Health risk prediction method and device, equipment, storage medium and computer program product
By using a preset prediction model trained by local sample data in the health risk prediction method, the physical examination data to be predicted in a specific region is solved, and the problem of accurate prediction is not possible in the prior art, and the accuracy of prediction is achieved.
Patent Information
- Application Number
- CN202411990987.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-31
- Publication Date
- 2025-05-06
AI Technical Summary
The prior art cannot accurately predict health risk for specific regions or populations, and it is difficult to adapt to the physiological characteristics and lifestyle differences of populations in different regions.
A health risk prediction method is proposed to obtain the final prediction result by obtaining the physical examination data to be predicted in the current area to be tested and inputting it to the first and second preset prediction models trained by local sample data.
The preset prediction model trained through local sample data can accurately predict the physical examination data to be predicted in a specific region, improving the accuracy of health risk prediction.
Smart Images
Figure CN119943378A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of health risk prediction, and in particular to a health risk prediction method, apparatus, device, storage medium and computer program product. Background Art
[0002] As the incidence of chronic diseases, such as hypertension and diabetes, continues to rise, early identification and intervention have become the key to improving public health. Traditional health risk prediction methods mainly rely on doctors' clinical experience and simple statistical models, which have problems such as limited coverage and insufficient personalized assessment capabilities, and are difficult to meet the needs of modern medical care. In recent years, machine learning technology has been widely used in health risk prediction, providing new solutions for early identification and intervention of chronic diseases.
[0003] Existing models that use machine learning technology to predict health risks are generally trained based on general data sets and cannot be optimized for specific regions or populations, making it difficult for the models to adapt to the physiological characteristics and lifestyle differences of people in different regions. Summary of the invention
[0004] The main purpose of this application is to provide a health risk prediction method, device, equipment, storage medium and computer program product, aiming to solve the problem that the existing technology cannot make accurate predictions for specific regions or populations.
[0005] To achieve the above objectives, the present application proposes a health risk prediction method, which comprises:
[0006] Obtain the predicted physical examination data of the current area to be tested;
[0007] Inputting the physical examination data to be predicted into a first preset prediction model to obtain a first initial prediction result, wherein the first preset prediction model is obtained by training the first initial prediction model with the local sample data corresponding to the current area to be tested;
[0008] Inputting the physical examination data to be predicted into a second preset prediction model to obtain a second initial prediction result, wherein the second preset prediction model is obtained by training the second initial prediction model with the local sample data;
[0009] A final prediction result is obtained based on the first initial prediction result and the second initial prediction result.
[0010] In one embodiment, the step of obtaining a final prediction result based on the first initial prediction result and the second initial prediction result includes:
[0011] Get the preset configuration weight;
[0012] Obtaining a health risk level based on the preset configuration weight, the first initial prediction result, and the second initial prediction result using a preset fusion algorithm;
[0013] The health risk level is taken as the final prediction result.
[0014] In one embodiment, the step of inputting the physical examination data to be predicted into a first preset prediction model to obtain a first initial prediction result includes:
[0015] Inputting the physical examination data to be predicted into a first preset prediction model to obtain a target distance between the physical examination data to be predicted and the local sample data corresponding to the current area to be tested;
[0016] A preset number of neighbors corresponding to the first preset prediction model is obtained, and a first initial prediction result is obtained based on the preset number of neighbors and each of the target distances.
[0017] In one embodiment, the step of obtaining a first initial prediction result based on the preset number of neighbors and each of the target distances includes:
[0018] Acquire the local sample data corresponding to each target distance and the local sample result corresponding to each local sample data;
[0019] Sorting the target distances, and filtering the target sample results from the local sample results based on the sorting result and the preset number of neighbors;
[0020] A first initial prediction result is obtained based on the target sample result.
[0021] In one embodiment, before the step of obtaining the physical examination data to be predicted in the current area to be tested, the method further includes:
[0022] Obtaining local sample data of the current area to be tested and sample prediction results corresponding to the local sample data;
[0023] Training a first initial prediction model based on the local sample data and the sample prediction results to obtain a first preset prediction model;
[0024] A second initial prediction model is trained based on the local sample data and the sample prediction results to obtain a second preset prediction model.
[0025] In one embodiment, the step of inputting the physical examination data to be predicted into the first preset prediction model includes:
[0026] Determine the physical examination data to be predicted to obtain a feature mean and a feature standard deviation corresponding to the physical examination data to be predicted;
[0027] Standardizing the physical examination data to be predicted according to the characteristic mean and the characteristic standard deviation;
[0028] Inputting the standardized physical examination data to be predicted into a first preset health risk prediction model;
[0029] The step of inputting the physical examination data to be predicted into the second preset prediction model comprises:
[0030] The standardized physical examination data to be predicted is input into the second preset health risk prediction model
[0031] In addition, to achieve the above objectives, the present application also proposes a health risk prediction device, the device comprising:
[0032] A data acquisition module is used to obtain the physical examination data to be predicted in the current area to be tested;
[0033] A first data processing module, used for inputting the physical examination data to be predicted into a first preset prediction model to obtain a first initial prediction result, wherein the first preset prediction model is obtained by training the first initial prediction model with the local sample data corresponding to the current area to be tested;
[0034] A second data processing module is used to input the physical examination data to be predicted into a second preset prediction model to obtain a second initial prediction result, where the second preset prediction model is obtained by training the second initial prediction model with the local sample data;
[0035] A data integration module is used to obtain a final prediction result based on the first initial prediction result and the second initial prediction result.
[0036] In addition, to achieve the above-mentioned purpose, the present application also proposes a device, which system includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the health risk prediction method as described above.
[0037] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the health risk prediction method described above are implemented.
[0038] In addition, in order to achieve the above-mentioned purpose, the present application also proposes a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the health risk prediction method described above are implemented.
[0039] The present application proposes a health risk prediction method, device, equipment, storage medium and computer program product, the method comprising: obtaining the physical examination data to be predicted in the current area to be tested; inputting the physical examination data to be predicted into a first preset prediction model to obtain a first initial prediction result, the first preset prediction model is obtained by training the first initial prediction model through the local sample data corresponding to the current area to be tested; inputting the physical examination data to be predicted into a second preset prediction model to obtain a second initial prediction result, the second preset prediction model is obtained by training the second initial prediction model through the local sample data; and obtaining a final prediction result based on the first initial prediction result and the second initial prediction result. Since the present application trains the first initial prediction model and the second initial prediction model through the local sample data corresponding to the current area to be tested, the trained first preset prediction model and the second preset prediction model can accurately predict the physical examination data to be predicted in the current area to be tested. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0041] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0042] Figure 1 This is a flow chart of the first embodiment of the health risk prediction method proposed in this embodiment;
[0043] Figure 2 This is a flow chart of a second embodiment of the health risk prediction method proposed in this embodiment;
[0044] Figure 3 A structural diagram of a first embodiment of a health risk prediction device provided in an embodiment of the present application;
[0045] Figure 4 It is a schematic diagram of the structure of a device suitable for implementing the embodiments of the present application.
[0046] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0047] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.
[0048] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0049] It should be noted that all directional indications in the embodiments of the present application (such as up, down, left, right, front, back, etc.) are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.
[0050] Understandably, with the aging of the population and changes in lifestyle, chronic diseases, such as hypertension and diabetes, have become major global health challenges, seriously threatening human health and life. Chronic diseases are characterized by high incidence, long course, and difficulty in cure, which imposes a heavy burden on individuals, families, and society. Hypertension is a major risk factor for cardiovascular disease and an important cause of serious diseases such as stroke and heart disease. According to statistics, about 1 billion people suffer from hypertension worldwide, causing about 10 million deaths each year. The main risk factors for hypertension include unhealthy diet, smoking and drinking habits, lack of exercise, and mental stress. Early identification and intervention of these bad habits can significantly reduce the incidence of hypertension, thereby improving the quality of life of patients. However, traditional health risk prediction methods mainly rely on the clinical experience of doctors and simple statistical models, with problems such as limited coverage and insufficient personalized evaluation capabilities, which are difficult to meet the needs of modern medical care. In recent years, machine learning technology has been widely used in health risk prediction, providing new solutions for early identification and intervention of chronic diseases.
[0051] When existing models that use machine learning technology to predict health risks are generally trained based on general data sets, they cannot be optimized for specific regions or populations, making it difficult for the models to adapt to the physiological characteristics and lifestyle differences of people in different regions. For example, factors such as the eating habits, lifestyles, and genetic backgrounds of people in different regions can affect the risk of hypertension, and general data sets cannot accurately reflect these differences.
[0052] Therefore, in order to solve the problem that the existing technology cannot make accurate predictions for specific regions or populations, this embodiment proposes a health risk prediction method, which includes: obtaining the physical examination data to be predicted in the current area to be tested; inputting the physical examination data to be predicted into a first preset prediction model to obtain a first initial prediction result, the first preset prediction model is obtained by training the first initial prediction model through local sample data corresponding to the current area to be tested; inputting the physical examination data to be predicted into a second preset prediction model to obtain a second initial prediction result, the second preset prediction model is obtained by training the second initial prediction model through local sample data; and obtaining a final prediction result based on the first initial prediction result and the second initial prediction result. Since this embodiment trains the first initial prediction model and the second initial prediction model through local sample data corresponding to the current area to be tested, the trained first preset prediction model and the second preset prediction model can make accurate predictions for the physical examination data to be predicted in the current area to be tested.
[0053] For ease of understanding, the following combination Figures 1 to 4 The health risk prediction method provided in the embodiments of the present application and the health risk prediction method, device, equipment, storage medium and computer program product provided in the following embodiments are introduced in detail.
[0054] The present application embodiment provides a health risk prediction method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the health risk prediction method proposed in this embodiment.
[0055] like Figure 1 As shown, the method includes:
[0056] Step S10: Obtain the physical examination data to be predicted in the current area to be tested.
[0057] It should be noted that the execution subject of this embodiment can be a computing service system with health risk prediction control, network communication and program running functions, such as a health risk prediction device, or an electronic device capable of realizing the above functions. This embodiment uses a health risk prediction device (hereinafter referred to as the device) for illustration, but does not specifically limit this embodiment.
[0058] It should also be noted that the current area to be tested may be an area of a certain range preset by the user, may be determined based on positioning information, or may be an area directly input by the user. The data to be examined may be body data directly uploaded by the user in the current area to be tested, or may be body data corresponding to a physical examination report obtained from a hospital in the current area to be tested.
[0059] In addition, in order to facilitate the acquisition of the physical examination data to be predicted in the current area to be tested, this embodiment also proposes an integrated platform to meet the needs of medical institutions and individual users in practical applications. Among them, the above-mentioned platform includes a front end, and the above-mentioned front end can be based on the Python Flask framework, providing users with a data upload and result display interface. Users can directly enter the physical examination data to be predicted in the above-mentioned interface or upload the physical examination data to be predicted through the medical institution's physical examination report number. This embodiment does not make specific restrictions. In a specific implementation, users in the current area to be tested can input the physical examination data to be predicted into the above-mentioned device through the above-mentioned front end, so that the above-mentioned device obtains the physical examination data to be predicted in the current area to be tested.
[0060] Step S20: input the physical examination data to be predicted into a first preset prediction model to obtain a first initial prediction result, wherein the first preset prediction model is obtained by training the first initial prediction model with local sample data corresponding to the current area to be tested.
[0061] Step S30: inputting the physical examination data to be predicted into a second preset prediction model to obtain a second initial prediction result, wherein the second preset prediction model is obtained by training the second initial prediction model with the local sample data.
[0062] It should be noted that the above-mentioned first preset prediction model can be a model obtained by training the first initial prediction model through the local sample data, and the above-mentioned local sample data can be sample physical examination data of the current area to be tested and the corresponding sample result data (for example, the physical examination data of user A one year ago and user A suffers from hypertension; the physical examination data of user B one year ago and user B does not suffer from hypertension). The above-mentioned first initial prediction model can be a big data model with a classification algorithm. This embodiment uses the K-Nearest Neighbors (KNN) model for explanation but does not make specific restrictions on this embodiment. The above-mentioned second preset prediction model can be a model obtained by training the second initial prediction model through the local sample data. The above-mentioned second initial prediction model can be a big data model with a classification algorithm. This embodiment uses the Light Gradient Boosting Machine (LightGBM) model for explanation but does not make specific restrictions on this embodiment.
[0063] In a specific implementation, health risks include a variety of situations such as high blood pressure, etc. In this embodiment, high blood pressure is used as a health risk for illustration, but this embodiment is not specifically limited. When the above-mentioned device obtains the physical examination data to be predicted in the current area to be tested, the physical examination data to be predicted is input into the first preset prediction model and the second preset prediction model trained with local sample data to obtain the first initial prediction result and the second initial prediction result.
[0064] Furthermore, in order to obtain the above-mentioned first preset prediction model and the second preset prediction model, before the step of obtaining the physical examination data to be predicted in the current area to be tested, it also includes:
[0065] Step S01: obtaining local sample data of the current area to be tested and sample prediction results corresponding to the local sample data;
[0066] Step S02: training a first initial prediction model based on the local sample data and the sample prediction results to obtain a first preset prediction model;
[0067] Step S03: training a second initial prediction model based on the local sample data and the sample prediction results to obtain a second preset prediction model.
[0068] It should be noted that the above sample prediction results can be user health risk results. In this embodiment, whether or not the user suffers from high blood pressure is used as the user health risk result for illustration, but this embodiment is not specifically limited. In this embodiment, in order to achieve the prediction of health risks, the physical examination data of the personnel in the current test area a period of time ago (for example, five years ago) can be obtained as local sample data and the health risk situation of the current user can be used as the sample prediction result. For example, the physical examination data of user C five years ago is used as the local sample data and whether user C currently suffers from high blood pressure is used as the sample prediction result.
[0069] In a specific implementation, before starting the prediction, the above-mentioned device will first obtain the local sample data of the current area to be tested and its corresponding sample prediction results. Subsequently, the device uses these data to train the first initial prediction model, and through continuous optimization, a first preset prediction model that is more adapted to local characteristics is formed. Similarly, the device will also train the second initial prediction model based on the same local sample data and prediction results, and finally obtain the second preset prediction model.
[0070] In addition, this embodiment can also optimize the KNN model and the LightGBM model by optimizing hyperparameters using grid search and cross-validation techniques. Among them, the hyperparameters in the KNN model include: the number of neighbors and the distance measurement method. In the specific implementation, the number of neighbors can be set to a series of values (for example, 1 to 20) by grid search, and the local sample data can be input into the KNN model corresponding to different numbers of neighbors to obtain different prediction results, and based on the prediction results and the sample prediction results corresponding to the local sample data, the target number of neighbors is selected from different numbers of neighbors as the hyperparameters of the first preset prediction model. The hyperparameters in the LightGBM model include: learning rate, maximum tree depth, number of leaf nodes, and subsampling rate and column sampling rate.
[0071] Step S40: obtaining a final prediction result based on the first initial prediction result and the second initial prediction result.
[0072] It should be noted that the above-mentioned final prediction result can be the probability that the user will suffer from health diseases such as hypertension in the future. In a specific implementation, after obtaining the first initial prediction result and the second initial prediction result, the above-mentioned device can perform weighted fusion on the above-mentioned first initial prediction result and the second initial prediction result to obtain the final prediction result.
[0073] Furthermore, in order to obtain an accurate final prediction result, the step of obtaining the final prediction result based on the first initial prediction result and the second initial prediction result includes:
[0074] Get the preset configuration weight;
[0075] Obtaining a health risk level based on the preset configuration weight, the first initial prediction result, and the second initial prediction result using a preset fusion algorithm;
[0076] The health risk level is taken as the final prediction result.
[0077] It should be noted that the above-mentioned preset configuration weights may be the configuration weights obtained by the user after training the first initial model and the second initial model through local sample data, and the above-mentioned health risk level may be the probability level (for example, high risk, medium risk, and low risk, etc.) of the health risk of the user corresponding to the physical examination data to be predicted after a period of time (such as one year later).
[0078] In a specific implementation, the above-mentioned device can divide the local sample data according to a certain ratio (such as 8:2) to obtain a training set and a test set. After training the first initial prediction model and the second initial prediction model through the training set, the trained first initial prediction model and the second initial prediction model can also be retrained through the training set to obtain preset configuration weights. After obtaining the first initial prediction result and the second initial prediction result, the above-mentioned device weightedly fuses the first initial prediction result and the second initial prediction result according to the above-mentioned preset configuration weights to obtain the health risk level corresponding to the physical examination data to be predicted, and uses the health risk level as the final prediction result.
[0079] In one example, the device uses the KNN model to obtain the first initial prediction result P KNN And use the LightGBM model to obtain the second initial prediction result P LightGBM After that, the first initial prediction model and the second initial prediction model are trained again through the training set to obtain the preset configuration weights ω1 and ω2, and finally the weighted average fusion algorithm is used to obtain the final prediction probability P final, where the weighted average fusion algorithm is:
[0080] P final =ω1P KNN +ω2P LightGBM ;
[0081] At the same time, according to the final predicted probability, the risk is divided into low risk (final predicted probability <50%), medium risk (50% ≤ final predicted probability <80%), and high risk (final predicted probability ≥80%), and the corresponding health risk level is obtained, and the health risk level is used as the final prediction result.
[0082] The present embodiment proposes a health risk prediction method, which includes: obtaining the physical examination data to be predicted of the current area to be tested; inputting the physical examination data to be predicted into a first preset prediction model to obtain a first initial prediction result, the first preset prediction model is obtained by training the first initial prediction model through local sample data corresponding to the current area to be tested; inputting the physical examination data to be predicted into a second preset prediction model to obtain a second initial prediction result, the second preset prediction model is obtained by training the second initial prediction model through local sample data; and obtaining a final prediction result based on the first initial prediction result and the second initial prediction result. Since the present embodiment trains the first initial prediction model and the second initial prediction model through local sample data corresponding to the current area to be tested, the trained first preset prediction model and the second preset prediction model can accurately predict the physical examination data to be predicted in the current area to be tested.
[0083] Based on the first embodiment, in the second embodiment, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be described in detail later. Figure 2 , Figure 2 This is a flow chart of the second embodiment of the health risk prediction method proposed in this embodiment. Further, the step of inputting the physical examination data to be predicted into the first preset prediction model to obtain the first initial prediction result includes:
[0084] Step S21: inputting the physical examination data to be predicted into a first preset prediction model to obtain a target distance between the physical examination data to be predicted and the local sample data corresponding to the current area to be tested;
[0085] Step S22: Obtain a preset number of neighbors corresponding to the first preset prediction model, and obtain a first initial prediction result based on the preset number of neighbors and each of the target distances.
[0086] It should be noted that the above-mentioned target distance can be a similarity measurement distance between the physical examination data to be predicted and the local sample data. The above-mentioned first preset prediction model can calculate the similarity distance between the above-mentioned predicted physical examination data and the local sample data as the target distance through a similarity distance algorithm (such as the Euclidean distance algorithm and the Manhattan distance algorithm, etc.).
[0087] In a specific implementation, when processing the physical examination data to be predicted, the above device first inputs it into the first preset prediction model that has been trained to calculate the target distance between the data to be predicted and the local sample data of the current area to be tested. Then, the device uses these target distances to determine the sample set closest to the data to be predicted based on the preset number of neighbors corresponding to the first preset prediction model. Based on the known prediction results of these neighbor samples, the above device comprehensively analyzes and outputs the first initial prediction result.
[0088] Furthermore, in order to obtain the first initial prediction result more accurately, the step of obtaining the first initial prediction result based on the preset number of neighbors and each of the target distances includes:
[0089] Acquire the local sample data corresponding to each target distance and the local sample result corresponding to each local sample data;
[0090] Sorting the target distances, and filtering the target sample results from the local sample results based on the sorting result and the preset number of neighbors;
[0091] A first initial prediction result is obtained based on the target sample result.
[0092] It should be noted that the above-mentioned preset number of neighbors can be a parameter for determining the number of most similar samples considered in the prediction process. In a specific implementation, when the above-mentioned device performs a prediction task, it first obtains the local sample data corresponding to each target distance, and the local sample results corresponding to these local sample data. These target distances are similarity measurement distances between the physical examination data to be predicted and the local sample data, and the local sample results are the health risk assessment results previously obtained through medical analysis or model prediction. The device then sorts the acquired target distances to ensure that it can accurately identify a group of samples that are most similar to the data to be predicted.
[0093] After the sorting is completed, the device selects the target sample results from each local sample result based on the sorting result and the preset number of neighbors. The preset number of neighbors is a specified value that determines how many of the most similar samples are considered in the prediction process. This step is critical because it ensures the accuracy of the prediction results by selecting the most relevant sample results to reflect the potential health risks of the data to be predicted.
[0094] Finally, the above-mentioned device obtains the first initial prediction result based on the screened target sample results by calculating the average value of these results or adopting other statistical methods.
[0095] In one example, assuming that the preset number of neighbors K = 2, and there are five local sample data, namely D, E, F, G, and H, the Euclidean distance algorithm is performed on the acquired physical examination data to be predicted and the above five local sample data to obtain the similarity distance between the physical examination data to be predicted and the above five local sample data, and they are sorted from large to small according to the similarity, and the two with the highest similarity are selected from the sorting results as the target sample results, and the first initial prediction result is obtained based on the sample prediction result corresponding to the target sample result.
[0096] Furthermore, in order to improve the accuracy and robustness of the overall prediction, the step of inputting the physical examination data to be predicted into the first preset prediction model includes:
[0097] Determine the physical examination data to be predicted to obtain a feature mean and a feature standard deviation corresponding to the physical examination data to be predicted;
[0098] Standardizing the physical examination data to be predicted according to the characteristic mean and the characteristic standard deviation;
[0099] Inputting the standardized physical examination data to be predicted into a first preset health risk prediction model;
[0100] The step of inputting the physical examination data to be predicted into the second preset prediction model comprises:
[0101] The standardized physical examination data to be predicted is input into a second preset health risk prediction model.
[0102] It should be noted that the above-mentioned feature mean can be the average value of each feature in the data set, which is used to describe the central tendency of the data. The above-mentioned feature standard deviation can be a statistic that measures the degree of dispersion of the distribution of each feature value in the data set, which is used to describe the variability of the data.
[0103] In the specific implementation, the above device performs a series of delicate steps when processing the physical examination data to be predicted for health risk assessment. First, the device determines the feature mean and feature standard deviation of the physical examination data to be predicted. These two statistics are key parameters in the data standardization process. The feature mean refers to the average of all feature values in the data set, while the feature standard deviation is an indicator of the degree of dispersion of feature values.
[0104] In this embodiment, a data normalization algorithm is also proposed:
[0105]
[0106] Among them, x is the physical examination data to be predicted, μ is the feature mean corresponding to the physical examination data to be predicted, and σ is the feature standard deviation corresponding to the physical examination data to be predicted.
[0107] Standardization is a data preprocessing technique that adjusts the data to a range of mean 0 and standard deviation 1 by subtracting the feature mean and dividing by the feature standard deviation. This eliminates the impact of different dimensions and numerical ranges and ensures the comparability of data during model training and prediction.
[0108] The above-mentioned device performs standardization processing on the physical examination data to be predicted according to the above-mentioned data standardization algorithm. After completing the standardization, the above-mentioned device inputs the processed physical examination data to be predicted into the first preset health risk prediction model. Similarly, the device also inputs the standardized physical examination data to be predicted into the second preset health risk prediction model.
[0109] This embodiment also provides a first embodiment of a health risk prediction device, please refer to Figure 3 , Figure 3 This is a structural diagram of a first embodiment of a health risk prediction device provided in an embodiment of the present application, wherein the health risk prediction device comprises:
[0110] A data acquisition module is used to obtain the physical examination data to be predicted in the current area to be tested;
[0111] A first data processing module, used for inputting the physical examination data to be predicted into a first preset prediction model to obtain a first initial prediction result, wherein the first preset prediction model is obtained by training the first initial prediction model with the local sample data corresponding to the current area to be tested;
[0112] A second data processing module is used to input the physical examination data to be predicted into a second preset prediction model to obtain a second initial prediction result, where the second preset prediction model is obtained by training the second initial prediction model with the local sample data;
[0113] A data integration module, configured to obtain a final prediction result based on the first initial prediction result and the second initial prediction result;
[0114] The data acquisition module is further used to acquire local sample data of the current area to be tested and sample prediction results corresponding to the local sample data; train a first initial prediction model based on the local sample data and the sample prediction results to obtain a first preset prediction model; train a second initial prediction model based on the local sample data and the sample prediction results to obtain a second preset prediction model;
[0115] The data integration module is also used to obtain preset configuration weights; use a preset fusion algorithm to obtain a health risk level based on the preset configuration weights, the first initial prediction result and the second initial prediction result; and use the health risk level as the final prediction result.
[0116] Based on the above-mentioned first embodiment of the health risk prediction device of the present application, a second embodiment of the health risk prediction device of the present application is proposed.
[0117] In this embodiment, the first data processing module is further used to input the physical examination data to be predicted into a first preset prediction model to obtain a target distance between the physical examination data to be predicted and the local sample data corresponding to the current area to be tested; obtain a preset number of neighbors corresponding to the first preset prediction model, and obtain a first initial prediction result based on the preset number of neighbors and each of the target distances;
[0118] The first data processing module is further used to obtain the local sample data corresponding to each of the target distances and the local sample results corresponding to each of the local sample data; sort the target distances, and filter out the target sample results from each of the local sample results based on the sorting result and the preset number of neighbors; and obtain a first initial prediction result based on the target sample results;
[0119] The first data processing module is further used to determine the physical examination data to be predicted to obtain the characteristic mean and characteristic standard deviation corresponding to the physical examination data to be predicted; standardize the physical examination data to be predicted according to the characteristic mean and the characteristic standard deviation; and input the standardized physical examination data to be predicted into the first preset health risk prediction model;
[0120] The second data processing module is also used to input the standardized physical examination data to be predicted into a second preset health risk prediction model.
[0121] The health risk prediction device provided in this embodiment adopts the health risk prediction method in the above embodiment, which can solve the problem that the prior art cannot accurately predict specific regions or populations. Compared with the prior art, the beneficial effects of the health risk prediction device provided in this embodiment are the same as the beneficial effects of the health risk prediction method provided in the above embodiment, and the other technical features in the health risk prediction device are the same as the features disclosed in the above embodiment method, which will not be repeated here.
[0122] This embodiment provides a health risk prediction device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the health risk prediction method in the above-mentioned embodiment one.
[0123] Reference below Figure 4 , Figure 4 Schematic diagram of the structure of the health risk prediction device suitable for implementing the embodiment of the present application. The device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), devices, etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 4 The device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0124] like Figure 4 As shown, the health risk prediction device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.
[0125] In particular, according to the present embodiment, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the present embodiment includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through a communication device, or installed from the storage device 1003, or installed from the ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present embodiment are executed.
[0126] The device provided in this embodiment adopts the health risk prediction method in the above embodiment, which can solve the problem that the prior art cannot accurately predict specific regions or populations. Compared with the prior art, the beneficial effects of the device provided in this embodiment are the same as the beneficial effects of the health risk prediction method provided in the above embodiment, and the other technical features in the device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.
[0127] It should be understood that the various parts disclosed in this embodiment can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.
[0128] The above is only a specific implementation of this embodiment, but the protection scope of this embodiment is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in this embodiment, which should be included in the protection scope of this embodiment. Therefore, the protection scope of this embodiment should be based on the protection scope of the claims.
[0129] This embodiment provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the health risk prediction method in the above-mentioned embodiment.
[0130] The computer-readable storage medium provided in this embodiment may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.
[0131] The computer-readable storage medium may be included in the device; or may exist independently without being installed in the device.
[0132] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the device, the device: performs health risk prediction.
[0133] The computer program code for performing the operation of the present embodiment can be written in one or more programming languages or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on the remote computer, or entirely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).
[0134] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present embodiment. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0135] The modules involved in the description of this embodiment may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.
[0136] The readable storage medium provided in this embodiment is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned health risk prediction method, and can solve the problem that the prior art cannot accurately predict specific regions or populations. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this embodiment are the same as the beneficial effects of the health risk prediction method provided in the above-mentioned embodiment, and will not be repeated here.
[0137] The above descriptions are only some embodiments, and are not intended to limit the patent scope of this embodiment. All equivalent structural changes made using the contents of the specification and drawings of this application under the technical concept of this application, or direct / indirect applications in other related technical fields are included in the patent protection scope of this application.
Claims
1. A health risk prediction method, characterized in that: The method comprises: Obtain the physical examination data to be predicted in the current area to be tested; Inputting the physical examination data to be predicted into a first preset prediction model to obtain a first initial prediction result, wherein the first preset prediction model is obtained by training the first initial prediction model with the local sample data corresponding to the current area to be tested; Inputting the physical examination data to be predicted into a second preset prediction model to obtain a second initial prediction result, wherein the second preset prediction model is obtained by training the second initial prediction model with the local sample data; A final prediction result is obtained based on the first initial prediction result and the second initial prediction result.
2. The method according to claim 1, characterized in that The step of obtaining a final prediction result based on the first initial prediction result and the second initial prediction result comprises: Get the preset configuration weight; Obtaining a health risk level based on the preset configuration weight, the first initial prediction result, and the second initial prediction result using a preset fusion algorithm; The health risk level is taken as the final prediction result.
3. The method according to claim 1, characterized in that The step of inputting the physical examination data to be predicted into a first preset prediction model to obtain a first initial prediction result includes: Inputting the physical examination data to be predicted into a first preset prediction model to obtain a target distance between the physical examination data to be predicted and the local sample data corresponding to the current area to be tested; A preset number of neighbors corresponding to the first preset prediction model is obtained, and a first initial prediction result is obtained based on the preset number of neighbors and each of the target distances.
4. The method according to claim 3, characterized in that The step of obtaining a first initial prediction result based on the preset number of neighbors and each of the target distances comprises: Acquire the local sample data corresponding to each target distance and the local sample result corresponding to each local sample data; Sorting the target distances, and filtering the target sample results from the local sample results based on the sorting result and the preset number of neighbors; A first initial prediction result is obtained based on the target sample result.
5. The method according to claim 1, characterized in that Before the step of obtaining the physical examination data to be predicted in the current area to be tested, the method further includes: Obtaining local sample data of the current area to be tested and sample prediction results corresponding to the local sample data; Training a first initial prediction model based on the local sample data and the sample prediction results to obtain a first preset prediction model; A second initial prediction model is trained based on the local sample data and the sample prediction results to obtain a second preset prediction model.
6. The method according to claim 1, characterized in that The step of inputting the physical examination data to be predicted into the first preset prediction model comprises: Determine the physical examination data to be predicted to obtain a feature mean and a feature standard deviation corresponding to the physical examination data to be predicted; Standardizing the physical examination data to be predicted according to the characteristic mean and the characteristic standard deviation; Inputting the standardized physical examination data to be predicted into a first preset health risk prediction model; The step of inputting the physical examination data to be predicted into the second preset prediction model comprises: The standardized physical examination data to be predicted is input into a second preset health risk prediction model.
7. A health risk prediction device, characterized in that: The device comprises: A data acquisition module is used to obtain the physical examination data to be predicted in the current area to be tested; A first data processing module, used for inputting the physical examination data to be predicted into a first preset prediction model to obtain a first initial prediction result, wherein the first preset prediction model is obtained by training the first initial prediction model with the local sample data corresponding to the current area to be tested; A second data processing module is used to input the physical examination data to be predicted into a second preset prediction model to obtain a second initial prediction result, where the second preset prediction model is obtained by training the second initial prediction model with the local sample data; A data integration module is used to obtain a final prediction result based on the first initial prediction result and the second initial prediction result.
8. A health risk prediction device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the health risk prediction method according to any one of claims 1 to 6.
9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the health risk prediction method according to any one of claims 1 to 6 are implemented.
10. A computer program product, characterized in that The computer program product comprises a computer program, which, when executed by a processor, implements the steps of the health risk prediction method according to any one of claims 1 to 6.