Big data medical information display system and display method thereof

Abstract

The embodiment of the invention discloses a big data medical information display system and a display method thereof. The system comprises a data acquisition module for acquiring medical data; the big data platform module is used for performing analysis by adopting a mode of combining machine learning and an expert system; and the visual display module is used for carrying out labeling and visual display on the analysis result. According to the embodiment of the invention, the method has the following advantages: 1, the medical data is deeply mined and analyzed in a mode of combining machine learning and an expert system, and more data support can be provided for medical research; 2, the result is labeled and visually displayed, so that the result is more visual; 3, data quality inspection is introduced, so that the acquired medical data can meet the quality standard, and a solid foundation is provided for subsequent analysis, display and application; and 4, network security detection is introduced, so that leakage of privacy and the like of the patient can be effectively prevented, and an anti-intrusion guarantee can be provided for normal operation of the medical information display system.

Description

Technical Field

[0001] The present invention relates to the technical field of data statistical analysis, and in particular to a big data medical information display system and a display method thereof. Background Art

[0002] Medical information display plays an important role in the medical industry. It can be achieved through a variety of methods and devices. Some common application scenarios and display methods are:

[0003] 1. Hospital lobby: Use large-size, high-definition splicing screens or commercial TVs to play the hospital's promotional videos, introduce featured departments, doctor teams, medical equipment, etc., and provide patients with medical guidance and choices; it can also display in real time the opening / suspension status of each window, the number of registrations in each outpatient department on the day, registration precautions and procedures, etc., to facilitate patients to understand and speed up the registration and treatment process.

[0004] 2. Registration window: The service status of each window is presented in real time through the display screen to prevent patients from queuing in the wrong line, and registration-related information is displayed in a carousel.

[0005] 3. Medical information desk / nurse station: commercial TV is used as the call screen, which is connected to the hospital system to achieve point-to-multiple content playback, and supports the switching of patient waiting list and call information on the same screen and split screen display. In addition to the triage queue information, important reminder content can also be scrolled to reduce the workload of nurses in consulting business.

[0006] 4. Doctor's office area: Use splicing screens or smart tablets to display medical images, real-time data, etc., which is convenient for doctors to compare and observe. It supports multi-screen display and can display the conditions of multiple patients at the same time, providing strong support for doctors to make accurate diagnosis and treatment decisions.

[0007] 5. Operating room: Equipped with multiple high-definition, high-brightness monitoring screens, such as LG splicing screens, which can clearly display the surgical process and the operation path of surgical instruments, provide doctors with a full range of observation images, reduce surgical risks and improve safety and accuracy.

[0008] 6. Blood collection station: After connecting to the hospital's testing and self-service reporting system, the display screen can be used to present the registration queue information of blood collection patients in real time, and scroll to display blood collection precautions, etc., to relieve patients' waiting anxiety and remind them to prepare for blood collection.

[0009] 7. Corridor: The corridor display screen can display various information in real time, such as doctor scheduling, surgery arrangement, examination report collection, drug inventory, etc., providing convenient information services for patients and also bringing convenience to the work of medical staff; it can also be used as a platform for health education, broadcasting health knowledge, disease prevention, rational use of drugs and other related content to improve the public's health awareness and self-care ability.

[0010] 8. Conference Room: Using smart conference tablets can bring clearer display effects and intelligent touch experience. It supports one-click wireless screen projection function for mobile devices such as mobile phones, notebooks, and tablets, which is convenient for multi-screen content switching and personal presentations. It is helpful for holding remote medical conferences, sharing medical data and patient information, and further realizing remote and efficient discussions and cross-regional and cross-departmental joint diagnosis.

[0011] 9. Medical Exhibition Hall: Through splicing screens, interactive slide screens and other equipment, the latest medical equipment, surgical techniques, hospital development history, introductions to various departments and other information are displayed in a vivid and intuitive way to enhance the public's awareness and understanding of medical technology.

[0012] 10. Rehabilitation Center: The smart exhibition hall uses splicing screens to achieve "micro-seam" splicing to ensure the integrity of the picture and output hospital education information, policy information, etc.; the conference room uses smart conference tablets to improve meeting efficiency; the teaching and training rooms are equipped with digital signage to support screen projection and improve teaching quality.

[0013] When designing a medical information display system, it is necessary to follow the principles of readability, interactivity, stability, and security. Readability requires that the content of the display screen is clear, and the font size and color must take into account the reading needs of different age groups; interactivity is reflected in the fact that modern display screens have functions such as touch screen operation to improve user experience; stability is because the display screen needs to work 24 hours a day, and it must be stable and durable, with fault self-detection and rapid recovery capabilities; security is to ensure that sensitive data in the hospital information system is not leaked or maliciously attacked.

[0014] There are currently some flaws in the display of medical information:

[0015] 1. Low information utilization: Although hospitals have a large amount of information on patients' medical history, treatment plans, etc., in-depth analysis and full utilization of this information are insufficient, and their potential value has not been fully tapped to adjust the direction of medical services or support scientific research.

[0016] 2. Privacy and security issues: During the information display process, there may be risks of patient privacy leakage and insufficient security protection of information systems. Summary of the invention

[0017] In view of the defects of the prior art mentioned in the background technology, the purpose of the embodiments of the present invention is to provide a big data medical information display system and method thereof.

[0018] To achieve the above objectives, in a first aspect, an embodiment of the present invention provides a big data medical information display system, comprising:

[0019] A data collection module is used to collect various medical data from multiple hospitals of different regions and types; the medical data includes patient data and medical equipment data;

[0020] A big data platform module, for analyzing the patient data and medical equipment data by combining machine learning and expert system to obtain a first analysis result and a second analysis result; the first analysis result includes the distribution of diseases in the study area, and the second analysis result includes the operation status and fault prediction status of the medical equipment;

[0021] A visualization display module is used to mark and visualize the first analysis result and the second analysis result.

[0022] Furthermore, as a preferred implementation of the present application, the system further includes a data quality inspection module, which is used to:

[0023] The patient data and medical device data are checked for accuracy, completeness, consistency and timeliness.

[0024] As a specific implementation of the present application, the patient data includes recent examination data, basic patient data, recent diagnosis data and historical medical data; the basic patient data includes the patient's gender and age, and the historical medical data includes the patient's past medical history, the age of first onset and the number of onsets; the big data platform module includes:

[0025] A first unit is used to form a first data set and a second data according to the patient data, and to construct and train a neural network model based on the first data set;

[0026] The second unit is used to extract features and classify the second data set using the neural network model to obtain a classification result, and obtain a first analysis result in combination with expert opinions provided by the expert system.

[0027] Furthermore, the medical equipment data includes basic information of the medical equipment, the number of times it has been used, and historical maintenance records; the big data platform module also includes a third unit for:

[0028] For each medical device, calculate the failure prediction value Q = A1 / A2*λ;

[0029] If the fault prediction value Q is greater than the preset value, it means that the medical device may be abnormal, and the hospital staff and the manufacturer of the medical device will be notified according to the basic information of the medical device;

[0030] Among them, A1 is the number of times the medical equipment is used, A2 is the historical maintenance record, and λ is the correction value.

[0031] Furthermore, as a preferred implementation of the present application, the system further includes a network security detection module, which is used to:

[0032] In the process of collecting medical data, obtain network status data;

[0033] Preprocessing the network status data to obtain data to be detected; the preprocessing includes removing irrelevant variables, completing missing data, and removing abnormal values;

[0034] A detection algorithm is used to extract network security determination parameters from the data to be detected; the network security determination parameters include IP address, port number, flow size and communication protocol;

[0035] The network security determination parameter is compared with the information stored in the database, and whether the network is secure is determined based on the comparison result.

[0036] Wherein, the network status data includes network traffic data, log files and intrusion detection system alarm records;

[0037] The detection algorithm includes a chi-square test method, a mutual information method or a feature importance method.

[0038] In a second aspect, an embodiment of the present invention provides a method for displaying medical information of big data, including:

[0039] Data collection step: collecting a variety of medical data from multiple hospitals of different regions and types; the medical data includes patient data and medical equipment data;

[0040] Data analysis step: analyzing the patient data and medical device data by combining machine learning and expert system to obtain a first analysis result and a second analysis result; the first analysis result includes the distribution of diseases in the study area, and the second analysis result includes the operation status and fault prediction status of the medical equipment;

[0041] Visualization display step: annotating and visualizing the first analysis result and the second analysis result.

[0042] Furthermore, before performing the data analysis step, the method further includes:

[0043] Data quality inspection step: Check the accuracy, completeness, consistency and timeliness of the patient data and medical device data.

[0044] Furthermore, as a preferred implementation of the present application, the method further includes:

[0045] Network security detection steps: In the process of collecting medical data, obtain network status data;

[0046] Preprocessing the network status data to obtain data to be detected; the preprocessing includes removing irrelevant variables, completing missing data, and removing abnormal values;

[0047] A detection algorithm is used to extract network security determination parameters from the data to be detected; the network security determination parameters include IP address, port number, flow size and communication protocol;

[0048] The network security determination parameter is compared with the information stored in the database, and whether the network is secure is determined based on the comparison result.

[0049] The big data medical information display system and method provided by the embodiments of the present invention have the following advantages:

[0050] 1. Collect a variety of medical data from multiple hospitals in different regions and types, and use a combination of machine learning and expert systems to conduct in-depth mining and analysis of the medical data. The first and second analysis results obtained can provide more data support for medical research;

[0051] 2. Label and visualize the first and second analysis results to make the results more intuitive and improve user experience;

[0052] 3. Before conducting data analysis, introducing data quality inspection steps can ensure that the collected medical data meets quality standards and provide a solid foundation for subsequent analysis, display and application;

[0053] 4. Introducing network security detection steps into the medical data collection process can not only effectively prevent the leakage of patient privacy, but also provide anti-intrusion protection for the normal operation of the medical information display system. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the specific implementation of the present invention or the technical solution in the prior art, the drawings required for use in the specific implementation or the description of the prior art are briefly introduced below.

[0055] Figure 1 is a structural diagram of a big data medical information display system provided by an embodiment of the present invention;

[0056] Figure 2 It is a flow chart of the method for displaying medical information of big data provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0057] 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 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.

[0058] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0059] Please refer to Figure 1 , is a big data medical information display system provided by an embodiment of the present invention, comprising:

[0060] A data collection module is used to collect various medical data from multiple hospitals of different regions and types; the medical data includes patient data and medical equipment data;

[0061] A big data platform module, for analyzing the patient data and medical equipment data by combining machine learning and expert system to obtain a first analysis result and a second analysis result; the first analysis result includes the distribution of diseases in the study area, and the second analysis result includes the operation status and fault prediction status of the medical equipment;

[0062] A visualization display module is used to mark and visualize the first analysis result and the second analysis result.

[0063] Furthermore, the patient data includes recent examination data, basic patient data, recent diagnosis data and historical medical data; the basic patient data includes the patient's gender and age, etc., and the historical medical data includes the patient's medical history, age of first onset and number of onsets, etc. The medical equipment data includes basic information of medical equipment, number of uses and historical maintenance records.

[0064] It should be noted that, combined with the description in the background section, there are many types of medical data. However, most of them currently focus only on the analysis of patient-related data. The inventors of the present invention have found in actual work that the supervision of medical equipment is also a very important link. The operating status of medical equipment will directly affect the accuracy and timeliness of inspection data. Therefore, the big data platform module in this embodiment is mainly responsible for the analysis of patient data and medical equipment data.

[0065] In specific implementation, the big data platform modules include:

[0066] A first unit is used to form a first data set and a second data according to the patient data, and to construct and train a neural network model based on the first data set; the neural network model can be selected from RNN, CNN, etc.;

[0067] The second unit is used to extract features and classify the second data set using the neural network model to obtain a classification result, and obtain a first analysis result in combination with expert opinions provided by the expert system;

[0068] The third unit is used to calculate the fault prediction value Q = A1 / A2*λ for each medical device; if the fault prediction value Q is greater than a preset value, it indicates that the medical device may be abnormal, and the hospital staff and the manufacturer of the medical device are notified according to the basic information of the medical device, and the hospital staff conducts on-site inspection of the medical device, that is, a manual review is used to determine whether the medical device has actually failed or is about to fail;

[0069] Among them, A1 is the number of times the medical equipment is used, A2 is the historical maintenance record, and λ is the correction value.

[0070] Furthermore, in a medical information system, the accuracy, completeness and reliability of data are directly related to the correctness of medical decisions and the safety of patients. Therefore, the system of the embodiment of the present invention introduces a data quality inspection module for:

[0071] The patient data and medical device data are checked for accuracy, completeness, consistency and timeliness.

[0072] Specifically, the accuracy check mainly includes:

[0073] Check whether the data values ​​are correct, for example, check whether the heart rate, voltage and other parameters in the electrocardiogram data are within a reasonable range.

[0074] Verify the accuracy of diagnostic results and ensure consistency of diagnosis by comparing with other diagnostic methods or expert opinions.

[0075] The integrity check mainly includes:

[0076] Check whether the data is complete and whether there are any missing fields or records. For example, the patient's basic information, examination time, examination items, etc. should be complete.

[0077] Ensure that each record in the dataset contains the necessary information for comprehensive analysis and presentation.

[0078] The consistency check mainly includes:

[0079] Check whether the data from different sources are consistent. For example, the data uploaded by the regional diagnostic center should be consistent with the data in the mobile ECG server.

[0080] Verify the consistency of data at different time points to ensure data stability and reliability.

[0081] Timeliness checks mainly include:

[0082] Check the data collection and update time to ensure that the data is up to date. In the medical field, timeliness is very important for the diagnosis and treatment of diseases.

[0083] Clean up expired data in a timely manner to avoid using outdated information for analysis and display.

[0084] Furthermore, medical information involves sensitive data such as the patient's personal privacy and health status. Once leaked, it may cause great distress and risks to the patient, and may even lead to serious consequences such as medical fraud. At the same time, network security issues may also affect the normal operation of the medical information display system and interfere with the provision of medical services. Based on this, the system of the embodiment of the present invention introduces a network security detection module for:

[0085] In the process of collecting medical data, network status data is obtained; the network status data includes network traffic data, log files, and intrusion detection system alarm records, etc.;

[0086] Preprocessing the network status data to obtain data to be detected; the preprocessing includes removing irrelevant variables, completing missing data, and removing abnormal values;

[0087] A detection algorithm is used to extract network security determination parameters from the data to be detected; the network security determination parameters include IP address, port number, flow size and communication protocol;

[0088] The network security determination parameters are compared with the information stored in the database, and whether the network is secure is determined based on the comparison results; for example, the database stores the network address IP1 of the system and hospital 1, and the network address of hospital 1 extracted this time is IP2, then it is determined that there is a network security risk and relevant processing is required.

[0089] It should be noted that the above-mentioned detection algorithms include but are not limited to the chi-square test method, mutual information method, feature importance method, model-based feature selection method and recursive feature elimination method. In the automatic selection of feature variables through the detection algorithm, one or more combinations are selected from the chi-square test method, mutual information method, feature importance method, model-based feature selection method and recursive feature elimination method.

[0090] The relevant explanations of the above detection algorithm are as follows:

[0091] Chi-Squared Test: The chi-squared value between each feature and the category is calculated to evaluate the discriminative power of the feature. The larger the chi-squared value, the stronger the correlation between the feature and the category, and the more discriminative it is.

[0092] Mutual Information: Mutual information measures the degree of mutual dependence between features and categories. For classification problems, features with larger mutual information values ​​have stronger correlation with categories and are more discriminative.

[0093] Feature Importance: Some machine learning algorithms (such as decision trees, random forests, etc.) can calculate the importance of each feature for the model's prediction. By comparing feature importance scores, you can find the most discriminating features.

[0094] Model-Based Feature Selection: This method uses machine learning models (such as support vector machines, neural networks, etc.) to evaluate the contribution of each feature. By comparing the contribution of features, the most discriminating features can be found.

[0095] Recursive Feature Elimination: This method selects the most discriminative features by gradually removing the least important features. At each step, the contribution of the current feature set to the model prediction is evaluated, and the feature with the lowest contribution is removed.

[0096] From the above description, it can be seen that the big data medical information display system provided by the embodiment of the present invention has the following advantages:

[0097] 1. Collect a variety of medical data from multiple hospitals in different regions and types, and use a combination of machine learning and expert systems to conduct in-depth mining and analysis of the medical data. The first and second analysis results obtained can provide more data support for medical research;

[0098] 2. Label and visualize the first and second analysis results to make the results more intuitive and improve user experience;

[0099] 3. Before conducting data analysis, introducing data quality inspection steps can ensure that the collected medical data meets quality standards and provide a solid foundation for subsequent analysis, display and application;

[0100] 4. Introducing network security detection steps into the medical data collection process can not only effectively prevent the leakage of patient privacy, but also provide anti-intrusion protection for the normal operation of the medical information display system.

[0101] Based on the same inventive concept, the embodiment of the present invention also provides a method for displaying medical information of big data, such as Figure 2 As shown, the method includes:

[0102] S1, data collection step: collect various medical data from multiple hospitals in different regions and types.

[0103] The medical data includes patient data and medical equipment data.

[0104] S2, data quality inspection step: perform accuracy check, completeness check, consistency check and timeliness check on the patient data and medical device data.

[0105] S3, data analysis step: analyzing the patient data and medical device data by combining machine learning and expert system to obtain a first analysis result and a second analysis result.

[0106] The first analysis result includes the distribution of diseases in the study area, and the second analysis result includes the operation status and fault prediction status of medical equipment.

[0107] Among them, the patient data includes recent examination data, basic patient data, recent diagnosis data and historical medical data; the basic patient data includes the patient's gender and age, and the historical medical data includes the patient's medical history, the age of first onset and the number of onsets; the medical equipment data includes basic information of medical equipment, the number of times it has been used and historical maintenance records; the data analysis steps are specifically as follows:

[0108] Forming a first data set and a second data according to the patient data, and constructing and training a neural network model based on the first data set;

[0109] Using the neural network model to extract features and classify the second data set to obtain a classification result, and combining it with expert opinions provided by the expert system to obtain a first analysis result;

[0110] For each medical device, calculate the failure prediction value Q = A1 / A2*λ;

[0111] If the fault prediction value Q is greater than the preset value, it means that the medical device may be abnormal, and the hospital staff and the manufacturer of the medical device will be notified according to the basic information of the medical device;

[0112] Among them, A1 is the number of times the medical equipment is used, A2 is the historical maintenance record, and λ is the correction value.

[0113] S4, visualization step: annotating and visualizing the first analysis result and the second analysis result.

[0114] Furthermore, in order to ensure network security, the method of the embodiment of the present invention also includes:

[0115] Network security detection steps: In the process of collecting medical data, obtain network status data;

[0116] Preprocessing the network status data to obtain data to be detected; the preprocessing includes removing irrelevant variables, completing missing data, and removing abnormal values;

[0117] A detection algorithm is used to extract network security determination parameters from the data to be detected; the network security determination parameters include IP address, port number, flow size and communication protocol;

[0118] The network security determination parameter is compared with the information stored in the database, and whether the network is secure is determined based on the comparison result.

[0119] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A big data medical information display system, characterized in that: include: Data collection module, used to collect various medical data from multiple hospitals of different regions and types; The medical data includes patient data and medical device data; A big data platform module, for analyzing the patient data and medical equipment data by combining machine learning and expert system to obtain a first analysis result and a second analysis result; the first analysis result includes the distribution of diseases in the study area, and the second analysis result includes the operation status and fault prediction status of the medical equipment; A visualization display module is used to mark and visualize the first analysis result and the second analysis result.

2. The big data medical information display system according to claim 1, characterized in that: The system also includes a data quality inspection module, which is used to: The patient data and medical device data are checked for accuracy, completeness, consistency and timeliness.

3. The big data medical information display system according to claim 2, characterized in that: The patient data includes recent examination data, basic patient data, recent diagnosis data and historical medical data; the basic patient data includes the patient's gender and age, and the historical medical data includes the patient's medical history, age of first onset and number of onsets; The big data platform module includes: A first unit is used to form a first data set and a second data according to the patient data, and to construct and train a neural network model based on the first data set; The second unit is used to extract features and classify the second data set using the neural network model to obtain a classification result, and obtain a first analysis result in combination with expert opinions provided by the expert system.

4. The big data medical information display system according to claim 3, characterized in that: The medical equipment data includes basic information of the medical equipment, the number of times it has been used, and historical maintenance records; the big data platform module also includes a third unit for: For each medical device, calculate the failure prediction value Q = A1 / A2*λ; If the fault prediction value Q is greater than the preset value, it means that the medical device may be abnormal, and the hospital staff and the manufacturer of the medical device will be notified according to the basic information of the medical device; Among them, A1 is the number of times the medical equipment is used, A2 is the historical maintenance record, and λ is the correction value.

5. The big data medical information display system according to any one of claims 1 to 4, characterized in that: The system also includes a network security detection module, which is used to: In the process of collecting medical data, obtain network status data; Preprocessing the network status data to obtain data to be detected; the preprocessing includes removing irrelevant variables, completing missing data, and removing abnormal values; Using detection algorithms to extract network security judgment parameters from the data to be detected; The network security determination parameters include IP address, port number, flow size and communication protocol; The network security determination parameter is compared with the information stored in the database, and whether the network is secure is determined based on the comparison result.

6. The big data medical information display system according to claim 5, characterized in that: The network status data includes network traffic data, log files and intrusion detection system alarm records; The detection algorithm includes a chi-square test method, a mutual information method or a feature importance method.

7. A method for displaying medical information of big data, characterized in that: include: Data collection steps: Collect a variety of medical data from multiple hospitals in different regions and of different types; The medical data includes patient data and medical device data; Data analysis step: analyzing the patient data and medical device data by combining machine learning and expert system to obtain a first analysis result and a second analysis result; the first analysis result includes the distribution of diseases in the study area, and the second analysis result includes the operation status and fault prediction status of the medical equipment; Visualization display step: annotating and visualizing the first analysis result and the second analysis result.

8. The method for displaying medical information of big data according to claim 7, characterized in that: Before performing the data analysis step, the method further comprises: Data quality inspection step: Check the accuracy, completeness, consistency and timeliness of the patient data and medical device data.

9. The method for displaying medical information of big data according to claim 7, characterized in that: The patient data includes recent examination data, basic patient data, recent diagnosis data and historical medical data; the basic patient data includes the patient's gender and age, and the historical medical data includes the patient's medical history, the age of first onset and the number of onsets; the medical equipment data includes basic information of medical equipment, the number of times used and historical maintenance records; the data analysis steps are specifically as follows: Forming a first data set and a second data according to the patient data, and constructing and training a neural network model based on the first data set; Using the neural network model to extract features and classify the second data set to obtain a classification result, and combining it with expert opinions provided by the expert system to obtain a first analysis result; For each medical device, calculate the failure prediction value Q = A1 / A2*λ; If the fault prediction value Q is greater than the preset value, it means that the medical device may be abnormal, and the hospital staff and the manufacturer of the medical device will be notified according to the basic information of the medical device; Among them, A1 is the number of times the medical equipment is used, A2 is the historical maintenance record, and λ is the correction value.

10. The method for displaying medical information of big data according to any one of claims 7 to 9, characterized in that: The method further comprises: Network security detection steps: In the process of collecting medical data, obtain network status data; Preprocessing the network status data to obtain data to be detected; the preprocessing includes removing irrelevant variables, completing missing data, and removing abnormal values; A detection algorithm is used to extract network security determination parameters from the data to be detected; the network security determination parameters include IP address, port number, flow size and communication protocol; The network security determination parameter is compared with the information stored in the database, and whether the network is secure is determined based on the comparison result.

Images