Disease risk prediction method and system based on big data analysis

Abstract

The invention discloses a disease risk prediction method and system based on big data analysis, and relates to the technical field of disease risk prediction. The method comprises the steps of obtaining multi-source data, and performing data cleaning, feature selection and data standardization processing; marking and labeling the collected data, constructing a disease risk prediction model through supervised learning, and performing real-time prediction and dynamic updating; the comprehensive disease risk value of the patient is calculated according to the multiple indexes, and abnormal early warning and personalized intervention including health suggestion, follow-up visit management and psychological support are carried out. The system comprises a data acquisition module, a screening module, a risk prediction module, an evaluation module, an abnormity early warning module and a control module. According to the system, through multi-source data acquisition and intelligent processing, accurate prediction and comprehensive evaluation of disease risks are realized, prediction accuracy is improved, personalization of health management is enhanced, and timely early warning and disease risk reduction are facilitated. According to the invention, the early discovery rate and prevention effect of diseases can be improved, and the medical cost is reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of disease risk prediction, and specifically relates to a disease risk prediction method and system based on big data analysis. Background Art

[0002] In traditional medical practice, doctors usually make disease diagnosis and risk prediction based on patients' symptoms, signs, laboratory test results, and medical history. However, this approach has the following limitations: Limited data volume: Relying only on data from a single or a few medical institutions makes it impossible to obtain comprehensive patient information.

[0003] Highly subjective: The diagnosis and prediction process is highly dependent on the doctor's experience, which may vary between different doctors.

[0004] Lack of dynamic updates: It cannot reflect changes in the patient's health status in real time, making it difficult to adjust prevention strategies in a timely manner.

[0005] Ignoring the influence of multiple factors: Failing to fully consider the combined impact of genes, environment, lifestyle and socioeconomic factors on the occurrence and development of the disease.

[0006] To overcome the above problems, researchers have begun to explore the use of big data analysis and machine learning techniques to improve the effect of disease risk prediction. The advantages of these new technologies are: Multi-source data integration: Data from multiple channels can be collected, including but not limited to hospital information systems, wearable devices, genetic testing platforms, etc., to obtain a more comprehensive patient portrait.

[0007] Automated feature extraction: Automatically identify features that are highly correlated with disease risk through algorithms, reduce human intervention, and improve the objectivity and accuracy of prediction models.

[0008] Real-time data processing: With the help of Internet of Things (IoT) technology and cloud computing platform, real-time monitoring of patients' physiological indicators and dynamic update of risk prediction can be achieved.

[0009] Personalized health management: Provide customized health advice and warnings based on each patient's specific situation to help them better manage their own health.

[0010] The present invention proposes a disease risk prediction method and system based on big data analysis (as described in Examples 1 and 2), which aims to integrate multi-source data (including medical records, physiological indicators, genes, environment, lifestyle and socioeconomic factors) and use advanced machine learning algorithms to build an accurate disease risk prediction model. This method not only improves the early detection rate and prevention effect of diseases, but also reduces medical costs. Summary of the invention

[0011] In order to overcome the shortcomings and deficiencies of the above-mentioned prior art, the first purpose of the present invention is to provide a disease risk prediction method based on big data analysis; the second purpose of the present invention is to provide a disease risk prediction system based on big data analysis.

[0012] The first object of the present invention adopts the following technical solution: A disease risk prediction method based on big data analysis, the process is as follows: Step 1: Obtain multi-source data related to disease risk, including patient history data, physiological indicator data, genetic data, environmental factor data, lifestyle data, and socioeconomic data; Step 2: Mark and annotate the collected data, including marking known disease events and non-disease events, and annotating the data information in detail, including disease type, disease development stage, treatment effect and follow-up data; Step 3: Build a disease risk prediction model through supervised learning. The input features include the patient's physiological indicators, genetic data, environmental factors, lifestyle and socioeconomic data. The output goal is to predict the patient's risk probability of contracting a certain disease in the future. Step 4: Conduct disease risk assessment and calculate the comprehensive disease risk value, which combines multiple risk assessment indicators, including changes in physiological indicators, genetic risk scores, environmental exposure risks, lifestyle risks, and socioeconomic risks; Step 5: Conduct abnormal warning and personalized intervention, divide the warning level according to the comprehensive risk value, and provide corresponding health advice, follow-up management and psychological support.

[0013] Preferably, step one also includes performing data cleaning, feature selection and data standardization on the acquired data.

[0014] Preferably, in step 2, a semi-supervised learning method is used to perform preliminary classification on some data that are not clearly labeled.

[0015] Preferably, in step three, 70% of the historical data is used as a training set and 30% of the data is used as a test set to train and verify the model, and the model performance is optimized through cross-validation, hyperparameter tuning and other methods.

[0016] Preferably, in step four, the patient's disease risk prediction results are updated in real time through a real-time data acquisition system, including wearable devices and mobile applications.

[0017] As a preferred method, the comprehensive disease risk value is calculated using the following formula: ; in, is the comprehensive disease risk value; , , , , is the weight of the risk factor; to score physiological risk factors; To score genetic risk factors; To score environmental exposure risk factors; to score lifestyle risk factors; Score for socioeconomic risk factors.

[0018] Preferably, the personalized intervention provided in step five includes diet adjustment, exercise plan, drug treatment, regular follow-up arrangement and psychological counseling.

[0019] The second object of the present invention adopts the following technical solution: A disease risk prediction system based on big data analysis is used to implement a disease risk prediction method based on big data analysis. The system includes a data acquisition module, a data screening module, a risk prediction module, a risk assessment module, an abnormal warning module and a control module; Data collection module: responsible for obtaining multi-source data related to disease risks from multiple data sources including hospital information systems, wearable devices, and genetic testing platforms; Technical implementation: Through API interface and database connection, patients’ medical records, physiological indicators, genetic data, environmental factors, and lifestyle information are collected in real time; Data screening module: cleans, selects features and standardizes the collected multi-source data to ensure data quality and consistency; Risk prediction module: build a disease risk prediction model through supervised learning algorithm to predict the disease risk probability of patients in real time; Risk assessment module: conducts comprehensive disease risk assessment based on the patient's physiological indicators, genetic data, environmental factors, lifestyle, and socioeconomics, and calculates the patient's comprehensive risk value; Abnormal warning module: Based on the patient's disease risk assessment results, abnormal warnings are issued and personalized health management suggestions are provided; Control module: responsible for coordinating the operation of each module to ensure the stability and efficiency of the system.

[0020] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are: 1. The present invention integrates multi-source data, including medical history, physiological indicators, genes, environment, lifestyle and socioeconomic factors, and uses advanced machine learning algorithms to build an accurate disease risk prediction model. This innovative data integration method can more comprehensively assess the patient's disease risk, thereby achieving more accurate predictions. By dynamically updating the patient's risk assessment in real time, potential risks can be discovered in the early stages of the disease, thereby improving the early detection rate of the disease; 2. The method of the present invention not only predicts disease risk, but also provides personalized health management suggestions based on the specific situation of the patient. By comprehensively evaluating multiple risk assessment indicators, the patient's comprehensive disease risk value is calculated, and early warning is issued according to the risk level classification. This personalized intervention method can help patients take appropriate preventive measures according to their own situation and improve the pertinence and effectiveness of health management; 3. The present invention can reduce unnecessary medical examinations and treatments through accurate disease risk prediction and personalized health management suggestions, thereby reducing medical costs. At the same time, real-time dynamic updates of patients' risk assessment results and personalized suggestions can make health management more efficient and convenient. In addition, the stability and efficiency of the system also ensure the accuracy of large-scale data processing and real-time prediction, further improving the efficiency of health management. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present invention 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, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 1 A flow chart of a disease risk prediction method based on big data analysis of the present invention is shown; Figure 2 A module diagram of a disease risk prediction system based on big data analysis of the present invention is shown. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] In addition, the described features, structures or characteristics may be combined in one or more example embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the example embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or other methods, components, steps, etc. may be adopted. In other cases, well-known structures, methods, implementations or operations are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0025] Embodiment 1:

[0026] See also Figure 1 As shown, a disease risk prediction method based on big data analysis in this embodiment has the following process: Step 1: Obtain multi-source data related to disease risk.

[0027] Data sources include patient historical medical records, physiological indicator data, genetic data, environmental factor data, lifestyle data and socioeconomic data.

[0028] Patient historical medical records: including past medical history, surgical records, medication usage, etc.

[0029] Physiological indicator data: real-time monitoring data such as blood pressure, blood sugar, heart rate, body temperature, etc.

[0030] Genetic data: Genetic sequencing data of patients, which is used to assess the impact of genetic factors on the disease.

[0031] Environmental factor data: such as air quality, water quality, climate conditions, etc. These external environmental factors may affect the incidence of the disease.

[0032] Lifestyle data: such as eating habits, exercise frequency, smoking and drinking habits, etc. These behavioral habits have an important impact on health.

[0033] Socioeconomic data: Socioeconomic factors such as income level, education level, and occupation type can also affect the occurrence and development of the disease.

[0034] Data screening strategies include data cleaning, feature selection, and data normalization.

[0035] Data cleaning: Remove duplicate, missing or abnormal data to ensure data quality.

[0036] Feature selection: Screen out features that are highly correlated with disease risk from large amounts of data, reduce redundant information, and improve the efficiency of the model.

[0037] Data standardization: Standardize data from different sources to ensure data comparability and consistency.

[0038] Step 2: Mark and annotate the collected data.

[0039] S21. Mark known disease events and non-disease events.

[0040] Disease event data: includes data on patients diagnosed with a disease, marked as "positive".

[0041] Non-disease event data: includes data of healthy people who are not sick, marked as "negative".

[0042] Semi-supervised learning: For some data that is not clearly labeled, semi-supervised learning methods can be used for preliminary classification, followed by manual labeling.

[0043] S22. Detailed information of the annotated data, including disease type, disease development stage, treatment effect and follow-up data.

[0044] Disease type: such as cardiovascular disease, diabetes, cancer, etc.

[0045] Disease development stage: such as early, middle, late, etc.

[0046] Treatment effect: such as cure, improvement, deterioration, etc.

[0047] Follow-up data: Long-term follow-up data of patients to evaluate disease progression and recurrence.

[0048] Step 3: Build a disease risk prediction model through supervised learning.

[0049] S31. Model construction.

[0050] Input features: including the patient's physiological indicators, genetic data, environmental factors, lifestyle and socioeconomic data.

[0051] Output goal: Predict the risk probability of a patient developing a certain disease in the future.

[0052] Model selection: You can choose from a variety of machine learning algorithms, such as logistic regression, support vector machine (SVM), random forest, gradient boosted tree (GBDT), neural network, etc. The specific choice depends on the characteristics of the data and the requirements of the prediction task.

[0053] Model training: Use 70% of the historical data as the training set and 30% of the data as the test set to train and verify the model to ensure the accuracy and generalization ability of the model.

[0054] Model optimization: Further improve the performance of the model through methods such as cross-validation and hyperparameter tuning.

[0055] S32. Real-time prediction.

[0056] Real-time data collection: The patient's physiological index data is collected in real time through wearable devices, mobile applications and other channels.

[0057] S33. Dynamic update.

[0058] Based on the latest real-time data, the patient's disease risk prediction results are dynamically updated to provide personalized health management recommendations.

[0059] Step 4: Conduct disease risk assessment.

[0060] S41. Risk assessment indicators.

[0061] Changes in physiological indicators: such as changing trends in blood pressure, blood sugar, heart rate, etc., to assess whether there is any abnormality in the patient's physical condition.

[0062] Genetic risk score: Calculate the genetic risk score for a patient to develop a disease based on their genetic data.

[0063] Environmental exposure risk: Assess the impact of harmful factors in the patient's environment (such as air pollution, radiation, etc.) on their health.

[0064] Lifestyle risks: Assess the impact of a patient's lifestyle (e.g., diet, exercise, smoking, etc.) on their health.

[0065] Socioeconomic risk: Assess the impact of a patient's socioeconomic status (such as income, education, occupation, etc.) on their health.

[0066] S42. Comprehensive risk assessment.

[0067] Risk value calculation formula: Combine multiple risk assessment indicators to calculate the patient's comprehensive disease risk value. The calculation formula is as follows: ; in, is the comprehensive disease risk value; , , , , is the weight of the risk factor; to score physiological risk factors; To score genetic risk factors; To score environmental exposure risk factors; to score lifestyle risk factors; Score for socioeconomic risk factors.

[0068] Step 5: Provide abnormal warning and personalized intervention.

[0069] S51. Classification of warning levels.

[0070] Low risk: The overall risk value is low. Patients are advised to continue to maintain a healthy lifestyle and have regular physical examinations.

[0071] Medium risk: The overall risk value is high, and patients are advised to take preventive measures, such as adjusting diet, increasing exercise, and avoiding harmful environments.

[0072] High risk: The overall risk value is very high. It is recommended that patients seek medical attention immediately for further examination and treatment.

[0073] Extremely high risk: The overall risk value is extremely high. It is recommended that patients seek emergency medical treatment and initiate emergency procedures.

[0074] S52. Personalized intervention.

[0075] Health advice: Provide personalized health management advice based on the patient's disease risk assessment results, such as diet adjustment, exercise plan, drug treatment, etc.

[0076] Follow-up management: arrange regular follow-up for high-risk patients to track their health status and adjust treatment plans in a timely manner.

[0077] Psychological support: Provide psychological counseling and support to patients to help them cope with the stress and anxiety caused by the disease.

[0078] The beneficial effects of this embodiment are as follows: the disease risk prediction method based on big data analysis integrates multi-source data including medical records, physiological indicators, genes, environment, lifestyle and socioeconomic factors, and uses advanced machine learning algorithms to build an accurate disease risk prediction model. It dynamically updates the patient's risk assessment in real time, provides personalized health management advice and early warnings, improves the early detection rate and prevention effect of diseases, and reduces medical costs.

[0079] Embodiment 2:

[0080] See also Figure 2 As shown, a disease risk prediction system based on big data analysis in this embodiment includes a data acquisition module, a data screening module, a risk prediction module, a risk assessment module, an abnormal warning module and a control module.

[0081] Data collection module: responsible for obtaining multi-source data related to disease risks from multiple data sources including but not limited to hospital information systems, wearable devices, and genetic testing platforms.

[0082] Technical implementation: Through API interfaces, database connections, etc., patients’ medical records, physiological indicators, genetic data, environmental factors, lifestyle and other information are collected in real time.

[0083] Data screening module: cleans, selects features and standardizes the collected multi-source data to ensure data quality and consistency.

[0084] Risk prediction module: Build a disease risk prediction model through supervised learning algorithm to predict the patient's disease risk probability in real time.

[0085] Risk assessment module: Conduct a comprehensive disease risk assessment based on the patient's physiological indicators, genetic data, environmental factors, lifestyle, and socioeconomics, and calculate the patient's comprehensive risk value.

[0086] Abnormal warning module: Based on the patient's disease risk assessment results, abnormal warnings are issued and personalized health management suggestions are provided.

[0087] Control module: responsible for coordinating the operation of each module to ensure the stability and efficiency of the system.

[0088] The beneficial effects of this embodiment are as follows: the disease risk prediction system based on big data analysis realizes accurate prediction and comprehensive evaluation of disease risk through multi-source data collection and intelligent processing, improves the accuracy of disease prediction, enhances the personalization of health management, and helps to timely warn and reduce disease risks.

[0089] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0090] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0091] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0092] 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 the units is only some logical function divisions. 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 through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0093] 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.

[0094] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A disease risk prediction method based on big data analysis, characterized in that: The method flow is as follows: Step 1: Acquire multi-source data related to disease risk, the data sources including patient historical medical records, physiological index data, gene data, environmental factor data, lifestyle data and socioeconomic data; Step 2: Mark and annotate the collected data, including marking known disease events and non-disease events, and annotating the data information in detail, including disease type, disease development stage, treatment effect and follow-up data; Step 3: Build a disease risk prediction model through supervised learning. The input features include the patient's physiological indicators, genetic data, environmental factors, lifestyle and socioeconomic data. The output goal is to predict the patient's risk probability of contracting a certain disease in the future. Step 4: Conduct disease risk assessment and calculate a comprehensive disease risk value, which combines multiple risk assessment indicators, including changes in physiological indicators, genetic risk scores, environmental exposure risks, lifestyle risks, and socioeconomic risks; Step 5: Conduct abnormal warning and personalized intervention, divide the warning level according to the comprehensive risk value, and provide corresponding health advice, follow-up management and psychological support.

2. A disease risk prediction method based on big data analysis according to claim 1, characterized in that: The step 1 also includes performing data cleaning, feature selection and data standardization on the acquired data.

3. The disease risk prediction method based on big data analysis according to claim 1, characterized in that: In the step 2, a semi-supervised learning method is used to perform preliminary classification on some data that are not clearly labeled.

4. The disease risk prediction method based on big data analysis according to claim 1, characterized in that: In step three, 70% of the historical data is used as a training set and 30% of the data is used as a test set to train and verify the model, and the model performance is optimized through cross-validation, hyperparameter tuning and other methods.

5. The disease risk prediction method based on big data analysis according to claim 1, characterized in that: In step 4, the patient's disease risk prediction results are updated in real time through a real-time data acquisition system, including wearable devices and mobile applications.

6. The disease risk prediction method based on big data analysis according to claim 1, characterized in that: The calculation formula for calculating the comprehensive disease risk value is as follows: ； in, is the comprehensive disease risk value; , , , , is the weight of the risk factor; to score physiological risk factors; To score genetic risk factors; To score environmental exposure risk factors; to score lifestyle risk factors; Score for socioeconomic risk factors.

7. The disease risk prediction method based on big data analysis according to claim 1, characterized in that: The personalized intervention provided in step five includes diet adjustment, exercise plan, drug treatment, regular follow-up arrangement and psychological counseling.

8. A disease risk prediction system based on big data analysis, used to implement the disease risk prediction method based on big data analysis as claimed in claim 1, characterized in that: The system includes a data acquisition module, a data screening module, a risk prediction module, a risk assessment module, an abnormal warning module and a control module; Data collection module: responsible for obtaining multi-source data related to disease risks from multiple data sources including hospital information systems, wearable devices, and genetic testing platforms; Technical implementation: Through API interface and database connection, patients’ medical records, physiological indicators, genetic data, environmental factors, and lifestyle information are collected in real time; Data screening module: cleans, selects features and standardizes the collected multi-source data to ensure data quality and consistency; Risk prediction module: build a disease risk prediction model through supervised learning algorithm to predict the disease risk probability of patients in real time; Risk assessment module: conducts comprehensive disease risk assessment based on the patient's physiological indicators, genetic data, environmental factors, lifestyle, and socioeconomics, and calculates the patient's comprehensive risk value; Abnormal warning module: Based on the patient's disease risk assessment results, abnormal warnings are issued and personalized health management suggestions are provided; Control module: responsible for coordinating the operation of each module to ensure the stability and efficiency of the system.

Images