Myeloma intelligent follow-up visit system and method

Abstract

The invention provides an intelligent follow-up visit system and method for myeloma, and the system comprises a data collection module which is used for collecting the basic information, clinical data, laboratory examination results and imaging data of a patient; the data storage module is used for storing data by adopting a cloud storage technology so as to ensure the safety and efficient access of the data; the data processing module is used for analyzing and processing the collected data by using an artificial intelligence algorithm; the follow-up visit plan management module formulates a personalized follow-up visit plan according to the illness state and the treatment scheme of the patient; the early warning module is used for providing abnormal condition early warning through real-time analysis of the data; and the doctor end and patient end application module can be convenient for doctors and patients to check follow-up visit results and health states at any time.

Description

Technical Field

[0001] The present invention relates to the field of medical health technology, and in particular to a myeloma intelligent follow-up system and method. Background Art

[0002] Myeloma, also known as plasma cell tumor, is a malignant tumor originating from plasma cells in the bone marrow. It is a relatively common malignant tumor. It can be divided into single and multiple, with the latter being more common. Multiple myeloma, also known as cellular myeloma, is caused by the malignant transformation of plasma cells that synthesize and secrete immunoglobulins. The proliferation of a large number of monoclonal malignant plasma cells easily involves soft tissues. In the late stage, there may be extensive metastasis, but rarely lung metastasis. It is more common in the spine, accounting for 10% of primary spinal tumors, and is more common in the lumbar spine.

[0003] Therefore, myeloma is a malignant blood disease, and patients need long-term follow-up to monitor disease changes and treatment effects. However, traditional follow-up methods have problems such as untimely information transmission and low data processing efficiency. An intelligent follow-up system is urgently needed to improve patient management and treatment effects. Summary of the invention

[0004] The problem solved by the invention is how to improve the information transmission rate and data processing efficiency of the myeloma follow-up system.

[0005] To solve the above problems, the present invention provides a myeloma intelligent follow-up system, comprising: a data acquisition module, which is used to collect basic information, clinical data, laboratory test results and imaging data of patients; a data storage module, which uses cloud storage technology to store data to ensure the security and efficient access of data; a data processing module, which uses an artificial intelligence algorithm to analyze and process the collected data; a follow-up plan management module, which formulates a personalized follow-up plan according to the patient's condition and treatment plan; an early warning module, which provides abnormal situation warnings through real-time analysis of data; and doctor-side and patient-side application modules, which can facilitate doctors and patients to view follow-up results and health status at any time.

[0006] Compared with the existing technology, the effect that this solution can achieve is: through comprehensive data collection, storage, processing and management, this system realizes comprehensive and real-time monitoring and management of myeloma patients, effectively improves the information transmission rate and data processing efficiency of the myeloma follow-up system, and significantly improves the quality of medical services and the quality of life of patients.

[0007] In one embodiment of the present invention, the data acquisition module includes: a home smart medical device, which is used to measure the patient's vital sign data at home; and a hospital examination device, which is used to regularly collect the patient's laboratory test results and imaging data.

[0008] Compared with the existing technology, the effect that this solution can achieve is: through the combination of home and hospital equipment, it ensures the comprehensiveness and timeliness of data collection.

[0009] In one embodiment of the present invention, the data processing module includes: an anomaly detection algorithm, which is used to detect abnormal values ​​in the data; and a trend analysis algorithm, which is used to analyze the changing trend of the data.

[0010] Compared with the existing technology, this solution can achieve the following effects: Through anomaly detection and trend analysis, accurate monitoring and early warning of patients' health status are achieved.

[0011] In one embodiment of the present invention, the early warning module includes: SMS, email and in-application message notification modules, which are used to notify doctors and patients when abnormal conditions are detected.

[0012] Compared with the existing technology, the effect that this solution can achieve is: multiple notification methods ensure that doctors and patients can obtain early warning information in a timely manner, thereby improving response speed.

[0013] In one embodiment of the present invention, a control method for a myeloma intelligent follow-up system is provided, the control method comprising: data collection and uploading, in which a patient uses an intelligent device to measure vital sign data, processes and analyzes the vital sign data, and uploads the analysis results to a cloud storage module through an application; data storage, in which the collected data is stored in a cloud storage module, and is encrypted and backed up; and follow-up plan management, early warning, and notification are performed based on the vital sign data.

[0014] Compared with the existing technology, this solution can achieve the following effects: ensuring the integrity and reliability of data through real-time data collection and secure storage.

[0015] In one embodiment of the present invention, data processing and analysis include: analyzing data using an anomaly detection algorithm to detect whether there are abnormal values; and analyzing data change trends using a trend analysis algorithm.

[0016] Compared with the existing technology, this solution can achieve the following effects: timely detect patients' health abnormalities through data analysis and improve the accuracy of early warning.

[0017] Compared with the existing technology, this solution can achieve the following effects: accurately analyze data change trends through the moving average algorithm and provide stable trend analysis results.

[0018] In one embodiment of the present invention, follow-up plan management includes: automatically generating or adjusting the patient's follow-up plan based on data analysis results; and the doctor viewing and confirming the follow-up plan through the doctor-side application.

[0019] Compared with the existing technology, the effect that this solution can achieve is: through automated follow-up plan management, it ensures the scientificity and personalization of the follow-up plan and improves the quality of follow-up.

[0020] In one embodiment of the present invention, the warning and notification include: generating a warning notification when data abnormality is detected; sending the warning notification to doctors and patients via SMS, email or in-application message.

[0021] Compared with the existing technology, this solution can achieve the following effects: multi-channel early warning notifications to ensure timely handling of abnormal situations and improve patient safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A schematic flow chart of the steps of a control method for a myeloma follow-up system. DETAILED DESCRIPTION

[0023] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, specific embodiments of the present invention are described in detail.

[0024] Embodiment 1 The present embodiment provides a myeloma intelligent follow-up system, including: a data acquisition module, which is used to collect basic information, clinical data, laboratory test results and imaging data of patients; a data storage module, which uses cloud storage technology to store data to ensure data security and efficient access; a data processing module, which uses an artificial intelligence algorithm to analyze and process the collected data; a follow-up plan management module, which formulates a personalized follow-up plan according to the patient's condition and treatment plan; an early warning module, which provides abnormal situation warnings through real-time analysis of data; and doctor-side and patient-side application modules, which can facilitate doctors and patients to view follow-up results and health status at any time.

[0025] Through comprehensive data collection, storage, processing and management, this system realizes comprehensive and real-time monitoring and management of myeloma patients, effectively improves the information transmission rate and data processing efficiency of the myeloma follow-up system, and significantly improves the quality of medical services and the quality of life of patients.

[0026] The data collection module includes: home smart medical devices, which are used to measure patients' vital signs data at home; hospital examination equipment, which is used to regularly collect patients' laboratory test results and imaging data.

[0027] The data processing module includes: an anomaly detection algorithm, which is used to detect outliers in the data; and a trend analysis algorithm, which is used to analyze the changing trend of the data.

[0028] Among them, the early warning module includes: SMS, email and in-app message notification modules, which are used to notify doctors and patients when abnormal conditions are detected.

[0029] Embodiment 2 See also Figure 1 The present embodiment provides a control method for a myeloma intelligent follow-up system, the control method comprising: S10 data collection and uploading, the patient uses a smart device to measure vital sign data, and processes and analyzes the vital sign data, and uploads the analysis results to a cloud storage module through an application; S20 data storage, the collected data is stored in the cloud storage module, and encrypted and backed up; S30 follow-up plan management, early warning and notification are performed according to the vital sign data.

[0030] Data processing and analysis include: using anomaly detection algorithms to analyze data to detect whether there are outliers; using trend analysis algorithms to analyze data change trends.

[0031] The anomaly detection algorithm is based on the following formula: ; Where Z is the Z-score value, which is used to measure the abnormality of the current data point, X is the current blood calcium data value, μ is the average blood calcium value of the historical data, and σ is the standard deviation of the historical data.

[0032] The trend analysis algorithm is based on the following formula: ; Among them, P t is the moving average of blood calcium at time t, n is the length of the time window, X t-i is the blood calcium data value at the ti moment.

[0033] Follow-up plan management includes: automatically generating or adjusting the patient's follow-up plan based on data analysis results; doctors review and confirm the follow-up plan through the doctor-side application.

[0034] Warnings and notifications include: generating warning notifications when data abnormalities are detected; sending warning notifications to doctors and patients via SMS, email or in-app messages.

[0035] Among them, what needs to be explained in detail is the data collection and upload stage.

[0036] Users can collect and upload data through home smart medical devices and hospital examination equipment. Specifically, patients use a variety of smart medical devices at home to perform daily measurements of vital sign data, including blood pressure monitors, blood glucose meters, thermometers, and body fat scales.

[0037] For example, a patient measures his blood pressure using a sphygmomanometer at 8 a.m. every day, and the recorded data is 140 / 90 mmHg.

[0038] The smart medical device connects to the patient's smartphone application via Bluetooth or Wi-Fi, and the measurement data is automatically uploaded to the myeloma follow-up system.

[0039] In addition, patients can also manually enter other health data, such as diet, exercise, sleep quality, etc. to complete their health information.

[0040] Furthermore, patients go to the hospital for comprehensive blood tests and bone marrow biopsies every month, and the collected data include hemoglobin, white blood cells, platelets, blood calcium, blood phosphorus, blood urea nitrogen and other indicators. Doctors use professional equipment to perform examinations, and the results are directly entered into the hospital information management system and simultaneously uploaded to the cloud storage module of the intelligent follow-up system.

[0041] For example, a patient has a blood test in the hospital and the blood calcium level is measured to be 11 mg / dL. The doctor enters the result into the system and uploads it.

[0042] Furthermore, during the data upload and synchronization stage, all collected data is uploaded to the cloud storage module in real time via the Internet to ensure the integrity and timeliness of the data. At the same time, the system uses efficient data compression and transmission algorithms to ensure the speed and accuracy of data upload and prevent data loss and damage.

[0043] For example, blood pressure data uploaded by patients at home and blood calcium data from hospital examinations are stored in the cloud at the same time, ensuring that doctors and patients can access the latest health data at any time.

[0044] Furthermore, in the data storage stage, cloud storage technology can be used for processing. The data storage module uses cloud storage technology and uses a distributed database system to store data in multiple data centers to ensure high availability and security of data. The system uses encryption technology to encrypt stored data to prevent unauthorized access and data leakage.

[0045] For example, all the patient's health data (such as blood pressure, blood calcium, etc.) are immediately encrypted after being uploaded to the cloud, and stored in different data centers to improve data security and reliability.

[0046] Furthermore, during the data backup and recovery phase, the system can automatically perform regular backups of stored data to prevent data loss. In the event of data corruption or loss, the system can quickly restore the data to ensure data integrity and continued availability.

[0047] For example, the system automatically backs up data every night and backs up all patients' health data to an off-site server to prevent data loss due to unexpected situations.

[0048] Furthermore, in the data processing and analysis phase, in the data processing flow, the data processing module extracts the latest health data from the cloud storage module and uses artificial intelligence algorithms to analyze and process the data. The system first pre-processes the data, including data cleaning, missing value filling and data standardization, to ensure the accuracy and consistency of the data.

[0049] For example, the system extracts the patient’s blood pressure and blood calcium data for the past month from cloud storage, cleans out abnormal values ​​and erroneous data, and standardizes them in preparation for further analysis.

[0050] Furthermore, during the anomaly detection algorithm stage, the system will use the anomaly detection algorithm to analyze the data to detect whether there are any outliers.

[0051] The anomaly detection algorithm formula in this embodiment is: , where Z is the Z-score value, which is used to measure the abnormality of the current data point. The critical value of the abnormality is 2. When the value of Z is greater than or equal to 2, the user's blood calcium value is judged to be abnormal. If the value of Z is less than 2, the user's blood calcium value is judged to be normal. X is the user's current blood calcium data value, μ is the average blood calcium value of the historical data, and σ is the standard deviation of the historical data.

[0052] Therefore, in a specific practical application, for example, the patient's blood calcium data for the past month is as follows: [9.5, 9.6, 9.4, 9.8, 10.0, 10.2, 11.0] mg / dL, the calculated mean value (μ) is 9.785 mg / dL, and the standard deviation (σ) is 0.46 mg / dL. The current data value (X) is 11 mg / dL, and the calculated Z-score value is: Z=(11-9.785) / 0.46=2.64. Therefore, since the Z-score value exceeds 2, the system determines that the current blood calcium value is an abnormal value and generates an early warning notification.

[0053] Furthermore, in the trend analysis algorithm, the system uses the trend analysis algorithm to analyze the trend of data changes and provide long-term health trend predictions.

[0054] Among them, the trend analysis algorithm formula is: , where P t is the moving average of blood calcium at time t, n is the length of the time window, X t-iis the blood calcium data value at the ti-th moment. i usually refers to the time step or time interval in the time series data, and i represents the time step from the current moment t to the past. For example, when i=0, it represents the data value at the current moment t; when i=1, it represents the data value at the previous moment t−1, and so on, until i=n−1, which represents the data value at the moment t−n+1. By averaging the data of these n time steps, the moving average value at the current moment t is obtained.

[0055] The above trend analysis algorithm is suitable for smoothing time series data, eliminating short-term fluctuations, and revealing long-term trends. In the myeloma follow-up system, it can be used to analyze the patient's blood indicators, such as the trend of blood calcium over time, to determine the progression or remission of the disease.

[0056] For example, suppose a patient's blood calcium level data for the past 7 days are as follows: [9.5, 9.6, 9.4, 9.8, 10.0, 10.2, 11.0] mg / dL, using a 3-day window to calculate the moving average; MA7=31×(10.0+10.2+11.0)=31×31.2=10.4mg / dL; The above moving average indicates the overall trend of blood calcium levels in the past three days, which helps doctors determine whether the patient's condition is stabilizing or worsening.

[0057] Furthermore, the following algorithm can be used for more sensitive scenarios in the user's recent data changes, which can more quickly reflect data changes. In the myeloma follow-up system of this embodiment, it can be used to monitor the fluctuation of the patient's blood sugar or blood pressure and warn of sudden abnormalities more promptly.

[0058] The algorithm formula is , where Q t is the exponential moving average of the user's blood sugar or blood pressure at time t, α is the smoothing coefficient, usually 2 / n+1, X t is the data value of the user's blood sugar or blood pressure at time t, Q t-1 It is the exponential moving average of blood sugar or blood pressure at the previous moment.

[0059] For example, suppose a patient's blood sugar data for the past five days are as follows: [5.6, 5.8, 6.0, 5.9, 6.1] mmol / L, the initial EMA value is 5.6, and the smoothing coefficient α is 0.33 (the time window is 5). That is, Q2=0.33×5.8+(1-0.33)×5.6=5.7mmol / L, Q3=0.33×6.0+(1-0.33)×5.7=5.8 mmol / L. This calculation method shows the trend of blood sugar levels in the recent period, allowing doctors to respond to abnormal changes more quickly.

[0060] Among them, blood calcium level monitoring can help doctors judge the progression and development trend of myeloma patients by performing moving average analysis on the patient's blood calcium data. If the blood calcium level continues to rise, it may indicate that the condition is getting worse and the treatment plan needs to be adjusted in time. Blood sugar fluctuation monitoring uses the above-mentioned review algorithm to analyze blood sugar data, which helps to quickly detect abnormal blood sugar fluctuations. It is especially suitable for patients with diabetes and myeloma to ensure that blood sugar is maintained within a safe range.

[0061] Therefore, during the data analysis result storage stage, the system stores the processed and analyzed data and results back to the cloud storage module for use by the follow-up plan management and early warning modules. For example, the system stores the Z-score value and moving average of the blood calcium level in the patient's health record, and the doctor can view the detailed analysis results at any time.

[0062] Furthermore, in the follow-up plan management, the myeloma follow-up system in this embodiment adds a personalized follow-up plan, and the system automatically generates or adjusts the personalized follow-up plan according to the data analysis results and the specific conditions of the patient. The follow-up plan includes the time, frequency, content and precautions of the follow-up, etc., to ensure the scientificity and effectiveness of the follow-up.

[0063] For example, based on the patient's blood calcium level analysis results, the system recommends increasing the frequency of blood calcium monitoring to once a week and records it in the follow-up plan.

[0064] Furthermore, during the doctor's confirmation and adjustment, the doctor can view the follow-up plan generated by the system through the doctor-side application, and adjust and confirm it based on clinical experience and the patient's specific situation. The doctor can add or reduce follow-up items and adjust the follow-up frequency to ensure the personalization and accuracy of the follow-up plan.

[0065] For example, after reviewing the patient's blood calcium level trend and abnormal test results, the doctor confirms the follow-up plan recommended by the system, increases the frequency of blood calcium monitoring, and adjusts other follow-up items, such as adding bone density testing.

[0066] Then, in the synchronization of the follow-up plan, the confirmed follow-up plan is synchronized to the cloud storage module and notified to the patient through the patient-side application. The patient can view the latest follow-up plan in the application and arrange regular examinations and monitoring according to the plan.

[0067] For example, patients receive new follow-up plan notifications in the app, prompting them to have their blood calcium tested once a week and go to the hospital for relevant examinations on time.

[0068] Finally, in the early warning and notification stage, including abnormal situation early warning and multi-channel notification, when the system detects data abnormalities, it automatically generates early warning notifications. Early warning notifications include abnormal data, possible risks and recommended treatment measures, helping patients and doctors to respond to health risks in a timely manner.

[0069] For example, the system detects that the patient's blood calcium level is abnormal, with a Z-score value of 2.64, and generates an early warning notification: "Your recent blood calcium level is abnormal, please contact your doctor as soon as possible."

[0070] The system sends early warning notifications through multiple channels (such as SMS, email, and in-app messages) to ensure that relevant personnel can receive information in a timely manner. For example, the system notifies patients and doctors at the same time through SMS and in-app messages to ensure timely delivery of information.

[0071] Furthermore, the myeloma follow-up system in this embodiment uses the following modules on the doctor side and the patient side: The doctor-side application provides comprehensive patient management functions, allowing doctors to view patients' detailed health data, analysis results, follow-up plans, and early warning information at any time. Doctors can use the application to adjust and confirm follow-up plans and send messages to communicate with patients.

[0072] For example, a doctor logs into the app to view the patient's blood calcium level data and analysis results. If any abnormality is found, the doctor will communicate with the patient by phone and recommend that he or she go to the hospital for a follow-up examination immediately.

[0073] The patient-side application provides the function of viewing and managing health data. Patients can view their health data, follow-up plans and early warning information at any time. The application also provides health knowledge, life advice and health self-management tools to help patients conduct comprehensive health management.

[0074] For example, patients log into the app to view their blood calcium level data and follow-up plans, receive early warning information, and perform self-health management according to system prompts.

[0075] Through the above embodiments, the myeloma intelligent follow-up system of the present invention realizes comprehensive and real-time monitoring and management of myeloma patients, ensures that the health data of patients is processed and analyzed in a timely and accurate manner, and improves the quality of medical services and the quality of life of patients. The system realizes the automatic generation and management of personalized follow-up plans through advanced artificial intelligence algorithms and cloud computing technology, and improves the scientificity and effectiveness of follow-up. In addition, the multi-channel early warning and notification mechanism ensures that doctors and patients can respond to health risks in a timely manner, improving the safety and quality of life of patients.

[0076] Although the present invention is disclosed as above, the present invention is not limited thereto. Any person skilled in the art can make various changes and modifications without departing from the spirit and scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the scope defined by the claims.

Claims

1. A myeloma intelligent follow-up system, characterized in that: include: Data collection module, used to collect patients' basic information, clinical data, laboratory test results and imaging data; A data storage module, which uses cloud storage technology to store data to ensure data security and efficient access; A data processing module, which uses an artificial intelligence algorithm to analyze and process the collected data; A follow-up plan management module, which formulates a personalized follow-up plan based on the patient's condition and treatment plan; An early warning module, which provides early warning of abnormal situations through real-time analysis of data; Doctor-side and patient-side application modules enable doctors and patients to view follow-up results and health status at any time.

2. The myeloma intelligent follow-up system according to claim 1, characterized in that: The data acquisition module comprises: A home smart medical device, wherein the home smart medical device is used for measuring vital sign data of a patient at home; Hospital examination equipment is used to regularly collect laboratory test results and imaging data of patients.

3. The myeloma intelligent follow-up system according to claim 1, characterized in that: The data processing module comprises: An anomaly detection algorithm, the anomaly detection algorithm is used to detect outliers in the data; A trend analysis algorithm is used to analyze the change trend of data.

4. The myeloma intelligent follow-up system according to claim 1, characterized in that: The early warning module comprises: SMS, email, and in-app message notification modules to notify doctors and patients when abnormal conditions are detected.

5. A control method for a myeloma intelligent follow-up system, characterized in that: The control method is applicable to the myeloma intelligent follow-up system according to any one of claims 1 to 4, and the control method comprises: Data collection and uploading: patients use smart devices to measure vital sign data, process and analyze the vital sign data, and upload the analysis results to the cloud storage module through the application; Data storage: storing the collected data in the cloud storage module, encrypting and backing up the data; Follow-up plan management, early warning and notification are carried out based on the physical sign data.

6. The control method according to claim 5, characterized in that: The data processing and analysis include: Use anomaly detection algorithms to analyze data and detect whether there are outliers; The trend analysis algorithm is used to analyze the data change trend.

7. The control method according to claim 5, characterized in that: The follow-up plan management includes: Automatically generate or adjust the patient's follow-up plan based on the data analysis results; The doctor views and confirms the follow-up plan through the doctor-side application.

8. The control method according to claim 5, characterized in that: The warnings and notifications include: When data anomalies are detected, an early warning notification is generated; Send alert notifications to doctors and patients via SMS, email or in-app messaging.

Images