data, y w1,n represents the weighted value of the depression feature numbered n-1 in the first group of weighted historical diagnostic data, y wm,1 represents the depression score in the mth group of weighted historical diagnostic data, y wm,2 represents the weighted value of the depression feature with sequence number 1 in the mth group of weighted historical diagnostic data, y wm,n represents the weighted value of the depression feature with sequence number n-1 in the mth group of weighted historical diagnostic data; The training data set Y w The data of each column in is regarded as a sequence, and the data of each sequence is accumulated once to obtain an accumulated data set. And expressed in matrix form: Based on the grey system theory, we get Among them, k represents a cumulative data group The kth row in the matrix, a,b2,…,b n is the undetermined coefficient, Calculate the matrix of unknown coefficients using the least squares method The grey prediction model is obtained.

6. The depression prediction method according to claim 5, characterized in that: The step of determining whether the prediction error meets the preset requirement includes: Calculate the mean absolute error MAPE of the grey prediction model, in, represents the predicted value calculated by the grey prediction model; Determining whether the mean absolute error is less than or equal to a preset error; If it is less than or equal to the preset error, it is determined that the prediction error meets the preset requirement.

7. The depression prediction method according to claim 2, characterized in that: The depressive characteristics include: age, gender, education level, sadness, insomnia, memory loss, suicidal impulses, suicidal behavior, financial pressure, self-image, childhood trauma, anxiety, weight change, hypochondria, substance dependence, chronic disease, life interests, physical disease, nightmares, pessimism, failure experiences, warm feelings from family or friends, interest in social activities, fatigue, mental work blockage, concentration level, pleasure, and residential area. Some or all of the characteristics.

8. A computer-readable storage medium, characterized in that A computer program is stored thereon, and when the computer program is executed by a processor, the steps of the depression prediction method based on the grey prediction model as claimed in any one of claims 1 to 7 are implemented.

9. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the depression prediction method based on the grey prediction model as claimed in any one of claims 1 to 7 are implemented.

10. A computer device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the depression prediction method based on the grey prediction model according to any one of claims 1 to 7.

Images