Household continuous ambulatory peritoneal dialysis operation behavior monitoring system and method

Abstract

The invention discloses a household continuous ambulatory peritoneal dialysis operation behavior monitoring system, and the system comprises a video data collection and preprocessing module which is used for collecting video data and carrying out the preprocessing of the video data; the key node extracting and marking module is used for extracting and marking key data nodes; the data transmission and storage module is used for transmitting and storing the data; the data processing and application module is used for processing and applying the data; and the monitoring alarm module is used for triggering an alarm when an abnormal operation behavior is found. According to the invention, the daily operation video data of a household CAPD (Continuous Ambulatory Peritoneal Dialysis) patient is efficiently collected in real time, so that the operation behavior of the patient is comprehensively and objectively recorded, and the abnormal operation behavior monitoring and alarm work of the peritoneal dialysis patient is carried out.

Description

Technical Field

[0001] The present invention belongs to the field of medical health technology, and specifically is a home continuous ambulatory peritoneal dialysis operation behavior monitoring system and method. Background Art

[0002] End-stage renal disease (i.e. uremia) is the final stage of chronic kidney disease. At present, the number of people receiving renal replacement therapy in China has exceeded 1 million. It is estimated that by 2030, this number will reach or even exceed 1.5 million. The annual economic cost is about 200 billion yuan, which constitutes a huge treatment group. For this group, optimizing renal replacement therapy, improving treatment effects and quality of life, and promoting their better return to society are the common efforts of kidney disease medical practitioners.

[0003] Renal replacement therapy mainly includes peritoneal dialysis, hemodialysis and allogeneic renal transplantation (kidney transplantation), and patients must choose one of them. The main limitation of renal transplantation is the scarcity of kidney sources, which makes the development of renal transplantation uncertain, and its high one-time medical investment is also difficult for ordinary patients to afford. Peritoneal dialysis and hemodialysis, as the two main methods of renal replacement therapy, have no significant difference in clinical effect, quality of life and survival rate. However, from the perspective of cost, data from multiple studies show that the medical cost of peritoneal dialysis is generally lower than that of hemodialysis. In many countries, the treatment cost of two peritoneal dialysis patients is only equivalent to the treatment cost of one hemodialysis patient. Compared with hemodialysis, peritoneal dialysis can better protect residual renal function, has less impact on the heart, blood and circulatory system, is not easy to cause complications such as heart disease, and allows patients to be treated at home, with more flexible treatment plans. Therefore, the preference for peritoneal dialysis helps patients with uremia to prolong their overall survival time. This view has gradually been recognized by physicians and generally accepted by patients.

[0004] At present, the mainstream treatment method for peritoneal dialysis is continuous ambulatory peritoneal dialysis (CAPD) at home. Compared with hemodialysis, peritoneal dialysis provides patients with more opportunities to return to their families and society, and is more in line with the "natural" treatment concept. In countries and regions with more developed medical services in the world, advocating the treatment concept of "peritoneal dialysis first" has become a trend. For example, Hong Kong, China has achieved remarkable results in implementing the "peritoneal dialysis first" policy. In these areas, patients will only be arranged for hemodialysis when they have contraindications to peritoneal dialysis or are not suitable for continuing peritoneal dialysis treatment due to complications. This policy greatly reduces medical costs, reduces the demand for purchasing hemodialysis machines and opening hemodialysis treatment centers, and has been supported by the majority of patients. In remote mountainous areas and economically underdeveloped areas in China, due to the lack of effective medical professional technical support and hardware support, the development of hemodialysis faces difficulties. The development of peritoneal dialysis in these areas can just make up for the above shortcomings. Faced with the growing population of end-stage renal disease patients in China and the increasing space and economic burden, giving priority to and implementing peritoneal dialysis has become an important measure at present.

[0005] Related studies have shown that the operating behavior of home CAPD patients, especially the establishment of operating behavior habits for new patients, has a significant impact on key nodes such as the protection of residual renal function and the incidence of peritoneal dialysis-related peritonitis, and is further related to core endpoint indicators such as the failure rate of peritoneal dialysis technology, patient quality of life and mortality.

[0006] However, there are many challenges in achieving real-time recording of patient behavior data. Although video recordings can intuitively show patient behavior, their huge data volume and high privacy sensitivity limit their application in long-term, large-scale health monitoring. In contrast, although text records, voice calls and other data are easy to obtain, it is often difficult to directly and comprehensively capture behavioral details. Effective analysis requires complex algorithm conversion and multi-dimensional information fusion, which places higher demands on technical implementation and data processing efficiency. Summary of the invention

[0007] In view of the above problems, the present invention is proposed to provide a home continuous ambulatory peritoneal dialysis operation behavior monitoring system and method that overcomes the above problems or at least partially solves the above problems.

[0008] To achieve the above object, the present invention adopts the following technical solutions:

[0009] A home continuous ambulatory peritoneal dialysis operation behavior monitoring system, the system comprising:

[0010] Video data acquisition and preprocessing module, used for acquiring video data and preprocessing the video data;

[0011] Key node extraction and marking module, used to extract and mark key data nodes;

[0012] Data transmission and storage module, used for transmitting and storing data;

[0013] Data processing and application module, used to process and apply data;

[0014] The monitoring alarm module is used to trigger an alarm when abnormal operating behavior is detected.

[0015] Optionally, the video data acquisition and preprocessing module includes:

[0016] A raw video capture unit, which uses a camera to capture video data in real time;

[0017] Edge computing and image analysis unit, used to analyze the collected video data.

[0018] Optionally, the edge computing and image analysis unit includes:

[0019] Transmit the captured video data to the chip built into the sensor;

[0020] Processing video data using chips;

[0021] Identify the human body area in the video data and calculate and analyze the data image matrix of the area.

[0022] Optionally, the key node extraction and marking module includes:

[0023] Generate key node data with clear location information;

[0024] Mark the information of each key node to ensure the structuring and traceability of data;

[0025] Traverse and mark the key point information of each frame image in the real-time video stream.

[0026] Optionally, the data transmission and storage module includes:

[0027] Transmit key point data information through network protocol;

[0028] The cloud server or dedicated application software database receives and stores data information in real time.

[0029] Optional data processing and application modules include:

[0030] The data receiving and distributing unit is used to receive data from sensors, store them locally and then push them;

[0031] A video simulation and display unit, used for video simulation and display of data;

[0032] The deep learning pattern recognition and statistics unit is used to integrate and analyze data and perform statistics.

[0033] Optionally, the video simulation and display unit includes:

[0034] Receive the pushed data, and use the key point video simulation algorithm to restore the discrete key point data frame by frame into a simulated compressed video;

[0035] Output analog video for external display, retaining key information of the original video and reducing storage and transmission burden.

[0036] Optionally, the deep learning pattern recognition and statistics unit includes:

[0037] After receiving the data, the key points of each frame are integrated and analyzed in combination with the standard operating procedures and standard behavior nodes of continuous ambulatory peritoneal dialysis at home;

[0038] By comparing the reference system, the difference between the data to be evaluated and the reference system is calculated, the operation behavior labels of continuous ambulatory peritoneal dialysis at home are marked, and abnormal operation behaviors are identified and labeled;

[0039] The simulated video is calculated frame by frame based on the processed data labels to generate statistical information of each behavior posture label.

[0040] The present invention also provides a method for monitoring operation behavior of continuous ambulatory peritoneal dialysis at home, which is based on any of the above-mentioned systems and comprises the following steps:

[0041] S1, collect video data through the camera;

[0042] S2, performing edge computing and image analysis on the captured video data;

[0043] S3, generating key point data of human body posture;

[0044] S4, storing and transmitting the generated human body posture key point data;

[0045] S5, receiving data and distributing it;

[0046] S6, converting the key point data into a simulation video and displaying it;

[0047] S7, performing frame-by-frame calculation on the simulated video to generate statistical information of various human postures;

[0048] S8. Compare the abnormal operation behavior labels of the reference system and trigger the monitoring alarm mechanism.

[0049] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0050] 1. The present invention realizes a comprehensive and objective record of the patient's operation behavior by real-time and efficient collection of daily operation video data of home CAPD (Continuous ambulatory peritoneal dialysis, CAPD for short). At the same time, the present invention will design and formulate a set of standard operation procedures as a reference benchmark, and realize accurate quantification and evaluation of operation behavior by comparing and analyzing the recorded operation behavior data with the reference system data.

[0051] 2. The present invention can monitor and alarm abnormal operation behaviors of peritoneal dialysis patients, and provide a new and quantitative evaluation index for behavioral-based evaluation of home CAPD-related diagnosis and treatment nodes. This innovative method is not only expected to significantly improve the follow-up efficiency of such diseases, but also provide strong technical support and guarantee for reducing the incidence of adverse events caused by bad operation habits. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 A schematic diagram of the process flow of a home continuous ambulatory peritoneal dialysis operation behavior monitoring system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0054] Embodiment 1:

[0055] See also Figure 1 This embodiment provides a home continuous ambulatory peritoneal dialysis operation behavior monitoring system, including:

[0056] The video data acquisition and preprocessing module is used to acquire video data and preprocess the video data.

[0057] The video data acquisition and preprocessing module includes:

[0058] The original video capture unit uses a high-precision ordinary camera to capture video data in the scene in real time.

[0059] Edge computing and image analysis unit, used to analyze the collected video data.

[0060] The edge computing and image analysis unit includes:

[0061] The captured video data is transmitted to the chip built into the sensor.

[0062] The powerful computing power of the chip is used to process video data frame by frame, including image decomposition and segmentation into digital image data matrices.

[0063] A deep learning human pose estimation algorithm is applied to identify the human body area in the video data, and perform deep calculation and analysis on the data image matrix of the area.

[0064] The key node extraction and marking module is used to extract and mark key data nodes.

[0065] The key node extraction and marking module includes:

[0066] Generate key node data with clear location information.

[0067] According to the predefined data table format, the information of each key node is marked in detail to ensure the structuring and traceability of the data.

[0068] Traverse and mark the key point information of each frame image in the real-time video stream.

[0069] The data transmission and storage module is used for transmitting and storing data.

[0070] The data transmission and storage module includes:

[0071] The key point data information is transmitted through the network protocol.

[0072] The cloud server or dedicated application software database receives and stores data information in real time.

[0073] Data processing and application module, used to process and apply data.

[0074] Data processing and application modules include:

[0075] The data receiving and distributing unit is used to receive data from sensors, store them locally, and then push them to different processing modules according to demand, such as the video simulation module and the deep learning pattern recognition algorithm module.

[0076] The video simulation and display unit is used to simulate and display the data in the form of video.

[0077] The deep learning pattern recognition and statistics unit is used to integrate and analyze data and perform statistics.

[0078] The video simulation and display unit comprises:

[0079] The video simulation module receives the data pushed by the database, and uses the key point video simulation algorithm to restore the discrete key point data frame by frame into a simulated compressed video.

[0080] Output analog video for external display, retaining key information of the original video and reducing storage and transmission burden.

[0081] The deep learning pattern recognition and statistics unit includes:

[0082] After receiving the data, the frame-by-frame key points were integrated and analyzed in combination with the standard operating procedures and standard behavior nodes for home continuous ambulatory peritoneal dialysis operations.

[0083] By comparing with the reference system, the difference between the data to be evaluated and the reference system is calculated, the operation behavior labels of home continuous ambulatory peritoneal dialysis are marked, and abnormal operation behaviors are identified and labeled.

[0084] The simulated video is calculated frame by frame based on the processed data labels to generate statistical information of each behavior posture label.

[0085] The monitoring alarm module is used to trigger an alarm when abnormal operating behavior is detected.

[0086] This embodiment realizes a comprehensive and objective record of the patient's operation behavior by real-time and efficient collection of daily operation desensitized video data of home CAPD (Continuous ambulatory peritoneal dialysis, CAPD for short). At the same time, the present invention will design and formulate a set of standard operation procedures as a reference benchmark, and realize accurate quantification and evaluation of operation behavior by comparing and analyzing the recorded operation behavior data with the reference system data.

[0087] This embodiment can monitor and alarm abnormal operation behaviors of peritoneal dialysis patients, and provide a new and quantitative evaluation index for behavioral-based evaluation of home CAPD-related diagnosis and treatment nodes. This innovative method is not only expected to significantly improve the follow-up efficiency of such diseases, but also provide strong technical support and guarantee for reducing the incidence of adverse events caused by bad operation habits.

[0088] Embodiment 2:

[0089] Embodiment 2 discloses a method for monitoring operation behavior of continuous ambulatory peritoneal dialysis at home. The method is based on the above-mentioned system for monitoring operation behavior of continuous ambulatory peritoneal dialysis at home. The method comprises the following steps:

[0090] S1. Collect video data through a camera.

[0091] S2. Perform edge computing and image analysis on the captured video data.

[0092] S3. Generate key point data of human body posture.

[0093] S4. Store and transmit the generated human body posture key point data.

[0094] S5. Receive data and distribute it.

[0095] S6. Convert key point data into simulated video and display it.

[0096] S7. Calculate the simulated video frame by frame to generate statistical information of various human postures.

[0097] S8. Compare the abnormal operation behavior labels of the reference system and trigger the monitoring alarm mechanism.

[0098] The above contents are further detailed descriptions of the present invention in combination with specific preferred embodiments, and it cannot be determined that the specific implementation of the present invention is limited to these descriptions. For ordinary technicians in the technical field to which the present invention belongs, several simple deductions or substitutions can be made without departing from the concept of the present invention, which should be regarded as falling within the protection scope of the present invention.

Claims

1. A home continuous ambulatory peritoneal dialysis operation behavior monitoring system, characterized in that: The system comprises: Video data acquisition and preprocessing module, used for acquiring video data and preprocessing the video data; Key node extraction and marking module, used to extract and mark key data nodes; Data transmission and storage module, used for transmitting and storing data; Data processing and application module, used to process and apply data; The monitoring alarm module is used to trigger an alarm when abnormal operating behavior is detected.

2. A home continuous ambulatory peritoneal dialysis operation behavior monitoring system as claimed in claim 1, characterized in that: The video data acquisition and preprocessing module includes: A raw video capture unit, which uses a camera to capture video data in real time; Edge computing and image analysis unit, used to analyze the collected video data.

3. A home continuous ambulatory peritoneal dialysis operation behavior monitoring system as claimed in claim 2, characterized in that: The edge computing and image analysis unit includes: Transmit the captured video data to the chip built into the sensor; Processing video data using chips; Identify the human body area in the video data and calculate and analyze the data image matrix of the area.

4. A home continuous ambulatory peritoneal dialysis operation behavior monitoring system as claimed in claim 1, characterized in that: The key node extraction and marking module includes: Generate key node data with clear location information; Mark the information of each key node to ensure the structuring and traceability of data; Traverse and mark the key point information of each frame image in the real-time video stream.

5. A home continuous ambulatory peritoneal dialysis operation behavior monitoring system as claimed in claim 1, characterized in that: The data transmission and storage module includes: Transmit key point data information through network protocol; The cloud server or dedicated application software database receives and stores data information in real time.

6. A home continuous ambulatory peritoneal dialysis operation behavior monitoring system as claimed in claim 1, characterized in that: Data processing and application modules include: The data receiving and distributing unit is used to receive data from sensors, store them locally and then push them; A video simulation and display unit, used for video simulation and display of data; The deep learning pattern recognition and statistics unit is used to integrate and analyze data and perform statistics.

7. A home continuous ambulatory peritoneal dialysis operation behavior monitoring system as claimed in claim 6, characterized in that: The video simulation and display unit comprises: Receive the pushed data, and use the key point video simulation algorithm to restore the discrete key point data frame by frame into a simulated compressed video; Output analog video for external display, retaining key information of the original video and reducing storage and transmission burden.

8. A home continuous ambulatory peritoneal dialysis operation behavior monitoring system as claimed in claim 6, characterized in that: The deep learning pattern recognition and statistics unit includes: After receiving the data, the key points of each frame are integrated and analyzed in combination with the standard operating procedures and standard behavior nodes of continuous ambulatory peritoneal dialysis at home; By comparing the reference system, the difference between the data to be evaluated and the reference system is calculated, the operation behavior labels of continuous ambulatory peritoneal dialysis at home are marked, and abnormal operation behaviors are identified and labeled; The simulated video is calculated frame by frame based on the processed data labels to generate statistical information of each behavior posture label.

9. A method for monitoring operation behavior of continuous ambulatory peritoneal dialysis at home, the method being based on a system for monitoring operation behavior of continuous ambulatory peritoneal dialysis at home according to any one of claims 1 to 8, characterized in that: The method comprises the following steps: S1, collect video data through the camera; S2, performing edge computing and image analysis on the captured video data; S3, generating key point data of human body posture; S4, storing and transmitting the generated human body posture key point data; S5, receiving data and distributing it; S6, converting the key point data into a simulation video and displaying it; S7, performing frame-by-frame calculation on the simulated video to generate statistical information of various human postures; S8. Compare the abnormal operation behavior labels of the reference system and trigger the monitoring alarm mechanism.

Images