Multi-source data generation system for diabetes management decision support

Abstract

The invention relates to the technical field of diabetes, in particular to a multi-source data generation system for diabetes management decision support, comprising a multi-source data acquisition module, a preprocessing module, a decision analysis module, a classification module and a display module, the preprocessing module is connected with the multi-source data acquisition module, the decision analysis module is connected with the preprocessing module, and the classification module is connected with the display module. The classification module is connected with the decision analysis module, the display module is connected with the decision analysis module, a patient can input diabetes types into the decision analysis module through the classification module, and the decision analysis module can adjust a decision rule base in the decision analysis module according to the diabetes types input by the patient. Therefore, the system can help the patient to give accurate treatment suggestions according to different types of diabetes mellitus of the patient.

Description

Technical Field

[0001] This invention relates to the field of diabetes technology, and in particular to a multi-source data generation system for diabetes management decision support. Background Technology

[0002] Traditional blood glucose testing methods cannot provide continuous blood glucose data, making it difficult to fully reflect a patient's blood glucose fluctuations.

[0003] Existing multi-source data generation systems for diabetes management decision support can collect patient health data from multiple data sources, providing basic data support for subsequent data processing and analysis. Through the system's decision analysis module, it can receive patient health data and generate personalized basic treatment suggestions by matching them with rules in the decision rule base. These suggestions may include dietary adjustments, exercise plans, medication regimens, etc., thereby helping patients effectively manage their diabetes.

[0004] However, the existing system cannot generate treatment recommendations that are more in line with the actual situation of patients based on their different types of diabetes, and therefore cannot accurately help patients manage and control their diabetes according to their own different types of diabetes. Summary of the Invention

[0005] The purpose of this invention is to provide a multi-source data generation system for diabetes management decision support, which solves the problem that existing systems cannot generate treatment suggestions that are more in line with the actual situation of patients based on different types of diabetes, and thus cannot accurately help patients manage and control their diabetes according to their own different types of diabetes.

[0006] To achieve the above objectives, the present invention provides a multi-source data generation system for decision support in diabetes management, comprising a multi-source data acquisition module, a preprocessing module, a decision analysis module, a classification module, and a display module. The preprocessing module is connected to the multi-source data acquisition module, the decision analysis module is connected to the preprocessing module, the classification module is connected to the decision analysis module, and the display module is connected to the decision analysis module. The multi-source data acquisition module is used to collect patient health data from multiple data sources; The preprocessing module is used to clean, transform, and fuse the collected raw data. The decision analysis module is used to build a decision rule base based on clinical guidelines and generate basic treatment recommendations that match the patient type. The classification module is used to help patients input their diabetes type; The display module is used to provide patients with a visual interface to help them view treatment suggestions.

[0007] The multi-source data acquisition module includes a device acquisition unit and a patient entry unit. The device acquisition unit is connected to the preprocessing module; the patient entry unit is connected to the preprocessing module. The device acquisition unit is used to acquire and transmit data collected by the wearable acquisition device in real time; The patient entry unit is used for inputting patient self-reported data.

[0008] The multi-source data generation system for diabetes management decision support further includes a storage module, which is connected to the preprocessing module. The storage module is used to store the data processed by the preprocessing module.

[0009] The multi-source data generation system for diabetes management decision support further includes a prompting module, which is connected to both the preprocessing module and the decision analysis module. The notification module is used to provide notifications for abnormal data and medication time.

[0010] The multi-source data generation system for diabetes management decision support also includes a security module, which is connected to the classification module. The security module is used to control the permission to modify diabetes types in the classification module.

[0011] The multi-source data generation system for diabetes management decision support further includes an update module, which is connected to the decision analysis module. The update module is used to connect to an external update database and periodically update the rule base of the decision analysis module.

[0012] The present invention discloses a multi-source data generation system for diabetes management decision support. Through the classification module, patients can input their diabetes type into the decision analysis module. The decision analysis module can adjust the decision rule base in the decision analysis module according to the diabetes type input by the patient to generate treatment suggestions that are more in line with the patient's actual situation. In this way, the system can help patients receive accurate treatment suggestions based on their different types of diabetes. Attached Figure Description

[0013] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below.

[0014] Figure 1 This is a schematic diagram of the structure of a multi-source data generation system for diabetes management decision support according to the first embodiment of the present invention.

[0015] Figure 2 This is a schematic diagram of the structure of the multi-source data generation system of the multi-source data acquisition module in the first embodiment of the present invention.

[0016] Figure 3 This is a schematic diagram of the structure of the multi-source data generation system of the prompt module in the first embodiment of the present invention.

[0017] Figure 4 This is a schematic diagram of the structure of a multi-source data generation system for diabetes management decision support according to the second embodiment of the present invention.

[0018] Figure 5 This is a schematic diagram of the structure of a multi-source data generation system for diabetes management decision support according to the third embodiment of the present invention.

[0019] In the diagram: 101-Multi-source data acquisition module, 102-Preprocessing module, 103-Decision analysis module, 104-Classification module, 105-Display module, 106-Prompt module, 107-Storage module, 108-Equipment acquisition unit, 109-Patient entry unit, 110-Abnormal alarm unit, 111-Medication prompt unit, 201-Security module, 301-Update module. Detailed Implementation

[0020] The embodiments of the present invention are described in detail below. Examples of the embodiments are shown in the accompanying drawings. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, but should not be construed as limiting the present invention.

[0021] The first embodiment of this application is as follows: Please see Figures 1-3 ,in Figure 1 This is a schematic diagram of the structure of a multi-source data generation system for diabetes management decision support according to the first embodiment of the present invention. Figure 2 This is a schematic diagram of the structure of the multi-source data generation system of the multi-source data acquisition module in the first embodiment of the present invention. Figure 3 This is a schematic diagram of the structure of the multi-source data generation system of the prompt module in the first embodiment of the present invention.

[0022] This invention provides a multi-source data generation system for diabetes management decision support, comprising a multi-source data acquisition module 101, a preprocessing module 102, a decision analysis module 103, a classification module 104, a display module 105, a prompting module 106, and a storage module 107. The multi-source data acquisition module 101 includes a device acquisition unit 108 and a patient entry unit 109. The prompting module 106 includes an anomaly alarm unit 110 and a medication prompting unit 111. This solution addresses the shortcomings of existing systems, which fail to generate treatment recommendations tailored to different patients' diabetes types, thus hindering accurate treatment and control for patients with varying degrees of diabetes.

[0023] In this embodiment, there are a multi-source data acquisition module 101, a preprocessing module 102, a decision analysis module 103, a classification module 104, and a display module 105. The preprocessing module 102 is connected to the multi-source data acquisition module 101, the decision analysis module 103 is connected to the preprocessing module 102, the classification module 104 is connected to the decision analysis module 103, and the display module 105 is connected to the decision analysis module 103. The multi-source data acquisition module 101 is used to collect patient health data from multiple data sources; The preprocessing module 102 is used to clean, transform, and fuse the collected raw data. The decision analysis module 103 is used to construct a decision rule base based on clinical guidelines and generate basic treatment recommendations that match the patient type. The classification module 104 is used to help patients input their diabetes type; The display module 105 is used to provide a visual interface to patients to help them view treatment suggestions.

[0024] The multi-source data acquisition module 101 can collect patient health data from multiple data sources, providing basic data support for subsequent data processing and analysis. The preprocessing module 102 can receive raw data from the multi-source data acquisition module 101, first performing data cleaning to remove noise, duplicate data, and invalid data. Then, the data is transformed, such as unifying units and standardizing formats, to facilitate subsequent processing. Finally, the data from different data sources are merged to form a complete and consistent patient health dataset. The decision analysis module 103 integrates a decision rule base based on clinical guidelines, covering all aspects of diabetes management, such as glycemic control targets, drug selection, and dosage adjustment. The decision analysis module 103 receives patient health data from the preprocessing module 102 and generates personalized basic treatment suggestions by matching them with rules in the decision rule base. These suggestions may include dietary adjustments, exercise plans, and medication regimens, thereby helping patients effectively manage diabetes. The classification module 104 provides a user interface, allowing patients to select or input their diabetes type, such as type 1 diabetes, type 2 diabetes, or gestational diabetes, into the decision analysis module 103. The decision analysis module 103 adjusts its decision rule base based on the patient's diabetes type to generate treatment suggestions that better suit the patient's specific situation. The display module 105 receives treatment suggestion data from the decision analysis module 103 and displays it on the patient's terminal using graphs, tables, and other formats. Patients can easily view detailed treatment suggestions, including dietary plans, exercise guidance, and medication reminders. This visual presentation helps patients better understand the treatment suggestions, improves treatment adherence, and thus effectively manages diabetes. Thus, the classification module 104 allows patients to input their diabetes type into the decision analysis module 103. The decision analysis module 103 can adjust the decision rule base in the decision analysis module 103 according to the diabetes type input by the patient to generate treatment suggestions that are more in line with the patient's actual situation, thereby accurately helping patients to treat and control their diabetes according to their different types.

[0025] The device acquisition unit 108 is connected to the preprocessing module 102; the patient entry unit 109 is connected to the preprocessing module 102. The device acquisition unit 108 is used to acquire and transmit data collected by the wearable acquisition device in real time. The patient entry unit 109 is used for inputting patient self-reported data.

[0026] The device acquisition unit 108 is responsible for collecting patient physiological data monitored by the wearable device in real time, such as blood glucose level, heart rate, and steps, and transmitting this data to the preprocessing module 102. The patient entry unit 109 allows patients to manually input self-reported data, such as dietary status, exercise experience, and medication usage, and these data are also transmitted to the preprocessing module 102 for processing.

[0027] Secondly, the storage module 107 is connected to the preprocessing module 102. The storage module 107 is used to store the data processed by the preprocessing module 102.

[0028] The storage module 107 uses a database management system to organize and manage this data. When the preprocessing module 102 has new data that needs to be stored, it sends this data to the storage module 107. After receiving the data, the storage module 107 writes the data into the database according to a preset storage strategy. The storage module 107 can also provide data query and retrieval functions.

[0029] Meanwhile, the prompting module 106 is connected to both the preprocessing module 102 and the decision analysis module 103. The prompting module 106 is used to provide prompts for abnormal data information and medication time.

[0030] The prompting module 106 can provide prompts regarding abnormal data information collected by the preprocessing module 102 and medication timing in treatment recommendations generated by the decision analysis module 103, thereby enhancing the system's usability and patient treatment compliance. Finally, the abnormal alarm unit 110 is connected to the preprocessing module 102, and the medication reminder unit 111 is connected to the decision analysis module 103. The abnormal alarm unit 110 is used to alarm for the abnormal data identified in the preprocessing module 102; The medication prompting unit 111 is used to prompt the medication time in the treatment suggestions generated by the decision analysis module 103.

[0031] The abnormality alarm unit 110 is connected to the preprocessing module 102 and continuously monitors the patient's health data processed by the preprocessing module 102. Once abnormal data is detected, such as excessively high or low blood sugar levels, or abnormal heart rate, the abnormality alarm unit 110 immediately triggers an alarm mechanism, sending an alert to the patient or medical staff via a pop-up window and sound prompts, so that timely countermeasures can be taken. The medication reminder unit 111 can receive medication time information from the treatment recommendations generated by the decision analysis module 103. Based on this information, the medication reminder unit 111 sends medication reminders to the patient at preset times, ensuring timely medication use through pop-up windows and sound prompts, thereby improving treatment adherence.

[0032] When using the multi-source data generation system for diabetes management decision support according to this embodiment, the classification module 104 enables patients to input their diabetes type into the decision analysis module 103. The decision analysis module 103 can adjust the decision rule base in the decision analysis module 103 according to the diabetes type input by the patient to generate treatment suggestions that are more in line with the patient's actual situation, thereby enabling the system to help patients receive accurate treatment suggestions based on their different types of diabetes.

[0033] The second embodiment of this application is as follows: Please see Figure 4 ,in Figure 4 This is a schematic diagram of the structure of a multi-source data generation system for diabetes management decision support according to a second embodiment of the present invention. Based on the first embodiment, the multi-source data generation system for diabetes management decision support in this embodiment further includes a security module 201.

[0034] The security module 201 is connected to the classification module 104. The security module 201 controls the permission to modify diabetes types within the classification module 104. When a patient or healthcare professional attempts to modify the diabetes type in the classification module 104, the security module 201 first verifies the user's identity and permissions. This includes requiring the user to enter login credentials (such as username and password) to ensure that only users with the appropriate permissions can perform the modification operation, preventing unauthorized personnel from modifying the diabetes type without the patient's knowledge, which could lead to incorrect treatment recommendations from the system.

[0035] The third embodiment of this application is as follows: Please see Figure 5 , Figure 5 This is a schematic diagram of the structure of a multi-source data generation system for diabetes management decision support according to the third embodiment of the present invention. Based on the second embodiment, the multi-source data generation system for diabetes management decision support in this embodiment further includes an update module 301.

[0036] The update module 301 is connected to the decision analysis module 103. The update module 301 is used to connect to an external update database and periodically update the rule base of the decision analysis module 103.

[0037] The update module 301 can update the database via a data cable or wireless connection, and periodically update the decision rule base in the decision analysis module 103, ensuring that the system as a whole can continuously absorb the latest medical research results and clinical guidelines, thereby providing more accurate and scientific decision support for diabetes management. The update module 301 can ensure the timeliness and accuracy of system data.

[0038] The above-disclosed embodiments are merely one or more preferred embodiments of this application and should not be construed as limiting the scope of this application. Those skilled in the art can understand that all or part of the processes for implementing the above embodiments and equivalent changes made in accordance with the claims of this application still fall within the scope of this application.

Claims

1. A multi-source data generation system for diabetes management decision support, characterized in that, The system includes a multi-source data acquisition module, a preprocessing module, a decision analysis module, a classification module, and a display module. The preprocessing module is connected to the multi-source data acquisition module, the decision analysis module is connected to the preprocessing module, the classification module is connected to the decision analysis module, and the display module is connected to the decision analysis module. The multi-source data acquisition module is used to collect patient health data from multiple data sources; The preprocessing module is used to clean, transform, and fuse the collected raw data. The decision analysis module is used to build a decision rule base based on clinical guidelines and generate basic treatment recommendations that match the patient type. The classification module is used to help patients input their diabetes type; The display module is used to provide patients with a visual interface to help them view treatment suggestions.

2. The multi-source data generation system for diabetes management decision support as described in claim 1, characterized in that, The multi-source data acquisition module includes a device acquisition unit and a patient entry unit. The device acquisition unit is connected to the preprocessing module, and the patient entry unit is also connected to the preprocessing module. The device acquisition unit is used to acquire and transmit data collected by the wearable acquisition device in real time; The patient entry unit is used for inputting patient self-reported data.

3. The multi-source data generation system for diabetes management decision support as described in claim 1, characterized in that, The multi-source data generation system for diabetes management decision support also includes a storage module, which is connected to the preprocessing module. The storage module is used to store the data processed by the preprocessing module.

4. The multi-source data generation system for diabetes management decision support as described in claim 1, characterized in that, The multi-source data generation system for diabetes management decision support also includes a prompting module, which is connected to both the preprocessing module and the decision analysis module. The notification module is used to provide notifications for abnormal data and medication time.

5. The multi-source data generation system for diabetes management decision support as described in claim 4, characterized in that, The notification module includes an anomaly alarm unit and a medication notification unit. The anomaly alarm unit is connected to the preprocessing module, and the medication notification unit is connected to the decision analysis module. The abnormal alarm unit is used to issue an alarm for the abnormal data identified in the preprocessing module; The medication reminder unit is used to provide reminders about the medication time in the treatment recommendations generated by the decision analysis module.

6. The multi-source data generation system for diabetes management decision support as described in claim 1, characterized in that, The multi-source data generation system for diabetes management decision support also includes a security module, which is connected to the classification module. The security module is used to control the permission to modify diabetes types in the classification module.

7. The multi-source data generation system for diabetes management decision support as described in claim 1, characterized in that, The multi-source data generation system for diabetes management decision support also includes an update module, which is connected to the decision analysis module. The update module is used to connect to an external update database and periodically update the rule base of the decision analysis module.

Images