Disease early warning method and device based on environmental monitoring and storage medium

Abstract

The invention discloses a disease early warning method and device based on environment monitoring and a storage medium, and belongs to the field of disease prevention and control, and the method comprises the steps: collecting environment data, determining a target disease, obtaining medical data of the target disease, and determining target environment data in the environment data according to the medical data; inputting the target environment data into a prediction model corresponding to the target disease; and determining a risk level of the target disease according to an output result of the prediction model, and performing early warning prompt of the target disease according to the risk level. The invention aims to realize early warning for residents from the perspective of disease prevention and control according to the environmental data, improve the guidance of early warning for the residents to obtain which medical help, and improve the body health of the residents.

Description

Technical Field

[0001] The present invention relates to the field of disease prevention and control, and in particular to a disease early warning method, device and storage medium based on environmental monitoring. Background Art

[0002] With the advancement of urbanization, the issues of residents' health and living environment quality have gradually become the focus of public attention. Air pollution, water pollution, etc. have subtly affected the physical health of residents. However, the current environmental monitoring of pollution is generally limited to data collection and monitoring. The polluted air quality data and water quality data reflect the impact on health and what diseases are likely to be induced. There is a lack of corresponding prompts. Residents also lack awareness of this and cannot issue timely warnings to residents from the perspective of disease prevention and control, which affects their physical health. Summary of the invention

[0003] The present invention provides a disease early warning method, device and storage medium based on environmental monitoring to solve one or more technical problems existing in the prior art and at least provide a beneficial choice or create conditions.

[0004] The present invention provides a disease early warning method based on environmental monitoring, the disease early warning method based on environmental monitoring comprising: Collect environmental data, determine a target disease, obtain medical data of the target disease, and determine target environmental data in the environmental data based on the medical data; Inputting the target environmental data into a prediction model corresponding to the target disease; The risk level of the target disease is determined according to the output result of the prediction model, and an early warning prompt of the target disease is issued according to the risk level.

[0005] Optionally, the disease early warning method based on environmental monitoring further includes: Determine a target time period according to the medical data, the medical data including historical diagnosis records of the target disease in various time periods, the target time period being a time period in which the number of diagnoses of the target disease is greater than or equal to a preset number; Acquire historical environmental data, filter data items of the historical environmental data within the target time period, and define the data items as environmental variables; A prediction model for the target disease is trained based on the environmental variables and the number of diagnoses.

[0006] Optionally, the step of training the prediction model of the target disease according to the environmental variables and the number of diagnoses includes: Performing standardization on the environmental variables; Calculating the covariance matrix of the standardized environmental variables, performing eigendecomposition on the covariance matrix, and obtaining eigenvalues ​​and eigenvectors; Determine the principal component in the environmental variable according to the eigenvalue and the eigenvector, and define the principal component in the environmental variable as the environmental indicator of the target disease; A prediction model for the target disease is trained according to the environmental indicators and the number of diagnoses.

[0007] Optionally, the step of determining target environmental data in the environmental data according to the target disease includes: The target environmental data in the environmental data is determined according to the environmental indicator of the target disease.

[0008] Optionally, the prediction model is a multivariate linear regression model, and the step of training the prediction model of the target disease according to the environmental index and the number of diagnoses includes: Taking the number of diagnoses as the predicted variable and the environmental index as the independent variable, the regression coefficient, intercept and error term of the multivariate linear regression equation are determined, and the prediction model of the target disease is determined based on the regression coefficient, intercept and error term.

[0009] Optionally, the step of training the prediction model of the target disease according to the environmental indicators and the number of diagnoses includes: forming the environmental index and the number of diagnoses into a data set; The prediction model is trained according to the data set through K-fold cross validation, where K is set to a preset number, and a preset number of validation errors are obtained; The average error of the preset number of verification errors is calculated, and when the average error is less than or equal to an error threshold, it is determined that the prediction model training is completed.

[0010] Optionally, the medical data further includes literature data of the target disease, and the step of training the prediction model of the target disease according to the environmental variables and the number of diagnoses includes: Determining environmental factors that induce the onset of the target disease from the literature data through natural language processing and text mining; Determine the environmental index in the environmental variable according to the environmental factor; A prediction model for the target disease is trained according to the environmental indicators and the number of diagnoses.

[0011] Optionally, the output result of the prediction model includes the predicted number of incidences of the target disease, and the steps of determining the risk level of the target disease according to the output result of the prediction model and providing an early warning prompt for the target disease according to the risk level include: When the predicted number of cases is less than a first threshold, the risk level is determined to be low risk, and the early warning prompt corresponding to the low risk is performed; When the predicted number of incidences is greater than or equal to the first threshold and less than or equal to the second threshold, the risk level is determined to be medium risk, and the early warning prompt corresponding to the medium risk is performed; When the predicted number of cases is greater than the second threshold, the risk level is determined to be high risk, and the early warning corresponding to the high risk is performed; The first threshold is smaller than the second threshold.

[0012] In addition, in order to achieve the above-mentioned purpose, the present application also proposes a disease warning device based on environmental monitoring, and the disease warning device based on environmental monitoring includes: a memory, a processor, and a disease warning program based on environmental monitoring stored on the memory and executable on the processor, and the disease warning program based on environmental monitoring is configured to implement the steps of the disease warning method based on environmental monitoring as described in any of the above items.

[0013] In addition, in order to achieve the above-mentioned purpose, the present application also proposes a storage medium, on which a disease warning program based on environmental monitoring is stored. When the disease warning program based on environmental monitoring is executed by a processor, the steps of the disease warning method based on environmental monitoring as described in any of the above items are implemented.

[0014] The present invention has at least the following beneficial effects: by collecting environmental data, after determining the target disease to be predicted, further obtaining medical data of the target disease, determining the target environmental data actually required in the environmental data based on the medical data, and then inputting the target environmental data into the prediction model corresponding to the target disease, determining the risk level of the target disease through the output result of the prediction model, and providing early warning prompts for the target disease according to the risk level. Compared with the current method of only collecting and monitoring air quality data and water quality data, the present invention determines the target environmental data actually associated with the onset of the target disease from the environmental data based on the medical data related to the target disease, and then analyzes it through the prediction model, and provides early warning prompts for the target disease, so as to associate the collected environmental data with the specific target disease, thereby providing early warnings to residents from the perspective of disease prevention and control, and is also conducive to guiding residents on what kind of medical help they should get for the disease, and improving the physical health of residents. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The accompanying drawings are used to provide a further understanding of the technical solution of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the technical solution of the present invention and do not constitute a limitation on the technical solution of the present invention.

[0016] Figure 1 It is a flow chart of the first embodiment of the disease early warning method based on environmental monitoring of the present invention; Figure 2 Another schematic flow chart of the first embodiment of the disease early warning method based on environmental monitoring of the present invention; Figure 3 It is a flow chart of the second embodiment of the disease early warning method based on environmental monitoring of the present invention; Figure 4 This is a schematic diagram of the device structure involved in the operation of an embodiment of a disease early warning device based on environmental monitoring of the present invention. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0018] It should be noted that, although the functional modules are divided in the system schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the system or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0019] The embodiment of the present invention provides a disease early warning method based on environmental monitoring. Figure 1 , a first embodiment of a disease early warning method based on environmental monitoring of the present application is proposed. In this embodiment, the disease early warning method based on environmental monitoring includes: Step S10, collecting environmental data, determining a target disease, obtaining medical data of the target disease, and determining target environmental data in the environmental data based on the medical data.

[0020] In order to cover the prevention and control of multiple diseases as much as possible and to determine the environmental factors related to each disease, the present embodiment scheme uses environmental factors in the present embodiment to define the concept of certain data and does not include specific numerical values. A sensor network is set up in the residential environment area of ​​residents to collect environmental data including at least air quality data, water quality data and meteorological data, wherein the air quality data includes the concentration data of substances such as PM2.5, carbon dioxide and formaldehyde in the air, the water quality data includes the data on various heavy metals, organic pollutants and other harmful substances in drinking water, and the meteorological data includes the temperature, humidity, air pressure, precipitation and wind speed of the surrounding area. In other embodiments, the environmental data may also include electrical data such as power consumption and operating status of power equipment, as well as other data such as noise, light pollution and green area.

[0021] The collected environmental data are marked with time tags, location tags and type tags, and can be classified according to their time tags, location tags and type tags, supporting separate query and analysis. Specifically, the time tag is the timestamp of the environmental data collection time, supporting classification by multiple time granularities such as year, month, week and day. The location tag is the geographical location where the environmental data is collected, supporting division by geographical area. The type tag is the specific parameter type of the environmental data, such as PM2.5-related data or carbon dioxide-related data. Furthermore, the collected environmental data is stored in the database after the verification process. The database regularly performs anomaly detection and data backup on the stored data, and connects to the external network to update the stored data. The verification process includes data integrity check, outlier detection and logical consistency verification.

[0022] On the other hand, the target diseases targeted by the scheme of this embodiment include multiple diseases, such as cardiovascular diseases, skin diseases, and allergic diseases, etc. This embodiment is described by taking asthma as an example. Further, medical data of the target disease is obtained, and the medical data includes literature data, case data, expert opinions, and other data of the target disease. From the collected multiple environmental data, target environmental data actually related to the onset of the target disease is determined according to the medical data.

[0023] Step S20, inputting the target environmental data into the prediction model corresponding to the target disease.

[0024] Optionally, for different types of diseases, the present embodiment is provided with corresponding prediction models respectively, and the corresponding prediction model is called according to the determined target disease, and the target environment data is input into the prediction model to make a prediction for the target disease.

[0025] Step S30, determining the risk level of the target disease according to the output result of the prediction model, and providing an early warning prompt for the target disease according to the risk level.

[0026] Optionally, the output results of the prediction model include the predicted number of incidences of the target disease, that is, how many residents may be sick. The risk level of the target disease is determined based on the output results, and early warning prompts corresponding to the risk level are issued to remind residents to take precautions.

[0027] The embodiments of the present invention have at least the following beneficial effects: by collecting environmental data, after determining the target disease to be predicted, further obtaining medical data of the target disease, determining the target environmental data actually required in the environmental data based on the medical data, and then inputting the target environmental data into the prediction model corresponding to the target disease, determining the risk level of the target disease through the output result of the prediction model, and providing early warning prompts for the target disease based on the risk level. Compared with the current method of only collecting and monitoring air quality data and water quality data, the present invention determines the target environmental data actually associated with the onset of the target disease from the environmental data based on the medical data related to the target disease, and then analyzes it through the prediction model, and provides early warning prompts for the target disease, so as to associate the collected environmental data with the specific target disease, thereby providing early warnings to residents from the perspective of disease prevention and control, and is also conducive to guiding residents on what kind of medical help they should get for the disease, thereby improving the physical health of residents.

[0028] Furthermore, in this embodiment, the disease early warning method based on environmental monitoring also includes: The target time period is determined based on medical data, where the medical data includes historical diagnosis records of the target disease in various time periods, and the target time period is a time period in which the number of diagnoses of the target disease is greater than or equal to a preset number.

[0029] Obtain historical environment data, filter the data items of the historical environment data within the target time period, and define the data items as environment variables.

[0030] A prediction model for the target disease is trained based on environmental variables and the number of diagnoses.

[0031] The prediction model for the target disease used in the present embodiment has a specific training method as follows: first, determine the historical diagnosis records in the medical data. The historical diagnosis records are recorded in the above-mentioned case data and classified by time periods. The time period may be, for example, one day or one week. According to the historical diagnosis records, determine whether the number of diagnoses of the target disease in each time period is greater than or equal to a preset number. The preset number may be set to, for example, 1 time or 5 times. When it is determined to be yes, determine the corresponding time period as the target time period, which is equivalent to screening out the time period in which the target disease is concentrated from various historical time periods according to the historical diagnosis records.

[0032] On the other hand, historical environmental data is obtained. Since environmental data is classified and stored according to its time label, the corresponding data items with collection time within the target time period can be filtered out from the historical environmental data. For the convenience of explanation and understanding, this data item in the prediction model training process is defined as an environmental variable, so that further model training can be performed based on the filtered environmental variables and the number of diagnoses.

[0033] By determining the target time period of concentrated outbreaks based on the historical diagnosis records of the target disease, and using this to screen out environmental variables, a relationship between environmental data and medical data is established, thereby supporting the prediction of follow-up plans for the target disease based on environmental data, and enabling early warnings to residents from the perspective of disease prevention and control based on environmental data.

[0034] Further, in this embodiment, referring to Figure 2 The step of training the prediction model of the target disease according to the environmental variables and the number of diagnoses includes: Step S41, standardizing the environment variables.

[0035] Step S42, calculating the covariance matrix of the standardized environmental variables, performing eigendecomposition on the covariance matrix, and obtaining eigenvalues ​​and eigenvectors.

[0036] Step S43, determining the principal components in the environmental variables according to the eigenvalues ​​and eigenvectors, and defining the principal components in the environmental variables as environmental indicators of the target disease.

[0037] Step S44, training a prediction model for the target disease based on environmental indicators and the number of diagnoses.

[0038] Specifically, the screened environmental variables still include multiple data such as the above-mentioned air quality data, water quality data and meteorological data. First, each variable in the environmental variables is standardized so that its mean is 0 and its standard deviation is 1. The covariance matrix of the standardized environmental variables is calculated. The covariance matrix can be used to evaluate the correlation between different variables. The covariance matrix is ​​then eigendecomposed to obtain eigenvalues ​​and eigenvectors. The eigenvalues ​​can reflect the importance of the corresponding eigenvectors. The ratio of each eigenvalue to the sum of all eigenvalues ​​is calculated. The ratio is equivalent to the percentage of variance that can be explained by the corresponding eigenvector. A preset ratio is set, for example, 0.8. When the ratio is greater than or equal to the preset ratio, the corresponding variable is determined to be the principal component required by the scheme of this embodiment. All principal components in the environmental variables are determined. For the sake of ease of explanation and understanding, the principal component is defined, that is, the environmental variable actually related to the onset of the target disease is an environmental indicator. Taking asthma as an example, the environmental indicators include PM2.5 concentration data, humidity data and temperature data, so that further model training is performed based on the environmental indicators and the number of diagnoses.

[0039] By screening out the principal components that are actually related to the onset of the target disease from the environmental variables, it supports the analysis of the target disease based on specific principal components, namely environmental indicators, thereby improving the accuracy of the prediction model for the target disease and improving the physical health of residents.

[0040] Further, in this embodiment, the step of determining target environmental data in the environmental data according to the target disease includes: Determine target environmental data in environmental data based on environmental indicators of target diseases.

[0041] Specifically, for the environmental indicators determined in the prediction model training, their types are associated with the target diseases and recorded. When the prediction model is applied in practice, the target environmental data can be directly screened out from the environmental data based on the environmental indicators of the target disease, so as to directly make predictions, thereby improving the computational efficiency of predicting the target disease.

[0042] Furthermore, in this embodiment, the prediction model is a multiple linear regression model, and the step of training the prediction model of the target disease according to the environmental indicators and the number of diagnoses includes: Taking the number of diagnoses as the predictor and environmental indicators as the independent variables, the regression coefficient, intercept and error term of the multivariate linear regression equation were determined, and the prediction model of the target disease was determined based on the regression coefficient, intercept and error term.

[0043] Taking the environmental indicators of asthma, including PM2.5 concentration data, humidity data and temperature data, as an example, the calculation of multiple linear regression can refer to the following formula (1): (1) in, is the predictor variable, equivalent to the number of diagnoses, and are independent variables, which are equivalent to PM2.5 concentration data, humidity data and temperature data respectively. and As and The corresponding regression coefficient is is the intercept, is the error term; the environmental variables and the number of diagnoses are fitted into the multivariate linear regression formula to determine and , obtain the prediction model for the target disease in this embodiment, which can predict the predicted number of incidences of the target disease based on the input environmental variables. Exemplarily, the calculation of a multivariate linear regression for a prediction model for asthma can refer to the following formula (2): (2) The intercept is 0.5, is 0.08, is -0.05, is 0.03, the error term is 0, is the concentration data of PM2.5, is the humidity data, is the temperature data.

[0044] By fitting, we obtain the calculation formula for predicting the predicted number of incidence of the target disease based on the input environmental variables, build a multivariate linear regression model, and predict the incidence of the target disease based on environmental data. This can further provide early warning for disease prevention and control to residents and improve their physical health.

[0045] Furthermore, in this embodiment, the step of training the prediction model of the target disease according to the environmental indicators and the number of diagnoses includes: The environmental indicators and the number of diagnoses are formed into a data set.

[0046] Through K-fold cross validation, the prediction model is trained according to the data set, K is set to a preset number, and a preset number of validation errors are obtained.

[0047] The average error of a preset number of validation errors is calculated, and when the average error is less than or equal to the error threshold, it is determined that the prediction model training is completed.

[0048] In addition to constructing the multivariate linear regression model as mentioned above, when training the prediction model, K-fold cross-validation is also used for training. Specifically, the environmental indicators and the number of diagnoses are formed into a data set, and a preset number K is set, for example, set to 5, and the data set is divided into a preset number of subsets. During the training iterations, each iteration uses a subset as a validation set, and the remaining subsets are used as training sets. Different subsets are selected as validation sets for each iteration, and a preset number of iterations are performed to obtain a preset number of validation errors, and the average error of the preset number of validation errors is calculated. An error threshold is set to evaluate the average error. When the average error is less than or equal to the error threshold, it is determined that the accuracy of the prediction model meets the requirements and the prediction model training is completed.

[0049] By adding K-fold cross-validation to evaluate the error during iterative training of the prediction model and limiting the error amplitude through the error threshold, the accuracy of the prediction model is improved, the accuracy of predicting the number of target disease incidences based on environmental data is improved, and the effectiveness of disease prevention and control is improved.

[0050] Furthermore, in this embodiment, the step of determining the risk level of the target disease according to the output result of the prediction model and providing an early warning prompt for the target disease according to the risk level includes: When the predicted number of cases is less than the first threshold, the risk level is determined to be low risk, and an early warning corresponding to the low risk is issued.

[0051] When the predicted number of cases is greater than or equal to the first threshold and less than or equal to the second threshold, the risk level is determined to be medium risk, and an early warning corresponding to the medium risk is issued.

[0052] When the predicted number of cases is greater than the second threshold, the risk level is determined to be high risk, and an early warning corresponding to the high risk is issued.

[0053] The first threshold is smaller than the second threshold.

[0054] For the predicted number of incidences of the target disease output by the prediction model, three risk levels are further set for qualitative criticality, and the predicted number of incidences is evaluated by the first threshold and the second threshold. For example, the first threshold is set to 5 times, the second threshold is set to 10 times, and the target disease is asthma. When the predicted number of incidences is less than the first threshold, the risk level is low risk, and a low-risk early warning prompt is issued, such as sending a reminder to residents to pay attention to air quality and maintain a normal life. When the predicted number of incidences is greater than or equal to the first threshold and less than or equal to the second threshold, the risk level is medium risk, and a medium-risk early warning prompt is issued, such as suggesting that residents reduce going out and keep the indoor air clean. When the predicted number of incidences is greater than the second threshold, the risk level is high risk, and a high-risk early warning prompt is issued, such as wearing a mask or avoiding going out, and suggesting to turn on the air purifier indoors. In addition, in addition to providing life advice to residents, early warning prompts can also include more specific medical protection measures, such as how to relieve symptoms when asthma occurs.

[0055] By setting specific risk levels and corresponding early warning prompts, the predicted number of cases can be converted into early warning prompts that can be specifically understood by residents, thereby improving the effectiveness of early warning prompts and thus improving the effectiveness of disease prevention and control.

[0056] Further, based on the above embodiment, a second embodiment of the disease early warning method based on environmental monitoring of the present application is proposed. Figure 3 , the medical data also includes literature data of the target disease, and the steps of training the prediction model of the target disease according to the environmental variables and the number of diagnoses include: Step S51, determining the environmental factors that induce the onset of the target disease from literature data through natural language processing and text mining.

[0057] Step S52: determining the environmental index in the environmental variable according to the environmental factor.

[0058] Step S53, training a prediction model for the target disease based on environmental indicators and the number of diagnoses.

[0059] For environmental factors related to the onset of the target disease, in addition to determining them through principal component analysis of environmental variables, corresponding descriptions may also exist in the literature data related to the target disease. Specifically, medical data of the target disease is obtained, and literature data in the medical data is extracted. In other embodiments, data including expert opinions can also be extracted, and descriptions related to the causes of the target disease can be found from the literature data through natural language processing and text mining, and key texts are extracted therefrom for analysis to determine the environmental factors that may induce the target disease, thereby determining data of the same type from the environmental variables based on the environmental factors, that is, determining the environmental indicators, and then training the target disease prediction model based on the environmental indicators and the number of diagnoses.

[0060] By analyzing the literature data of the target disease, the environmental indicators of the target disease can be determined from another perspective, so that the determined environmental indicators are actually based on the experts in the medical field, thereby improving the accuracy of the determined environmental indicators, thereby improving the prediction accuracy of the prediction model and improving the effect of disease prevention and control.

[0061] In other embodiments, in addition to determining environmental factors by analyzing literature data, it is also possible to further analyze features including symptoms of the target disease, and form an association rule table with the name of the target disease and environmental factors. This operation can also be used not only for the target disease, but also for all diseases that can be analyzed by medical data to form an association rule table for various diseases. For the formed association rule table, the medical terms and disease names therein are standardized and coded using the international or industry standard International Classification of Diseases (ICD). At the same time, it is also possible to regularly update medical data, introduce modification opinions from medical experts and user feedback, maintain medical data, and thus maintain the formed association rule table to ensure its accuracy. After the association rule table is formed, when it is necessary to predict the predicted number of incidences of the target disease or train a prediction model, the association rule table can be directly queried to obtain the corresponding environmental factors to improve calculation efficiency.

[0062] On the other hand, the environmental indicators determined by principal component analysis and the environmental indicators determined based on medical data can be used in combination when training the prediction model. The differences in the environmental indicators determined by the two approaches can be compared and their union can be taken, or appropriate environmental indicators can be selected after manual review by medical experts, thereby combining the two approaches to determine the environmental indicators, improving the correctness of the environmental indicators, improving the prediction accuracy of the prediction model, and improving the effectiveness of disease prevention and control.

[0063] On the other hand, reference Figure 4 , Figure 4 It is a schematic diagram of the device structure of the disease early warning device based on environmental monitoring.

[0064] A disease early warning device based on environmental monitoring is provided, comprising: a processor and a memory; wherein the memory is used to store a computer-readable program. When the computer-readable program is executed by the processor, the processor implements the disease early warning method based on environmental monitoring as described in any one of the above technical solutions.

[0065] It will be appreciated by those skilled in the art that all or some of the steps and systems in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or temporary medium). As known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. As is well known to those skilled in the art, communication media typically embodies computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0066] In addition, an embodiment of the present invention also proposes a storage medium, on which a disease warning program based on environmental monitoring is stored. When the disease warning program based on environmental monitoring is executed by a processor, the relevant steps of any embodiment of the above disease warning method based on environmental monitoring are implemented.

[0067] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein, for example. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0068] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0069] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0070] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0071] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0072] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store program codes.

[0073] Although the description of the present application has been quite detailed and specifically describes several embodiments, it is not intended to be limited to any of these details or embodiments or any particular embodiment, but should be regarded as providing a broad possible interpretation of these claims by reference to the attached claims, taking into account the prior art, so as to effectively cover the intended scope of the present application. In addition, the above description of the present application is based on the embodiments foreseeable by the inventor, and its purpose is to provide a useful description, and those non-substantial changes to the present application that have not yet been foreseen may still represent equivalent changes to the present application.

Claims

1. A disease early warning method based on environmental monitoring, characterized in that: The disease early warning method based on environmental monitoring includes: Collect environmental data, determine a target disease, obtain medical data of the target disease, and determine target environmental data in the environmental data based on the medical data; Inputting the target environmental data into a prediction model corresponding to the target disease; The risk level of the target disease is determined according to the output result of the prediction model, and an early warning prompt of the target disease is issued according to the risk level.

2. The disease early warning method based on environmental monitoring according to claim 1, characterized in that: The disease early warning method based on environmental monitoring also includes: Determine a target time period according to the medical data, the medical data including historical diagnosis records of the target disease in various time periods, the target time period being a time period in which the number of diagnoses of the target disease is greater than or equal to a preset number; Acquire historical environmental data, filter data items of the historical environmental data within the target time period, and define the data items as environmental variables; A prediction model for the target disease is trained based on the environmental variables and the number of diagnoses.

3. The disease early warning method based on environmental monitoring according to claim 2 is characterized in that: The step of training the prediction model of the target disease according to the environmental variables and the number of diagnoses comprises: Performing standardization on the environmental variables; Calculating the covariance matrix of the standardized environmental variables, performing eigendecomposition on the covariance matrix, and obtaining eigenvalues ​​and eigenvectors; Determine the principal component in the environmental variable according to the eigenvalue and the eigenvector, and define the principal component in the environmental variable as the environmental indicator of the target disease; A prediction model for the target disease is trained according to the environmental indicators and the number of diagnoses.

4. The disease early warning method based on environmental monitoring according to claim 3 is characterized in that: The step of determining target environmental data in the environmental data according to the target disease comprises: The target environmental data in the environmental data is determined according to the environmental indicator of the target disease.

5. The disease early warning method based on environmental monitoring according to claim 3 is characterized in that: The prediction model is a multiple linear regression model, and the step of training the prediction model of the target disease according to the environmental index and the number of diagnoses includes: Taking the number of diagnoses as the predicted variable and the environmental index as the independent variable, the regression coefficient, intercept and error term of the multivariate linear regression equation are determined, and the prediction model of the target disease is determined based on the regression coefficient, intercept and error term.

6. The disease early warning method based on environmental monitoring according to claim 3, characterized in that: The step of training the prediction model of the target disease according to the environmental index and the number of diagnoses comprises: forming the environmental index and the number of diagnoses into a data set; The prediction model is trained according to the data set through K-fold cross validation, where K is set to a preset number, and a preset number of validation errors are obtained; The average error of the preset number of verification errors is calculated, and when the average error is less than or equal to an error threshold, it is determined that the prediction model training is completed.

7. The disease early warning method based on environmental monitoring according to claim 2, characterized in that: The medical data also includes literature data of the target disease, and the step of training the prediction model of the target disease according to the environmental variables and the number of diagnoses includes: Determining environmental factors that induce the onset of the target disease from the literature data through natural language processing and text mining; Determine the environmental index in the environmental variable according to the environmental factor; A prediction model for the target disease is trained according to the environmental indicators and the number of diagnoses.

8. The disease early warning method based on environmental monitoring according to any one of claims 1 to 7, characterized in that: The output result of the prediction model includes the predicted number of incidences of the target disease, and the steps of determining the risk level of the target disease according to the output result of the prediction model and providing an early warning prompt for the target disease according to the risk level include: When the predicted number of cases is less than a first threshold, the risk level is determined to be low risk, and the early warning prompt corresponding to the low risk is performed; When the predicted number of incidences is greater than or equal to the first threshold and less than or equal to the second threshold, the risk level is determined to be medium risk, and the early warning prompt corresponding to the medium risk is performed; When the predicted number of cases is greater than the second threshold, the risk level is determined to be high risk, and the early warning corresponding to the high risk is performed; The first threshold is smaller than the second threshold.

9. A disease early warning device based on environmental monitoring, characterized in that: The disease warning device based on environmental monitoring includes: a memory, a processor, and a disease warning program based on environmental monitoring stored in the memory and executable on the processor, wherein the disease warning program based on environmental monitoring is configured to implement the steps of the disease warning method based on environmental monitoring as described in any one of claims 1 to 8.

10. A storage medium, characterized in that: The storage medium stores a disease early warning program based on environmental monitoring, and when the disease early warning program based on environmental monitoring is executed by the processor, the steps of the disease early warning method based on environmental monitoring as described in any one of claims 1 to 8 are implemented.

Images