Intelligent medical data collection and analysis system and method based on the Internet

Abstract

The present invention relates to an intelligent medical data collection and analysis system and method based on the Internet. The system includes: a data acquisition module, which is used to acquire the medical data of a first user on the Internet in real time; a data processing module, which is used to preprocess the medical data of the first user to obtain preprocessed data; a feature extraction module, which is used to extract features from the preprocessed data to obtain corresponding key features; a model construction module, which is used to construct a risk prediction model for analyzing medical data according to the key features; a treatment prediction module, which is used to analyze the medical data of a second user to be treated through a risk prediction model, generate a corresponding treatment plan, and predict the treatment effect on the second user in combination with the treatment data of each stage; a health score module, which is used to predict the health score of the second user according to the treatment effect of the second user through the risk prediction model. This system can improve the efficiency and accuracy of medical data analysis.

Description

Technical Field

[0001] The present invention relates to the field of medical data processing technology, and in particular to an Internet-based intelligent medical data collection and analysis system, method, electronic equipment and non-transient computer-readable storage medium. Background Art

[0002] Nowadays, with the advancement of medical informatization, more and more medical data are collected and stored. These data contain a large amount of medical information, providing valuable resources for medical institutions and related research. Through data analysis of chronic diseases such as diabetes, it can help medical institutions and doctors better understand the development of the disease, predict its risk level, and carry out precise intervention and treatment for patients at different stages, thereby improving the quality of life of patients and prolonging their lifespan.

[0003] However, traditional medical data collection and analysis solutions require manual input and processing, which is not only easily interfered by human factors, but also inefficient. Existing medical data collection and analysis solutions mainly support basic statistics and applications, and cannot deeply explore the value behind the data, making it difficult for medical institutions and doctors to more effectively analyze, intervene and treat patients' conditions. Summary of the invention

[0004] In view of the technical problems existing in the prior art, the present invention provides an Internet-based intelligent medical data collection and analysis system, method, electronic device and non-transitory computer-readable storage medium that can improve the efficiency and accuracy of medical data analysis.

[0005] The technical solution of the present invention to solve the above technical problems is as follows:

[0006] The present invention provides an intelligent medical data collection and analysis system based on the Internet, the system comprising:

[0007] A data acquisition module, used for acquiring medical data of a first Internet user in real time;

[0008] A data processing module, used for preprocessing the medical data of the first user to obtain preprocessed data;

[0009] A feature extraction module, used to extract features from the preprocessed data to obtain corresponding key features;

[0010] A model building module, used to build a risk prediction model for analyzing medical data based on the key features;

[0011] a treatment prediction module, configured to analyze the medical data of the second user to be treated by using the risk prediction model, generate a corresponding treatment plan, and predict the treatment effect on the second user in combination with the treatment data of each stage;

[0012] A health scoring module is used to predict the health score of the second user according to the treatment effect of the second user through the risk prediction model.

[0013] Optionally, the treatment prediction module is further specifically used for:

[0014] Obtaining the current value of each health indicator of the treatment data in each treatment effect evaluation;

[0015] Obtaining a baseline value of each health indicator of the treatment data in each treatment effect evaluation;

[0016] Obtaining a target value for each health indicator of the treatment data in each treatment effect evaluation;

[0017] constructing an improvement degree function according to the current value, the baseline value and the target value;

[0018] A comprehensive evaluation value of the treatment effect of the second user is determined according to the improvement degree functions corresponding to the multiple treatment effect evaluations.

[0019] Optionally, the comprehensive evaluation value of the treatment effect is expressed as:

[0020]

[0021] Where E is the comprehensive evaluation value of the treatment effect, m is the number of treatment effect evaluations, j is the index of the evaluation times, i is the index of the evaluation times, n is the number of health indicators considered in each evaluation, ω ij is the weight of the i-th health indicator in the j-th evaluation, P ij is the current value of the i-th health indicator in the j-th evaluation, B ij is the baseline value of the i-th health indicator in the j-th assessment, A ij is the target value of the i-th health indicator in the j-th evaluation, t is the time parameter, and f ij (P ij ,B ij ,A ij ,t) is a function used to measure the improvement degree of the i-th health indicator in the j-th evaluation.

[0022] Optionally, the treatment prediction module is further specifically used for:

[0023] Obtaining a first progress degree of each of the health indicators from the current value to the corresponding target value;

[0024] Obtaining a first degree of deviation of a current value of each of the health indicators relative to an ideal state;

[0025] The improvement degree function is constructed according to the first progress degree and the first deviation degree.

[0026] Optionally, the improvement degree function is expressed as:

[0027]

[0028] Among them, P ij is the current value of the ith health indicator in the jth evaluation,

[0029] B ij is the baseline value of the ith health indicator in the jth assessment,

[0030] A ij is the target value of the ith health indicator in the jth evaluation,

[0031] A ij -B ij is the range of improvement of the i-th indicator during treatment, exp(-λ ij t) is the time decay factor, t is the time parameter, k ij is the parameter that controls the slope of the function, θ ij It is a parameter that controls the ideal state of the center position of the function.

[0032] Optionally, the health scoring module is further specifically used for:

[0033] Obtaining the weight of each of the health indicators;

[0034] Obtaining a health factor for each of the health indicators;

[0035] Obtain the evaluation value of each treatment effect evaluation;

[0036] Constructing a state function according to the weight of each health indicator, the health factor, and the evaluation value;

[0037] The health score of the second user is determined according to the state functions corresponding to the multiple treatment effect evaluations.

[0038] Optionally, the health score is expressed as:

[0039]

[0040] Among them, g i (E j ) is the state function, m is the number of treatment effect evaluations, n is the number of health indicators considered in each evaluation, and v i is the weight of the ith health indicator, h i is the health factor related to the i-th health indicator.

[0041] Optionally, the health scoring module is further specifically used for:

[0042] Obtaining a second progress degree of each of the health indicator's evaluation values ​​from reaching a corresponding target value;

[0043] Obtaining a second degree of deviation of the evaluation value of each of the health indicators relative to an ideal state;

[0044] The state function is constructed according to the second progress degree and the second deviation degree.

[0045] Optionally, the state function is expressed as:

[0046]

[0047] Among them, B i and A i is the baseline value and target value of the ith health indicator, α i It is a parameter related to the i-th health indicator and is used to adjust the function shape.

[0048] The present invention also provides an intelligent medical data collection and analysis method based on the Internet, the method comprising:

[0049] Real-time access to the medical data of the first Internet user;

[0050] Preprocessing the medical data of the first user to obtain preprocessed data;

[0051] Performing feature extraction on the preprocessed data to obtain corresponding key features;

[0052] Based on the key features, construct a risk prediction model for analyzing medical data;

[0053] Analyze the medical data of the second user to be treated by using the risk prediction model, generate a corresponding treatment plan, and predict the treatment effect on the second user in combination with the treatment data of each stage;

[0054] The health score of the second user is predicted according to the treatment effect of the second user through the risk prediction model.

[0055] In addition, to achieve the above-mentioned purpose, the present invention also proposes an electronic device, comprising: a memory for storing computer software programs; a processor for reading and executing the computer software programs, thereby realizing an Internet-based intelligent medical data collection and analysis method as described above.

[0056] In addition, to achieve the above-mentioned purpose, the present invention also proposes a non-transitory computer-readable storage medium, in which a computer software program is stored. When the computer software program is executed by a processor, it implements an Internet-based intelligent medical data collection and analysis method as described above.

[0057] The beneficial effects of the present invention are:

[0058] (1) The present invention can comprehensively evaluate the impact of treatment plans on the patient's health status through the comprehensive treatment effect, and can integrate the changing trends and weights of multiple health indicators, accurately evaluate the impact of treatment plans on the patient's health status, and provide objective quantitative indicators.

[0059] (2) The present invention integrates the user's health score, treatment effect and weight distribution of multiple health indicators to fully reflect the patient's overall health status and provide a comprehensive basis for medical decision-making.

[0060] (3) The present invention is based on big data and machine learning technology. The system can customize personalized treatment plans and intervention measures according to the health data and characteristics of different patients, thereby improving the treatment effect and the quality of life of patients.

[0061] (4) Through accurate data analysis and prediction, the present invention can avoid unnecessary waste of medical resources and worsening of disease conditions, thereby reducing medical costs and improving resource utilization efficiency.

[0062] (5) The present invention can provide scientific, data-driven decision support to help medical professionals more effectively formulate treatment strategies, optimize patient management, and promote long-term improvements in health outcomes.

[0063] In summary, the present invention can improve the efficiency and accuracy of medical data analysis, help improve the quality and efficiency of medical services, and has significant practical value and benefits for medical institutions, doctors and patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 A scene diagram of an intelligent medical data collection and analysis method based on the Internet provided by the present invention;

[0065] Figure 2 A flowchart of an intelligent medical data collection and analysis method based on the Internet provided by the present invention;

[0066] Figure 3 A schematic diagram of the structure of an Internet-based intelligent medical data collection and analysis system provided by the present invention;

[0067] Figure 4 A schematic diagram of the hardware structure of a possible electronic device provided by the present invention;

[0068] Figure 5A schematic diagram of the hardware structure of a possible computer-readable storage medium provided by the present invention. DETAILED DESCRIPTION

[0069] 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0070] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0071] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0072] See also Figure 1 , Figure 1 A scene diagram of an intelligent medical data collection and analysis method based on the Internet provided by the present invention. Figure 1 As shown, the terminal and the server are connected via a network, such as a wired or wireless network connection. The terminal may include but is not limited to portable terminals such as mobile phones and tablets installed with various network platform applications, as well as fixed terminals such as computers, query machines, and advertising machines. The server provides users with various business services, including service push servers, user recommendation servers, etc.

[0073] It should be noted that Figure 1The scenario diagram of an Internet-based intelligent medical data collection and analysis method shown is only an example. The terminal, server and application scenario described in the embodiment of the present invention are intended to more clearly illustrate the technical solution of the embodiment of the present invention, and do not generate limitations on the technical solution provided by the embodiment of the present invention. Ordinary technicians in this field can know that with the evolution of the system and the emergence of new business scenarios, the technical solution provided by the embodiment of the present invention is also applicable to similar technical problems.

[0074] Among them, the terminal can be used for:

[0075] Real-time access to the medical data of the first Internet user;

[0076] Preprocessing the medical data of the first user to obtain preprocessed data;

[0077] Performing feature extraction on the preprocessed data to obtain corresponding key features;

[0078] Based on the key features, construct a risk prediction model for analyzing medical data;

[0079] Analyze the medical data of the second user to be treated by using the risk prediction model, generate a corresponding treatment plan, and predict the treatment effect on the second user in combination with the treatment data of each stage;

[0080] The health score of the second user is predicted according to the treatment effect of the second user through the risk prediction model.

[0081] See also Figure 2 , Figure 2 A structural schematic diagram of an Internet-based intelligent medical data acquisition and analysis system provided by the present invention.

[0082] like Figure 2 As shown, an intelligent medical data collection and analysis system based on the Internet proposed in an embodiment of the present invention includes:

[0083] The data acquisition module 201 is used to acquire the medical data of the first Internet user in real time.

[0084] Among them, the first user is a historical user who has undergone treatment. In some embodiments, devices such as smart bracelets and smart watches worn by users can continuously monitor the user's physiological indicators, such as heart rate, blood sugar, blood pressure, etc., and transmit the data to the cloud via a wireless network. Smart blood glucose meters, blood pressure meters and other devices used by users at home can regularly collect the user's health data, connect to the user's smartphone or home gateway device via Wi-Fi or Bluetooth, and then upload it to the cloud. The user's smartphone or tablet can also manually or automatically record and upload health data, including weight, diet, exercise, etc., through a health application (App).

[0085] In some embodiments, the collected medical data can be transmitted to the cloud server in real time through the Internet to ensure the timeliness of the data. The cloud server stores and backs up the received data to ensure the security and availability of the data. At the same time, the cloud server can provide efficient data processing capabilities and support the rapid storage and retrieval of large-scale data.

[0086] In some embodiments, data from different devices and sources can be integrated to form a comprehensive user health profile. This data may include physiological indicators, living habits, medical history records, laboratory test results, etc. The integrated data can be processed using data cleaning, format conversion, and standardization techniques to ensure data accuracy and consistency. Then, advanced data analysis techniques (such as machine learning, artificial intelligence, etc.) are used to deeply analyze the data to explore health trends and potential risks.

[0087] In some embodiments, the medical data collected in real time can be analyzed through preset algorithms and models to promptly detect abnormal conditions or health risks and generate health reports. Based on the analysis results, personalized health advice and intervention measures can be provided to users, such as reminding users to take medication, adjust their diet, increase exercise, etc. At the same time, the analysis results and suggestions are fed back to the user's doctor to help the doctor make further diagnosis and treatment adjustments.

[0088] During data transmission and storage, advanced encryption technologies (such as SSL / TLS, AES, etc.) are used to protect data security and prevent data theft or tampering. Identity authentication and permission management can be used to ensure that only authorized users and medical personnel can access and operate medical data. In accordance with relevant laws and regulations (such as GDPR, HIPAA, etc.), measures are taken to protect user privacy and ensure the anonymity and confidentiality of user data.

[0089] Through the above steps, the medical data collection and analysis system of the present invention can obtain the medical data of the first user of the Internet in real time, and provide the user with comprehensive health management services and personalized medical advice through data integration, processing, analysis and feedback, thereby improving the user's quality of life and health level.

[0090] The data processing module 202 is used to pre-process the medical data of the first user to obtain pre-processed data.

[0091] In some embodiments, preprocessing may include data cleaning, data standardization and normalization, data conversion and encoding, data aggregation and filtering, and time series processing.

[0092] In some embodiments, there may be missing values ​​in medical data. Common processing methods include deleting records with missing values, filling missing values ​​with mean / median / mode, or using interpolation, regression, etc. to fill in missing values. Detect outliers in the data through statistical methods or machine learning algorithms and process them. Common methods include removing outliers and replacing outliers with appropriate values. Check and delete duplicate records in the data to prevent data redundancy and analysis bias.

[0093] In some embodiments, medical data of different dimensions can be converted to the same scale. A common method is z-score normalization, which converts the data into a standard normal distribution with a mean of 0 and a standard deviation of 1. In some embodiments, the data can be scaled to a specific range (such as 0 to 1). A common method is Min-Max normalization. Normalization helps to eliminate the impact of differences in the dimensions of different indicators.

[0094] In some embodiments, the raw data is converted into a format suitable for analysis. For example, the date format is converted into a timestamp or other easy-to-process format. For categorical variables, they are converted into numerical data using a suitable encoding method, common methods include One-Hot Encoding, Label Encoding, etc.

[0095] In some embodiments, data can be summarized and aggregated as needed. For example, multiple days of heart rate data can be summarized into daily averages, maximum values, minimum values, etc. In some embodiments, data is filtered according to specific conditions, and data that meets the conditions is retained. For example, blood glucose value data that is not within the normal range is filtered out, and valid data is retained.

[0096] In some embodiments, for time series data, data at different time points are aligned to ensure that data at the same time point is complete. For example, data collected by different devices are aligned to the same time axis. Time series data is segmented to generate fixed-length time window data for subsequent analysis. For example, blood pressure data for a week is segmented into daily time windows.

[0097] For example, assuming that the user's medical data includes information such as heart rate, blood sugar, blood pressure, and weight, the specific steps of preprocessing are as follows:

[0098] Missing value handling: Missing values ​​of heart rate and blood glucose were filled with the most recent measurement value.

[0099] Outlier processing: Delete obviously abnormal heart rate (such as more than 200bpm) and blood sugar (such as more than 20mmol / L) data.

[0100] Data standardization and normalization:

[0101] All data are standardized to have a mean of 0 and a standard deviation of 1.

[0102] Data conversion and encoding:

[0103] Converts a timestamp to a standard date format.

[0104] One-hot encode categorical variables (such as drug type).

[0105] Data aggregation and filtering:

[0106] Summarize heart rate data by day and calculate daily average heart rate.

[0107] Filter out data older than one month and keep only the data from the most recent month.

[0108] Time Series Processing:

[0109] Time-align the heart rate and blood glucose data to ensure that there is corresponding data at each time point.

[0110] Split the data into daily time windows to generate daily health reports.

[0111] Through the above preprocessing steps, the quality and consistency of medical data can be effectively improved, making it suitable for subsequent analysis and processing. The preprocessed data is not only more accurate and reliable, but also can better support the implementation of personalized medical care and intelligent health management systems.

[0112] The feature extraction module 203 is used to extract features from the preprocessed data to obtain corresponding key features.

[0113] In some embodiments, the feature extraction step may include the following aspects:

[0114] Basic statistical feature extraction:

[0115] Mean: Calculates the mean of each health indicator within a specified time window. For example, calculates the average of daily heart rate, blood sugar, blood pressure, and weight.

[0116] Standard Deviation: Calculate the standard deviation of each health indicator to measure the fluctuation of the data.

[0117] Maximum value (Max) and minimum value (Min): Extract the maximum and minimum values ​​of each health indicator to reflect the range and extreme values ​​of the indicator.

[0118] Median: Calculate the median of each health indicator and provide the middle position value of the data.

[0119] Quartiles: Calculate the quartiles of each health indicator to reflect the distribution of data.

[0120] Temporal feature extraction:

[0121] Trend: Use regression analysis or other methods to extract the trend of health indicators over time. For example, use linear regression to extract the upward or downward trend of heart rate.

[0122] Periodicity: Identify periodic changes in health indicators, such as day-night fluctuations in blood sugar levels, and use methods such as Fourier transform to extract periodic features.

[0123] Window Features: Perform sliding window calculations on the data to extract features within the window, such as average heart rate and blood sugar per hour.

[0124] Frequency domain feature extraction:

[0125] Spectral Analysis: Perform spectral analysis on time series data to extract the energy distribution of the signal at different frequencies.

[0126] Power Spectral Density (PSD): Calculate the power spectral density of a signal and analyze the frequency components and energy of the signal.

[0127] Non-linear feature extraction:

[0128] Entropy: Calculate the entropy value of data to reflect the complexity and randomness of the data.

[0129] Fractal Dimension: Use fractal dimension to measure the complexity and self-similarity of data.

[0130] Characteristics of specific health indicators:

[0131] Heart Rate Variability (HRV): Analyze the variability of heart rate data and extract features that reflect the function of the autonomic nervous system.

[0132] Blood Glucose Variability: Calculate the fluctuation range and frequency of blood glucose levels and extract features that reflect blood glucose control.

[0133] Exemplarily, the specific steps of feature extraction are as follows:

[0134] Basic statistical feature extraction:

[0135] The mean, standard deviation, maximum, minimum, median, and quartiles of daily heart rate, blood glucose, blood pressure, and weight were calculated.

[0136] Temporal feature extraction:

[0137] Linear regression was used to extract the trend of heart rate over time.

[0138] Identify diurnal fluctuations in blood sugar levels and extract their periodic features.

[0139] Perform a sliding window calculation on the heart rate data and extract the average heart rate once every hour.

[0140] Frequency domain feature extraction:

[0141] Perform spectrum analysis on heart rate data to extract energy distribution at different frequencies.

[0142] Calculate the power spectral density of heart rate data and analyze its frequency content and energy.

[0143] Non-linear feature extraction:

[0144] Calculate the entropy of the heart rate data to measure its complexity and randomness.

[0145] Calculate the fractal dimension of heart rate data to reflect its self-similarity.

[0146] Characteristics of specific health indicators:

[0147] Analyze heart rate variability (HRV) to extract features that reflect the function of the autonomic nervous system.

[0148] Calculate the fluctuation range and frequency of blood sugar levels and extract features that reflect blood sugar control.

[0149] Through the above feature extraction steps, key features can be extracted from the preprocessed medical data. These features can effectively reflect the user's health status and provide important input data for subsequent analysis and prediction. The data after feature extraction can not only improve the accuracy and robustness of the model, but also provide richer information and support for medical decision-making.

[0150] The model building module 204 is used to build a risk prediction model for analyzing medical data based on the key features.

[0151] In some embodiments, the following are detailed steps for building and applying a risk prediction model:

[0152] The dataset after preprocessing and extracting key features can be divided into training set and test set. Usually, the dataset is divided in a ratio of 7:3 or 8:2 to ensure that the model can perform well in the training and evaluation stages.

[0153] If the health status categories in the dataset are unbalanced (i.e., the amount of data in some categories is much larger than that in other categories), methods such as oversampling, undersampling, or synthetic minority oversampling technique (SMOTE) can be used to balance the data.

[0154] In some embodiments, a suitable machine learning or deep learning algorithm can be selected according to the specific requirements of the task. Commonly used machine learning algorithms include logistic regression, support vector machine (SVM), decision tree, random forest and gradient boosting tree, etc. Deep learning algorithms can use neural networks and long short-term memory networks (LSTM), etc.

[0155] In some embodiments, key features can be scaled, such as standardized or normalized, to ensure that the features have similar dimensions, which is helpful for model training and convergence. Features can be selected using statistical methods (such as chi-square test, mutual information method) or algorithms (such as LASSO regression, tree-based feature selection), retaining the most important features to improve model performance and interpretability.

[0156] In some embodiments, the selected model can be trained using the training set data. During the training process, the model parameters are adjusted by optimizing the loss function (such as logarithmic loss, mean square error, etc.) so that the model can accurately predict the risk of disease. The cross-validation method is used during the training process to ensure the generalization ability of the model and avoid overfitting.

[0157] In some embodiments, the performance of the model can be evaluated using test set data. Common evaluation indicators include accuracy, precision, recall, F1 score, and receiver operating characteristic curve (ROC Curve) and the area under it (AUC). In some embodiments, model parameters (such as regularization parameters, learning rate, etc.) can be adjusted according to the evaluation results or other more suitable models can be selected to further improve model performance.

[0158] In some embodiments, the trained risk prediction model can be deployed into the medical system to ensure that the model can process new data and make predictions in real time. New medical data is acquired in real time, preprocessed and feature extracted, and then input into the model to generate disease risk assessment results. The prediction results can be explained to doctors and patients to provide actionable health advice and intervention measures.

[0159] For example, assuming that Random Forest is used as a disease risk prediction model, the specific steps are as follows:

[0160] Data preparation:

[0161] The preprocessed dataset is divided into a training set (80%) and a test set (20%). The SMOTE method is used to balance the health status categories in the training set.

[0162] Model selection:

[0163] Random forest was selected as the prediction model.

[0164] Feature Engineering:

[0165] Standardize the key features. Use tree-based feature selection to select the most important features.

[0166] Model training:

[0167] The random forest model is trained using the training set data to optimize the logarithmic loss function. The 5-fold cross-validation method is used to evaluate the generalization ability of the model.

[0168] Model Evaluation:

[0169] Use the test set data to evaluate the model performance and calculate the accuracy, precision, recall, F1 score, and AUC value. Adjust the model parameters based on the evaluation results, such as increasing or decreasing the number of decision trees.

[0170] Model deployment and application:

[0171] Deploy the trained random forest model to the cloud server of the medical system. Process the newly collected medical data in real time, input the model after preprocessing and feature extraction, and generate risk assessment results. Feedback the prediction results and health advice to doctors and patients.

[0172] Through the above steps, the risk prediction model can be constructed and applied using the extracted key features to accurately assess and predict disease risks. This will not only help medical institutions and doctors to manage the disease more effectively and make treatment decisions, but also provide patients with personalized health advice and intervention measures, thus improving the overall level of medical services and the quality of life of patients.

[0173] The treatment prediction module 205 is used to analyze the medical data of the second user to be treated through the risk prediction model, generate a corresponding treatment plan, and predict the treatment effect on the second user in combination with the treatment data of each stage.

[0174] In some embodiments, the treatment prediction module 205 is further specifically configured to:

[0175] Obtaining the current value of each health indicator of the treatment data in each treatment effect evaluation;

[0176] Obtaining a baseline value of each health indicator of the treatment data in each treatment effect evaluation;

[0177] Obtaining a target value for each health indicator of the treatment data in each treatment effect evaluation;

[0178] constructing an improvement degree function according to the current value, the baseline value and the target value;

[0179] A comprehensive evaluation value of the treatment effect of the second user is determined according to the improvement degree functions corresponding to the multiple treatment effect evaluations.

[0180] In some embodiments, the comprehensive evaluation value of the therapeutic effect is expressed as:

[0181]

[0182] Where E is the comprehensive evaluation value of the treatment effect, m is the number of treatment effect evaluations, j is the index of the evaluation times, i is the index of the evaluation times, n is the number of health indicators considered in each evaluation, ω ij is the weight of the i-th health indicator in the j-th evaluation, P ij is the current value of the i-th health indicator in the j-th evaluation, B ij is the baseline value of the i-th health indicator in the j-th assessment, A ij is the target value of the i-th health indicator in the j-th evaluation, t is the time parameter, and f ij (Pij ,B ij ,A ij ,t) is a function used to measure the improvement degree of the i-th health indicator in the j-th evaluation.

[0183] In the specific implementation, E is the treatment effect, which is the multiple treatment effect evaluation f ij The average value of

[0184] m is the number of treatment effect evaluations, that is, the number of repetitions of the evaluation of the treatment regimen;

[0185] j is the index of the number of evaluations, ranging from 1 to m;

[0186] i is the index of the evaluation number, ranging from 1 to n;

[0187] n is the number of health indicators considered in each assessment;

[0188] ω ij is the weight of the i-th health indicator in the j-th assessment, which is used to reflect the importance of the indicator in the comprehensive assessment;

[0189] P ij is the current value of the i-th health indicator at the j-th evaluation;

[0190] V ij is the baseline value of the ith health indicator at the jth assessment;

[0191] A ij is the target value of the ith health indicator in the jth evaluation;

[0192] t is a time parameter, reflecting the time effect during the treatment process, such as the duration of the treatment course or the durability of the treatment effect;

[0193] f ij (P ij ,B ij ,A ij ,t) is a function used to measure the improvement degree of the i-th health indicator in the j-th evaluation.

[0194] In the specific implementation, The average of each treatment effect evaluation j is used to obtain the overall average effect of all evaluations. This step ensures the stability and reliability of the evaluation results and reflects the consistency of the treatment plan in multiple applications.

[0195] is the weighted average of all health indicators i considered in each evaluation, where the weight ω ij The contribution of different indicators to the comprehensive evaluation of treatment effect is considered. Function f ij Each health indicator is measured relative to its baseline Bij and target value A ij The improvement of the performance and the influence of the time factor t.

[0196] ω ij It reflects the importance of each health indicator in the overall treatment effect evaluation. Different health indicators may have different weights due to their different impacts on the patient's health status.

[0197] f ij (P ij ,B ij ,A ij ,t) is based on the current value P ij , baseline value B ij , target value A ij and time parameter t, quantifying the degree of improvement of each health indicator during the treatment process. This functional form usually takes into account the linear or nonlinear changes of the indicators, as well as the time decay or gain effect.

[0198] In this way, the formula provides a systematic and quantitative approach to evaluate the comprehensive effect of treatment options, thereby providing a scientific basis for medical decision-making and helping to optimize and personalize patient treatment management.

[0199] In some embodiments, the treatment prediction module 205 is further specifically configured to:

[0200] Obtaining a first progress degree of each of the health indicators from the current value to the corresponding target value;

[0201] Obtaining a first degree of deviation of a current value of each of the health indicators relative to an ideal state;

[0202] The improvement degree function is constructed according to the first progress degree and the first deviation degree.

[0203] In some embodiments, the improvement function is expressed as:

[0204]

[0205] Among them, P ij is the current value of the ith health indicator in the jth evaluation,

[0206] B ij is the baseline value of the ith health indicator in the jth assessment,

[0207] A ij is the target value of the ith health indicator in the jth evaluation,

[0208] A ij -B ijis the range of improvement of the i-th indicator during treatment, exp(-λ ij t) is the time decay factor, t is the time parameter, k ij is the parameter that controls the slope of the function, θ ij It is a parameter that controls the ideal state of the center position of the function.

[0209] In the specific implementation, P ij is the current value of the i-th health indicator at the j-th evaluation;

[0210] B ij is the baseline value of the ith health indicator at the jth assessment;

[0211] A ij is the target value of the ith health indicator in the jth evaluation;

[0212] A ij -B ij is the range within which the ith indicator can be improved during treatment;

[0213] It is the indicator P ij Achieve Target A ij progress;

[0214] exp(-λ ij t) is the time decay factor, where λ ij is the parameter that controls the decay rate, and t is the time parameter, which reflects the time effect during the treatment process. This part expresses the actual improvement progress of the indicator and takes into account the decrease in the improvement rate over time;

[0215] k ij is the parameter that controls the slope of the function;

[0216] θ ij is a parameter that controls the ideal state of the center position of the function;

[0217] exp(-k ij (P ij -θ ij ) is a sigmoid function used to quantify P ij Relative to θ ij The degree of deviation, which partly expresses the index P ij Relative to the ideal state θ ij The closer the deviation is to the ideal state, the closer the value is to 1, and vice versa.

[0218] Part I Measured the indicator P ij Achieve Target A ijThe degree of progress is also considered, and the influence of time is taken into account. ij Target A not achieved ij , and its influence will gradually decrease due to time decay.

[0219] Part 2 The index P is quantified by the sigmoid function. ij Relative to the ideal state θ ij This function form can effectively express the degree to which the indicator deviates from the ideal state, and has good continuity and smoothness in mathematics.

[0220] This function combines the target value, baseline value, current value and time parameters, and can objectively and quantitatively evaluate the improvement of health indicators during the treatment process, providing important data support and analytical basis for medical decision-making.

[0221] The health score module 206 is used to predict the health score of the second user according to the treatment effect of the second user through the risk prediction model.

[0222] In some embodiments, the health score module 206 is further specifically configured to:

[0223] Obtaining the weight of each of the health indicators;

[0224] Obtaining a health factor for each of the health indicators;

[0225] Obtain the evaluation value of each treatment effect evaluation;

[0226] Constructing a state function according to the weight of each health indicator, the health factor, and the evaluation value;

[0227] The health score of the second user is determined according to the state functions corresponding to the multiple treatment effect evaluations.

[0228] In some embodiments, the health score is expressed as:

[0229]

[0230] Among them, g i (E j ) is the state function, m is the number of treatment effect evaluations, n is the number of health indicators considered in each evaluation, and v i is the weight of the ith health indicator, h i is the health factor related to the i-th health indicator.

[0231] In the specific implementation, S is the comprehensive patient health score, which comprehensively considers multiple treatment effect evaluations E j Result;

[0232] m is the number of treatment effect evaluations, that is, the number of repetitions of the evaluation of the treatment regimen;

[0233] n is the number of health indicators considered in each assessment;

[0234] v i is the weight of the i-th health indicator, reflecting the importance of this indicator to the patient's overall health score;

[0235] h i is the health factor related to the ith health indicator, reflecting the contribution of the indicator to overall health. It can be a coefficient or function used to adjust the influence of the indicator in the comprehensive score;

[0236] E j is the result of the j-th treatment effect evaluation, that is, the E value;

[0237] g i (E j ) is a state function used to measure the current state of each health indicator. It can be a linear or nonlinear function, and the specific form can be determined according to the specific health indicator.

[0238] In the specific implementation, The average of each treatment effect evaluation j is used to obtain the overall average result of all evaluations. This step ensures the stability and reliability of the evaluation results and reflects the consistency of the treatment plan in multiple applications.

[0239] is the weighted average of all health indicators iii considered in each evaluation, where the weight v i Reflecting the importance of each health indicator in the overall health score, the health factor h i The contribution of indicator i in the comprehensive score is adjusted, and function g i (E j ) represents the health indicator iii in the current treatment effect evaluation E j These elements comprehensively reflect the status of various health indicators of the patient throughout the treatment process and their contribution to the patient's overall health.

[0240] Formula S is designed to comprehensively consider the performance of multiple health indicators in multiple treatment effect assessments to quantify and evaluate the patient's overall health status. This comprehensive score helps medical professionals understand the patient's health status more comprehensively, optimize treatment plans, and provide personalized medical advice and management.

[0241] In some embodiments, the health score module 206 is further specifically configured to:

[0242] Obtaining a second progress degree of each of the health indicator's evaluation values ​​from reaching a corresponding target value;

[0243] Obtaining a second degree of deviation of the evaluation value of each of the health indicators relative to an ideal state;

[0244] The state function is constructed according to the second progress degree and the second deviation degree.

[0245] In some embodiments, the state function is expressed as:

[0246]

[0247] Among them, B i and A i is the baseline value and target value of the ith health indicator, α i It is a parameter related to the i-th health indicator and is used to adjust the function shape.

[0248] In the specific implementation, B i and A i is the baseline value and target value of the ith health indicator, α i It is a parameter related to the i-th health indicator and is used to adjust the function shape.

[0249] E j is the result of the jth treatment effect evaluation, that is, the value of formula EEE

[0250] B i is the baseline value of the ith health indicator at the jth evaluation

[0251] A i is the target value of the ith health indicator in the jth evaluation

[0252] A i -B i is the range in which the ith indicator can be improved during treatment

[0253] It is the indicator E j Achieve Target A i When E j =B i When it is 0, it reaches A i When 1

[0254] is an exponential decay function, where α i is the parameter that controls the decay rate. This part expresses the index E j Relative to target A i The closer the deviation is to the target, the closer the function value is to 1, and vice versa.

[0255] g i (E j ) Comprehensively considers health indicators E j In the current treatment effect evaluation j The actual degree of progress and deviation under the

[0256] Indicator E j Achieve Target A i degree of progress, It quantifies the degree of deviation and takes into account the speed and stability of the indicator as it approaches the target.

[0257] Can effectively express the indicator E j Relative to target A i It can reflect the actual progress of treatment and has good mathematical continuity and smoothness, making it suitable for quantifying the improvement of health indicators during the treatment process.

[0258] Such a formula g i (E j ) provides a quantitative assessment of the actual improvement of various health indicators during the treatment process when comprehensively evaluating the patient's overall health status, providing important data support and analytical basis for medical decision-making.

[0259] See also Figure 3 , provides a flowchart of an Internet-based intelligent medical data collection and analysis method of the present invention, comprising the following steps:

[0260] Step 301: Obtain medical data of a first Internet user in real time.

[0261] Step 302: pre-process the medical data of the first user to obtain pre-processed data.

[0262] Step 303: extracting features from the preprocessed data to obtain corresponding key features;

[0263] Step 304: construct a risk prediction model for analyzing medical data based on the key features;

[0264] Step 305: Analyze the medical data of the second user to be treated by the risk prediction model, generate a corresponding treatment plan, and predict the treatment effect on the second user in combination with the treatment data of each stage;

[0265] Step 306: predict the health score of the second user according to the treatment effect of the second user through the risk prediction model.

[0266] See also Figure 4 , Figure 4Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 4 As shown, an embodiment of the present invention provides an electronic device 400, including a memory 410, a processor 420, and a computer program 411 stored in the memory 410 and executable on the processor 420. When the processor 420 executes the computer program 411, the following steps are implemented:

[0267] Real-time access to the medical data of the first Internet user;

[0268] Preprocessing the medical data of the first user to obtain preprocessed data;

[0269] Performing feature extraction on the preprocessed data to obtain corresponding key features;

[0270] Based on the key features, construct a risk prediction model for analyzing medical data;

[0271] Analyze the medical data of the second user to be treated by using the risk prediction model, generate a corresponding treatment plan, and predict the treatment effect on the second user in combination with the treatment data of each stage;

[0272] The health score of the second user is predicted according to the treatment effect of the second user through the risk prediction model.

[0273] See also Figure 5 , Figure 5 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 5 As shown, this embodiment provides a computer-readable storage medium 500, on which a computer program 411 is stored. When the computer program 411 is executed by a processor, the following steps are implemented:

[0274] Real-time access to the medical data of the first Internet user;

[0275] Preprocessing the medical data of the first user to obtain preprocessed data;

[0276] Performing feature extraction on the preprocessed data to obtain corresponding key features;

[0277] Based on the key features, construct a risk prediction model for analyzing medical data;

[0278] Analyze the medical data of the second user to be treated by using the risk prediction model, generate a corresponding treatment plan, and predict the treatment effect on the second user in combination with the treatment data of each stage;

[0279] The health score of the second user is predicted according to the treatment effect of the second user through the risk prediction model.

[0280] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0281] Those skilled in the art will appreciate that embodiments of the present invention may be provided as systems, methods, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0282] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A system that specifies the functions of a box or multiple boxes.

[0283] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction system, which is implemented in the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0284] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0285] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0286] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An intelligent medical data collection and analysis system based on the Internet, characterized in that: The system comprises: A data acquisition module, used for acquiring medical data of a first Internet user in real time; A data processing module, used for preprocessing the medical data of the first user to obtain preprocessed data; A feature extraction module, used to extract features from the preprocessed data to obtain corresponding key features; A model building module, used to build a risk prediction model for analyzing medical data based on the key features; The treatment prediction module is used to analyze the medical data of the second user to be treated through the risk prediction model, generate a corresponding treatment plan, and predict the treatment effect on the second user in combination with the treatment data of each stage; the treatment prediction module is also specifically used to: obtain the current value of each health indicator of the treatment data in each treatment effect evaluation; obtain the baseline value of each health indicator of the treatment data in each treatment effect evaluation; obtain the target value of each health indicator of the treatment data in each treatment effect evaluation; construct an improvement degree function according to the current value, the baseline value and the target value; determine the comprehensive evaluation value of the treatment effect of the second user according to the improvement degree function corresponding to multiple treatment effect evaluations; the comprehensive evaluation value of the treatment effect is expressed as: ; Where E is the comprehensive evaluation value of the treatment effect, m is the number of treatment effect evaluations, j is the index of the evaluation times, i is the index of the evaluation times, and n is the number of health indicators considered in each evaluation. is the weight of the i-th health indicator in the j-th evaluation, is the current value of the ith health indicator in the jth evaluation, is the baseline value of the ith health indicator in the jth assessment, is the target value of the i-th health indicator in the j-th evaluation, t is the time parameter, is a function used to measure the improvement degree of the i-th health indicator in the j-th evaluation; the treatment prediction module is also specifically used to: obtain the first progress degree of the current value of each health indicator from reaching the corresponding target value; obtain the first deviation degree of the current value of each health indicator relative to the ideal state; construct the improvement degree function according to the first progress degree and the first deviation degree; the improvement degree function is expressed as: ;in, is the current value of the ith health indicator in the jth evaluation, is the baseline value of the ith health indicator in the jth assessment, is the target value of the ith health indicator in the jth evaluation, is the range in which the ith indicator can be improved during treatment, is the time decay factor, t is the time parameter, is the parameter that controls the slope of the function, is a parameter that controls the ideal state of the center position of the function; A health scoring module is used to predict the health score of the second user according to the treatment effect of the second user through the risk prediction model.

2. The intelligent medical data collection and analysis system based on the Internet according to claim 1 is characterized in that: The health scoring module is also specifically used for: Obtaining the weight of each of the health indicators; Obtaining a health factor for each of the health indicators; Obtain the evaluation value of each treatment effect evaluation; Constructing a state function according to the weight of each health indicator, the health factor, and the evaluation value; According to the state functions corresponding to the multiple treatment effect evaluations, the health score of the second user is determined; the health score is expressed as: ;in, is the state function, m is the number of treatment effect evaluations, n is the number of health indicators considered in each evaluation, is the weight of the ith health indicator, is the health factor related to the ith health indicator; The health scoring module is also specifically used to: obtain the second progress degree of each health indicator's evaluation value from reaching the corresponding target value; obtain the second deviation degree of each health indicator's evaluation value from the ideal state; construct the state function according to the second progress degree and the second deviation degree; the state function is expressed as: ; in, and is the baseline value and target value of the ith health indicator, It is a parameter related to the i-th health indicator and is used to adjust the function shape.

3. An intelligent medical data collection and analysis method based on the Internet, characterized in that: The method comprises: Real-time access to the medical data of the first Internet user; Preprocessing the medical data of the first user to obtain preprocessed data; Performing feature extraction on the preprocessed data to obtain corresponding key features; Based on the key features, construct a risk prediction model for analyzing medical data; The medical data of the second user to be treated is analyzed by the risk prediction model to generate a corresponding treatment plan, and the treatment effect on the second user is predicted in combination with the treatment data of each stage, including: obtaining the current value of each health indicator of the treatment data in each treatment effect evaluation; obtaining the baseline value of each health indicator of the treatment data in each treatment effect evaluation; obtaining the target value of each health indicator of the treatment data in each treatment effect evaluation; constructing an improvement degree function according to the current value, the baseline value and the target value; determining a comprehensive evaluation value of the treatment effect of the second user according to the improvement degree functions corresponding to multiple treatment effect evaluations; the comprehensive evaluation value of the treatment effect is expressed as: ; Where E is the comprehensive evaluation value of the treatment effect, m is the number of treatment effect evaluations, j is the index of the evaluation times, i is the index of the evaluation times, and n is the number of health indicators considered in each evaluation. is the weight of the i-th health indicator in the j-th evaluation, is the current value of the ith health indicator in the jth evaluation, is the baseline value of the ith health indicator in the jth assessment, is the target value of the i-th health indicator in the j-th evaluation, t is the time parameter, is a function used to measure the improvement degree of the i-th health indicator in the j-th evaluation; obtain the first progress degree of the current value of each health indicator from reaching the corresponding target value; obtain the first deviation degree of the current value of each health indicator relative to the ideal state; construct the improvement degree function according to the first progress degree and the first deviation degree; the improvement degree function is expressed as: ;in, is the current value of the ith health indicator in the jth evaluation, is the baseline value of the ith health indicator in the jth assessment, is the target value of the ith health indicator in the jth evaluation, is the range in which the ith indicator can be improved during treatment, is the time decay factor, t is the time parameter, is the parameter that controls the slope of the function, is a parameter that controls the ideal state of the center position of the function; The health score of the second user is predicted according to the treatment effect of the second user through the risk prediction model.

Images