Medical data processing method and device, storage medium and electronic equipment
By constructing active sub -networks and combining statistical indicators, the problem of low recognition efficiency and poor accuracy of infectious diseases has been solved, and more efficient and accurate disease identification has been achieved.
Patent Information
- Application Number
- CN202411318290.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-20
- Publication Date
- 2025-01-24
AI Technical Summary
In the prior art, the identification efficiency of infectious disease hot diseases is low and the accuracy is poor, mainly due to the limitations of relying on manual analysis and intelligence data.
By obtaining medical intelligence data and statistical data, build an active sub -network, calculate the comprehensive activity of the disease, and determine the target diseases of the research area in combination with statistical indicators parameters.
The identification efficiency and accuracy of the infectious disease hot spots is improved, the limitations of manual processing are avoided, and the comprehensiveness and accuracy of the data are enhanced.
Smart Images
Figure CN119361167A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of computer technology, and in particular, to a medical data processing method, a medical data processing device, a computer-readable storage medium, and an electronic device. Background Art
[0002] Domestic and foreign infectious disease data mainly include intelligence data and statistical data released by domestic and foreign official websites. The sources of infectious disease data are scattered and the dimensions of statistical data vary.
[0003] In related technologies, the output of major infectious disease events is mainly achieved manually. In each cycle, it is necessary to analyze the hot diseases of the current cycle through manual judgment based on intelligence data.
[0004] Among the above methods, the processing efficiency of analyzing hot diseases manually is low, and analyzing hot diseases based on intelligence data has certain limitations and low accuracy. Summary of the invention
[0005] The purpose of the present disclosure is to provide a medical data processing method and device, a storage medium, and an electronic device, thereby overcoming, at least to a certain extent, the problems of low efficiency and poor accuracy in identifying hot disease types due to the limitations and defects of related technologies.
[0006] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present disclosure.
[0007] According to one aspect of the present disclosure, a medical data processing method is provided, including: obtaining medical intelligence data and medical statistical data for each disease to be processed in the current cycle; constructing an active subnetwork for each disease to be processed, and processing the medical intelligence data based on the active subnetwork to obtain the comprehensive activity of each disease to be processed; determining the statistical indicators of the medical statistical data in the study area, and determining the statistical indicator parameters corresponding to the statistical indicators; determining the comprehensive data of each disease to be processed in the study area according to the comprehensive activity of the disease and the statistical indicator parameters, and determining the target disease in the study area from the diseases to be processed according to the comprehensive data.
[0008] In an exemplary embodiment of the present disclosure, an active subnetwork is constructed for each disease to be treated, including: performing keyword extraction on the medical intelligence data corresponding to the disease to be treated, obtaining subject words and subject word distribution to obtain keywords for the current cycle; mapping an established disease knowledge base with keywords to obtain reference keywords and reference keyword distribution for each topic related to the disease to be treated; determining nodes based on topics and reference keywords to construct an active subnetwork for the disease to be treated.
[0009] In an exemplary embodiment of the present disclosure, medical intelligence data is processed based on active subnetworks to obtain comprehensive activity of disease types, including: determining a first activity score for each reference keyword in the active subnetwork; determining second activity scores for multiple topics based on the first activity score for each reference keyword; and determining the comprehensive activity of the disease type to be processed based on the second activity score.
[0010] In an exemplary embodiment of the present disclosure, second activity scores of multiple topics are determined based on the first activity score of each reference keyword, including: taking the position of the reference keyword in the knowledge base as a weight, performing weighted averaging on the first activity scores of the reference keywords, and obtaining second activity scores of the multiple topics.
[0011] In an exemplary embodiment of the present disclosure, keyword extraction is performed on medical intelligence data to obtain subject words and subject word distribution to obtain keywords for the current period, including: converting the document set corresponding to the medical intelligence data into a bag-of-words model text representation to determine the number of times different words appear in the document; determining the topic and topic number parameters, and randomly assigning a topic to each word; iteratively determining the topic distribution and word distribution through Gibbs sampling, obtaining subject words and subject word distribution, and extracting keywords for the current period.
[0012] In an exemplary embodiment of the present disclosure, determining the statistical indicators of medical statistical data in a study area includes: mapping the medical statistical data with an indicator dictionary table to obtain standard indicator data; when there are multiple data sources for the standard indicator data of the disease to be treated in the study area, and the multiple data sources include official data sources of the study area, determining the statistical indicators according to a first weight of the official data source of the study area and a second weight of other sources; the first weight is greater than the second weight; when there are multiple data sources for the standard indicator data of the disease to be treated in the study area, and the multiple data sources are all official data sources of other regions except the study area, determining the statistical indicators by weighted average; when there is one data source for the standard indicator data of the disease to be treated in the study area, using the standard indicator data of the data source as the statistical indicator.
[0013] In an exemplary embodiment of the present disclosure, comprehensive data of the diseases to be treated in the study area are determined based on the comprehensive activity of the diseases and statistical indicator parameters, including: superimposing the comprehensive activity of the diseases and the statistical indicator change rate to obtain the comprehensive data of the diseases to be treated in the study area; or using the disease activity as the base and the statistical indicator change rate as the index to determine the comprehensive data of the diseases to be treated in the study area.
[0014] According to one aspect of the present disclosure, there is provided a medical data processing device, comprising: a data acquisition module, used to acquire medical intelligence data and medical statistical data of each disease to be processed in the current cycle; an activity determination module, used to construct an active sub-network for each disease to be processed, and process the medical intelligence data based on the active sub-network to obtain the comprehensive activity of each disease to be processed; a statistical indicator parameter determination module, used to determine the statistical indicators of the medical statistical data in a study area, and determine the statistical indicator parameters corresponding to the statistical indicators; a target disease judgment module, used to determine the comprehensive data of each disease to be processed in the study area according to the comprehensive activity of the disease and the statistical indicator parameters, and determine the target disease in the study area from the diseases to be processed according to the comprehensive data.
[0015] According to one aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, any one of the medical data processing methods described above is implemented.
[0016] According to one aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform any one of the medical data processing methods by executing the executable instructions.
[0017] In the medical data processing method, medical data processing device, computer-readable storage medium, and electronic device provided in the embodiments of the present disclosure, on the one hand, since the comprehensive activity of the disease can be obtained based on the active subnetwork, the statistical indicator parameters of the medical statistical data in the study area can be determined; the target disease in the study area is determined according to the comprehensive activity of the disease and the statistical indicator parameters determined based on the medical statistical data, thereby avoiding the problems caused by manual processing methods and improving the efficiency and timeliness of identifying the target disease. On the other hand, since it is necessary to determine the comprehensive activity of the disease based on the medical intelligence data and determine the statistical indicator parameters based on the medical statistical data, the target disease can be identified from multiple dimensions, thus avoiding the limitations in the relevant technology, increasing the comprehensiveness of the data, and improving the accuracy of identifying the target disease.
[0018] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without creative work.
[0020] Figure 1 A schematic diagram schematically illustrates a medical data processing method in an embodiment of the present disclosure.
[0021] Figure 2 The following is a schematic diagram showing a process for determining the comprehensive activity of a disease to be treated in an embodiment of the present disclosure.
[0022] Figure 3 The flowchart of keyword extraction in the embodiment of the present disclosure is schematically shown.
[0023] Figure 4 The structural diagram of the active sub-network in the embodiment of the present disclosure is schematically shown.
[0024] Figure 5 A schematic diagram schematically illustrates the construction of an active subnetwork for each medical intelligence data in an embodiment of the present disclosure.
[0025] Figure 6 The overall process flow diagram for identifying hot spot diseases in an embodiment of the present disclosure is schematically shown.
[0026] Figure 7 A block diagram of a medical data processing device in an embodiment of the present disclosure is schematically shown.
[0027] Figure 8 A block diagram of an electronic device in an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION
[0028] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as being limited to the examples set forth herein; on the contrary, these embodiments are provided so that the present disclosure will be more comprehensive and complete, and the concepts of the example embodiments are fully conveyed to those skilled in the art. The described features, structures, or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known technical solutions are not shown or described in detail to avoid obscuring various aspects of the present disclosure.
[0029] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.
[0030] The data on major infectious diseases at home and abroad mainly include intelligence data and statistics published on official websites at home and abroad. The sources of intelligence data and statistics are scattered, and the dimensions of statistical data vary. The output of major events of major infectious diseases at home and abroad is mainly achieved manually, which is cumbersome and consumes huge manpower costs. Although there are multiple data sources such as Promed-Mail, Health, WHO Dons, etc. for foreign intelligence data, hot information can be obtained according to word segmentation technology, but some key points still require manual intervention.
[0031] In some embodiments, data collection and preprocessing are performed on data from different sources at home and abroad to obtain global infectious disease report data, and risk analysis and knowledge base construction are performed on the data. However, which disease is a hot disease in each cycle and how to confirm hot diseases are still mainly determined by manual judgment. In addition, when determining hot diseases, hot diseases are extracted from domestic and foreign infectious disease intelligence data, that is, the current hot infectious diseases are confirmed. Therefore, it has certain limitations and the accuracy of determining hot diseases is poor.
[0032] In order to solve the technical problems in the related technologies, a medical data processing method is provided in the embodiments of the present disclosure, which can be executed by a server or a client to process medical intelligence data and medical statistical data to obtain comprehensive data of the diseases to be processed in the target area, and then determine the hot diseases in the current period based on the comprehensive data.
[0033] Next, refer to Figure 1 The figure shows a detailed description of the medical data processing method in the embodiment of the present disclosure.
[0034] In step S110, medical intelligence data and medical statistical data of each disease to be processed in the current cycle are obtained.
[0035] In the disclosed embodiment, the data to be processed in the current cycle can be obtained. The data to be processed can be multiple pieces of medical data. Further, the data to be processed can be processed into medical intelligence data of multiple types of diseases to be processed. It should be noted that the medical intelligence data is obtained through authorization.
[0036] Exemplarily, the data to be processed can first be collected from the data source, and the collected data to be processed can be normalized according to one or more dimensions of disease type, region, and date to obtain medical intelligence data. Data accuracy can be improved through data normalization. The data to be processed can be data used to represent the overall situation of the disease. For example, labels corresponding to the dimensions used for data normalization can be displayed at any position below the data to be processed. The labels may include, but are not limited to, disease type, media, source, region, and time. It should be noted that each piece of data to be processed can be processed into medical intelligence data corresponding to the disease to be processed.
[0037] The disease to be processed can be any type of disease in the current cycle, for example, every infectious disease or other type of disease in the current cycle. Infectious diseases are used as an example for illustration. Medical data can be all data related to the disease to be processed, for example, disease type, disease symptoms, disease transmission, etiology, vaccine status, policy information, case data, variant strain data, new data, disease status ratio, etc.
[0038] Among them, medical intelligence data is used to represent the overall situation of the diseases to be treated. Exemplarily, the data sources of medical intelligence data can be multiple, and the data sources of medical intelligence data can include, for example, Promed-Mail, HealthMap, WHO DONs, etc. However, the descriptions of the status of a certain disease in medical intelligence data from different data sources are complex and diverse, and it is impossible to quickly locate the key content. For example, the definition of the title of medical intelligence data only includes disease, region, and event keywords, and the content of medical intelligence data includes descriptions of different dimensions such as disease transmission, etiology, vaccine status, policy information, etc.
[0039] At the same time, the pending statistical data of each pending disease in the current cycle can also be obtained. The pending statistical data can be used to indicate the specific situation of the pending disease. After obtaining the pending statistical data, the pending statistical data can be preprocessed to obtain medical statistical data. Data preprocessing can include one or more of data cleaning, deduplication, format conversion, disease type normalization, regional normalization, and date normalization. Data preprocessing can improve data accuracy.
[0040] Based on this, medical statistical data can be statistical data of the diseases to be treated, and the statistical data is used to indicate the specific situation of the diseases to be treated. The data sources of the statistical data can also be multiple, and the medical statistical data can cover multiple regions. The region can be a country, a province, a city, etc., which is not specifically limited here. In some embodiments, the statistical data may include data obtained from the medical database of one or more medical institutions in each region, such as outpatient medical data or inpatient medical data, and online consultation data. Among them, the outpatient medical data and inpatient medical data can be medical record data stored in the internal database of any medical institution, or can be medical record data disclosed in the database of other platforms. Among them, the medical database within the medical institution is authorized by the medical institution, and the data in the medical database meets the requirements of rationality and legality. Statistical data can also include data obtained from non-medical institutions in each region, such as medical data related to the diseases to be treated obtained from various social platforms. It should be noted that medical statistical data is also data obtained through authorization.
[0041] In the disclosed embodiments, medical statistical data may include one or more of case data, variant data, new data, laboratory data, and disease status ratios. Specifically, the statistical data may include newly confirmed cases, newly confirmed deaths, cumulative confirmed cases, cumulative deaths, vaccine data, variant data, newly hospitalized cases, existing hospitalized cases, confirmed cases by age group, hospitalized cases by age group, severe cases, laboratory samples and positive rates, number of animal infections, morbidity, mortality, severe disease rate, case fatality rate, etc.
[0042] In step S120, an active sub-network is constructed for each disease to be treated, and the medical intelligence data is processed based on the active sub-network to obtain the comprehensive activity of each disease to be treated.
[0043] In the disclosed embodiment, after obtaining the medical intelligence data and medical statistical data of each disease to be treated, the medical intelligence data and medical statistical data can be analyzed separately. Specifically, the comprehensive activity of the disease to be treated can be determined based on the medical intelligence data, and the statistical indicator parameters of the disease to be treated in the study area can be determined based on the medical statistical data. Among them, the comprehensive activity of the disease is used to indicate the importance of the disease to be treated in the intelligence dimension; the statistical indicator parameters are used to indicate the range of changes in the statistical indicators of the disease to be treated in the study area, and the range of changes in the statistical indicators can be used as an evaluation dimension to evaluate whether the disease to be treated is a hot disease.
[0044] In some embodiments, the process of determining the comprehensive activity of the disease to be treated based on the medical intelligence data is first described in detail. Figure 2 As shown in , it mainly includes the following steps:
[0045] In step S210, keyword extraction is performed on the medical intelligence data corresponding to the disease to be processed, and the subject words and the subject word distribution are obtained to obtain the keywords of the current cycle.
[0046] In the disclosed embodiment, since the description of the status of a certain disease in medical intelligence data from different data sources is complex and diverse, it is impossible to quickly locate the key content. Based on this, keyword extraction can be performed on the medical intelligence data. During the keyword extraction process, the intelligence data of the disease to be processed in the current cycle in each research area can be taken as a document, and further the documents corresponding to all research areas can be taken as a document set.
[0047] Figure 3 A flowchart for keyword extraction is schematically shown in FIG. Figure 3 As shown in , it mainly includes the following steps:
[0048] In step S310, the document set corresponding to the medical intelligence data is converted into a bag-of-words model text representation to determine the number of times different words appear in the document.
[0049] The bag-of-words model can convert a document into a vector representation, regardless of the order of words in the document, but only considers the number of times a word appears in the document. Based on this, the documents of each region corresponding to the medical intelligence data can be converted into a bag-of-words model text representation to obtain the number of times the words contained in each document appear in the document.
[0050] In step S320, the topic and topic quantity parameters are determined, and a topic is randomly assigned to each word.
[0051] The content of the topic can be determined, and the setting of the content of the topic is related to the content of the intelligence data represented by the medical intelligence data. The content of the topic can include, for example, one or more of the following: disease type, region, etiology information, symptoms, vaccine, new outbreak, indicator, and transmission route, which is configured according to the actual situation.
[0052] The topic number parameter may be a given topic number, and may also be used to indicate the number of hot diseases screened out. For example, when the topic number parameter K is 20, data of the top 20 hot diseases may be displayed.
[0053] Furthermore, a topic can be randomly assigned to each word according to the LDA (Latent Dirichlet Allocation, document topic generation) model.
[0054] In step S330, the topic distribution and word distribution are iteratively calculated by Gibbs sampling to obtain the subject words and the subject word distribution to obtain the keywords of the current period.
[0055] In this step, each document has its own topic distribution, which can be a multinomial distribution. Each topic has its own word distribution, which can also be a multinomial distribution.
[0056] Gibbs sampling can generate data from complex probability distributions, and only requires knowing the conditions of each component on other components. The specific sampling steps may include: initially randomly assigning a topic to each word in each document, and counting the information of words and topics.
[0057] In some embodiments, after randomly assigning a topic to each word, the topic distribution and word distribution can be iteratively calculated by Gibbs sampling. When the Gibbs sampling algorithm solves the LDA method, the goal is to obtain the topic distribution and word distribution of the document. Specifically, select a suitable topic number parameter, that is, the number of topics K, and select a suitable hyperparameter vector. For each word in the document, a topic is randomly assigned. All documents can be combined to form a word vector to determine the topic distribution of all words. Assume that the joint distribution of the word vector and the topic distribution is first obtained, and then the conditional probability distribution of the topic feature corresponding to a certain word can be obtained. Gibbs sampling can be further performed to obtain the topic of each word after convergence. On this basis, the number of topics for each word is counted to obtain the topic distribution of all words. Gibbs sampling is to sample in the K document-topic-word paths. When the sampling converges, the topics of all words can be obtained. The topic probability in each document can be counted to obtain the topic distribution of the document, and the probability of all words in each topic can be counted to obtain the topic word distribution. Among them, the topic distribution refers to the distribution of the topic of each document. The topic word distribution refers to the distribution of all words in each topic.
[0058] Furthermore, after counting the topics of all words, the number of topics of all words can be counted, thereby obtaining the word distribution of each topic. The word distribution refers to the distribution of each word in multiple topics.
[0059] After obtaining the topic distribution and word distribution, it can be considered that a stable distribution result is obtained. Based on this, since the topic distribution and word distribution have been determined, the subject words can be determined according to the words contained in each topic, and the subject word distribution can be determined according to the probability of all words contained in each topic. After determining the subject words, the keywords related to the subject words can be determined according to the subject words to complete the keyword extraction process. Among them, keywords refer to different types of words that can be extracted from medical intelligence data. Keywords may contain words related to or unrelated to the disease, such as names, times, cases, etc.
[0060] It should be noted that keyword extraction may also be achieved through a suitable word segmentation algorithm, which is not specifically limited here.
[0061] In the disclosed embodiment, according to the method of step S310 to step S330, the document set corresponding to the medical intelligence data of each disease to be processed is converted into a bag-of-words model text representation, a topic is randomly assigned to each word, and the topic distribution and word distribution are iteratively calculated using Gibbs sampling to obtain the keywords of the current cycle. For each cycle, the subject word distribution and subject words can be determined by the above method, thereby determining the keywords, which will not be repeated here. By extracting keywords, effective information can be obtained from the data, accuracy can be improved, and attention can be increased.
[0062] In step S220, the established disease knowledge base is mapped with keywords to obtain reference keywords and reference keyword distribution of each topic related to the disease to be processed.
[0063] In the disclosed embodiment, the disease knowledge base may be an official standard database established based on disease data from different data sources. The disease knowledge base may include fixed-form knowledge content, which at least includes pathogens, transmission routes, global epidemic overview, clinical manifestations, diagnosis, treatment, risk factors, prevention and control, and disease case status.
[0064] Since the extracted keywords may include non-focused words, such as patient names, etc. In order to highlight the key information about the diseases to be treated in the medical intelligence data, the acquired keywords can be mapped with the constructed disease knowledge base, so as to obtain the keywords associated with the diseases to be treated as reference keywords, which can be specifically mapped to the reference keywords and reference keyword distribution corresponding to each topic. That is, the reference keywords and reference keyword distribution obtained by mapping are keywords that are strongly related to the diseases to be treated. For example, the correlation between the reference keywords and the reference keyword distribution and the diseases to be treated may be greater than the correlation threshold. The mapping here refers to establishing an association relationship between the keywords and the fixed form of knowledge content in the disease knowledge base. For example, keyword 1 is associated with diagnosis, and keyword 2 is associated with pathogens. Based on this, the reference keywords include at least pathogens, transmission routes, global epidemic profiles, clinical manifestations, diagnosis, treatment, risk factors, prevention and control, and disease case conditions.
[0065] Next, continue to refer to Figure 2 As shown in , in step S230 , nodes are determined based on the subject and reference keywords to construct an active sub-network of the disease to be treated.
[0066] In the disclosed embodiment, since each topic may correspond to multiple keywords, in order to improve accuracy, one or more keywords existing in the disease knowledge base can be screened out from the multiple keywords corresponding to the topic as reference keywords. Furthermore, the topic and the reference keywords can be used as nodes of the network to construct an active sub-network of the disease to be processed.
[0067] Exemplarily, the subject can be used as a node to construct a keyword network. For example, the disease to be treated can be used as the root node, the subject can be used as the parent node, and the keyword network can be constructed. Furthermore, the disease to be treated can be used as the root node, the subject can be used as the parent node, and the reference keyword can be used as the child node to construct an active sub-network corresponding to each disease to be treated. Figure 4 The structure of the active subnetwork is schematically shown in Figure 4 As shown in , an active subnetwork may include a root node, a parent node, and a child node. The root node may be the disease type A to be treated; the parent node may be a symptom, pathogen, transmission route, disease type, indicator, new outbreak, and other topics. The child node may correspond to the parent node. For example, when the parent node is an indicator, its child node may be a confirmed case, a death case, or a suspected case; when the parent node is a new outbreak, its child node may be the first case, a variant, or the first discovery. When the parent node is a symptom, its child node may be skin ulcer, cough, or fever, and so on.
[0068] It should be noted that after the medical intelligence data is updated, the subject word network and active sub-network can be dynamically updated. Through continuous updates, it can be ensured that the active sub-network always reflects the latest intelligence dynamics. This avoids the problem of not being able to obtain the latest hotspot intelligence of a certain disease to be treated only through subject words and subject word distribution, and improves the accuracy and intuitiveness of obtaining hotspot intelligence.
[0069] In step S240, the medical intelligence data is processed based on the active sub-network to obtain the comprehensive activity of the disease to be processed.
[0070] In the disclosed embodiment, after obtaining the active sub-network, the second activity scores of the parent nodes represented by the multiple subject words can be determined based on the paths in the active sub-network and the first activity scores of the child nodes represented by the reference keywords, and then the comprehensive activity of the diseases to be treated can be determined based on the second activity scores of the multiple subject words.
[0071] The first activity score of each reference keyword can be determined based on the number of times each reference keyword appears in the documents of each research area in the current period. Figure 4 As shown in , if the reference keyword represented by the variant appears 1 times in the documents of the study area, the first activity score of the reference keyword represented by the variant is 1. Similarly, if the reference keyword represented by skin ulcer appears 2 times in the documents of the study area, the first activity score of the reference keyword represented by skin ulcer is 2.
[0072] After determining the first activity score of the reference keyword, the position of the reference keyword in the knowledge base can be used as a weight, and the first activity score of the reference keyword can be weighted averaged to obtain the second activity score of multiple topics. Exemplarily, a topic may include one or more reference keywords, and the first activity score of each reference keyword can be used as a calculated value, and the position of each reference keyword in the knowledge base can be used as a weight. The first activity scores of multiple reference keywords are weighted averaged according to their respective weights to obtain the second activity score of the topic. The knowledge base where each reference keyword is located includes multiple nodes, and the position represented by each node can correspond to different weights. For example, the weight is positively correlated with the importance, and the larger the weight, the higher the importance.
[0073] For example, when the parent node represented by the topic is a symptom, its child nodes may be skin ulcer, cough, and fever, that is, the reference keywords may include skin ulcer, cough, and fever. At this time, if the reference keyword represented by skin ulcer appears 2 times in the documents of the study area, the first activity score of the reference keyword represented by skin ulcer is 2. If cough and fever do not appear, the corresponding first activity score is 0. On this basis, if the weight of the reference keyword represented by skin ulcer is 1, the second activity score of the topic represented by the symptom is 2. Similarly, the second activity score of each topic can be calculated.
[0074] Furthermore, the second activity scores of each topic can be arranged in descending order, and the largest second activity score can be determined as the comprehensive activity of the disease to be treated. Of course, the second activity scores of each topic can also be averaged to determine the comprehensive activity of the disease to be treated.
[0075] It should be noted that for each disease to be treated in the current cycle, the comprehensive activity can be determined according to the above method. The comprehensive activity can be used to measure the importance of the disease to be treated in the intelligence dimension represented by the intelligence data.
[0076] refer to Figure 5 As shown in , if the data to be processed is obtained, it can be processed as follows Figure 5 Medical intelligence data in. Furthermore, for each piece of medical intelligence data, it represents the medical data about the diseases to be treated in each research area in the current period. Keywords and keyword distribution can be extracted from it, and then the keywords are mapped with the established disease knowledge base to obtain reference keywords and reference keyword distribution. On this basis, keywords that are strongly related to each topic are determined as reference keywords. The disease to be treated is taken as the root node, the topic as the parent node, and the reference keyword as the child node to construct an active subnetwork for each disease to be treated.
[0077] Next, continue to refer to Figure 1 As shown in , in step S130, the statistical indicators of the medical statistical data in the research area are determined, and the statistical indicator parameters corresponding to the statistical indicators are determined.
[0078] In the embodiment of the present disclosure, after obtaining medical statistical data, the statistical indicator parameters of the diseases to be treated in the research area can be determined according to the medical statistical data. The statistical indicator parameters are used to represent the change range of the statistical indicators of the diseases to be treated in the research area, and the change range of the statistical indicators can be used as an evaluation dimension to evaluate whether the diseases to be treated are hot diseases.
[0079] Medical statistical data may be statistical data used to represent the specific situation of the disease to be treated. Exemplarily, the statistical data may include one or more of case data, variant data, new data, laboratory data, and disease state ratios. Specifically, the statistical data may include newly confirmed cases, newly confirmed deaths, cumulative confirmed cases, cumulative deaths, vaccine data, variant data, newly hospitalized cases, existing hospitalized cases, confirmed cases by age group, hospitalized cases by age group, severe cases, laboratory samples and positive rates, number of animal infections, morbidity, mortality, severe disease rate, case fatality rate, etc.
[0080] Diseases from different data sources also have multiple definition dimensions for the same disease. In order to facilitate the use of statistical data dimensions, an indicator dictionary table for the source of disease data can be established, and the indicator dimensions of key concerns can be maintained in the indicator dictionary table. Different naming methods for the same indicator can also be defined in the indicator dictionary table to facilitate the normalization of indicators in medical statistical data. The indicator dictionary can include indicator dimensions for multiple diseases, and can contain different indicator dimensions for each disease.
[0081] After obtaining the medical statistics data of a certain research area, the medical statistics data can be mapped with the defined indicator dictionary table to obtain standard indicator data for further analysis and use of the medical statistics data. Standard indicator data refers to the medical statistics data that have been normalized according to the indicator dimensions of the indicator dictionary table.
[0082] Furthermore, the statistical indicator parameter of the medical statistical data may be calculated. The statistical indicator parameter may be an evaluation dimension for evaluating whether the disease to be treated is a hot disease, which may represent the change range of the statistical indicator of the disease to be treated. Exemplarily, the statistical indicator parameter may be a statistical indicator change rate, and in addition, other types of parameters may be used as long as they can reflect the change range.
[0083] Since the medical statistical data used to calculate the statistical indicator parameters come from multiple data sources, the statistical periods of different data sources are inconsistent. In order to improve accuracy, the statistical data of different data sources of the same indicator dimension can be normalized to obtain a result value as the statistical indicator. For example, the standard indicator data of multiple data sources with the same research area, date and statistical period can be weighted and calculated to obtain the statistical indicator.
[0084] In some embodiments, medical statistical data can be mapped to an established indicator dictionary table to map the medical statistical data to standard indicator data. Furthermore, the statistical indicators of the study area can be determined based on the status information of the standard indicator data from different data sources in each study area to achieve the unification of different data sources. The status information may include at least the number of data sources of the standard indicator data of the disease to be treated in the study area and whether the standard indicator data comes from the official data of the study area. Based on this, the statistical indicators corresponding to each standard indicator data can be determined based on the number of data sources of the standard indicator data of the disease to be treated in the study area and whether the standard indicator data comes from the official data of the study area.
[0085] Specifically, whether the standard indicator data comes from official data of the study area, including at least part of the official data from the study area, or all of the official data from other regions except the study area. That is, the data source only includes the official data source of the study area, or the data source includes both the official data source of the study area and the official data source of other regions, or the data source only includes the official data source of other regions.
[0086] When there are multiple data sources for the standard indicator data of the disease to be treated in the study area, the multiple data sources may include official data sources of the study area and other sources, and the other sources may be official data sources of other regions. The first weight of the official data source of the study area is determined, and the second weight of the other sources is determined. The statistical indicators are further determined based on the first weight of the official data source of the study area and the second weight of other sources; wherein the first weight is greater than the second weight. For example, the first weight can be set to 0.7, and the second weight can be set to 0.3 on average.
[0087] When there are multiple data sources for the standard indicator data of the disease to be treated in the study area, and the multiple data sources are official data sources from other regions except the study area, the weighted average is taken through the weights corresponding to the official data sources in other regions to determine the statistical indicators. Among them, the weights of official data sources in different regions can be the same or different, and can also be determined according to actual conditions.
[0088] When there is a data source for standard indicator data of the disease to be treated in the study area, the standard indicator data of the data source can be used as statistical indicators.
[0089] By obtaining statistical indicators of medical statistical data in the research area, indicator data from multiple data sources can be managed in a unified manner, thereby improving accuracy.
[0090] In the disclosed embodiment, after determining the statistical indicator, the corresponding statistical indicator parameter can be determined based on the statistical indicator, so as to determine whether the disease to be treated is a hot disease that is the focus of attention in the current cycle in combination with the statistical indicator parameter. Exemplarily, the statistical indicator parameter can be the statistical indicator change rate. The corresponding statistical indicator change rate can be determined based on the statistical indicator, and the statistical indicator change rate can be determined as an evaluation parameter for evaluating whether the disease to be treated is a hot disease that is the focus of attention in the current cycle. Among them, the statistical indicator change rate is determined by the following calculation method: determine the difference between the statistical indicator of the current cycle and the statistical indicator of the previous cycle, and calculate the ratio of the difference to the statistical indicator of the previous cycle, take the absolute value of the ratio and multiply it by 100% to obtain the statistical indicator change rate.
[0091] For example, the change rate of the statistical indicator of a certain disease to be processed in a certain data source can be used to evaluate the importance of the statistical indicator. For example, if there are 100 confirmed cases of a disease to be processed in a certain data source, and if there are 100 people in each time period, then it can be considered that the change rate of the statistical indicator in the data source is 0, that is, the statistical indicator changes slowly, so the disease to be processed may be a non-hotspot disease.
[0092] Next, continue to refer to Figure 1 As shown in, in step S140, the comprehensive data of each disease to be treated in the study area is determined according to the comprehensive activity of the disease and the statistical indicator parameters, and the target disease in the study area is determined from the multiple diseases to be treated according to the comprehensive data.
[0093] In the disclosed embodiment, the statistical indicator parameter may be a statistical indicator change rate. The target disease may be a hot disease with high attention. On this basis, the comprehensive activity of the disease corresponding to the medical intelligence data and the statistical indicator change rate related to the medical statistical data may be combined to determine the comprehensive data of a disease to be treated in the research area, and then the hot disease may be screened out from the disease to be treated based on the comprehensive data.
[0094] In some embodiments, the comprehensive activity of the disease can be used as the base number, and the rate of change of the statistical indicator can be used as the index to determine the comprehensive data of the disease to be treated in the study area.
[0095] In other embodiments, the comprehensive activity of the disease and the rate of change of the statistical indicators can be superimposed to obtain the comprehensive data of the disease to be treated in the study area. Exemplarily, the comprehensive activity of the disease in a certain area is vector A, and the rate of change of the statistical indicators of the disease is vector B. The superimposed calculation can be achieved through the ratio of vector A to vector B, that is, vector A / vector B to obtain the superimposed calculation result, and the superimposed calculation result is used as the comprehensive data of the disease to be treated in the study area. In addition, the comprehensive data of the disease to be treated in the study area can also be determined according to the weighted average method. For example, the weight corresponding to the comprehensive activity of the disease and the weight of the rate of change of the statistical indicator are used to achieve weighted average of the comprehensive activity of the disease and the rate of change of the statistical indicator to obtain comprehensive data, which is not specifically limited here.
[0096] After obtaining the comprehensive data, it is possible to evaluate whether the diseases to be treated in the study area are the target diseases in the study area in the current cycle based on the comprehensive data. The target diseases may be, for example, hot diseases, which may be diseases with high attention. The number of hot diseases may be one or more, which is determined based on a pre-set number of topic parameters or actual needs. For example, when the number of topics parameter is 10, the top 10 diseases may be ranked as hot diseases based on the order of the comprehensive data from large to small.
[0097] It should be noted that for any type of pending disease in the current cycle, a comprehensive data can be determined through the combination of disease comprehensive activity and statistical indicator parameters, and then based on the comprehensive data, it can be evaluated whether the pending disease belongs to a hot disease in any research area. Through comprehensive data, it is possible to accurately evaluate whether the pending disease belongs to a hot disease, which improves comprehensiveness and reliability.
[0098] After obtaining the hot diseases of the current cycle, if it is necessary to determine the hot diseases of the next cycle, the research areas and diseases of the current cycle can be eliminated to avoid obtaining the same hot diseases and improve the accuracy of identifying hot diseases.
[0099] The technical solution provided in the embodiments of the present disclosure can be applied to infectious disease research scenarios, and can help researchers timely understand the intelligence hotspot situation, intelligence dynamics, and disease situation changes of each disease type, so as to make accurate decisions.
[0100] Figure 6 A flowchart for identifying hotspot diseases is schematically shown in Figure 6 As shown in , it mainly includes the following steps:
[0101] In step S602, domestic and foreign intelligence data, that is, medical intelligence data, is obtained.
[0102] In step S604, keywords are extracted from the collected medical intelligence data to obtain keywords and keyword distribution of the current period.
[0103] In step S606, the established disease knowledge base is mapped with multiple keywords to obtain reference keywords and reference keyword distribution.
[0104] In step S608, an active sub-network of each disease to be treated is constructed according to the topic and the reference keywords corresponding to the topic.
[0105] In step S610, the second activity score of the topic is determined according to the first activity score of the reference keyword, and the comprehensive activity of the disease to be processed is determined according to the second activity score.
[0106] In step S612, domestic and foreign statistical data, that is, medical statistical data, are obtained.
[0107] In step S614, the medical statistical data is mapped to the indicator dictionary table to determine the statistical indicators of each disease to be treated in each research area.
[0108] In step S616, weighted calculation is performed on statistical indicators that are consistent with the study area, date, and period to determine the statistical indicators of the study area.
[0109] In step S618, the statistical indicator change rate is determined according to the statistical indicator.
[0110] In step S620, the comprehensive activity of the disease is used as the base number, and the statistical indicator change rate is used as the index to determine the comprehensive data of the disease to be treated in the study area.
[0111] In step S622, it is evaluated based on the comprehensive data whether the disease to be processed is a hot disease in the current cycle.
[0112] In the disclosed embodiment, when processing domestic and foreign infectious disease intelligence, an active sub-network method is used to obtain the comprehensive activity of the disease. The disease hot spots obtained by this method are more in line with the application scenarios of infectious disease intelligence; the normalized calculation process of domestic and foreign statistical data pays more attention to the application perspective to solve the problem of inconsistent data indicators. Hot diseases are defined by these two dimensions. The index amplifier effect is achieved by taking the comprehensive activity of the disease as the base number and the rate of change of the statistical indicator as the index, which amplifies the content of attention, highlights the key hot spots, and can improve the accuracy of identifying hot diseases. The active sub-network automatically and dynamically calculates the comprehensive data of each disease to be processed in the research area, which can run uninterruptedly and improve flexibility. In addition, the hot diseases of concern can be dynamically adjusted according to the infectious disease situation to meet the business needs of different disease control. The speed and accuracy of data reporting and release are improved, and the work efficiency and decision-making accuracy are improved.
[0113] The present disclosure provides a medical data processing device, referring to Figure 7 As shown in , the medical data processing device 700 may include:
[0114] The data acquisition module 701 is used to acquire medical intelligence data and medical statistical data of multiple diseases to be processed in the current cycle;
[0115] The activity determination module 702 is used to construct an active sub-network for each disease to be treated, and to process the medical intelligence data based on the active sub-network to obtain the comprehensive activity of each disease to be treated;
[0116] The statistical indicator parameter determination module 703 is used to determine the statistical indicator of the medical statistical data in the research area and determine the statistical indicator parameters corresponding to the statistical indicator;
[0117] The target disease determination module 704 is used to determine the comprehensive data of the diseases to be treated in the study area according to the comprehensive activity of the diseases and statistical indicator parameters, and determine the target diseases in the study area from multiple diseases to be treated according to the comprehensive data.
[0118] In an exemplary embodiment of the present disclosure, an active subnetwork is constructed for each disease to be treated, including: performing keyword extraction on the medical intelligence data corresponding to the disease to be treated, obtaining subject words and subject word distribution to obtain keywords for the current cycle; mapping an established disease knowledge base with keywords to obtain reference keywords and reference keyword distribution for each topic related to the disease to be treated; determining nodes based on topics and reference keywords to construct an active subnetwork for the disease to be treated.
[0119] In an exemplary embodiment of the present disclosure, medical intelligence data is processed based on active subnetworks to obtain comprehensive activity of disease types, including: determining a first activity score for each reference keyword in the active subnetwork; determining second activity scores for multiple topics based on the first activity score for each reference keyword; and determining the comprehensive activity of the disease type to be processed based on the second activity score.
[0120] In an exemplary embodiment of the present disclosure, second activity scores of multiple topics are determined based on the first activity score of each reference keyword, including: taking the position of the reference keyword in the knowledge base as a weight, performing weighted averaging on the first activity scores of the reference keywords, and obtaining second activity scores of the multiple topics.
[0121] In an exemplary embodiment of the present disclosure, keyword extraction is performed on medical intelligence data to obtain subject words and subject word distribution to obtain keywords for the current period, including: converting the document set corresponding to the medical intelligence data into a bag-of-words model text representation to determine the number of times different words appear in the document; determining the topic and topic number parameters, and randomly assigning a topic to each word; iteratively determining the topic distribution and word distribution through Gibbs sampling, obtaining subject words and subject word distribution, and extracting keywords for the current period.
[0122] In an exemplary embodiment of the present disclosure, determining the statistical indicators of medical statistical data in a study area includes: mapping the medical statistical data with an indicator dictionary table to obtain standard indicator data; when there are multiple data sources for the standard indicator data of the disease to be treated in the study area, and the multiple data sources include official data sources of the study area, determining the statistical indicators according to a first weight of the official data source of the study area and a second weight of other sources; the first weight is greater than the second weight; when there are multiple data sources for the standard indicator data of the disease to be treated in the study area, and the multiple data sources are all official data sources of other regions except the study area, determining the statistical indicators by weighted average; when there is one data source for the standard indicator data of the disease to be treated in the study area, using the standard indicator data of the data source as the statistical indicator.
[0123] In an exemplary embodiment of the present disclosure, comprehensive data of the diseases to be treated in the study area are determined based on the comprehensive activity of the diseases and statistical indicator parameters, including: superimposing the comprehensive activity of the diseases and the statistical indicator change rate to obtain the comprehensive data of the diseases to be treated in the study area; or using the disease activity as the base and the statistical indicator change rate as the index to determine the comprehensive data of the diseases to be treated in the study area.
[0124] It should be noted that the specific details of each module in the above-mentioned medical data processing device have been described in detail in the corresponding medical data processing method, so they will not be repeated here.
[0125] The exemplary embodiment of the present disclosure also provides an electronic device. The electronic device may be the above-mentioned client or a server. Generally, the electronic device may include a processor and a memory, the memory is used to store executable instructions of the processor, and the processor is configured to execute the above-mentioned medical data processing method by executing the executable instructions.
[0126] Refer to the following Figure 8 The electronic device 800 according to this embodiment of the present disclosure is described. Figure 8 The electronic device 800 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.
[0127] like Figure 8 As shown, the electronic device 800 is in the form of a general computing device. The components of the electronic device 800 may include, but are not limited to: the at least one processing unit 810, the at least one storage unit 820, a bus 830 connecting different system components (including the storage unit 820 and the processing unit 810), and a display unit 840.
[0128] The storage unit stores program codes, which can be executed by the processing unit 810, so that the processing unit 810 performs the steps according to various exemplary embodiments of the present disclosure described in the above “Exemplary Method” section of this specification. For example, the processing unit 810 can perform the following steps: Figure 1 Follow the steps shown in .
[0129] The storage unit 820 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 8201 and / or a cache memory unit 8202 , and may further include a read-only memory unit (ROM) 8203 .
[0130] The storage unit 820 may also include a program / utility 8204 having a set (at least one) of program modules 8205, such program modules 8205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.
[0131] Bus 830 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, a graphics acceleration interface, a processing unit, or a local bus using any of a variety of bus architectures.
[0132] The electronic device 800 may also communicate with one or more external devices 900 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 800, and / or communicate with any device that enables the electronic device 800 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 850. Furthermore, the electronic device 800 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 860. As shown, the network adapter 860 communicates with other modules of the electronic device 800 via a bus 830. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 800, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.
[0133] In an embodiment of the present disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the above method of the present specification is stored. In some possible implementations, various aspects of the present disclosure can also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary implementations of the present disclosure described in the above "Exemplary Method" section of the present specification.
[0134] According to the program product for implementing the above method in the embodiment of the present disclosure, it can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto. In this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.
[0135] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.
[0136] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.
[0137] The program code contained on the readable medium can be transmitted with any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above. The program code for performing the disclosed operation can be written in any combination of one or more programming languages, including object-oriented programming languages-such as Java, C++, etc., and also including conventional procedural programming languages-such as "C" language or similar programming languages. The program code can be executed completely on the user computing device, partially on the user device, as an independent software package, partially on the user computing device, partially on the remote computing device, or completely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).
[0138] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to the embodiment of the present disclosure, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.
[0139] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The specification and examples are to be considered as exemplary only, and the true scope and spirit of the present disclosure are indicated by the claims.
[0140] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims
1. A medical data processing method, characterized in that: include: Obtain medical intelligence data and medical statistics for each disease to be processed in the current cycle; Constructing an active sub-network for each of the diseases to be treated, and processing the medical intelligence data based on the active sub-network to obtain the comprehensive activity of each of the diseases to be treated; Determine the statistical indicators of the medical statistical data in the research area, and determine the statistical indicator parameters corresponding to the statistical indicators; According to the comprehensive activity of the diseases and the statistical indicator parameters, the comprehensive data of each disease to be treated in the study area is determined, and the target disease in the study area is determined from the diseases to be treated based on the comprehensive data.
2. The medical data processing method according to claim 1, characterized in that: The active sub-network is constructed for each of the diseases to be processed, including: For each of the diseases to be treated, extract keywords from the medical intelligence data corresponding to the diseases to be treated, obtain subject words and subject word distribution, and obtain keywords for the current period; Mapping the established disease knowledge base with keywords to obtain reference keywords and reference keyword distribution for each topic related to the disease to be treated; Nodes are determined based on the subject and the reference keywords, and an active sub-network of the disease to be treated is constructed.
3. The medical data processing method according to claim 2, characterized in that: The step of processing the medical intelligence data based on the active subnetwork to obtain the comprehensive activity of each disease to be processed includes: determining a first activity score for each reference keyword in the active subnetwork; Determining second activity scores of the plurality of topics according to the first activity score of each reference keyword; The comprehensive activity of the disease to be treated is determined according to the second activity score.
4. The medical data processing method according to claim 3, characterized in that: The determining, according to the first activity score of each reference keyword, second activity scores of the plurality of topics includes: The position of the reference keyword in the knowledge base is used as a weight, and the first activity scores of the reference keyword are weighted averaged to obtain second activity scores of multiple topics.
5. The medical data processing method according to claim 2, characterized in that: Perform keyword extraction on the medical intelligence data to obtain subject words and subject word distribution to obtain keywords for the current period, including: Convert the document set corresponding to the medical intelligence data into a bag-of-words model text representation to determine the number of times different words appear in the document; Determine the topic and number of topics parameters and randomly assign topics to each word; The topic distribution and word distribution are iteratively determined by Gibbs sampling, and the subject words and subject word distribution are obtained to extract the keywords of the current period.
6. The medical data processing method according to claim 1, characterized in that: The statistical indicators for determining the medical statistics in the research area include: Mapping the medical statistical data with the indicator dictionary table to obtain standard indicator data; When there are multiple data sources for the standard indicator data of the disease to be treated in the study area, and the multiple data sources include official data sources of the study area, the statistical indicator is determined according to the first weight of the official data source of the study area and the second weight of other sources; the first weight is greater than the second weight; When there are multiple data sources for the standard indicator data of the disease to be treated in the study area, and the multiple data sources are official data sources from other regions except the study area, the statistical indicators shall be determined by weighted average; When there is a data source for standard indicator data of the disease to be treated in the research area, the standard indicator data of the data source is used as the statistical indicator.
7. The medical data processing method according to claim 1, characterized in that: Determining the comprehensive data of the diseases to be treated in the research area according to the comprehensive activity of the diseases and the statistical indicator parameters includes: The comprehensive activity of the disease and the change rate of the statistical indicator are superimposed and calculated to obtain the comprehensive data of the disease to be treated in the research area; or Taking the activity of the disease as the base number and the rate of change of the statistical indicator as the index, the comprehensive data of the diseases to be treated in the study area are determined.
8. A medical data processing device, characterized in that: include: The data acquisition module is used to obtain medical intelligence data and medical statistics for each disease to be processed in the current cycle; An activity determination module, used to construct an active sub-network for each of the diseases to be treated, and to process the medical intelligence data based on the active sub-network to obtain the comprehensive activity of each of the diseases to be treated; A statistical indicator parameter determination module, used to determine the statistical indicators of the medical statistical data in the research area, and determine the statistical indicator parameters corresponding to the statistical indicators; The target disease judgment module is used to determine the comprehensive data of each disease to be treated in the study area according to the comprehensive activity of the disease and the statistical indicator parameters, and determine the target disease in the study area from the diseases to be treated according to the comprehensive data.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the medical data processing method according to any one of claims 1 to 7 is implemented.
10. An electronic device, characterized in that: include: processor; as well as A memory, configured to store executable instructions of the processor; Wherein, the processor is configured to perform the medical data processing method described in any one of claims 1-7 by executing the executable instructions.