Big data-based infectious disease data processing system

Abstract

The invention discloses an infectious disease data processing system based on big data, and relates to the technical field of information processing, and the system comprises a disease data collection module used for collecting clinical features of various infectious diseases, a patient data collection module used for collecting patient data in a monitoring period, and a disease model construction module used for constructing a disease model. The analysis module is used for carrying out clustering analysis on clinical characteristics of various infectious diseases to obtain various clustered clinical clusters and various index characteristics, and is also used for analyzing disease distinguishing characteristics and similar characteristics of various infectious diseases and analyzing distinguishing paths of various infectious diseases, and the patient data processing module is used for classifying patient data in a monitoring period and sending the classified patient data to the analysis module. A trend analysis module used for analyzing the disease trend, and a risk early warning module used for analyzing the transmission state of regional infectious diseases and performing disease risk early warning for users. According to the invention, the efficiency of infectious disease data processing is effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of information processing technology, and in particular to an infectious disease data processing system based on big data. Background Art

[0002] With the acceleration of globalization and the increase in population mobility, the speed and scope of the spread of infectious diseases are also expanding. Traditional infectious disease monitoring methods often rely on manual reporting and limited data sources, resulting in problems such as data lag and poor accuracy, making it difficult to meet the needs of rapid response. In recent years, with the development of big data technology, by integrating multi-source heterogeneous data, it is possible to more accurately predict and control the spread of infectious diseases and provide support for public health decision-making.

[0003] Chinese patent publication number CN109166630A discloses a method and system for monitoring and processing infectious disease data, which obtains data information of specific infectious diseases; the data information includes: historical data of individual illness time during the outbreak period of infectious diseases in health records; constructs a group monitoring set; calculates the individual risk index of the individual based on the historical data of the individual illness time, and sorts all individuals from high to low risk, and selects them in sequence. Each monitoring set contains N individuals, and a total of M monitoring groups are constructed as group monitoring sets; when it is detected that the proportion of the population infected with a specific infectious disease in any monitoring group exceeds the set warning value, an early warning of the specific infectious disease is issued; it can be seen that the invention does not accurately analyze the identification method of infectious diseases, nor does it analyze the disease trends of various infectious diseases, and cannot achieve efficient analysis of infectious disease data, and then judge the situation of infectious diseases in a region, and there is a problem of low efficiency in processing infectious disease data. Summary of the invention

[0004] The object of the present invention is to provide an infectious disease data processing system based on big data to solve at least one of the problems existing in the prior art.

[0005] To achieve the above object, the present invention adopts the following technical solutions: Disease data collection module, used to collect clinical characteristics of various infectious diseases; A patient data collection module is used to collect patient data within the monitoring period; A disease model building module is used to cluster the clinical characteristics of various infectious diseases according to the clinical characteristics of various infectious diseases to obtain each cluster clinical cluster and each index feature. The disease model building module is also used to analyze the disease distinguishing characteristics and similar characteristics of various infectious diseases according to each cluster clinical cluster, and analyze the identification path of various infectious diseases according to the analysis results of the disease distinguishing characteristics and similar characteristics of various infectious diseases; Patient data processing module, used to classify patient data within the monitoring period according to the results of identification path analysis of various infectious diseases; Trend analysis module, used to analyze disease trends based on the classification results of patient data within the monitoring period; The risk warning module is used to analyze the regional infectious disease transmission status based on the classification results of patient data during the monitoring period, and to provide disease risk warnings to users based on the regional infectious disease transmission status analysis results.

[0006] Furthermore, the disease model building module includes a cluster analysis unit, which is used to cluster the clinical characteristics of various infectious diseases to obtain each cluster clinical cluster and each cluster clinical characteristic, and use the cluster clinical characteristics as index characteristics of the corresponding cluster clinical cluster.

[0007] Further, an iterative analysis unit is connected to the cluster analysis unit, and the iterative analysis unit is used to analyze the disease distinguishing characteristics of various infectious diseases; The iterative analysis unit uses the clinical features other than the similar features as clustering variables of the clustered clinical clusters, performs secondary clustering on each infectious disease in the clustered clinical clusters, and obtains each secondary clustered clinical cluster and each secondary similar feature; The iterative analysis unit performs iterative analysis on each secondary cluster clinical feature using the secondary clustering process as iterative logic to obtain disease distinguishing features of various infectious diseases.

[0008] Furthermore, the disease model building module also includes a model building unit, which is used to use the disease distinguishing features and similar features of each clustered clinical cluster as identification paths for various infectious diseases, and store the identification paths for various infectious diseases.

[0009] Furthermore, the patient data processing module includes a data matching unit, which is used to match the patient's clinical characteristics with the identification paths of various infectious diseases, and calculate the matching similarity α(j) between the patient data and the j-th infectious disease, and compare α(j) with the similarity judgment threshold A to determine the matching result between the patient data and the j-th infectious disease, and the matching result between the patient data and the j-th infectious disease includes a successful match and a failed match; The data matching unit classifies the patient data into the jth infectious disease when the matching is successful; and does not classify when the matching fails; When the patient data fails to match with all types of infectious diseases, the data matching unit classifies the patient data as non-infectious diseases.

[0010] Furthermore, the patient data processing module also includes a physical sign analysis unit, which calculates the patient's physical sign index β; The physical sign analysis unit compares the physical sign index β with the preset physical sign indexes to determine the abnormality of the patient's physical sign index, and adjusts the classification process of the patient data within the monitoring period according to the abnormal judgment result of the patient's physical sign index. The abnormality of the patient's physical sign index includes a low patient's physical sign index, a normal patient's physical sign index and a high patient's physical sign index. When the patient's physical sign index is low, the similarity judgment threshold is adjusted to A'; when the patient's physical sign index is high, the similarity judgment threshold is adjusted to A".

[0011] Furthermore, the patient data processing module further includes a medical analysis unit, and the medical analysis unit is used to optimize the adjustment process of patient data classification according to hospital information; The medical analysis unit calculates the medical saturation index η of the hospital; The medical analysis unit optimizes the adjustment process of the patient data classification process according to the medical saturation index η, optimizes the first preset vital sign index to B1', and optimizes the second preset vital sign index to B2'.

[0012] Furthermore, the trend analysis module is used to analyze the disease trends of various infectious diseases according to the classification results of patient data within the monitoring period; The trend analysis module counts the number of patient data n(j) of the jth infectious disease during the monitoring period, and calculates the disease trend index γ(j) of the jth infectious disease; The trend analysis module compares γ(j) with each preset trend index to analyze the disease trend of the j-th infectious disease. The analysis results of the disease trend of the j-th infectious disease include containment, slow growth and rapid growth.

[0013] Further, the risk warning module includes a transmission status analysis unit, which is used to analyze the regional infectious disease transmission status according to the classification results of patient data and the disease trend analysis results within the monitoring period; The transmission status analysis unit counts the patient data within the monitoring period as the number n1 of infectious diseases and the number n2 of non-infectious diseases; The transmission status analysis unit counts the number n3 of infectious diseases with a slow growth trend and the number n4 of infectious diseases with a fast growth trend during the monitoring period; The transmission status analysis unit analyzes the regional infectious disease transmission status according to the statistical results. The regional infectious disease transmission status includes normal, type clustering abnormal, controllable abnormal, explosive abnormal and common abnormal.

[0014] Furthermore, the risk warning module also includes a risk warning unit, which warns the user based on the analysis results of the regional infectious disease transmission status within the monitoring period: When n4=0, if the regional infectious disease transmission status is normal, the risk warning unit does not issue a warning; if the regional infectious disease transmission status is type aggregation abnormality, the risk warning unit sends a second-level risk warning to the user; if the regional infectious disease transmission status is controllable abnormality, the risk warning unit sends a third-level risk warning to the user; if the regional infectious disease transmission status is explosive abnormality, the risk warning unit sends a first-level risk warning to the user; if the regional infectious disease transmission status is ordinary abnormality, the risk warning unit sends a second-level risk warning to the user; When n4>0, the risk warning unit sends a first-level risk warning to the user.

[0015] Compared with the prior art, the beneficial effect of the present invention lies in that the system realizes efficient classification and type judgment of patient data by extracting the clinical characteristics of infectious diseases, and realizes the transmission status judgment and efficient early warning of regional infectious diseases based on the classification results of patient data, thereby improving the efficiency of infectious disease data processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 This is a schematic diagram of the structure of the infectious disease data processing system based on big data in this embodiment.

[0018] Figure 2 This is a schematic diagram of the structure of the disease model building module in this embodiment.

[0019] Figure 3 Schematic diagram of the structure of the patient data processing module in this embodiment.

[0020] Figure 4 Schematic diagram of the structure of the risk warning module of this embodiment. DETAILED DESCRIPTION

[0021] In order to more clearly illustrate the present invention, the present invention is further described below in conjunction with preferred embodiments and accompanying drawings. Similar components in the accompanying drawings are represented by the same reference numerals. It should be understood by those skilled in the art that the content specifically described below is illustrative rather than restrictive, and should not be used to limit the scope of protection of the present invention.

[0022] It should be noted that, although the terms first, second, third, etc. may be used to describe in the embodiments of the present application, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, without departing from the scope of the embodiments of the present application, the first may also be referred to as the second, and similarly, the second may also be referred to as the first.

[0023] Specifically, the infectious disease data processing system based on big data described in this embodiment is applied to the disease classification of infectious disease data, and the system is set in the diagnosis database of multiple hospitals in the monitoring area; the monitoring area described in this embodiment includes multiple hospitals, and the multiple hospitals share a diagnosis database; the scope of the monitoring area in this embodiment is freely set by the user, and the monitoring area includes at least one hospital; the infectious disease data is specifically patient data, and the patient data includes a description text of the patient's symptoms; it is worth noting that the object information (including but not limited to the patient's clinical characteristics, the patient's vital signs information, etc.) and data (including but not limited to the clinical characteristics of various infectious diseases) involved in this embodiment are all information and data authorized by the object or fully authorized by all parties, and the collection, use and processing of relevant data need to comply with relevant national and regional laws, regulations and standards.

[0024] See also Figure 1 As shown, it is a structural diagram of the infectious disease data processing system based on big data in this embodiment, including a disease data collection module, which is used to collect clinical characteristics of various infectious diseases; Specifically, the clinical characteristics of various infectious diseases described in this embodiment are specifically a collection of clinical characteristics, and the data format is: [clinical characteristic 1, clinical characteristic 2, clinical characteristic 3, ...]. For example, the clinical characteristics of hepatitis C are: [general fatigue, nausea, abdominal distension, right hypochondrium pain, low fever, hepatomegaly, splenomegaly, low fever, ...]; it can be understood that the clinical characteristics described in this embodiment are standard and professional medical terms described by doctors, and the clinical characteristics are the clinical characteristics of various infectious diseases in healthy people.

[0025] Please continue reading Figure 1 As shown, the system further includes a patient data acquisition module, which is used to collect patient data within a monitoring period.

[0026] Specifically, the patient data includes the patient's clinical characteristics; the patient's clinical characteristics are in the same data format as the clinical characteristics of the various infectious diseases; the present embodiment does not specifically limit the method for obtaining the patient's clinical characteristics, and those skilled in the art can set it freely, and only need to meet the requirements for obtaining the patient's clinical characteristics, such as obtaining it through a hospital database; at the same time, the present embodiment does not specifically limit the value of the monitoring period duration, and those skilled in the art can set it freely, and only need to meet the requirements for the value of the monitoring period duration, such as the monitoring period duration can be set to 2 hours, 3 hours, 4 hours, etc.

[0027] Please continue reading Figure 1 As shown, the system also includes a disease model construction module, which is connected to the disease data acquisition module. The disease model construction module is used to perform cluster analysis on the clinical characteristics of various infectious diseases according to the clinical characteristics of various infectious diseases to obtain each cluster clinical cluster and each index feature. The disease model construction module is also used to analyze the disease distinguishing characteristics and similar characteristics of various infectious diseases according to each cluster clinical cluster, and analyze the identification path of various infectious diseases according to the analysis results of the disease distinguishing characteristics and similar characteristics of various infectious diseases.

[0028] See also Figure 2 As shown, the disease model building module includes a cluster analysis unit, and the cluster analysis unit is used to analyze similar characteristics of various infectious diseases according to the clinical characteristics of various infectious diseases; The cluster analysis unit clusters the clinical characteristics of various infectious diseases to obtain each cluster clinical cluster and each cluster clinical characteristic, and uses the cluster clinical characteristic as an index characteristic of the corresponding cluster clinical cluster; Each clustered clinical cluster includes multiple infectious diseases, which are specifically a set of infectious diseases containing the same clinical characteristics; the clustered clinical characteristics are clinical characteristics contained in all infectious diseases in the clustering results; the clustering analysis unit clusters the clinical characteristics of various infectious diseases so that each clustering result has its own unique similar characteristics, so as to preliminarily construct a disease model for each infectious disease.

[0029] Specifically, in this embodiment, the correspondence between each clustered clinical cluster and each clustered clinical feature is one-to-one, that is, each clustered clinical cluster corresponds to a unique clustered clinical feature.

[0030] Specifically, the process of clustering the clinical characteristics of various infectious diseases in this embodiment is as follows: the cluster analysis unit clusters the infectious diseases containing the same clinical characteristics into a clustered clinical cluster. The same type of infectious disease can belong to multiple clustered clinical clusters, and the relationship between the infectious disease and the clustered clinical cluster is many-to-many; the process of "clustering infectious diseases containing the same clinical characteristics into a clustered clinical cluster" in this embodiment is implemented by a programming language, and the process is disclosed in the prior art and will not be repeated in this embodiment.

[0031] Please continue reading Figure 2 As shown, the disease model building module further includes an iterative analysis unit, which is connected to the cluster analysis unit, and the iterative analysis unit is used to analyze the disease distinguishing characteristics of various infectious diseases; The iterative analysis unit uses the clinical features other than the similar features as clustering variables of the clustered clinical clusters, performs secondary clustering on each infectious disease in the clustered clinical clusters, and obtains each secondary clustered clinical cluster and each secondary similar feature; The iterative analysis unit performs iterative analysis on each secondary cluster clinical feature using the secondary clustering process as the iterative logic. When the N-time cluster clinical cluster (i) contains only one type of infectious disease, the iteration is stopped, and the remaining clinical features of the infectious disease are used as the disease distinguishing features of the infectious disease; when the N-time cluster clinical cluster (i) contains multiple types of infectious diseases, the iteration is continued; Wherein, N is the number of clustering times, and N-times clustered clinical cluster (i) represents the clustering result of the i-th clustered clinical cluster in the N-times clustered clinical cluster; the disease distinguishing feature is a true subset of the clinical features, wherein N is the number of iterations; the remaining clinical features are the clinical features of the infectious disease except for the similar features; the similar features include index features (i), secondary similar features (i), ..., N-times similar features (i); the secondary similar features (i), ..., N-times similar features (i) are all similar features obtained in the clustering process of obtaining the N-times clustered clinical cluster (i); by performing multiple iterative analyses on the clustered clinical clusters, the features of various infectious diseases can be extracted, thereby achieving the accuracy of type judgment of patient data.

[0032] Please continue reading Figure 2 As shown, the disease model building module also includes a model building unit, and the model building unit is used to analyze the identification path of each infectious disease according to the disease distinguishing feature analysis results and similar features of each clustered clinical cluster; The model building unit is used to use the disease distinguishing features and similar features of each clustered clinical cluster as the identification path of each infectious disease, and store the identification path of each infectious disease; by analyzing and storing the identification path of each infectious disease, the accuracy of classifying patient data within the monitoring period is improved.

[0033] Specifically, the “storing the identification paths of various infectious diseases” in this embodiment specifically refers to storing the identification paths in a diagnosis database.

[0034] Specifically, the storage format of the identification paths of the various infectious diseases is {similar feature 1, similar feature 2, ..., [disease distinguishing feature 1, disease distinguishing feature 2, ...]}.

[0035] Please continue reading Figure 1 As shown, the system also includes a patient data processing module, which is connected to the disease model building module and the patient data acquisition module. The patient data processing module is used to classify the patient data within the monitoring period according to the identification path analysis results of various infectious diseases.

[0036] See also Figure 3 As shown, the patient data processing module includes a data matching unit, and the data matching unit is used to classify the patient data within the monitoring period according to the identification paths of various infectious diseases; The data matching unit matches the patient's clinical characteristics with the identification paths of various infectious diseases, and calculates the matching similarity α(j) between the patient data and the j-th infectious disease, setting α(j)=a1×m1(j) / M1(j)+a2×m2(j) / M2(j); wherein a1 is the path matching weight, a2 is the disease distinguishing feature matching weight, a1>a2 and a1+a2=1, m1(j) is the number of matches between the patient's clinical characteristics and similar features of the j-th infectious disease, M1(j) is the number of similar features of the j-th infectious disease, m2(j) is the number of matches between the patient's clinical characteristics and the disease distinguishing features of the j-th infectious disease, and M2(j) is the number of disease distinguishing features of the j-th infectious disease; The data matching unit compares α(j) with the similarity judgment threshold A, and analyzes the matching result of the patient data according to the comparison result: if α(j) < A, the data matching unit determines that the patient data fails to match the infectious disease of this type; if α(j) ≥ A, the data matching unit determines that the patient data successfully matches the infectious disease of this type, and classifies the patient data as the infectious disease of this type; When the patient data fails to match all types of infectious diseases, the data matching unit classifies the patient data as non-infectious diseases; by classifying the patient data, rapid classification and type judgment of the patient data are achieved, thereby improving the accuracy and efficiency of classifying the patient data within the monitoring period.

[0037] Specifically, this embodiment does not make specific restrictions on the values ​​of the path matching weight a1 and the disease distinguishing feature matching weight a2. Those skilled in the art can set them freely, and only need to meet the value requirements of "a1>a2 and a1+a2=1". In this embodiment, the path matching weight a1 is set to 0.7, and the disease distinguishing feature matching weight a2 is set to 0.3; at the same time, this embodiment does not make specific restrictions on the value of the similarity judgment threshold A. Those skilled in the art can set it freely, and only need to meet the value requirements of the similarity judgment threshold A, such as the similarity judgment threshold A can be set to 0.9; it can be understood that this embodiment does not make specific restrictions on the process of "matching the clinical characteristics of the patient with the similar characteristics of the j-th infectious disease" and "matching the clinical characteristics of the patient with the disease distinguishing characteristics of the j-th infectious disease". Those skilled in the art can set it freely, and only need to meet the requirements of "matching the clinical characteristics of the patient with the similar characteristics of the j-th infectious disease" and "matching the clinical characteristics of the patient with the disease distinguishing characteristics of the j-th infectious disease". In this embodiment, only the patient's clinical characteristics are compared with the similar characteristics and the patient's clinical characteristics respectively to complete the matching process.

[0038] Please continue reading Figure 3 As shown, the patient data processing module further includes a physical sign analysis unit, which is connected to the data matching unit, and is used to obtain the patient's physical sign information, wherein the patient's physical sign information includes the patient's blood pressure and the patient's blood oxygen saturation; the physical sign analysis unit is also used to analyze the patient's physical sign status according to the patient's physical sign information, and adjust the classification process of the patient data within the monitoring period according to the patient's physical sign status analysis result; The physical sign analysis unit calculates the patient's physical sign index β, and sets β=ln[e+(pP) / P+(hH) / H]; Where, e is the natural logarithm, p is the patient's blood pressure, P is the reference healthy blood pressure, h is the patient's blood oxygen saturation, and H is the reference blood oxygen saturation; The physical sign analysis unit compares the physical sign index β with each preset physical sign index, and adjusts the classification process of the patient data according to the comparison result: if β<B1, the physical sign analysis unit determines that the patient's physical sign index is low, and adjusts the similarity judgment threshold to A', setting A'=A×(β-B1) / B1; if B1≤β<B2, the physical sign analysis unit determines that the patient's physical sign index is normal and does not make any adjustment; if β≥B2, the physical sign analysis unit determines that the patient's physical sign index is high, and adjusts the similarity judgment threshold to A", setting A"=A×exp{(B2-β) / B1}; B1 is the first preset physical sign index, B2 is the second preset physical sign index, B1<B2; by adjusting the classification process of the patient data within the monitoring period, the accuracy of the classification process of the patient data within the monitoring period is improved.

[0039] Specifically, this embodiment does not impose any specific limitation on the method for obtaining the patient's vital sign information. Those skilled in the art can set it freely as long as the patient's vital sign information acquisition needs are met, such as obtaining it through the patient's test form; at the same time, the reference healthy blood pressure and reference blood oxygen saturation in this embodiment are the medians of the reference healthy blood pressure range and the reference blood oxygen saturation range, respectively, and the reference healthy blood pressure range and the reference blood oxygen saturation range can be queried through the Physical Sign Health Network.

[0040] Specifically, this embodiment does not make any specific limitations on the values ​​of the first preset vital sign index B1 and the second preset vital sign index B2. Technical personnel in this field can set them freely as long as the value requirements of the first preset vital sign index B1 and the second preset vital sign index B2 are met. For example, the first preset vital sign index B1 can be set to 1.2, and the value of the second preset vital sign index B2 can be set to 1.4.

[0041] Please continue reading Figure 3 As shown, the patient data processing module also includes a medical analysis unit, which is connected to the vital sign analysis unit, and is used to obtain hospital information within the monitoring period, and optimize the adjustment process of patient data classification according to the hospital information; the hospital information includes the total number of patients in the hospital within the monitoring period and the total number of patients carried by the hospital; the total number of patients carried by the hospital is the maximum number of patients that the hospital can carry; The medical analysis unit calculates the medical saturation index η of the hospital, and sets η=yn / ym; yn is the total number of patients in the hospital during the monitoring period, and ym is the total number of patients carried by the hospital.

[0042] The medical analysis unit optimizes the adjustment process of the patient data classification process according to the medical saturation index η, optimizes the first preset vital sign index to B1', sets B1'=B1×η, and optimizes the second preset vital sign index to B2', sets B2'=B2×η; by analyzing the saturation of hospitals in the monitored area to judge the hospital's ability to treat patients' diseases, the adjustment process of patient data classification is optimized, thereby improving the accuracy of the patient data classification process.

[0043] Specifically, this embodiment does not impose any specific restrictions on the method of obtaining hospital information. Technical personnel in this field can set it freely as long as the needs for obtaining hospital information are met. For example, it can be obtained through user interactive input, or the total number of patients in the hospital during the monitoring period can be obtained through the hospital real-time monitoring system.

[0044] Please continue reading Figure 1As shown, the system further includes a trend analysis module, which is connected to the patient data processing module, and is used to analyze the disease trend according to the patient data classification results within the monitoring period; The trend analysis module counts the number of patient data n(j) of the jth infectious disease in the monitoring period, and calculates the disease trend index γ(j) of the jth infectious disease, γ(j)=[n(j)-pn(j)] / T; wherein pn(j) is the number of patients with the jth infectious disease in the previous monitoring period, and T is the duration of the monitoring period; The trend analysis module compares γ(j) with each preset trend index, and analyzes the disease trend of the j-th infectious disease according to the comparison result: if γ(j)<Y1, the trend analysis unit determines that the disease trend of this type of infectious disease during the monitoring period is contained; if Y1≤γ(j)<Y2, the trend analysis unit determines that the disease trend of this type of infectious disease during the monitoring period is slowly growing; if γ(j)≥Y2, the trend analysis unit determines that the disease trend of this type of infectious disease during the monitoring period is rapidly growing; Y1 is the first preset trend index, Y2 is the second preset trend index, and Y1<Y2; by analyzing the disease trends of various infectious diseases, the development trends of various infectious diseases during the monitoring period can be determined, thereby improving the accuracy of disease trend analysis of various infectious diseases.

[0045] Specifically, this embodiment does not impose specific limitations on the values ​​of the first preset trend index Y1 and the second preset trend index Y2. Technical personnel in this field can set them freely as long as the value requirements of the first preset trend index Y1 and the second preset trend index Y2 are met. For example, in an area with a population of 100,000, the first preset trend index Y1 can be set to 1 person / hour, and the second preset trend index Y2 can be set to 2 people / hour.

[0046] Please continue reading Figure 1 As shown, the system also includes a risk warning module, which is connected to the trend analysis module and the patient data processing module. The risk warning module is used to analyze the infectious disease transmission status according to the classification results of the patient data within the monitoring period, and to provide disease risk warnings to users based on the infectious disease transmission status analysis results.

[0047] See also Figure 4 As shown, the risk warning module includes a transmission status analysis unit, which is used to analyze the regional infectious disease transmission status according to the classification results of patient data and the disease trend analysis results within the monitoring period; The transmission status analysis unit counts the patient data within the monitoring period as the number n1 of infectious diseases and the number n2 of non-infectious diseases; The transmission status analysis unit counts the number n3 of infectious diseases with a slow growth trend and the number n4 of infectious diseases with a fast growth trend during the monitoring period; The propagation status analysis unit analyzes the regional infectious disease propagation status according to the statistical results: when n1 / n2<U, if n3≥K, the propagation status analysis unit determines that the regional infectious disease propagation status is a type of clustered abnormality; if 0<n3<K, the propagation status analysis unit determines that the regional infectious disease propagation status is a controllable abnormality; if n3=0, the propagation status analysis unit determines that the regional infectious disease propagation status is normal; when n1 / n2≥U, if n3≥K, the propagation status analysis unit determines that the regional infectious disease propagation status is an explosive abnormality; if n3<K, the propagation status analysis unit determines that the regional infectious disease propagation status is a common abnormality; Among them, U is the ratio threshold, U>0, and K is the infectious disease type threshold; by analyzing the regional infectious disease transmission status, we can achieve a comprehensive analysis of various types of infectious diseases in the monitored areas and an analysis of the promotion of transmission among various infectious diseases, thereby improving the accuracy of the regional infectious disease transmission status analysis.

[0048] Specifically, this embodiment does not impose any specific restrictions on the values ​​of the ratio threshold U and the infectious disease type threshold K. Technical personnel in this field can set them freely as long as the value requirements of the ratio threshold U and the infectious disease type threshold K are met. In this embodiment, the optimal value of the ratio threshold U is 0.02, and the optimal value of the infectious disease type threshold K is 2.

[0049] Please continue reading Figure 4 As shown, the risk warning module also includes a risk warning unit, which warns the user based on the analysis results of the regional infectious disease transmission status within the monitoring period: When n4=0, if the regional infectious disease transmission status is normal, the risk warning unit does not issue a warning; if the regional infectious disease transmission status is type aggregation abnormality, the risk warning unit sends a second-level risk warning to the user; if the regional infectious disease transmission status is controllable abnormality, the risk warning unit sends a third-level risk warning to the user; if the regional infectious disease transmission status is explosive abnormality, the risk warning unit sends a first-level risk warning to the user; if the regional infectious disease transmission status is ordinary abnormality, the risk warning unit sends a second-level risk warning to the user; When n4>0, the risk warning unit sends a first-level risk warning to the user; through the infectious disease risk warning in the monitored area, efficient analysis of infectious disease data is achieved, thereby improving the efficiency of infectious disease data processing.

[0050] Specifically, the first-level risk warning described in this embodiment is the highest level of risk warning, which is suitable for scenarios where multiple infectious diseases occur collectively and the number of patients is large or the number of patients with a certain infectious disease increases rapidly; the second-level risk warning is a scenario where the number of patients is small but the number of infectious diseases is large or the number of patients is large but the types of infectious diseases are normal; the third-level risk warning is a scenario where infectious diseases occur in normal numbers with a low growth trend.

[0051] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. An infectious disease data processing system based on big data, characterized in that: include: Disease data collection module, used to collect clinical characteristics of various infectious diseases; A patient data collection module is used to collect patient data within the monitoring period; A disease model building module is used to cluster the clinical characteristics of various infectious diseases according to the clinical characteristics of various infectious diseases to obtain each cluster clinical cluster and each index feature. The disease model building module is also used to analyze the disease distinguishing characteristics and similar characteristics of various infectious diseases according to each cluster clinical cluster, and analyze the identification path of various infectious diseases according to the analysis results of the disease distinguishing characteristics and similar characteristics of various infectious diseases; Patient data processing module, used to classify patient data within the monitoring period according to the results of the identification path analysis of various infectious diseases; Trend analysis module, used to analyze disease trends based on the classification results of patient data within the monitoring period; The risk warning module is used to analyze the regional infectious disease transmission status based on the classification results of patient data during the monitoring period, and to provide disease risk warnings to users based on the regional infectious disease transmission status analysis results.

2. The infectious disease data processing system based on big data according to claim 1, characterized in that: The disease model building module includes a cluster analysis unit, which is used to cluster the clinical characteristics of various infectious diseases to obtain each cluster clinical cluster and each cluster clinical characteristic, and use the cluster clinical characteristic as the index characteristic of the corresponding cluster clinical cluster.

3. The infectious disease data processing system based on big data according to claim 2, characterized in that: The disease model building module also includes an iterative analysis unit, which is used to analyze the disease distinguishing characteristics of various infectious diseases; The iterative analysis unit uses the clinical features other than the similar features as clustering variables of the clustered clinical clusters, performs secondary clustering on each infectious disease in the clustered clinical clusters, and obtains each secondary clustered clinical cluster and each secondary similar feature; The iterative analysis unit performs iterative analysis on each secondary cluster clinical feature using the secondary clustering process as iterative logic to obtain disease distinguishing features of various infectious diseases.

4. The infectious disease data processing system based on big data according to claim 3 is characterized in that: The disease model building module also includes a model building unit, which is used to use the disease distinguishing features and similar features of each clustered clinical cluster as identification paths for various infectious diseases, and store the identification paths for various infectious diseases.

5. The infectious disease data processing system based on big data according to claim 4, characterized in that: The patient data processing module includes a data matching unit, which is used to match the patient's clinical characteristics with the identification paths of various infectious diseases, and calculate the matching similarity α(j) between the patient data and the j-th infectious disease, and compare α(j) with the similarity judgment threshold A to determine the matching result between the patient data and the j-th infectious disease, and the matching result between the patient data and the j-th infectious disease includes a successful match and a failed match; The data matching unit classifies the patient data into the jth infectious disease when the matching is successful; and does not classify when the matching fails; When the patient data fails to match with all types of infectious diseases, the data matching unit classifies the patient data as non-infectious diseases.

6. The infectious disease data processing system based on big data according to claim 5, characterized in that: The patient data processing module also includes a physical sign analysis unit, which calculates the patient's physical sign index β; The physical sign analysis unit compares the physical sign index β with each preset physical sign index to determine the abnormality of the patient's physical sign index, and adjusts the classification process of the patient data within the monitoring period according to the abnormal judgment result of the patient's physical sign index. The abnormality of the patient's physical sign index includes a low patient's physical sign index, a normal patient's physical sign index and a high patient's physical sign index. When the patient's physical sign index is low, the similarity judgment threshold is adjusted to A'; when the patient's physical sign index is high, the similarity judgment threshold is adjusted to A".

7. The infectious disease data processing system based on big data according to claim 6, characterized in that: The patient data processing module further includes a medical analysis unit, which is used to optimize the adjustment process of patient data classification according to hospital information; The medical analysis unit calculates the medical saturation index η of the hospital; The medical analysis unit optimizes the adjustment process of the patient data classification process according to the medical saturation index η, optimizes the first preset vital sign index to B1', and optimizes the second preset vital sign index to B2'.

8. The infectious disease data processing system based on big data according to claim 7, characterized in that: The trend analysis module is used to analyze the disease trends of various infectious diseases according to the classification results of patient data within the monitoring period; The trend analysis module counts the number of patient data n(j) of the jth infectious disease during the monitoring period, and calculates the disease trend index γ(j) of the jth infectious disease; The trend analysis module compares γ(j) with each preset trend index to analyze the disease trend of the j-th infectious disease. The analysis results of the disease trend of the j-th infectious disease include containment, slow growth and rapid growth.

9. The infectious disease data processing system based on big data according to claim 8, characterized in that: The risk warning module includes a transmission status analysis unit, which is used to analyze the regional infectious disease transmission status according to the classification results of patient data and the disease trend analysis results within the monitoring period; The transmission status analysis unit counts the patient data within the monitoring period as the number n1 of infectious diseases and the number n2 of non-infectious diseases; The transmission status analysis unit counts the number n3 of infectious diseases with a slow growth trend and the number n4 of infectious diseases with a fast growth trend during the monitoring period; The transmission status analysis unit analyzes the regional infectious disease transmission status according to the statistical results. The regional infectious disease transmission status includes normal, type clustering abnormal, controllable abnormal, explosive abnormal and common abnormal.

10. The infectious disease data processing system based on big data according to claim 9, characterized in that: The risk warning module also includes a risk warning unit, which warns the user based on the analysis results of the regional infectious disease transmission status within the monitoring period: When n4=0, if the regional infectious disease transmission status is normal, the risk warning unit does not issue a warning; If the regional infectious disease transmission status is abnormal type aggregation, the risk warning unit sends a secondary risk warning to the user; If the regional infectious disease transmission status is controllable abnormal, the risk warning unit sends a third-level risk warning to the user; If the regional infectious disease transmission status is abnormally explosive, the risk warning unit sends a first-level risk warning to the user; If the regional infectious disease transmission status is normal abnormal, the risk warning unit sends a secondary risk warning to the user; When n4>0, the risk warning unit sends a first-level risk warning to the user.

Images