Infectious disease epidemic prediction method and device, storage medium, and electronic device

Abstract

The embodiment of the present invention relates to a method and device for predicting an infectious disease epidemic, a storage medium, and an electronic device, and relates to the field of medical big data processing technology. The method includes obtaining known medical data; wherein the known medical data includes the number of suspected cases, the number of confirmed cases, and the number of removed cases in a specific area at multiple times; constructing multiple functional relationships between the number of suspected cases, the number of confirmed cases, and the number of removed cases based on dynamic equations, and calculating parameter values of multiple parameters included in each functional relationship based on the known medical data and each functional relationship; and predicting the number of confirmed cases of the infectious disease in a future time period based on each parameter value and each functional relationship. The embodiment of the present invention improves the accuracy of the predicted number of confirmed cases.

Description

[0001] Cross-references

[0002] This case is based on the parent case with application number: 202010224851.X, application date: March 26, 2020, invention name: Titled: Divisional application for infectious disease epidemic prediction method and device, storage medium, and electronic device. Technical Field

[0003] The embodiments of the present invention relate to the technical field of medical big data processing, and specifically, to a method for predicting an infectious disease epidemic, an infectious disease epidemic prediction device, a computer-readable storage medium, and an electronic device. Background Art

[0004] Epidemics have always been a major threat to human health and life safety. For infectious disease emergencies, only by early detection and timely warning can we buy time to implement various response measures, nip the incident in the bud, and minimize the harm of the incident.

[0005] Among the existing infectious disease epidemic prediction methods, predictions are mainly made through the following two methods: one is through the experience and intuition of experts in the field of epidemiology; the other is based on the existing transmission dynamics model.

[0006] However, the above method has the following defects: on the one hand, empirical prediction is particularly dependent on the level of experts, the prediction results lack scientific basis and have poor interpretability; on the other hand, traditional transmission dynamics models make various assumptions when modeling, such as assuming there is no incubation period, or assuming that the incubation period is not contagious. These assumptions are not valid in some epidemics, and therefore will lead to lower accuracy of the prediction results.

[0007] Therefore, there is a need to provide a new method for predicting infectious disease epidemics.

[0008] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present invention, and therefore may include information that does not constitute prior art known to ordinary technicians in this field. Summary of the Invention

[0009] The purpose of the present invention is to provide an infectious disease epidemic prediction method, an infectious disease epidemic prediction device, a computer-readable storage medium and an electronic device, thereby at least to a certain extent overcoming the problem of low accuracy of prediction results caused by the limitations and defects of related technologies.

[0010] According to one aspect of the present disclosure, a method for predicting an infectious disease epidemic is provided, comprising:

[0011] Obtaining known medical data; wherein the known medical data includes the number of suspected cases, confirmed cases, and removed cases in a specific area at multiple times;

[0012] Constructing multiple functional relationships between the number of suspected cases and the number of confirmed cases, and between the number of confirmed cases and the number of removed cases based on kinetic equations;

[0013] Calculating parameter values of multiple parameters included in each functional relationship based on the known medical data and each functional relationship; wherein the parameters include the proportion of true virus carriers among the number of suspected cases, the average number of daily contacts between latent patients and healthy people, the average transmission probability per contact between latent patients and healthy people, the average number of daily contacts between confirmed patients and healthy people, the average transmission probability between confirmed patients and healthy people, the average number of days in the incubation period, and the average number of days for confirmed patients to be discharged;

[0014] Based on the parameter values and the functional relationships, the number of confirmed cases of the infectious disease in a future time period is predicted.

[0015] In an exemplary embodiment of the present disclosure, constructing multiple functional relationships between the number of suspected cases and the number of confirmed cases, and the number of confirmed cases and the number of removed cases based on the kinetic equation includes:

[0016]

[0017] Among them, E(t) is the number of suspected cases at time t; I(t) is the number of confirmed cases at time t; R(t) is the number of people removed at time t; p is the proportion of true virus carriers among the number of suspected cases at time t; k1 is the average number of daily contacts between latent cases and normal people at time t; b1 is the average probability of transmission between latent cases and normal people at time t; k2 is the average number of daily contacts between confirmed patients at time t; b2 is the average probability of transmission between confirmed patients and normal people at time t; T1 is the average number of days in the incubation period; T2 is the average number of days for confirmed patients to be removed at time t.

[0018] In an exemplary embodiment of the present disclosure, calculating the values of the multiple parameters included in each of the functional relationships according to the known medical data and each of the functional relationships includes:

[0019] Discretize each of the functional relationships to obtain the relationship between the number of suspected cases, the relationship between the number of confirmed cases, and the relationship between the number of removed cases at two adjacent moments;

[0020] According to the relationship between the number of suspected cases, the relationship between the number of confirmed cases, and the relationship between the number of removed cases at two adjacent moments, multiple equations are obtained;

[0021] An objective function is constructed with the goal of minimizing the absolute value of the difference between both sides of each equation, and parameter values of multiple parameters included in each functional relationship are calculated based on the known medical data and the objective function.

[0022] In an exemplary embodiment of the present disclosure, constructing an objective function with the goal of minimizing the absolute value of the difference between the two sides of the equation includes:

[0023]

[0024] Among them, A1(t)=k1*b1*p;A2(t)=k2*b2;

[0025] In an exemplary embodiment of the present disclosure, calculating parameter values of the plurality of parameters included in each of the functional relationships according to the known medical data and the target function includes:

[0026] Based on the projected gradient descent and alternating minimum methods, parameter values of multiple parameters included in each of the functional relationships are calculated according to the known medical data and the objective function.

[0027] In an exemplary embodiment of the present disclosure, the infectious disease epidemic prediction method further includes:

[0028] Predicting the maximum number of confirmed cases of the infectious disease in a future time period based on the parameter values;

[0029] The turning point time of the infectious disease is predicted based on the time point corresponding to the maximum number of confirmed cases.

[0030] In an exemplary embodiment of the present disclosure, the infectious disease epidemic prediction method further includes:

[0031] Determine whether the growth rate of the number of confirmed cases is continuously zero within a preset time period; wherein the preset time period is not less than one week;

[0032] When it is determined that the growth rate of the number of confirmed cases is continuously zero within a preset time period, the total number of infected people of the epidemic is calculated based on the total number of confirmed cases of the infectious disease from the start time to the time when the growth rate is zero.

[0033] According to one aspect of the present disclosure, there is provided an infectious disease epidemic prediction device, comprising:

[0034] A medical data acquisition module is used to acquire known medical data; wherein the known medical data includes the number of suspected cases, confirmed cases, and removed cases in a specific area at multiple times;

[0035] A functional relationship construction module, for constructing multiple functional relationships between the number of suspected cases and the number of confirmed cases, and between the number of confirmed cases and the number of removed cases based on a dynamic equation;

[0036] a parameter value calculation module, configured to calculate parameter values of a plurality of parameters included in each of the functional relationships based on the known medical data and the functional relationships; wherein the parameters include the proportion of true virus carriers among the number of suspected cases, the average number of daily contacts between latent patients and healthy individuals, the average probability of transmission between latent patients and healthy individuals per contact, the average number of daily contacts between confirmed patients and healthy individuals, the average probability of transmission between confirmed patients and healthy individuals, the average number of days in the latent period, and the average number of days it takes for confirmed patients to be discharged;

[0037] The first prediction module is used to predict the number of confirmed cases of the infectious disease in a future time period based on the parameter values and the functional relationships.

[0038] According to one aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, it implements any one of the above-mentioned infectious disease epidemic prediction methods.

[0039] According to one aspect of the present disclosure, there is provided an electronic device, including:

[0040] processor; and

[0041] a memory for storing executable instructions of the processor;

[0042] Wherein, the processor is configured to execute any one of the above-mentioned infectious disease epidemic prediction methods by executing the executable instructions.

[0043] An embodiment of the present invention provides a method for predicting an infectious disease epidemic. On the one hand, by acquiring known medical data, multiple functional relationships between the number of suspected cases and the number of confirmed cases, as well as the number of confirmed cases and the number of removed cases, are constructed based on dynamic equations, and parameter values of multiple parameters included in each functional relationship are calculated based on the known medical data and each functional relationship; finally, based on each parameter value and each functional relationship, the number of suspected cases and the number of confirmed cases of the infectious disease in a future time period are predicted. This solves the problem in the prior art that empirical prediction is particularly dependent on the level of experts, the prediction results lack scientific basis, and have poor interpretability, and provides a method for predicting the number of confirmed cases of infectious diseases in a future time period. Scientific basis; on the other hand, it solves the problem in the existing technology that the traditional transmission dynamics model makes various assumptions when modeling, such as assuming that there is no incubation period, or assuming that the incubation period is not contagious, which are not valid in some epidemics, resulting in low accuracy of the prediction results, thereby improving the accuracy of the predicted number of confirmed cases; on the other hand, since the above-mentioned known medical data is the number of suspected cases, confirmed cases and removed people in a specific area at multiple times, the parameter values ​​calculated based on the known medical data of the specific area are more targeted, thereby improving the accuracy of the parameter values, and further improving the accuracy of the predicted number of confirmed cases.

[0044] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The accompanying drawings are incorporated into and constitute a part of this specification, illustrate embodiments consistent with the present invention, and together with the description, serve to explain the principles of the present invention. Obviously, the drawings described below are only some embodiments of the present invention, and it is clear that those skilled in the art can derive other drawings based on these drawings without inventive effort.

[0046] Figure 1 The following schematically shows a flow chart of a method for predicting an epidemic situation of an infectious disease according to an exemplary embodiment of the present invention.

[0047] Figure 2 A flowchart of a method for calculating parameter values of a plurality of parameters included in each functional relationship based on the known medical data and each functional relationship according to an exemplary embodiment of the present invention is schematically shown.

[0048] Figure 3 An example diagram of a prediction result obtained by using the above infectious disease epidemic prediction method according to an example embodiment of the present invention is schematically shown.

[0049] Figure 4Another example diagram of prediction results obtained by using the above infectious disease epidemic prediction method according to an example embodiment of the present invention is schematically shown.

[0050] Figure 5 A flowchart schematically illustrates another infectious disease epidemic prediction method according to an exemplary embodiment of the present invention.

[0051] Figure 6 A flowchart schematically illustrates another infectious disease epidemic prediction method according to an exemplary embodiment of the present invention.

[0052] Figure 7 A block diagram schematically illustrates an infectious disease epidemic prediction device according to an exemplary embodiment of the present invention.

[0053] Figure 8 An electronic device for implementing the above infectious disease epidemic prediction method according to an exemplary embodiment of the present invention is schematically shown. DETAILED DESCRIPTION

[0054] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the present invention will be more comprehensive and complete and the concepts of the example embodiments will be fully conveyed to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present invention. However, those skilled in the art will appreciate that the technical solutions of the present invention may be practiced while omitting one or more of the specific details, or that other methods, components, devices, steps, etc. may be employed. In other cases, well-known technical solutions are not shown or described in detail to avoid obscuring various aspects of the present invention.

[0055] In addition, the accompanying drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. Identical reference numerals in the figures denote identical or similar parts, and thus repetitive descriptions thereof will be omitted. Some of the blocks shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0056] This exemplary embodiment first provides an infectious disease epidemic prediction method, which can be run on a server, server cluster, or cloud server; of course, those skilled in the art can also run the method of the present invention on other platforms as needed, and this exemplary embodiment does not specifically limit this. Figure 1 As shown, the infectious disease epidemic prediction method may include the following steps:

[0057] Step S110. Obtain known medical data; wherein the known medical data includes the number of suspected cases, confirmed cases, and removed cases in a specific area at multiple times.

[0058] Step S120: constructing multiple functional relationships between the number of suspected cases and the number of confirmed cases, and the number of confirmed cases and the number of removed cases based on the kinetic equation;

[0059] Step S130. Calculate the parameter values of multiple parameters included in each functional relationship based on the known medical data and each functional relationship; wherein the parameters include the proportion of true virus carriers among the number of suspected cases, the average number of times a latent case contacts normal people per day, the average probability of transmission between a latent case and a normal person per contact, the average number of times a confirmed patient contacts people per day, the average probability of transmission between a confirmed patient and a normal person, the average number of days of the latent period, and the average number of days for confirmed patients to be removed.

[0060] Step S140: Based on the parameter values and the functional relationships, predict the number of confirmed cases of the infectious disease in a future time period.

[0061] In the above infectious disease epidemic prediction method, on the one hand, by obtaining known medical data, multiple functional relationships between the number of suspected cases and the number of confirmed cases, as well as the number of confirmed cases and the number of removed cases, are constructed based on dynamic equations, and the parameter values of multiple parameters included in each functional relationship are calculated based on the known medical data and each functional relationship; finally, based on each parameter value and each functional relationship, the number of suspected cases and the number of confirmed cases of infectious diseases in the future time period are predicted, which solves the problem in the existing technology that the prediction through experience is particularly dependent on the level of experts, the prediction results lack scientific basis, and the interpretability is poor, and provides a scientific basis for the prediction of the number of confirmed cases of infectious diseases in the future time period. On the other hand, it solves the problem in the existing technology that the traditional transmission dynamics model makes various assumptions when modeling, such as assuming that there is no incubation period, or assuming that the incubation period is not contagious. These assumptions are not valid in some epidemics, which will lead to low accuracy of the prediction results, thereby improving the accuracy of the predicted number of confirmed cases; on the other hand, since the above-mentioned known medical data are the number of suspected cases, confirmed cases and removed people in a specific area at multiple times, the parameter values of each parameter calculated based on the known medical data of the specific area are more targeted, thereby improving the accuracy of the parameter values, and further improving the accuracy of the predicted number of confirmed cases.

[0062] Hereinafter, each step involved in the infectious disease epidemic prediction method according to an exemplary embodiment of the present invention will be explained and illustrated in detail with reference to the accompanying drawings.

[0063] First, the dynamic models involved in the exemplary embodiments of the present invention are explained and illustrated. Specifically, dynamic models, also known as infectious disease models, are basic mathematical models of infectious diseases. They study issues such as the spread rate, spatial range, transmission pathways, and dynamic mechanisms of infectious diseases to guide effective prevention and control of infectious diseases. Common infectious disease models are categorized by infectious disease type, including SI, SIR, SIRS, and SEIR models. These models are further categorized by transmission mechanism, based on ordinary differential equations, partial differential equations, and network dynamics.

[0064] Generally speaking, people affected by an infectious disease are divided into the following categories:

[0065] Category S, Susceptible, refers to people who are not sick but lack immunity and are easily infected after contact with infected people;

[0066] Category E, Exposed, latent state, suspected case, refers to people who have been in contact with infected people but are temporarily unable to infect others. It is applicable to infectious diseases with a long incubation period;

[0067] Category I, Infectious, refers to people who are infected with infectious diseases and can spread them to Category S members, turning them into Category E or Category I members;

[0068] R category, or recovered, refers to people who have been isolated or are immune due to recovery from an illness. If the immunity period is limited, R category members can return to S category.

[0069] The differential equations of the traditional SEIR model for the changes in the number of the above four groups are:

[0070]

[0071] Among them, β is the infection rate, γ is the recovery rate, α is the rate at which the latent period develops into a patient, and N is the total number of people in the infected area.

[0072] However, the parameters included in this model do not include the infectious ability of the virus carrier E population, so the accuracy of the final prediction results will be low.

[0073] Hereinafter, steps S110 to S130 will be explained and illustrated in conjunction with the above-mentioned infectious disease model.

[0074] In step S110, known medical data is obtained; wherein the known medical data includes the number of suspected cases, confirmed cases, and removed cases in a specific area at multiple times.

[0075] In this example embodiment, since the epidemic situation in each region is not consistent, such as the number of infected people and the total number of people are different, in order to improve the accuracy of the calculated parameters, it is necessary to actively calculate the parameters involved with the number of suspected cases, confirmed cases, and removed people in a specific region at multiple times; wherein, the specific region may include areas with sick people, that is, infected areas or outbreak areas; the removed people include the number of cured people and the number of deaths. Specifically, the known medical data can be obtained based on the public data of each region published by the National Health Commission every day.

[0076] In step S120, multiple functional relationships between the number of suspected cases and the number of confirmed cases, and between the number of confirmed cases and the number of removed cases are constructed based on the kinetic equation.

[0077] In step S130, parameter values of multiple parameters included in each functional relationship are calculated based on the known medical data and each functional relationship; wherein the parameters include the proportion of true virus carriers among the number of suspected cases, the average number of times a latent case contacts normal people per day, the average probability of transmission between a latent case and a normal person per contact, the average number of times a confirmed patient contacts people per day, the average probability of transmission between a confirmed patient and a normal person, the average number of days of the latent period, and the average number of days for confirmed patients to be removed.

[0078] Steps S120-S130 are explained and illustrated below. Specifically, in this exemplary embodiment, by adding the parameters of the average number of daily contacts between latent-period cases and healthy individuals and the average probability of transmission per contact between latent-period cases and healthy individuals, the problem of the prior art failing to consider the infectious capacity of the virus carrier population E, which results in a low accuracy rate in the final prediction results, can be resolved, thereby further improving the accuracy of the prediction results.

[0079] Furthermore, first, multiple functional relationships between the number of suspected cases and the number of confirmed cases, as well as the number of confirmed cases and the number of removed cases, are constructed based on the dynamic equations. Specifically, the following functional relationships may be constructed:

[0080]

[0081] Among them, S(t) represents the number of normal people at time t; E(t) represents the number of suspected cases at time t; I(t) represents the number of confirmed cases at time t; R(t) represents the number of people removed at time t; p represents the proportion of true virus carriers among the number of suspected cases at time t; k1 represents the average number of daily contacts between latent cases and normal people at time t; b1 represents the average probability of transmission between latent cases and normal people at time t; k2 represents the average number of daily contacts between confirmed patients at time t; b2 represents the average probability of transmission between confirmed patients and normal people at time t; T1 represents the average number of days in the incubation period; T2 represents the average number of days for confirmed patients to be removed at time t.

[0082] It should be noted that b1 and b2 are related to personal protection (such as wearing a mask, washing hands, etc.) and physical fitness, and b1 can be adaptively adjusted according to specific circumstances. At the same time, k2 is related to prevention and control policies and can also be adaptively adjusted according to specific circumstances. T2 is related to the supply of medical resources and can also be adaptively adjusted according to specific circumstances. Furthermore, in Formula 1, since the total number of normal people S in a normal group (such as the whole of China) far exceeds the number of infected people, the change in the number of normal people can be ignored, that is, Formula 1 can be ignored during calculation. Since the calculation of Formula (1) is omitted, the calculation efficiency of the parameters can be further improved.

[0083] Furthermore, after obtaining the above multiple functional relationships, it is necessary to calculate the parameter values of the multiple parameters included in each functional relationship based on the known medical data and each functional relationship. Figure 2 As shown, calculating the parameter values of the multiple parameters included in each functional relationship based on the known medical data and each functional relationship may include steps S210 to S230.

[0084] In step S210, each of the functional relationships is discretized to obtain the relationship between the number of suspected cases, the relationship between the number of confirmed cases, and the relationship between the number of removed cases at two adjacent moments.

[0085] In step S220, multiple equations are obtained based on the relationship between the number of suspected cases, the relationship between the number of confirmed cases, and the relationship between the number of removed cases at two adjacent moments.

[0086] In step S230, an objective function is constructed with the goal of minimizing the absolute value of the difference between both sides of each equation, and parameter values of multiple parameters included in each functional relationship are calculated based on the known medical data and the objective function.

[0087] Below, steps S210 to S230 will be explained and illustrated. Specifically, since the differential equation description is continuous, the model can be simplified in units of days. In Formula 1, since the total number of normal people S in a normal group (such as the whole of China) far exceeds the number of infected people, the change in the number of normal people can be ignored, that is, Formula 1 can be ignored during the calculation.

[0088] Furthermore, after discretizing Formula 2, we can obtain the following Formula (5):

[0089]

[0090] Therefore, the number of suspected people at time t+1 can be expressed as follows:

[0091]

[0092] At the same time, after discretizing formula (3), we can get the following formula (7):

[0093]

[0094] Therefore, the number of confirmed cases at time t+1 can be expressed as follows:

[0095]

[0096] In addition, after discretizing formula (4), we can obtain the following formula (9):

[0097]

[0098] Therefore, the number of people moving out at time t+1 can be expressed as follows:

[0099]

[0100] It should be noted that since k1, b1, k2, b2, p, and T2 are all functions of time t, in order to simplify the formula and reduce the scale of variables, the following definitions can be made:

[0101] A1(t)=k1*b1*p; A2(t)=k2*b2;

[0102] Then formulas (6), (8) and (10) can be replaced by formulas (11), (12) and (13) as shown below:

[0103] E(t+1)=(A1(t)-A3(t)+1)*E(t)+A2(t)I(t); Formula (11)

[0104] I(t+1)=A3(t)E(t)+(1-A4(t))I(t); Formula (12)

[0105] R(t+1)=A4(t)I(t)+R(t); Formula (13)

[0106] From this, we can conclude that, after simplifying the formula, the number of people in the three groups at any time t+1 is a function of the number of people in the three groups at time t, with A1(t), A2(t), A3(t), and A4(t) as coefficients. Therefore, solving the above system of equations requires estimating the parameters of the four equations A1(t), A2(t), A3(t), and A4(t).

[0107] Furthermore, the above parameters can be estimated based on official public data (data released by the National Health Commission). The parameters of the above four equations A1(t), A2(t), A3(t), and A4(t) are all functions of the parameter t. Because polynomial functions can approximate any function expression, the above four parameters can be defined as follows:

[0108]

[0109] Therefore, the parameter estimation goal is to estimate λ based on public data. i,j According to optimization theory, the following objective function can be defined. The goal is to find the parameter combination that minimizes the total difference between formulas (11), (12), and (13). Here, the L1 distance (the absolute value of the difference between the two sides of the equation) can be used. The objective function can be shown as follows in formula (15):

[0110]

[0111] in:

[0112]

[0113] Among them, E(t) represents the number of suspected cases at time t; I(t) represents the number of confirmed cases at time t; R(t) represents the number of people removed at time t.

[0114] Furthermore, based on the official data, E(t) at time t can be taken as the number of suspected cases announced daily, I(t) as the number of confirmed cases announced daily, and R(t) as the number of deaths and cured cases announced daily. Time t is measured in days from the official release of the data to the present. It should be further explained that since this problem is a typical non-convex function optimization problem, heuristic methods (such as projected gradient descent and alternating minimization) can be used to estimate all parameters λ. i,j Parameter value.

[0115] In step S140, the number of confirmed cases of the infectious disease in a future time period is predicted based on the parameter values and the functional relationships.

[0116] In this exemplary embodiment, when all parameters λ are obtained i,j After the parameter values are determined, the number of suspected cases and confirmed cases of infectious diseases in the future period of time can be predicted based on the parameter values and functional relationships.

[0117] For example, after the parameter estimation is completed, the four equations A1(t), A2(t), A3(t), and A4(t) become functions that only depend on time t. Knowing E(t), I(t), and R(t) at time t, the specific number of people at time t+1 can be calculated by directly substituting them into the formula. Furthermore, by calculating E(t), I(t), and R(t) at any time, the number of confirmed cases in the next three days can be predicted. Specifically, it can be obtained directly by calculating the model values at times t+1, t+2, and t+3. Of course, the number of suspected cases can also be predicted, and this example does not impose any special restrictions on this. Furthermore, through this method, hospitals and other departments can make timely arrangements based on the number of confirmed cases to avoid further deterioration of the epidemic. Specifically, the example diagram of the prediction results can be referred to. Figure 3 as well as Figure 4 As shown. Among them, Figure 3 as well as Figure 4 Figure 2 shows example diagrams of predictions for two different regions using this prediction method, where the dotted line represents the predicted data and the circle represents the actual data. Figure 3 as well as Figure 4 The horizontal axis is time (days), and the vertical axis is the specific number of confirmed cases (individuals). Figure 3 as well as Figure 4 It can be seen that the predicted data and the actual data are basically consistent.

[0118] Figure 5 Another infectious disease epidemic prediction method according to an exemplary embodiment of the present invention is schematically shown. Figure 5 As shown, the infectious disease epidemic prediction method may further include step S510 and step S520.

[0119] In step S510, based on the parameter values, the maximum number of confirmed cases of the infectious disease in a future time period and the time point corresponding to the maximum value are determined.

[0120] In step S520, the turning point time of the infectious disease is predicted based on the time point corresponding to the maximum number of confirmed cases.

[0121] Steps S510 and S520 are explained and illustrated below. First, based on the estimated parameters, the model value for any future time can be iteratively calculated. The maximum number of confirmed cases I is then obtained based on the model value at each time. The time t corresponding to the maximum number of confirmed cases I is then used as the inflection point of the epidemic. Based on this inflection point, other departments can arrange the work and activities of other personnel to avoid further losses.

[0122] Figure 6 Another infectious disease epidemic prediction method according to an exemplary embodiment of the present invention is schematically shown. Figure 6 As shown, the infectious disease epidemic prediction method may further include step S610 and step S620.

[0123] In step S610, it is determined whether the growth rate of the number of confirmed cases is continuously zero within a preset time period; wherein, the preset time period is not less than one week.

[0124] In step S620, when it is determined that the growth rate of the number of confirmed cases is continuously zero within the preset time period, the total number of infected people of the epidemic is calculated based on the total number of confirmed cases of the infectious disease from the start time to the time when the growth rate is zero.

[0125] Below, step S610 and step S620 will be explained and illustrated. For example, as time t increases, the calculation model is iterated multiple times until the number of confirmed cases I increases to 0 for a week, and then the calculation can be stopped. Of course, it can also be stopped until the number of confirmed cases I increases to 0 for 10 days or half a month. This example does not impose any special restrictions on this. Then, the number of all confirmed cases from the start time to this moment is added up to obtain the total number of people infected by the epidemic. Through this method, the total number of confirmed cases during the entire epidemic period can be clearly calculated, and then a formal written report can be issued based on the total number of confirmed cases, and the written report can be displayed so that the public can read it.

[0126] The infectious disease epidemic prediction method provided by the example embodiment of the present invention, on the one hand, takes into account the infectious characteristics of the incubation period disease by optimizing the SIER model, thereby improving the accuracy of the prediction results; on the other hand, the recursive expression of the model is obtained by using the non-convex function optimization estimation method, reducing the scale of parameters requiring manual intervention, thereby improving the accuracy of the model; on the other hand, the SIER model takes into account the infectious characteristics of the incubation period and rewrites the differential equation of the dynamic model; the latent case data is replaced with suspected case data, which is more convenient for calculation; at the same time, the parameters of the differential equation of the degree model are integrated and simplified, thereby improving the calculation speed.

[0127] The exemplary embodiment of the present invention also provides an infectious disease epidemic prediction device. Figure 7 As shown, the infectious disease epidemic prediction device may include a medical data acquisition module 710, a function relationship construction module 720, a parameter value calculation module 730, and a first prediction module 740.

[0128] The medical data acquisition module 710 can be used to acquire known medical data; wherein the known medical data includes the number of suspected cases, confirmed cases, and removed cases in a specific area at multiple times.

[0129] The functional relationship construction module 720 can be used to construct multiple functional relationships between the number of suspected cases and the number of confirmed cases, and the number of confirmed cases and the number of removed cases based on dynamic equations.

[0130] The parameter value calculation module 730 can be used to calculate the parameter values of multiple parameters included in each functional relationship based on the known medical data and each functional relationship; wherein the parameters include the proportion of true virus carriers among the number of suspected cases, the average number of times a latent case contacts normal people per day, the average probability of transmission between a latent case and a normal person per contact, the average number of times a confirmed patient contacts people per day, the average probability of transmission between a confirmed patient and a normal person, the average number of days of the latent period, and the average number of days for confirmed patients to be removed.

[0131] The first prediction module 740 can be used to predict the number of confirmed cases of the infectious disease in a future time period based on the parameter values and the functional relationships.

[0132] In an exemplary embodiment of the present disclosure, constructing multiple functional relationships between the number of suspected cases and the number of confirmed cases, and the number of confirmed cases and the number of removed cases based on the kinetic equation includes:

[0133]

[0134] Among them, E(t) is the number of suspected cases at time t; I(t) is the number of confirmed cases at time t; R(t) is the number of people removed at time t; p is the proportion of true virus carriers among the number of suspected cases at time t; k1 is the average number of daily contacts between latent cases and normal people at time t; b1 is the average probability of transmission between latent cases and normal people at time t; k2 is the average number of daily contacts between confirmed patients at time t; b2 is the average probability of transmission between confirmed patients and normal people at time t; T1 is the average number of days in the incubation period; T2 is the average number of days for confirmed patients to be removed at time t.

[0135] In an exemplary embodiment of the present disclosure, calculating the values of the multiple parameters included in each of the functional relationships according to the known medical data and each of the functional relationships includes:

[0136] Discretize each of the functional relationships to obtain the relationship between the number of suspected cases, the relationship between the number of confirmed cases, and the relationship between the number of removed cases at two adjacent moments;

[0137] According to the relationship between the number of suspected cases, the relationship between the number of confirmed cases, and the relationship between the number of removed cases at two adjacent moments, multiple equations are obtained;

[0138] An objective function is constructed with the goal of minimizing the absolute value of the difference between both sides of each equation, and parameter values of multiple parameters included in each functional relationship are calculated based on the known medical data and the objective function.

[0139] In an exemplary embodiment of the present disclosure, constructing an objective function with the goal of minimizing the absolute value of the difference between the two sides of the equation includes:

[0140]

[0141]

[0142] Among them, A1(t)=k1*b1*p;A2(t)=k2*b2;

[0143] In an exemplary embodiment of the present disclosure, calculating parameter values of the plurality of parameters included in each of the functional relationships according to the known medical data and the target function includes:

[0144] Based on the projected gradient descent and alternating minimum methods, parameter values of multiple parameters included in each of the functional relationships are calculated according to the known medical data and the objective function.

[0145] In an exemplary embodiment of the present disclosure, the infectious disease epidemic prediction device further includes:

[0146] The second prediction module can be used to determine the maximum number of confirmed cases of the infectious disease in a future time period and the time point corresponding to the maximum value based on the parameter values;

[0147] The third prediction module can be used to predict the turning point time of the infectious disease based on the time point corresponding to the maximum number of confirmed cases.

[0148] In an exemplary embodiment of the present disclosure, the infectious disease epidemic prediction device further includes:

[0149] A judgment module may be used to judge whether the growth rate of the number of confirmed cases is continuously zero within a preset time period; wherein the preset time period is not less than one week;

[0150] The infected number calculation module can be used to calculate the total number of infected people of the epidemic based on the total number of confirmed cases of the infectious disease from the start time to the time when the growth rate of the confirmed number is continuously zero within a preset time period.

[0151] The specific details of each module in the above-mentioned infectious disease epidemic prediction device have been described in detail in the corresponding infectious disease epidemic prediction method, so they will not be repeated here.

[0152] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to an embodiment of the present invention, the features and functions of two or more modules or units described above can be concretized in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into multiple modules or units to be concretized.

[0153] Furthermore, although the steps of the method of the present invention are described in a particular order in the accompanying drawings, this does not require or imply that the steps must be performed in this particular order, or that all steps must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0154] In an exemplary embodiment of the present invention, an electronic device capable of implementing the above method is also provided.

[0155] Those skilled in the art will appreciate that various aspects of the present invention may be implemented as systems, methods, or program products. Therefore, various aspects of the present invention may be implemented in the following forms: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementations, which may be collectively referred to herein as "circuits," "modules," or "systems."

[0156] Refer to the following Figure 8 An electronic device 800 according to this embodiment of the present invention will be described. Figure 8 The electronic device 800 shown is merely an example and should not limit the functions and scope of use of the embodiments of the present invention.

[0157] like Figure 8As shown, electronic device 800 is implemented as a general-purpose computing device. Components of electronic device 800 may include, but are not limited to, the aforementioned at least one processing unit 810, the aforementioned at least one storage unit 820, a bus 830 connecting various system components (including storage unit 820 and processing unit 810), and a display unit 840.

[0158] The storage unit stores program codes that can be executed by the processing unit 810, so that the processing unit 810 performs the steps according to various exemplary embodiments of the present invention described in the "Exemplary Method" section above. For example, the processing unit 810 may perform the following steps: Figure 1 Step S110 shown in: obtaining known medical data; wherein the known medical data includes the number of suspected cases, the number of confirmed cases and the number of removed people in a specific area at multiple times; step S120: constructing multiple functional relationships between the number of suspected cases and the number of confirmed cases, and the number of confirmed cases and the number of removed people based on the dynamic equation; step S130: calculating the parameter values of multiple parameters included in each functional relationship according to the known medical data and each functional relationship; wherein the parameters include the proportion of true virus carriers among the number of suspected cases, the average number of times that latent cases contact normal people per day, the average probability of transmission between latent cases and normal people per contact, the average number of times confirmed patients contact people per day, the average probability of transmission between confirmed patients and normal people, the average number of days in the latent period and the average number of days for confirmed patients to be removed; step S140: predicting the number of confirmed cases of the infectious disease in a future time period based on each parameter value and each functional relationship.

[0159] The storage unit 820 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 8201 and / or a cache memory unit 8202 , and may further include a read-only memory unit (ROM) 8203 .

[0160] The storage unit 820 may also include a program / utility 8204 having a set (at least one) of program modules 8205, such program modules 8205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0161] Bus 830 may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0162] The electronic device 800 can also communicate with one or more external devices 900 (e.g., a keyboard, a pointing device, a Bluetooth device, etc.), one or more devices that enable a user to interact with the electronic device 800, and / or any device that enables the electronic device 800 to communicate with one or more other computing devices (e.g., a router, a modem, etc.). Such communication can occur via an input / output (I / O) interface 850. Furthermore, the electronic device 800 can also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network such as the Internet) via a network adapter 860. As shown, the network adapter 860 communicates with other modules of the electronic device 800 via a bus 830. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the electronic device 800, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0163] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the embodiments of the present invention 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 flash drive, a mobile hard disk, etc.) or on a network, and includes a number of instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present invention.

[0164] In exemplary embodiments of the present invention, a computer-readable storage medium is also provided, storing a program product capable of implementing the methods described above. In some possible implementations, various aspects of the present invention may also be implemented in the form of a program product comprising program code. When the program product is executed on a terminal device, the program code is configured to cause the terminal device to perform the steps according to various exemplary embodiments of the present invention described in the "Exemplary Methods" section above.

[0165] According to an embodiment of the present invention, a program product for implementing the above-mentioned method can be a portable compact disc read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, a readable storage medium can be any tangible medium containing or storing a program, and the program can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0166] The program product may be implemented in any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0167] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0168] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0169] The program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, and the like, as well as conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a stand-alone software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0170] Furthermore, the above-described figures are merely illustrative of the processes included in the method according to exemplary embodiments of the present invention and are not intended to be limiting. It is readily understood that the processes illustrated in the above-described figures do not indicate or limit the temporal order of these processes. Furthermore, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0171] Other embodiments of the present invention will readily occur to those skilled in the art after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention that follow from the general principles of the invention and include common knowledge or customary techniques in the art not invented herein. The specification and examples are to be considered as exemplary only, with the true scope and spirit of the invention being indicated by the claims.

Claims

1. A method for predicting an infectious disease epidemic, characterized in that: include: Obtaining known medical data; wherein the known medical data includes the number of suspected cases, confirmed cases, and removed cases in a specific area at multiple times; Constructing multiple functional relationships between the number of suspected cases and the number of confirmed cases, and between the number of confirmed cases and the number of removed cases based on kinetic equations; Discretize each of the functional relationships to obtain the relationship between the number of suspected cases, the relationship between the number of confirmed cases, and the relationship between the number of removed people at two adjacent moments; obtain multiple equations based on the relationship between the number of suspected cases, the relationship between the number of confirmed cases, and the relationship between the number of removed people at two adjacent moments; construct an objective function with the goal of minimizing the absolute value of the difference between both sides of each of the equations, and calculate the parameter values of multiple parameters included in each of the functional relationships based on the known medical data and the objective function; wherein the parameters include the proportion of true virus carriers among the number of suspected cases, the average number of daily contacts between latent cases and normal people, the average probability of transmission between latent cases and normal people per contact, the average number of daily contacts between confirmed patients, the average probability of transmission between confirmed patients and normal people, the average number of days in the incubation period, and the average number of days for confirmed patients to be removed; Predicting the number of confirmed cases of the infectious disease in a future time period based on the parameter values and the functional relationships; Among them, multiple equations are obtained based on the relationship between the number of suspected cases, the relationship between the number of confirmed cases, and the relationship between the number of removed cases at two adjacent moments; an objective function is constructed with the goal of minimizing the absolute value of the difference between the two sides of each equation, and parameter values of multiple parameters included in each functional relationship are calculated based on the known medical data and the objective function, including: Let A1(t) = k1*b1*p; A2(t) = k2*b2; By using A1(t), A2(t), A3(t), and A4(t) to simplify the relationship between the number of suspected cases, the relationship between the number of confirmed cases, and the relationship between the number of removed cases at each adjacent time, the following equations are obtained: E(t+1)=(A1(t)-A3(t)+1)*E(t)+A2(t)I(t); I(t+1)=A3(t)E(t)+(1-A4(t))I(t); R(t+1)=A4(t)I(t)+R(t); The number of suspected cases, confirmed cases, and removed cases at any time t+1 is a function of the number of suspected cases, confirmed cases, and removed cases at time t, with A1(t), A2(t), A3(t), and A4(t) as coefficients. The parameters included in the above functional relationships are calculated by calculating the parameters included in A1(t), A2(t), A3(t), and A4(t). The equation is simplified based on the preset simplification rules to obtain the following equation: Based on the official public data i,j Estimating to obtain the parameters included in A1(t), A2(t), A3(t) and A4(t); According to the parameters included in A1(t), A2(t), A3(t) and A4(t), parameter values of the multiple parameters included in each of the functional relationships are obtained, and the preset simplification rule is that a polynomial function can approximate an arbitrary function expression rule; Among them, E(t) is the number of suspected cases at time t; I(t) is the number of confirmed cases at time t; R(t) is the number of people removed at time t; p is the proportion of true virus carriers among the number of suspected cases at time t; k1 is the average number of daily contacts between latent cases and normal people at time t; b1 is the average probability of transmission between latent cases and normal people at time t; k2 is the average number of daily contacts between confirmed patients at time t; b2 is the average probability of transmission between confirmed patients and normal people at time t; T1 is the average number of days in the incubation period; T2 is the average number of days for confirmed patients to be removed at time t.

2. The infectious disease epidemic prediction method according to claim 1, characterized in that: Based on the dynamic equation, multiple functional relationships between the number of suspected cases and the number of confirmed cases, and the number of confirmed cases and the number of removed cases are constructed, including: Among them, E(t) is the number of suspected cases at time t; I(t) is the number of confirmed cases at time t; R(t) is the number of people removed at time t; p is the proportion of true virus carriers among the number of suspected cases at time t; k1 is the average number of daily contacts between latent cases and normal people at time t; b1 is the average probability of transmission between latent cases and normal people at time t; k2 is the average number of daily contacts between confirmed patients at time t; b2 is the average probability of transmission between confirmed patients and normal people at time t; T1 is the average number of days in the incubation period; T2 is the average number of days for confirmed patients to be removed at time t.

3. The infectious disease epidemic prediction method according to claim 1, characterized in that: The objective function is constructed with the goal of minimizing the absolute value of the difference between the two sides of the equation, including:

4. The infectious disease epidemic prediction method according to claim 3, characterized in that: Calculating parameter values of the multiple parameters included in each of the functional relationships according to the known medical data and the target function includes: Based on the projected gradient descent and alternating minimum methods, parameter values of multiple parameters included in each functional relationship are calculated according to the known medical data and the objective function.

5. The infectious disease epidemic prediction method according to claim 1, characterized in that: The infectious disease epidemic prediction method further includes: Based on the parameter values, determining the maximum number of confirmed cases of the infectious disease in a future time period and the time point corresponding to the maximum value; The turning point time of the infectious disease is predicted based on the time point corresponding to the maximum number of confirmed cases.

6. The infectious disease epidemic prediction method according to claim 1, characterized in that: The infectious disease epidemic prediction method further includes: Determine whether the growth rate of the number of confirmed cases is continuously zero within a preset time period; wherein the preset time period is not less than one week; When it is determined that the growth rate of the number of confirmed cases is continuously zero within a preset time period, the total number of infected people of the epidemic is calculated based on the total number of confirmed cases of the infectious disease from the start time to the time when the growth rate is zero.

7. An infectious disease epidemic prediction device, characterized in that: include: A medical data acquisition module is used to acquire known medical data; wherein the known medical data includes the number of suspected cases, confirmed cases, and removed cases in a specific area at multiple times; A functional relationship construction module, for constructing multiple functional relationships between the number of suspected cases and the number of confirmed cases, and between the number of confirmed cases and the number of removed cases based on a dynamic equation; a parameter value calculation module for discretizing each of the functional relationships to obtain the relationship between the number of suspected cases, the relationship between the number of confirmed cases, and the relationship between the number of removed people at two adjacent moments; obtaining multiple equations based on the relationship between the number of suspected cases, the relationship between the number of confirmed cases, and the relationship between the number of removed people at two adjacent moments; constructing an objective function with the goal of minimizing the absolute value of the difference between both sides of each of the equations, and calculating the parameter values of multiple parameters included in each of the functional relationships based on the known medical data and the objective function; wherein the parameters include the proportion of true virus carriers among the number of suspected cases, the average number of daily contacts between latent cases and normal people, the average probability of transmission between latent cases and normal people per contact, the average number of daily contacts between confirmed patients, the average probability of transmission between confirmed patients and normal people, the average number of days in the incubation period, and the average number of days for confirmed patients to be removed; A first prediction module is used to predict the number of confirmed cases of the infectious disease in a future time period based on the parameter values and the functional relationships; Among them, multiple equations are obtained based on the relationship between the number of suspected cases, the relationship between the number of confirmed cases, and the relationship between the number of removed cases at two adjacent moments; an objective function is constructed with the goal of minimizing the absolute value of the difference between the two sides of each equation, and parameter values of multiple parameters included in each functional relationship are calculated based on the known medical data and the objective function, including: Let A1(t) = k1*b1*p; A2(t) = k2*b2; By using A1(t), A2(t), A3(t), and A4(t) to simplify the relationship between the number of suspected cases, the relationship between the number of confirmed cases, and the relationship between the number of removed cases at each adjacent time, the following equations are obtained: E(t+1)=(A1(t)-A3(t)+1)*E(t)+A2(t)I(t); I(t+1)=A3(t)E(t)+(1-A4(t))I(t); R(t+1)=A4(t)I(t)+R(t); The number of suspected cases, confirmed cases, and removed cases at any time t+1 is a function of the number of suspected cases, confirmed cases, and removed cases at time t, with A1(t), A2(t), A3(t), and A4(t) as coefficients. The parameters included in the above functional relationships are calculated by calculating the parameters included in A1(t), A2(t), A3(t), and A4(t). The equation is simplified based on the preset simplification rules to obtain the following equation: Based on the official public data i,j Estimating to obtain the parameters included in A1(t), A2(t), A3(t) and A4(t); According to the parameters included in A1(t), A2(t), A3(t) and A4(t), parameter values of the multiple parameters included in each of the functional relationships are obtained, and the preset simplification rule is that a polynomial function can approximate an arbitrary function expression rule; Among them, E(t) is the number of suspected cases at time t; I(t) is the number of confirmed cases at time t; R(t) is the number of people removed at time t; p is the proportion of true virus carriers among the number of suspected cases at time t; k1 is the average number of daily contacts between latent cases and normal people at time t; b1 is the average probability of transmission between latent cases and normal people at time t; k2 is the average number of daily contacts between confirmed patients at time t; b2 is the average probability of transmission between confirmed patients and normal people at time t; T1 is the average number of days in the incubation period; T2 is the average number of days for confirmed patients to be removed at time t.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the infectious disease epidemic prediction method according to any one of claims 1 to 6 is implemented.

9. An electronic device, characterized in that: include: processor; as well as a memory for storing executable instructions of the processor; Wherein, the processor is configured to execute the infectious disease epidemic prediction method according to any one of claims 1 to 6 by executing the executable instructions.

Images