Artificial intelligence-based early warning and prevention and control system for infectious diseases in children

Abstract

The present application relates to the technical field of infectious disease monitoring, in particular to an early warning and prevention and control system for children's infectious diseases based on artificial intelligence. The system obtains pathogenic microorganism types and test data of sick children in a current time period; according to the sick children corresponding to the pathogenic microorganism types in the current time period and the sick children corresponding to the pathogenic microorganism types in a historical time period, a target microorganism type is screened out; the sick children corresponding to the target microorganism type are taken as target children, and the test data of the target children with a high proportion are taken as target data; according to the change of the target children and the occurrence of the target data, the prevalence of children's infectious diseases at the current time is judged to determine whether early warning and prevention and control of children's infectious diseases are needed. The present application can accurately obtain the prevalence of children's infectious diseases in real time, so that early warning and prevention and control can be more accurate and timely, and the situation of diagnosis delay and prevention and control lag of children's infectious diseases can be effectively reduced.

Description

Technical Field

[0001] This invention relates to the field of infectious disease surveillance technology, specifically to an artificial intelligence-based early warning and prevention system for infectious diseases in children. Background Technology

[0002] Childhood infectious diseases are common infectious diseases caused by pathogens such as bacteria, viruses, fungi, or parasites, characterized by rapid transmission and complex pathogenic mechanisms. Because children's immune systems are not yet fully developed, their risk of infection is significantly higher than that of adults, and the disease progresses rapidly. Some diseases (such as severe influenza, hand-foot-and-mouth disease, and pneumococcal infection) can lead to serious complications or even be life-threatening. Therefore, early warning and prevention are of great significance in pediatric clinical practice and public health management.

[0003] In existing methods, doctors use the clinical symptoms of sick children to provide early warning and control of infectious diseases in children. However, in reality, there are many types of pathogens causing infectious diseases in children, the transmission routes of diseases are complex, and different sick children may have different clinical symptoms due to their own differences. This increases the complexity of early warning. At the same time, subjective judgment can easily lead to problems such as delayed diagnosis and delayed response to infectious diseases in children, which is not conducive to the control of infectious diseases in children. Summary of the Invention

[0004] To address the technical problems of delayed diagnosis and lagging response to infectious diseases in children, the present invention aims to provide an artificial intelligence-based early warning and prevention system for infectious diseases in children. The specific technical solution adopted is as follows:

[0005] This invention provides an artificial intelligence-based early warning and prevention system for infectious diseases in children, the system comprising:

[0006] The data acquisition module is used to acquire the electronic medical records of each sick child within the current time period; the electronic medical records contain the types of pathogenic microorganisms and various laboratory data.

[0007] The target microorganism type acquisition module is used to screen out the most pathogenic target microorganism types based on the number of sick children corresponding to each pathogenic microorganism type in the current time period and the difference between the number of sick children corresponding to each pathogenic microorganism type in the historical time period.

[0008] The prevalence acquisition module is used to identify all sick children with the target microorganism type in the current time period as target children, and to identify the test data with higher rates among target children as target data. Based on the changes in target children in the current time period and the occurrence of each target data among target children, the prevalence of infectious diseases in children at the current moment is obtained.

[0009] The data processing module is used to determine whether early warning and prevention of infectious diseases in children should be carried out at the current time based on the prevalence level.

[0010] Furthermore, the method for obtaining the target microbial type is as follows:

[0011] The prominence of each pathogenic microorganism type is obtained by comparing the percentage of infected children in the current time period with the percentage of infected children in historical time periods.

[0012] The pathogenic microorganism type corresponding to the highest degree of prominence is taken as the target microorganism type.

[0013] Furthermore, the method for obtaining the degree of prominence is as follows:

[0014] For any type of pathogenic microorganism, the ratio of the number of children with that type of pathogenic microorganism in the current time period to the total number of children with the disease in the current time period is obtained as the first reference value;

[0015] The ratio of the number of children with this type of pathogenic microorganism within a historical period to the total number of children with the disease within that historical period is used as a second reference value.

[0016] The normalized result of the difference between the first reference value and the second reference value is used as the adjustment weight;

[0017] The product of the adjusted weight and the first reference value is used as the degree of prominence of this type of pathogenic microorganism.

[0018] Furthermore, the AI-based early warning and prevention system for infectious diseases in children also includes:

[0019] When there are at least two types of pathogenic microorganisms corresponding to the highest degree of prominence, the number of sick children corresponding to each type of pathogenic microorganism in the current time period is taken as the first number.

[0020] The pathogenic microorganism type corresponding to the largest first quantity is taken as the target microorganism type.

[0021] Furthermore, the method for obtaining the popularity level is as follows:

[0022] Based on the changes in the target children within the current time period, obtain the prevalence trend of infectious diseases among children at the current moment;

[0023] Based on the proportion of each target data in the target children, obtain the disease test similarity of the target microbial type at the current moment;

[0024] The normalized result of the product of the prevalence level and the similarity of disease test results is taken as the prevalence level of infectious diseases in children at the current moment.

[0025] Furthermore, the method for obtaining the degree of popularity tendency is as follows:

[0026] The current time period is evenly divided into several local time periods, and the number of target children in each local time period is obtained and used as a reference number.

[0027] Based on changes in the reference quantity, obtain the potential stage and epidemic stage of the disease in the current time period;

[0028] The largest reference number in the potential stage of the disease is used as the potential representative number, and all local time periods in the epidemic stage of the disease are used as the analysis time periods.

[0029] For any given analysis period, the ratio of the reference number to the potential representative number for that analysis period is used as the disease prevalence analysis value for that analysis period.

[0030] The difference between the reference quantity of the analysis time period and the previous adjacent local time period is taken as the first value of the analysis time period;

[0031] The ratio of the first value to the reference quantity of the preceding adjacent local time period is used as the reference weight for the analysis time period.

[0032] The product of the disease prevalence analysis value and the reference weight is used as the local disease prevalence reference value for the analysis period.

[0033] The result of normalizing the mean of the local disease prevalence reference values ​​for all analysis time periods is used as the prevalence tendency of infectious diseases in children at the current moment.

[0034] Furthermore, the method for obtaining the potential stage and epidemic stage of the disease in the current time period is as follows:

[0035] Obtain the first value of each local time period, take the local time period corresponding to the largest first value as the segmented time period, and take the segmented time period and the time periods corresponding to all the local time periods before it as the potential stage of the disease.

[0036] The time periods corresponding to all local time periods after the segmentation of the time period are taken as the disease epidemic stage.

[0037] Furthermore, the AI-based early warning and prevention system for infectious diseases in children also includes:

[0038] When the largest first value corresponds to multiple local time periods, the local time period corresponding to the first occurrence of the largest first value is taken as the segmented time period.

[0039] Furthermore, the method for obtaining the degree of similarity in the disease tests is as follows:

[0040] For any type of target data, the ratio of the number of target children containing that target data to the total number of all target children is taken as the proportion of that type of target data.

[0041] The sum of the proportions of all target data is used as the similarity of the target microorganism type in disease testing at the current moment.

[0042] Furthermore, the method for determining whether to conduct early warning and prevention of infectious diseases in children based on the prevalence level at the current moment is as follows:

[0043] When the prevalence exceeds a preset prevalence threshold, early warning and prevention of infectious diseases in children are required at the current moment.

[0044] When the prevalence level is less than or equal to the preset prevalence level threshold, there is no need for early warning and prevention of infectious diseases in children at the current moment.

[0045] The present invention has the following beneficial effects:

[0046] This invention first identifies prominent target microbial types based on the number of infected children of each pathogenic microorganism type in the current time period and the difference between this number and the number of infected children in historical time periods. This accurately determines the pathogenic microorganism types that may cause the spread of infectious diseases in children in the current time period, which is beneficial for subsequent accurate and efficient analysis of the current prevalence of infectious diseases in children. Furthermore, all infected children of the target microorganism type in the current time period are designated as target children, and laboratory data with higher rates among target children are designated as target data. Then, based on the changes in target children and the occurrence of each target data among target children in the current time period, the prevalence of infectious diseases in children at the current moment is obtained, accurately reflecting the severity of the current infectious disease epidemic. Based on the prevalence level, it accurately determines whether early warning and prevention of infectious diseases in children should be implemented at the current moment, enabling more accurate and timely early warning and prevention of infectious diseases in children. This effectively reduces delays in diagnosis and lag in prevention and control responses, and is conducive to further control of infectious diseases in children. Attached Figure Description

[0047] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0048] Figure 1 This is a schematic flowchart illustrating an artificial intelligence-based method for early warning and prevention of infectious diseases in children, provided as an embodiment of the present invention.

[0049] Figure 2 This is a flowchart of a method for obtaining a target microbial type according to an embodiment of the present invention;

[0050] Figure 3 A flowchart illustrating a method for obtaining popularity according to an embodiment of the present invention;

[0051] Figure 4 This is a structural diagram of an artificial intelligence-based early warning and prevention system for infectious diseases in children, provided as an embodiment of the present invention.

[0052] Figure 5 This is a schematic diagram of a computer device provided according to an embodiment of the present invention. Detailed Implementation

[0053] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of the artificial intelligence-based early warning and prevention method for infectious diseases in children proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0054] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0055] The following description, in conjunction with the accompanying drawings, details the specific scheme of the artificial intelligence-based early warning and prevention method for childhood infectious diseases provided by this invention.

[0056] Example 1:

[0057] This invention proposes an artificial intelligence-based method for early warning and prevention of infectious diseases in children. Please refer to [link / reference]. Figure 1The diagram illustrates a schematic flowchart of an artificial intelligence-based early warning and prevention method for infectious diseases in children, according to an embodiment of the present invention. The method includes the following steps:

[0058] Step S1: Obtain the electronic medical record for each sick child within the current time period; the electronic medical record contains the type of pathogenic microorganism and various laboratory data.

[0059] Infectious diseases in children (such as influenza, pneumonia, and hand-foot-and-mouth disease) typically present with symptoms such as fever, vomiting, diarrhea, cough, and shortness of breath, causing discomfort and disrupting their daily lives and rest. Severe infections can also lead to complications, and in severe cases, even endanger a child's life. Because infectious diseases can damage a child's immune system, especially for infants and young children whose immune systems are not yet fully mature, and for children with weakened immune systems, infection can lead to prolonged periods of weakness and increased susceptibility to infection. Therefore, early warning and prevention of infectious diseases in children are crucial.

[0060] To analyze the prevalence of infectious diseases in children in real time and enable timely control, this embodiment retrieves the electronic medical records of each sick child in the pediatric department within the current time period from the hospital's database. These electronic medical records contain the type of pathogenic microorganism and various laboratory data. This embodiment sets the current time period to 30 days; however, the implementer can adjust the length of the current time period according to actual circumstances, and this is not limited here. The end time of the current time period must be the current moment. It should be noted that the types of pathogenic microorganisms include viruses, bacteria, and fungi; the laboratory data include serum alanine aminotransferase, aspartate aminotransferase, and white blood cells, etc., and the types of laboratory data are consistent for each sick child.

[0061] Step S2: Based on the number of sick children corresponding to each type of pathogenic microorganism in the current time period and the difference between the number of sick children in the historical time period, screen out the target microorganism types that are prominent in causing the disease.

[0062] Specifically, prevalent infectious diseases in children are usually caused by a certain type of pathogenic microorganism. Therefore, this embodiment analyzes the number of sick children corresponding to each type of pathogenic microorganism in the current time period. The more sick children a certain type of pathogenic microorganism corresponds to in the current time period, the more likely that type of pathogenic microorganism is to be the source of the epidemic of infectious diseases in children in the current time period.

[0063] Considering that in reality, there may be a situation where a certain type of pathogenic microorganism naturally presents a larger number of infected children than other types of pathogenic microorganisms, in order to avoid misidentifying pathogenic microorganisms that do not cause the spread of infectious diseases in children as the source of the spread of infectious diseases in children, this embodiment further combines the difference between the number of infected children corresponding to each type of pathogenic microorganism in the current time period and the number of infected children corresponding to the historical time period, so as to more accurately analyze the types of pathogenic microorganisms that may cause the spread of infectious diseases in children in the current time period.

[0064] Therefore, this embodiment uses the number of sick children corresponding to each pathogenic microorganism type in the current time period and the difference between this number and the number of sick children in historical time periods to screen out the target microorganism types with prominent pathogenicity, so as to accurately and efficiently analyze the prevalence of infectious diseases in children at the current moment. It should be noted that this embodiment sets the duration of the historical time period to 30 days; implementers can set the duration of the historical time period according to actual conditions, and it is not limited here. It should also be noted that the end time of the historical time period must be the beginning time of the current time period, and at least two months of pediatric medical records must have been recorded in the hospital's database.

[0065] Preferably, in one feasible embodiment, the method for obtaining the target microbial type is described in [reference needed]. Figure 2 The document presents a flowchart of a method for obtaining a target microbial type, as provided in this embodiment. The method includes the following steps:

[0066] Step S201: Based on the proportion of children with each type of pathogenic microorganism in the current time period and the difference between the proportion of children with each type of pathogenic microorganism and the proportion of children with each type of pathogenic microorganism in historical time periods, obtain the prominence of each type of pathogenic microorganism.

[0067] A higher percentage of children infected with a particular pathogenic microorganism within a given time period indicates that this type of pathogenic microorganism is more likely to be the primary cause of illness among children in that time period. Furthermore, a higher percentage of children infected with this type of pathogenic microorganism within the current time period compared to historical time periods further reinforces the likelihood that this type of pathogenic microorganism is the primary cause of illness among children in that time period. Therefore, this embodiment uses the percentage of children infected with each type of pathogenic microorganism within the current time period and the difference between this percentage and the percentage within historical time periods to determine the prominence of each pathogenic microorganism type. A higher prominence indicates that the corresponding pathogenic microorganism type is more likely to be the primary cause of illness among children in that time period.

[0068] In one possible implementation of this embodiment, the method for obtaining the salience level is as follows: For any type of pathogenic microorganism, the ratio of the number of children with this type of pathogenic microorganism in the current time period to the total number of children with the pathogenic microorganism in the current time period is obtained as a first reference value; the larger the first reference value, the more likely this type of pathogenic microorganism is to be a key source of concern for children with the pathogenic microorganism in the current time period; to more accurately analyze whether this type of pathogenic microorganism is a key source of concern for children with the pathogenic microorganism in the current time period, the ratio of the number of children with this type of pathogenic microorganism in a historical time period to the total number of children with the pathogenic microorganism in the historical time period is obtained as a second reference value; when the first reference value is significantly greater than the second reference value, it more accurately indicates that this type of pathogenic microorganism is more likely to be a key source of concern for children with the pathogenic microorganism in the current time period, and then the result of normalizing the difference between the first reference value and the second reference value is used as an adjustment weight; the larger the adjustment weight, the more meaningful the first reference value is, therefore, the product of the adjustment weight and the first reference value is used as the salience level of this type of pathogenic microorganism.

[0069] The formula for calculating the degree of prominence is as follows: In the formula, The prominence of the i-th pathogenic microorganism type; Let N be the number of children suffering from the i-th type of pathogenic microorganism in the current time period; N is the total number of children suffering from the disease in the current time period. This is the first reference value; represents the number of children suffering from the i-th type of pathogenic microorganism within a historical time period; This represents the total number of sick children within a historical time period. This is the second reference value; To adjust the weights.

[0070] This allows us to determine the prominence of each type of pathogenic microorganism.

[0071] Step S202: The pathogenic microorganism type corresponding to the highest degree of prominence is taken as the target microorganism type.

[0072] It is known that the greater the degree of prominence, the more likely the corresponding pathogenic microorganism type is to be the main source of infection for children with the disease in the current time period. Therefore, in this embodiment, the pathogenic microorganism type corresponding to the highest degree of prominence is taken as the target microorganism type. It should be noted that when there are at least two pathogenic microorganism types corresponding to the highest degree of prominence, the number of children with the disease corresponding to each pathogenic microorganism type corresponding to the highest degree of prominence in the current time period is taken as the first number; the pathogenic microorganism type corresponding to the largest first number is taken as the target microorganism type.

[0073] Step S3: Select all sick children with the target microorganism type in the current time period as target children, and select all test data with higher levels in the target children as target data. Based on the changes in the target children in the current time period and the occurrence of each target data in the target children, obtain the prevalence of infectious diseases in children at the current moment.

[0074] Specifically, when an infectious disease outbreak occurs in children, pediatric outpatient clinics will experience a surge in the number of children with the target microorganism type in a short period of time. In particular, the number of children with the target microorganism type will show two completely different states before and after the outbreak of the infectious disease in children. To better describe this, this embodiment takes all children with the target microorganism type in the current time period as target children, and then analyzes the prevalence of infectious diseases in children at the current moment based on the changes in the number of target children in the current time period.

[0075] Considering the differences in the individual conditions of the target children, their symptoms may vary. However, the changes in their laboratory data should be consistent, as the cause of their illness is the same: the target microorganism. It is known that when a certain laboratory data deviates from its normal range, it indicates an abnormality. To further determine the accuracy of the analysis of the prevalence of infectious diseases in children at the current moment, all elevated laboratory data of the target children are used as target data. That is, all laboratory data of the target children that are above the normal range are considered target data. Then, the occurrence of each target data point in the target children is analyzed. The higher the proportion of each target data point in the target children, the more accurate the analysis of the prevalence of infectious diseases in children during the current time period. Therefore, this embodiment obtains the prevalence of infectious diseases in children at the current moment based on the changes in the target children and the occurrence of each target data point. The higher the prevalence, the greater the need for early warning and prevention of infectious diseases in children at the current moment to prevent further spread.

[0076] Preferably, in one possible implementation of this embodiment, the method for obtaining popularity can be found in [reference needed]. Figure 3 The document presents a flowchart of a method for obtaining popularity based on this embodiment, which includes the following steps:

[0077] Step S301: Based on the changes in the target children within the current time period, obtain the prevalence trend of infectious diseases among children at the current moment.

[0078] The greater the prevalence, the more severe the current prevalence of infectious diseases among children, and the greater the need for early warning so that timely prevention and control of infectious diseases among children can be achieved.

[0079] The method for obtaining the prevalence trend is as follows: First, the current time period is evenly divided into several local time periods. Then, the number of target children in each local time period is obtained and used as a reference number to accurately analyze the changes in the target children within the current time period. In this embodiment, the duration of the local time period is set to 1 day (24 hours). Implementers can set the size of the local time period according to the actual situation, which is not limited here. It is known that when an epidemic of infectious diseases occurs in children, the reference number will increase sharply. Therefore, this embodiment obtains the potential stage and epidemic stage of the disease in the current time period based on the changes in the reference number, so as to accurately analyze the prevalence of infectious diseases in children within the current time period.

[0080] The methods for obtaining the potential and epidemic stages of the disease are as follows: The difference between the reference number of each local time period and its preceding adjacent local time period is obtained as the first value of each local time period. It should be noted that the first local time period does not have a preceding adjacent local time period; therefore, the first local time period in the current time period is not analyzed. Then, the local time period corresponding to the largest first value is taken as the segmented time period. The time periods corresponding to the segmented time period and all the local time periods preceding it are then taken as the potential stage of the disease. The time periods corresponding to all the local time periods after the segmented time period are taken as the epidemic stage of the disease. It should be noted that when the largest first value corresponds to multiple local time periods, the local time period corresponding to the first occurrence of the largest first value is taken as the segmented time period.

[0081] To analyze the prevalence of infectious diseases in children within the current time period, the largest reference number in the potential disease stage is used as the potential representative number, and all local time periods in the disease epidemic stage are used as analysis time periods. For any analysis time period, the ratio of the reference number to the potential representative number is obtained as the disease prevalence analysis value for that analysis time period. The larger the disease prevalence analysis value, the more severe the prevalence of infectious diseases in children represented by that analysis time period. To more accurately represent the prevalence of infectious diseases in children corresponding to that analysis time period, the ratio of the first value of that analysis time period to the reference number of the preceding adjacent local time period is obtained as the reference weight for that analysis time period. The larger the reference weight, the more severe the prevalence of infectious diseases in children represented by that analysis time period. The product of the disease prevalence analysis value and the reference weight is then used as the local disease prevalence reference value for that analysis time period. The larger the local disease prevalence reference value, the more severe the prevalence of infectious diseases in children represented by that analysis time period. In order to analyze the overall prevalence of infectious diseases in children during the current period, that is, to determine the prevalence of infectious diseases in children at the current moment, the mean of the local disease prevalence reference values ​​of all analysis periods is normalized as the prevalence tendency of infectious diseases in children at the current moment.

[0082] The formula for calculating the degree of popularity is as follows: In the formula, W represents the prevalence of infectious diseases among children at the current moment; J represents the number of time periods analyzed. This is the reference quantity for the j-th analysis time period; The number of potential representatives; The disease prevalence analysis value for the j-th analysis period; This is the reference number for the (j-1)th analysis time period; This is the first value in the j-th analysis time period; The reference weight for the j-th analysis time period; Here, represents the local disease prevalence reference value for the j-th analysis time period; norm is the normalization function. It should be noted that when j is 1, This is a reference number for dividing the time period.

[0083] Step S302: Based on the proportion of each target data in the target children, obtain the disease test similarity of the target microbial type at the current time.

[0084] When each target data point appears in every target child, it indicates a more accurate assessment of the prevalence of infectious diseases in children at the current time. Therefore, this embodiment uses the proportion of each target data point among the target children to obtain the disease test similarity of the target microorganism type at the current time. A higher disease test similarity indicates a more accurate assessment of the prevalence of infectious diseases in children at the current time.

[0085] In one possible implementation of this embodiment, the method for obtaining the similarity of disease tests is as follows: for any type of target data, the ratio of the number of target children containing the target data to the total number of target children is taken as the proportion of that type of target data; the sum of the proportions of all types of target data is taken as the similarity of disease tests of the target microorganism type at the current moment.

[0086] Step S303: Normalize the product of the prevalence level and the similarity of disease test results, and use the result as the prevalence level of infectious diseases in children at the current moment.

[0087] It is known that the greater the prevalence of infectious diseases in children at the current moment, the more severe the prevalence of infectious diseases; the greater the similarity of disease test results, the more accurate the prevalence of infectious diseases. To accurately represent the current prevalence of infectious diseases in children, the product of the prevalence of infectious diseases and the similarity of disease test results is normalized and used as the prevalence of infectious diseases in children at the current moment. This embodiment uses the norm normalization function to normalize the product of the prevalence of infectious diseases and the similarity of disease test results.

[0088] Step S4: Determine whether early warning and prevention of infectious diseases in children should be carried out at the current time based on the prevalence level.

[0089] The greater the prevalence of a known infectious disease, the more necessary it is to issue an early warning about its spread in children, enabling timely prevention and control measures to prevent further spread. Therefore, this embodiment determines whether early warning and control measures for infectious diseases in children should be implemented based on the prevalence level.

[0090] Preferably, in one feasible way of this embodiment, the method for determining whether to conduct early warning and prevention of infectious diseases in children based on the prevalence is as follows: In this embodiment, a preset prevalence threshold is set to 0.42. The implementer can set the size of the preset prevalence threshold according to the actual situation, which is not limited here; When the prevalence is greater than the preset prevalence threshold, early warning and prevention of infectious diseases in children are required at the current moment. That is, at the current moment, the real-time warning panel of the doctor's terminal will issue an early warning of infectious diseases in children and simultaneously submit an epidemic trend report to the CDC, reminding that it is necessary to prevent and control infectious diseases in children, providing prevention and control suggestions to schools, parents and medical institutions in advance, and preparing corresponding prevention and control resources (such as vaccines, medicines, medical facilities, etc.), thereby improving the ability to identify infectious diseases in children at an early stage and effectively reducing the risk of transmission of infectious diseases in children.

[0091] When the prevalence level is less than or equal to the preset prevalence level threshold, there is no need for early warning and prevention of infectious diseases in children at the current moment.

[0092] In summary, this embodiment obtains the pathogenic microorganism types and laboratory data of sick children within the current time period; based on the sick children corresponding to the pathogenic microorganism types within the current time period and the sick children corresponding to historical time periods, target microorganism types are screened; sick children corresponding to the target microorganism types are designated as target children, and laboratory data with higher levels in the target children are designated as target data; based on changes in the target children and the occurrence of target data, the prevalence of infectious diseases in children at the current moment is obtained to determine whether early warning and prevention of infectious diseases in children should be carried out. This invention, by accurately obtaining the prevalence of infectious diseases in children in real time, enables more accurate and timely early warning and prevention, effectively reducing delays in diagnosis and lag in response to infectious diseases in children.

[0093] Example 2:

[0094] This invention also proposes an artificial intelligence-based early warning and prevention system for infectious diseases in children. Please refer to [link / reference]. Figure 4 The diagram illustrates a structural diagram of an artificial intelligence-based early warning and prevention system for infectious diseases in children, provided by an embodiment of the present invention. The system includes: a data acquisition module 10, a target microorganism type acquisition module 20, a prevalence acquisition module 30, and a data processing module 40.

[0095] The data acquisition module 10 is used to acquire the electronic medical records of each sick child within the current time period; the electronic medical records contain the types of pathogenic microorganisms and various laboratory data.

[0096] The target microorganism type acquisition module 20 is used to screen out the target microorganism types that are prominent in causing disease based on the number of sick children corresponding to each pathogenic microorganism type in the current time period and the difference between the number of sick children corresponding to each pathogenic microorganism type in the historical time period.

[0097] The prevalence acquisition module 30 is used to identify all sick children of the target microorganism type in the current time period as target children, and to identify the laboratory data with higher levels of the target children as target data. Based on the changes in the target children in the current time period and the occurrence of each type of target data in the target children, the prevalence of infectious diseases in children at the current moment is obtained.

[0098] The data processing module 40 is used to determine whether early warning and prevention of infectious diseases in children should be carried out at the current time based on the prevalence level.

[0099] It should be noted that the system provided in the above embodiments is only an example of the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device can be divided into different functional modules to complete all or part of the functions described above. In addition, the artificial intelligence-based early warning and prevention system for infectious diseases in children and the artificial intelligence-based method for early warning and prevention of infectious diseases in children provided in the above embodiments belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0100] Example 3:

[0101] This invention also proposes an artificial intelligence-based early warning and prevention device for infectious diseases in children. The device includes a memory and a processor. The memory stores executable program code, and the processor is used to call and execute the executable program code to perform an artificial intelligence-based early warning and prevention method for infectious diseases in children provided in the embodiments of this application. Specifically, the device may be a chip, component, or module. The chip may include a connected processor and memory; the memory stores instructions, and when the processor calls and executes the instructions, the chip can perform the artificial intelligence-based early warning and prevention method for infectious diseases in children provided in the above embodiments.

[0102] Furthermore, this application also protects a computer device; please refer to [link to relevant documentation]. Figure 5 The computer device includes a memory 401, a processor 402, and a computer program 403 stored in the memory 401 and running on the processor 402. When the processor 402 executes the computer program 403, the computer device can execute any of the aforementioned artificial intelligence-based early warning and prevention methods for infectious diseases in children.

[0103] Example 4:

[0104] This embodiment also provides a computer-readable storage medium storing computer program code. When the computer program code is run on a computer, the computer executes the aforementioned related method steps to implement the artificial intelligence-based early warning and prevention method for infectious diseases in children provided in the above embodiment.

[0105] Example 5:

[0106] This embodiment also provides a computer program product that, when run on a computer, causes the computer to perform the aforementioned related steps to realize the artificial intelligence-based early warning and prevention method for infectious diseases in children provided in the above embodiment.

[0107] In this embodiment, the device, computer-readable storage medium, computer program product, or chip are all used to execute the corresponding methods provided above. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods provided above, and will not be repeated here.

[0108] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0109] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. An artificial intelligence-based early warning and prevention and control system for infectious diseases in children, characterized in that, The method comprises a data acquisition module, a target microorganism type acquisition module, a prevalence acquisition module and a data processing module. The data acquisition module is configured to acquire electronic medical records of each sick child in a current time period, wherein the electronic medical records contain pathogenic microorganism types and various test data. The target microorganism type acquisition module is configured to screen a target microorganism type with prominent pathogenicity according to a difference between a number of sick children corresponding to each pathogenic microorganism type in the current time period and a number of sick children corresponding to each pathogenic microorganism type in a historical time period. The prevalence acquisition module is configured to take each sick child corresponding to the target microorganism type in the current time period as a target child, take test data with a high proportion of target children as target data, and acquire a prevalence of a child infectious disease at the current time according to a change of the target children in the current time period and an occurrence of each target data in the target children. The data processing module is configured to determine whether to perform early warning and prevention and control of the child infectious disease at the current time based on the prevalence. The target microorganism type acquisition method comprises the following steps: According to a difference between a proportion of sick children corresponding to each pathogenic microorganism type in the current time period and a proportion of sick children corresponding to each pathogenic microorganism type in the historical time period, the prominence of each pathogenic microorganism type is acquired. The pathogenic microorganism type corresponding to the maximum prominence is taken as the target microorganism type. When there are at least two pathogenic microorganism types corresponding to the maximum prominence, the number of sick children corresponding to each pathogenic microorganism type corresponding to the maximum prominence in the current time period is taken as a first number. The pathogenic microorganism type corresponding to the maximum first number is taken as the target microorganism type. The prominence acquisition method comprises the following steps: For any pathogenic microorganism type, a ratio of the number of sick children corresponding to the pathogenic microorganism type in the current time period to the number of all sick children in the current time period is taken as a first reference value. A ratio of the number of sick children corresponding to the pathogenic microorganism type in the historical time period to the number of all sick children in the historical time period is taken as a second reference value. A result of normalizing a difference between the first reference value and the second reference value is taken as an adjustment weight. A product of the adjustment weight and the first reference value is taken as the prominence of the pathogenic microorganism type. The prominence calculation formula is as follows: ； In the formula, is the prominence degree of the i-th pathogenic microorganism type; is the number of sick children corresponding to the i-th pathogenic microorganism type in the current time period; N is the number of all sick children in the current time period; is the first reference value; is the number of sick children corresponding to the i-th pathogenic microorganism type in the historical time period; is the number of all sick children in the historical time period; is the second reference value; is the adjustment weight; The prevalence acquisition method comprises the following steps: According to a change of the target children in the current time period, a prevalence tendency degree of the child infectious disease at the current time is acquired. According to an occurrence proportion of each target data in the target children, a disease test similarity degree of the target microorganism type at the current time is acquired. A result of normalizing a product of the prevalence tendency degree and the disease test similarity degree is taken as the prevalence of the child infectious disease at the current time. The prevalence tendency degree acquisition method comprises the following steps: Each local time period in the current time period is uniformly divided, and the number of target children in each local time period is taken as a reference number. According to a change of the reference number, a disease potential stage and a disease prevalence stage in the current time period are acquired. The maximum number of references in the potential stage of the disease is taken as the potential representative number, and each local time period in the epidemic stage of the disease is taken as an analysis time period; For any analysis time period, the ratio of the number of references in the analysis time period to the potential representative number is taken as the disease prevalence analysis value of the analysis time period; The difference between the number of references in the analysis time period and the number of references in the previous adjacent local time period is taken as the first value of the analysis time period; The ratio of the first value to the number of references in the previous adjacent local time period of the analysis time period is taken as the reference weight of the analysis time period; The product of the disease prevalence analysis value and the reference weight is taken as the local disease prevalence reference value of the analysis time period; The average of the local disease prevalence reference values of all analysis time periods is normalized to obtain the prevalence tendency degree of the infectious disease of children at the current time; The calculation formula of the epidemic tendency degree is: ; in the formula, W is the epidemic tendency degree of the infectious disease of the child at the current time; J is the number of analysis time periods; is the reference number of the jth analysis time period; is the potential representative number; is the disease epidemic analysis value of the jth analysis time period; is the reference number of the j-1th analysis time period; is the first value of the jth analysis time period; is the reference weight of the jth analysis time period; is the local disease epidemic reference value of the jth analysis time period; norm is a normalization function; it should be noted that when j is 1, is the reference number of the segmentation time period.

2. The artificial intelligence-based early warning and prevention and control system for infectious diseases in children according to claim 1, characterized in that, The method for obtaining the potential stage of the disease and the epidemic stage of the disease in the current time period is: The first value of each local time period is obtained, the local time period corresponding to the maximum first value is taken as the segmentation time period, and the time period corresponding to all local time periods before the segmentation time period is taken as the potential stage of the disease; The time period corresponding to all local time periods after the segmentation time period is taken as the epidemic stage of the disease.

3. The early warning and prevention system for children's infectious diseases based on artificial intelligence according to claim 2, characterized in that, When the maximum first value corresponds to multiple local time periods, the local time period corresponding to the first maximum first value is taken as the segmentation time period.

4. The artificial intelligence-based early warning and prevention and control system for infectious diseases in children according to claim 1, characterized in that, The method for obtaining the disease test similarity degree is: For any target data, the ratio of the number of target children containing the target data to the total number of target children is taken as the proportion degree of the target data; The sum of the proportion degrees of all target data is taken as the disease test similarity degree of the target microorganism type at the current time.

5. The artificial intelligence-based early warning and prevention and control system for infectious diseases in children according to claim 1, characterized in that, The method for determining whether to perform early warning and prevention and control of the infectious disease of children at the current time based on the prevalence degree is: When the prevalence degree is greater than the preset prevalence degree threshold, early warning and prevention and control of the infectious disease of children at the current time are needed; When the prevalence degree is less than or equal to the preset prevalence degree threshold, early warning and prevention and control of the infectious disease of children at the current time are not needed.

Images