Abdominal pressure monitoring device and system for peritoneal dialysis

Abstract

The invention provides an abdominal cavity pressure monitoring device and system for peritoneal dialysis, and the device comprises a pressure monitoring module which is used for monitoring the abdominal cavity pressure of a to-be-monitored object in real time in a current pressure monitoring process, and obtaining real-time first pressure data; the posture recognition module is used for recognizing the posture of the to-be-detected object in real time and determining the real-time target posture of the to-be-detected object; the labeling module is used for labeling the first pressure data at the corresponding moment according to the real-time target attitude of the to-be-detected object and determining labeled second pressure data; and the data analysis module is used for analyzing whether the cause of the abnormality is related to the target attitude or not according to the second pressure data under the condition that the second pressure data is abnormal. By adopting the technical scheme of the invention, the abdominal pressure data of the to-be-tested object can be better used and analyzed.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a peritoneal pressure monitoring device and system for peritoneal dialysis. Background Art

[0002] Peritoneal dialysis mainly involves injecting dialysate into the patient's abdominal cavity to remove metabolic products and toxic substances in the patient's body and correct water and electrolyte imbalance. The abdominal cavity pressure is an important indicator of peritoneal dialysis. On the one hand, it may affect the effectiveness of peritoneal dialysis, that is, increased intra-abdominal pressure will reduce the dialysis efficiency; on the other hand, greater abdominal pressure may cause complications such as hernia and leakage, increasing the risk of other dangerous situations. Therefore, it is necessary to monitor the patient's abdominal cavity pressure.

[0003] In the related art, when monitoring the abdominal pressure of patients, related abdominal pressure monitoring devices are mostly used. These abdominal pressure monitoring devices mainly measure and record the abdominal pressure of patients through pressure measuring tubes or sensor technology. Based on this, how to better use the abdominal pressure obtained by the above technology is a technical problem that needs to be solved urgently. Summary of the invention

[0004] The present invention provides an abdominal pressure monitoring device and system for peritoneal dialysis, which are used to solve the defect in the prior art that, under continuous monitoring, the abdominal pressure data cannot be interpreted for guiding diagnosis and treatment due to the interference of the posture of the object to be measured, and achieve the purpose of posture annotation and abnormal analysis of the abdominal pressure data of the object to be measured.

[0005] In a first aspect, the present invention provides a peritoneal pressure monitoring device for peritoneal dialysis, comprising: A pressure monitoring module, used to monitor the abdominal pressure of the subject to be tested in real time during the current pressure monitoring process to obtain real-time first pressure data; A posture recognition module is used to recognize the posture of the object to be measured in real time and determine the real-time target posture of the object to be measured; A labeling module, used for labeling the first pressure data at a corresponding moment according to the real-time target posture of the object to be measured, and determining the labeled second pressure data; The data analysis module is used to analyze whether the cause of the abnormality is related to the target posture according to the second pressure data when the second pressure data is abnormal.

[0006] According to the abdominal cavity pressure monitoring device for peritoneal dialysis provided by the present invention, the above-mentioned posture recognition module is specifically used for

[0007] Acquire the image of the object to be tested in real time, classify the posture of the object to be tested in the image to determine the initial posture corresponding to the object to be tested; According to the initial posture and the image to be measured, the posture of the object to be measured is identified to determine the target posture corresponding to the object to be measured; the accuracy of the above target posture is higher than the accuracy of the initial posture.

[0008] According to the abdominal cavity pressure monitoring device for peritoneal dialysis provided by the present invention, the above-mentioned posture recognition module is specifically used for

[0009] Using a preset human posture estimation model to identify key points of the object to be measured in the image to be measured, and determining multiple key points corresponding to the object to be measured; Determine a plurality of target key points associated with the initial pose from the plurality of key points; According to the position information of each target key point, the target posture of the object to be measured is determined.

[0010] According to the peritoneal pressure monitoring device for peritoneal dialysis provided by the present invention, the initial posture includes any one of sitting, standing and lying positions, the target key points include hip key points, shoulder key points and knee key points, and the posture recognition module is specifically used for

[0011] Calculate a first vector based on the position information of the hip key point and the position information of the shoulder key point; and calculate a second vector based on the position information of the hip key point and the position information of the knee key point; Calculating the angle between the first vector and the second vector, and determining the degree of waist bending of the object to be measured according to the angle; The target posture is determined based on the degree of waist bending.

[0012] According to the abdominal cavity pressure monitoring device for peritoneal dialysis provided by the present invention, the above-mentioned posture recognition module is specifically used for

[0013] A neural network is used to classify the posture of the object to be tested in the image to be tested, and an initial posture corresponding to the object to be tested is determined; The neural network is trained based on multiple training images and the annotation posture corresponding to each training image, and the annotation postures corresponding to the training images are not completely the same.

[0014] According to a peritoneal pressure monitoring device for peritoneal dialysis provided by the present invention, in the current pressure monitoring process, the target posture of the above-mentioned object to be measured at each moment is not completely the same; The data analysis module is further used to extract the second pressure data belonging to the same target posture at different times from the second pressure data, and determine the change trend of the abdominal pressure under the corresponding target posture according to the second pressure data of each target posture at different times; the change trend of the abdominal pressure under each target posture is different; Furthermore, the changing trends of the abdominal pressure under each target posture are compared, and the optimal posture of the object to be measured in the next pressure monitoring process is determined from each target posture.

[0015] According to the present invention, a peritoneal pressure monitoring device for peritoneal dialysis is provided.

[0016] The above-mentioned data analysis module is specifically used to adjust the target posture of the object to be measured at the current moment, and detect whether the second pressure data at the subsequent moment is abnormal after the adjustment; if the second pressure data at the subsequent moment is not abnormal, it is determined that the reason why the second pressure data at the current moment is abnormal is related to the target posture at the current moment; If the second pressure data at the subsequent moment is still abnormal, it is determined that the reason why the second pressure data at the current moment is abnormal is related to the amount of peritoneal dialysis fluid infused or the amount of ultrafiltration of the subject to be tested.

[0017] According to the present invention, a peritoneal pressure monitoring device for peritoneal dialysis further comprises: An alarm module, used to compare the real-time second pressure data with a preset pressure threshold range, and when the second pressure data at any moment exceeds the pressure threshold range, determine that the second pressure data at any moment is abnormal, and output an alarm message; The alarm information includes the reason why the second pressure data at any moment is abnormal and decision-making suggestion information determined based on the reason.

[0018] According to the present invention, a peritoneal pressure monitoring device for peritoneal dialysis further comprises: The auxiliary decision-making module is used to generate a personalized treatment plan corresponding to the subject to be tested based on the second pressure data of the subject to be tested in multiple pressure monitoring processes, the clinical treatment data of the subject to be tested, and the living habit data of the subject to be tested; the above-mentioned clinical treatment data includes the initial treatment plan and / or predicted treatment results.

[0019] In a second aspect, the present invention further provides a peritoneal pressure monitoring system for peritoneal dialysis, comprising an image acquisition device and the peritoneal pressure monitoring device for peritoneal dialysis of the first aspect; The above-mentioned image acquisition device is used to obtain the image to be tested of the object to be tested in real time, and transmit the image to be tested to the abdominal cavity pressure monitoring device used for peritoneal dialysis.

[0020] The present invention provides an abdominal cavity pressure monitoring device and system for peritoneal dialysis, wherein the abdominal cavity pressure monitoring device for peritoneal dialysis includes a pressure monitoring module, a posture recognition module, a labeling module and a data analysis module, wherein the pressure monitoring module can monitor the abdominal cavity pressure of the object to be measured in real time in the current pressure monitoring process to obtain real-time first pressure data; the posture recognition module can identify the neutron state of the object to be measured in real time to determine the real-time target posture of the object to be measured; the labeling module can label the first pressure data at the corresponding moment according to the real-time target posture of the object to be measured to determine the labeled second pressure data; the data analysis module can analyze whether the cause of the abnormality is related to the target posture according to the second pressure data when there is an abnormality in the second pressure data. The abdominal pressure monitoring device for peritoneal dialysis of the present invention can identify the real-time posture of the object to be measured and mark the identified posture on the real-time pressure data. In this way, when the abdominal pressure is continuously monitored, the pressure data with the posture marked in real time can be used to quickly analyze whether the cause of the abnormality is related to the posture when there is an abnormality in the abdominal pressure, so as to well interpret the abdominal pressure data of the object to be measured caused by posture interference and can be used to guide subsequent diagnosis and treatment, thereby realizing the effective use and accurate analysis of the abdominal pressure data of the object to be measured. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 1 It is a schematic structural diagram of the abdominal cavity pressure monitoring device for peritoneal dialysis provided by the present invention.

[0023] Figure 2 It is a schematic diagram of key points of the body parts of the object to be tested provided by the present invention.

[0024] Figure 3 It is a schematic diagram of calculating the first vector and the second vector and the angle between them provided by the present invention.

[0025] Figure 4 It is a schematic diagram of various target postures provided by the present invention.

[0026] Figure 5 It is a structural schematic diagram of the abdominal cavity pressure monitoring system for peritoneal dialysis provided by the present invention.

[0027] Description of reference numerals: 10: Abdominal cavity pressure monitoring device for peritoneal dialysis; 110: Pressure monitoring module; 120: Posture recognition module; 130: Labeling module; 140: Data analysis module; 20: Image acquisition device. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings 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.

[0029] Abdominal pressure is an important indicator of peritoneal dialysis. On the one hand, it affects the effectiveness of dialysis. Increased intra-abdominal pressure will reduce the efficiency of dialysis. On the other hand, greater abdominal pressure may lead to complications such as hernia, leakage, thoracoabdominal fistula, gastroesophageal reflux or delayed emptying, increase the risk of enterogenic peritonitis, and is a risk factor for death and technical failure. Therefore, real-time and accurate monitoring of abdominal pressure can help improve the treatment effect, prevent complications, and thus improve the quality of life of patients. At present, there are some abdominal pressure monitoring devices, which mainly measure and record the patient's abdominal pressure through pressure gauges or sensor technology. There is an obvious defect in the application of existing abdominal pressure monitoring devices: they fail to fully consider the significant impact of human posture on abdominal pressure. In fact, abdominal pressure is greatly affected by human posture. For example, when the patient is sitting, his abdominal pressure is significantly higher than that in the standing state, while when lying flat, the abdominal pressure is reduced to the lowest. Since the current abdominal pressure monitoring device fails to take into account this pressure change caused by posture, the monitoring data it provides is often difficult to accurately interpret and apply, which undoubtedly increases the difficulty and uncertainty of treatment decision-making. Based on this, an embodiment of the present invention provides a peritoneal pressure monitoring device and system for peritoneal dialysis, which can solve this technical problem.

[0030] Combine the following Figure 1-Figure 4 The abdominal cavity pressure monitoring device for peritoneal dialysis according to an embodiment of the present invention is described.

[0031] Figure 1 : is a structural block diagram of the peritoneal pressure monitoring device for peritoneal dialysis provided by the present invention, such as Figure 1As shown, the peritoneal pressure monitoring device 10 for peritoneal dialysis includes a pressure monitoring module 110, a posture recognition module 120, a labeling module 130 and a data analysis module 140. Among them, the pressure monitoring module 110 is used to monitor the peritoneal pressure of the object to be measured in real time in the current pressure monitoring process to obtain real-time first pressure data; the posture recognition module 120 is used to recognize the posture of the object to be measured in real time and determine the real-time target posture of the object to be measured; the labeling module 130 is used to label the first pressure data at the corresponding moment according to the real-time target posture of the object to be measured and determine the labeled second pressure data; the data analysis module 140 is used to analyze whether the cause of the abnormality is related to the target posture according to the second pressure data when there is an abnormality in the second pressure data.

[0032] The pressure monitoring module 110 may include a high-precision, high-sensitivity pressure sensor, which may be disposed outside the abdomen of the subject to be tested or inside the abdominal cavity. The subject to be tested may be a patient who needs peritoneal dialysis. Usually, the subject to be tested may undergo multiple peritoneal dialysis cycles in one peritoneal dialysis treatment course, and a corresponding pressure monitoring process will be performed during each peritoneal dialysis cycle.

[0033] The pressure monitoring module 110 can collect the abdominal pressure of the subject to be tested in real time using a sensor or other equipment in the current pressure monitoring process (i.e., the current peritoneal dialysis process) when the subject to be tested is undergoing peritoneal dialysis, and can convert the measured abdominal pressure into an electrical signal to obtain abdominal pressure data at each moment, which is recorded as first pressure data. The first pressure data is the original data collected for the abdominal pressure of the subject to be tested. The first pressure data may include abdominal pressure data at one moment, or may include abdominal pressure data at multiple moments.

[0034] While the abdominal pressure data of the object to be tested is monitored in real time, the posture recognition module 120 can also be used to recognize the posture of the object to be tested at each moment in real time to obtain the target posture of the object to be tested at each moment during the pressure monitoring process. When identifying the posture of the object to be tested, the target posture of the object to be tested can be obtained by performing posture recognition on the collected image of the object to be tested's action, or the action data of the object to be tested can be collected by a sensor set on the body part of the object to be tested to identify the target posture of the object to be tested (for example, a pressure sensor is set on the buttocks of the object to be tested, and when the pressure signal is detected, it can be identified that the target posture of the object to be tested is a sitting posture). Of course, the target posture of the object to be tested at each moment can also be identified by other methods, which are not specifically limited here. The target posture here can include, for example, standing, sitting, lying (such as lying flat or lying on the side), etc., or can also include specific angles when standing / sitting / lying flat.

[0035] After identifying the target posture of the object to be tested at each moment, since posture recognition and pressure monitoring are both performed in real time, there is a time correlation between the two. Therefore, the target posture of the object to be tested at each moment can be correspondingly annotated to the pressure data at the corresponding moment of the first pressure data through the labeling module 130. After labeling, the pressure data carrying the posture label can be obtained, which is recorded as the second pressure data.

[0036] Furthermore, the above-mentioned marking module 130 can also mark the identified target posture on the first pressure data in real time, and at the same time, it can also detect in real time whether the second pressure data at each moment is abnormal during the real-time marking process. If the second pressure data at a certain moment is abnormal, the target posture of the object to be measured at this moment can be obtained through the second pressure data at this moment, and then the second pressure data at this moment is analyzed according to the target posture of the object to be measured at this moment to obtain the analysis result; the analysis result indicates whether the reason for the abnormality of the second pressure data at this moment is related to the target posture at this moment. After obtaining the analysis result, different adjustment operations can be performed according to the different contents of the analysis result, so that the second pressure data at the next moment is not abnormal / restored to normal. For example, if the reason for the abnormality of the second pressure data at this moment is related to the target posture at this moment, the object to be measured can be prompted to adjust the target posture so that the second pressure data at the next moment is not abnormal / restored to normal; if the reason for the abnormality of the second pressure data at this moment is not related to the target posture at this moment, the influence of the target posture can be eliminated, and other reasons, such as ultrafiltration volume, infusion volume, etc., can be used to eliminate the cause of the abnormality and eliminate the abnormality, so that the second pressure data at the next moment is not abnormal / restored to normal.

[0037] When the above-mentioned real-time detection of whether there is an abnormality in the second pressure data at each moment, it may specifically include: obtaining the pressure threshold range pre-set for the object to be tested, and determining whether the second pressure data at each moment exceeds the pressure threshold range. If exceeded, it can be analyzed that the second pressure data at that moment is abnormal. The pressure threshold range here may be composed of a threshold, or may be composed of a range consisting of a lower threshold limit and an upper threshold limit. In addition, the pressure threshold range of the above-mentioned object to be tested may be a personalized pressure threshold range for the object to be tested, which may be specifically set in advance according to the attribute information of the object to be tested, and the attribute may include, for example, age, gender, height, weight, etc., or may also include other information. The pressure threshold ranges for different objects to be tested may be different.

[0038] In this embodiment, the peritoneal pressure monitoring device for peritoneal dialysis includes a pressure monitoring module, a posture recognition module, a marking module and a data analysis module, wherein the pressure monitoring module can monitor the peritoneal pressure of the object to be measured in real time in the current pressure monitoring process to obtain real-time first pressure data; the posture recognition module can recognize the neutron state of the object to be measured in real time to determine the real-time target posture of the object to be measured; the marking module can mark the first pressure data at the corresponding moment according to the real-time target posture of the object to be measured to determine the marked second pressure data; the data analysis module can analyze whether the cause of the abnormality is related to the target posture according to the second pressure data when the second pressure data is abnormal. The peritoneal pressure monitoring device for peritoneal dialysis of the present invention can recognize the real-time posture of the object to be measured and mark the recognized posture on the real-time pressure data. In this way, under the state of continuous monitoring of the peritoneal pressure, the pressure data with real-time marking posture can quickly analyze whether the cause of the abnormality is related to the posture when the peritoneal pressure is abnormal, so as to interpret the peritoneal pressure data of the object to be measured due to posture interference well and can be used to guide subsequent diagnosis and treatment, thereby realizing the effective use and accurate analysis of the peritoneal pressure data of the object to be measured.

[0039] The following embodiment describes a possible implementation method of identifying the target posture of the object to be detected by using the image of the object to be detected.

[0040] In one embodiment, the above-mentioned posture recognition module 120 is specifically used to obtain the image to be tested of the object to be tested in real time, and classify the posture of the object to be tested in the image to be tested to determine the initial posture corresponding to the object to be tested; according to the initial posture and the image to be tested, the posture of the object to be tested is identified to determine the target posture corresponding to the object to be tested; the accuracy of the above-mentioned target posture is higher than the accuracy of the initial posture.

[0041] Among them, an image acquisition device can be pre-arranged around the object to be tested, and the image acquisition device is used to acquire images of the object to be tested, including full-body images or partial body images, etc. The image acquisition device can be, for example, a camera, a video camera, etc. The image acquisition device can acquire images of the whole body or partial body parts of the object to be tested in real time, and transmit the acquired images to the posture recognition module 120 in real time for processing, where the acquired images can be recorded as images to be tested.

[0042] The posture recognition module 120 can acquire the image to be tested transmitted by the image acquisition device in real time, and can perform two-level posture recognition on the object to be tested in the image to be tested, including rough posture recognition and fine posture recognition. The rough posture recognition here can be implemented by a preset neural network, and the fine posture recognition can be implemented by a preset human posture estimation model (such as a MediaPipe model).

[0043] In the process of rough posture recognition, optionally, the above-mentioned posture recognition module 120 is specifically used to classify the posture of the object to be tested in the image to be tested using a neural network, and determine the initial posture corresponding to the object to be tested; wherein the above-mentioned neural network is trained based on multiple training images and the annotated posture corresponding to each training image, and the annotated posture corresponding to each training image is not exactly the same.

[0044] The neural network may be CNN (Convolutional Neural Networks), VGG (Visual Geometry Group), ResNet (Deep Residual Network), etc. It may be pre-trained, specifically, a picture data set labeled with different human postures may be pre-collected, the picture data set includes multiple training images, and the initial neural network is trained using these training images labeled with human postures, and the model parameters and structure of the initial neural network are adjusted so that the initial neural network can learn and recognize the human posture features in the image, such as standing, lying or sitting, and meet certain performance requirements, and finally obtain the final trained neural network. The trained neural network can recognize the posture of the human body in an image after inputting an image, so after the images of the object to be tested at each moment are obtained in real time, the images to be tested at each moment can be input into the trained neural network for posture recognition or posture classification, etc., to obtain the posture of the object to be tested, which is recorded as the initial posture.

[0045] It should be noted that the above-mentioned image to be tested may be a frame of image, or may be a video sequence including multiple frames of image.

[0046] After obtaining the initial posture of the object to be measured, the posture of the object to be measured can be further finely identified. In the process of fine posture identification, optionally, the posture identification module 120 is specifically used to identify the key points of the object to be measured in the image to be measured using a preset human posture estimation model, determine multiple key points corresponding to the object to be measured; determine multiple target key points related to the initial posture from the multiple key points; and determine the target posture of the object to be measured according to the position information of each target key point.

[0047] The preset human body posture estimation model may be, for example, a MediaPipe model, or other human body posture estimation models.

[0048] After the initial posture of the object to be tested is recognized in real time, the image to be tested at a certain moment can be input into the human posture estimation model, and multiple key points on the object to be tested can be identified through its built-in key point detection model. Figure 2The key points of the body parts of the object to be tested are shown in the schematic diagram. The multiple key points identified may include 33 (0-32) key points such as shoulders, elbows, wrists, hips, knees and ankles. The key points of the object to be tested in the image to be tested identified by the above human posture estimation model can be expressed as Figure 2 The two-dimensional coordinate points in the image are each corresponding to a specific part of the object to be measured.

[0049] Then, according to the initial posture of the object to be tested, multiple target key points corresponding to the initial state can be selected from the multiple key points detected above. For example, if the initial posture includes sitting or standing, the multiple target key points may include hip key points (such as points 23 and 24), shoulder key points (such as points 11 and 12), and knee key points (such as points 25 and 26). It can be understood that the multiple target key points selected corresponding to different initial postures are not completely the same.

[0050] After selecting multiple target key points related to the initial state from the multiple key points obtained by detection, a more precise target posture of the object to be detected can be calculated through the positional relationship between the target key points. Here, multiple target key points related to the initial state are selected from multiple key points, and the number of selected multiple target key points is also less than the number of multiple key points obtained by detection, which can save the amount of posture recognition calculation while improving the posture recognition accuracy.

[0051] Furthermore, when a more precise target posture of the object to be measured is calculated through the positional relationship between each target key point, optionally, taking the initial posture including sitting or standing, and the multiple target key points including hip key points, shoulder key points and knee key points as an example, the posture recognition module 120 is specifically used to calculate a first vector according to the position information of the hip key point and the position information of the shoulder key point; and calculate a second vector according to the position information of the hip key point and the position information of the knee key point; calculate the angle between the first vector and the second vector, and determine the degree of waist bending of the object to be measured according to the angle; and determine the target posture according to the degree of waist bending.

[0052] Among them, when the initial posture is any one of sitting, standing and lying, the degree / angle of waist bending has a greater impact on the abdominal cavity pressure. After selecting the multiple target key points of the hip key point, the shoulder key point and the knee key point, the position information of each target key point in the image to be measured can also be obtained accordingly; then, the vector between the hip key point and the shoulder key point (recorded as the first vector a) and the vector between the hip key point and the knee key point (recorded as the second vector b) can be calculated through the position information of these target key points; then, the angle between the first vector and the second vector can be calculated through the calculation formula of the angle between the two vectors, and the angle can be used as the degree of waist bending of the object to be measured, or the angle can be post-processed to obtain the degree of waist bending of the object to be measured; then, the degree of waist bending of the object to be measured and the initial posture can be combined to determine the target posture of the object to be measured at this time, for example, the target posture can be: a bent-over standing posture with an angle close to 90 degrees, and in this way, the degree of body bending when bending in a sitting position, standing position or lying position (such as a side-lying position) can be finely judged.

[0053] For example, see Figure 3 As shown in the schematic diagram of calculating the first vector and the second vector and the angle between them, it can be seen that the angle between the first vector and the second vector is different, and the posture of the object to be measured is also different.

[0054] Continue to see Figure 4 From the schematic diagrams of various target postures shown, it can be seen that there are different refined postures for sitting postures, such as "sitting leaning back", "upright sitting posture", "sitting leaning forward", "sitting bending forward", etc. The abdominal pressure data under different target postures are also different. By refining the target posture of the object to be tested, the accuracy of subsequent analysis of the pressure data annotated with the target posture can be improved, thereby providing a more accurate data basis for subsequent processing.

[0055] In this embodiment, the posture of the object to be measured is subjected to two levels of coarse recognition and fine recognition, so that the accuracy or precision of the target posture finally obtained can be improved. In addition, a neural network is used to perform coarse recognition on the posture of the object to be measured, so that the recognition efficiency can be improved on the basis of ensuring the accuracy of posture recognition. Furthermore, a human body posture estimation model is used to detect the key points of the object to be measured and multiple target key points are selected in combination with the initial posture for refined posture recognition, so that the posture recognition accuracy can be improved while saving the amount of posture recognition calculation; at the same time, the relevant vectors and the angles between the vectors can be calculated through the position information of the target key points, and the process of this refined calculation can further improve the posture recognition accuracy.

[0056] The following embodiment illustrates the process of analyzing the posture change trend in the current pressure monitoring process.

[0057] In one embodiment, in the current pressure monitoring process, the target postures of the above-mentioned object to be measured are not exactly the same at each moment; the above-mentioned data analysis module is also used to extract second pressure data belonging to the same target posture at different moments from the second pressure data, and determine the change trend of the abdominal pressure under the corresponding target posture according to the second pressure data of each target posture at different moments; the change trend of the abdominal pressure under each target posture is different; and, the change trend of the abdominal pressure under each target posture is compared, and the optimal posture of the object to be measured in the next pressure monitoring process is determined from each target posture.

[0058] Among them, in the current pressure monitoring process, the subject to be tested may change postures, and there may be a variety of different target postures. For example, the duration of the current pressure monitoring is 2 hours, the subject to be tested is in a 90-degree sitting posture within 0-5 minutes, and in a 180-degree standing posture within 6-10 minutes, and may change postures in the subsequent time, etc. The second pressure data belonging to the same target posture can be extracted from the second pressure data at each moment in the current pressure monitoring process, and then the second pressure data of the same target posture can be arranged in chronological order and curve fitted to obtain the change trend of the abdominal pressure under the target state.

[0059] The changing trends of abdominal pressure under different target postures are generally different. Therefore, here we can compare the changing trends of abdominal pressure corresponding to each target posture, select the optimal changing trend, and use the target posture corresponding to the optimal changing trend as the optimal posture in the next cycle / next pressure monitoring process.

[0060] When making a selection here, you can choose according to the following conditions, such as the stability of the changing trend, whether the second pressure data on the changing trend exceeds the pressure threshold range, etc.; for example, here you can choose the changing trend with the most stable changing trend and the second pressure data within the pressure threshold range as the optimal trend, and then obtain the corresponding optimal posture.

[0061] In this embodiment, the optimal posture of the object to be measured in the next pressure monitoring process is determined by comparing the changing trends of the abdominal pressure of different target postures in the current pressure monitoring process. This can ensure that the pressure data in the next pressure monitoring process is as close to the pressure threshold as possible, thereby improving the effect of pressure monitoring.

[0062] The following embodiment describes the process of analyzing whether the reason for the abnormality in the second pressure data is related to the target posture in the current pressure monitoring process.

[0063] In one embodiment, the above-mentioned data analysis module is specifically used to adjust the target posture of the object to be measured at the current moment, and detect whether the second pressure data at the subsequent moment is abnormal after the adjustment; if the second pressure data at the subsequent moment is not abnormal, it is determined that the reason why the second pressure data at the current moment is abnormal is related to the target posture at the current moment; if the second pressure data at the subsequent moment is still abnormal, it is determined that the reason why the second pressure data at the current moment is abnormal is related to the peritoneal dialysis fluid infusion or ultrafiltration volume of the object to be measured.

[0064] Among them, when the second pressure data at the current moment is abnormal (generally, the abdominal pressure is high), the target posture at the current moment can be adjusted, for example, the target posture at the current moment can be adjusted to a more appropriate posture (for example, when the abdominal pressure is too high, the posture can be adjusted to a posture with lower abdominal pressure), and then the abdominal pressure data under the adjusted posture can be continuously detected to see if there is an abnormality, that is, to detect whether the second pressure data at subsequent moments (which can be one moment or multiple moments) after the current moment is abnormal. If the second pressure data at the subsequent moments is not abnormal, it is determined that the reason why the second pressure data at the current moment is abnormal is related to its target posture.

[0065] In addition, if the second pressure data at the subsequent moment is still abnormal after the posture is adjusted (generally, the abdominal pressure is high), it is determined that the reason for the abnormality of the second pressure data at the current moment is irrelevant to the target posture, and may be related to the peritoneal dialysis fluid infusion or ultrafiltration volume of the subject to be tested, such as excessive infusion or excessive ultrafiltration. In addition, if the second pressure data at the current moment shows that the abdominal pressure is too low when the abnormality exists, the reason for the abnormality is that the peritoneal dialysis fluid infusion or ultrafiltration volume of the subject to be tested is too small.

[0066] For the above different abnormal reasons, the subsequent operations may be different. For example: if the abnormal reason is the posture of the subject to be tested, the subject to be tested is reminded to adjust the posture; if the abnormal reason is too much peritoneal dialysis fluid infusion, the medical staff is reminded to modify the prescription, and the appropriate infusion volume is recommended according to the monitored second pressure data; if the abnormal reason is too much ultrafiltration, the medical staff is reminded to modify the prescription, and the appropriate fluid replacement time is recommended according to the monitored second pressure data.

[0067] In this embodiment, when there is an abnormality in the second pressure data, it is first determined whether it is related to the posture of the object to be measured, and then it is determined whether it is due to other reasons when it is not related. In this way, the accuracy and efficiency of determining the cause of the abnormality in the pressure data can be improved through a multi-layer judgment method, thereby improving the accuracy and efficiency of the subsequent execution operations.

[0068] The following embodiment illustrates the process of issuing an alarm when the second pressure data is abnormal.

[0069] In one embodiment, the above-mentioned peritoneal pressure monitoring device for peritoneal dialysis may further include: an alarm module, which is used to compare the real-time second pressure data with a preset pressure threshold range, and when the second pressure data at any moment exceeds the pressure threshold range, determine that the second pressure data at any moment is abnormal, and output an alarm message; wherein the above-mentioned alarm message includes the reason why the second pressure data at any moment is abnormal and decision-making recommendation information determined based on the reason.

[0070] As mentioned above, in the real-time pressure monitoring process, the real-time annotated second pressure data can be compared with the pressure threshold range pre-set for the object to be measured, that is, to determine whether the second pressure data at each moment exceeds the pressure threshold range. When the second pressure data at any moment exceeds the upper limit of the pressure threshold range (i.e., greater than the upper limit), or exceeds the lower limit of the pressure threshold range (i.e., less than the lower limit), it is determined that the second pressure data at any moment is abnormal.

[0071] When it is determined that the second pressure data at any time is abnormal, the cause of the abnormality and the decision-making suggestion information corresponding to the cause of the abnormality (i.e., the above-mentioned subsequent operation) can also be determined according to the above method; then the second pressure data at any time is abnormal, the cause of the abnormality and the corresponding decision-making suggestion information can be output to the user / medical staff through alarm information, so as to perform corresponding operations in time. In addition, the above alarm information can be output in the form of voice, text, sound and light, etc.

[0072] Furthermore, when the second pressure data at any time is abnormal, different alarm messages can be output to distinguish between the two situations of exceeding the upper limit of the pressure threshold range and exceeding the lower limit of the pressure threshold range. For example, when the lower limit of the pressure threshold range is exceeded, a low abdominal pressure value reminder can be issued to the medical staff and the subject to be tested, and the medical staff is advised to increase the infusion volume and infusion time of the peritoneal dialysis fluid according to the actual situation.

[0073] In this embodiment, by outputting an alarm message when the second pressure data at any moment exceeds the pressure threshold range, it is convenient for medical staff and the subject to be tested to promptly know that there are abnormalities in the current pressure data and take corresponding operations in time to avoid abnormal situations and ensure the effectiveness of the treatment process.

[0074] The following embodiment illustrates the process of generating a user personalized treatment plan based on multiple pressure monitoring results.

[0075] In one embodiment, the peritoneal pressure monitoring device for peritoneal dialysis may also include: an auxiliary decision-making module, which is used to generate a personalized treatment plan corresponding to the subject to be tested based on the second pressure data of the subject to be tested in multiple pressure monitoring processes, the clinical treatment data of the subject to be tested, and the living habit data of the subject to be tested; the above-mentioned clinical treatment data includes the initial treatment plan and / or predicted treatment results.

[0076] Among them, in the long-term multiple pressure monitoring process of the subject to be tested, the second pressure data of each marked posture can be obtained, and the living habit data of the subject to be tested (such as sleep time, activity pattern, etc.) can be collected at the same time, and the initial treatment plan (such as treatment prescription) set by the doctor for the subject to be tested in advance and the treatment results predicted based on the initial treatment plan (such as dialysis adequacy, ultrafiltration volume, etc.) can also be obtained. Then, based on these data, the influence of the subject's activity pattern, living habits, and treatment prescription on the abdominal pressure and treatment results can be analyzed, and a comprehensive analysis can be performed to generate a personalized treatment plan for the subject to be tested, including living habits and treatment prescription recommendations. This personalized treatment plan, for example: (1) It is found that the abdominal pressure of the subject to be tested is generally low when sleeping at night, which may be related to the sleeping posture, and it is recommended to adjust the sleeping posture or mattress hardness; (2) It is found that in the sitting position at 90 degrees, the abdominal pressure reaches the maximum after 2 hours of dialysis each time, and the efficiency is significantly reduced or the risk of complications increases if dialysis is continued. When lying flat, it takes 3 hours for the abdominal pressure to reach the maximum. Therefore, it is recommended that medical staff adjust the dialysis time of the subject to be tested according to the body posture to improve the dialysis efficiency.

[0077] In this embodiment, by generating a corresponding personalized treatment plan based on the second pressure data, clinical treatment data, and living habit data in the multiple pressure monitoring processes of the subject to be tested, a treatment plan that is more suitable for the subject to be tested can be determined, which helps to optimize the treatment plan and improve the peritoneal dialysis treatment effect on the subject to be tested.

[0078] It can be seen from the description of the above embodiments that the technical solutions of the embodiments of the present invention have the following technical effects: Improved data accuracy: Through posture recognition, the interference of posture changes on abdominal pressure measurement is eliminated, making the data closer to the actual value.

[0079] Real-time monitoring and feedback: The abdominal pressure monitoring device for peritoneal dialysis can continuously and in real time monitor the abdominal pressure and patient posture, providing instant data feedback to medical staff.

[0080] Assisted decision making: Accurate data provides strong support for medical staff to formulate and adjust treatment plans, helping to improve treatment outcomes and prevent complications.

[0081] Enhanced patient self-management capabilities: By displaying abdominal pressure data and posture information in real time, patients can more intuitively understand their physical condition. At the same time, patients can adjust their treatment plans based on the system's reminders and suggestions, such as adjusting posture, controlling the amount and time of peritoneal dialysis fluid infusion, etc. This enhanced self-management capability not only reduces the burden on medical staff, but also improves patients' treatment participation and satisfaction.

[0082] Improved quality of life for patients: Timely intervention and personalized treatment can significantly reduce the incidence of complications associated with peritoneal dialysis. For example, high intra-abdominal pressure may cause symptoms such as abdominal discomfort and dyspnea, while low intra-abdominal pressure may lead to problems such as insufficient dialysis. The technical solution of the embodiment of the present invention can detect these problems in a timely manner and take corresponding measures, thereby reducing the occurrence of complications and improving the treatment effect of patients.

[0083] Reduce medical costs: Through timely monitoring and feedback, unnecessary medical interventions and complications can be reduced, thereby reducing medical costs. At the same time, by optimizing treatment decisions and personalized treatment management, treatment efficiency can be improved and medical costs can be further reduced.

[0084] The following is a description of the peritoneal pressure monitoring system for peritoneal dialysis provided in an embodiment of the present invention.

[0085] Figure 5 is a schematic diagram of the structure of the abdominal cavity pressure monitoring system for peritoneal dialysis provided by the present invention, see Figure 5 As shown, the system may include an image acquisition device 20 and the peritoneal pressure monitoring device 10 for peritoneal dialysis in the above embodiment; the above image acquisition device 20 is used to obtain the image to be tested of the object to be tested in real time, and transmit the image to be tested to the peritoneal pressure monitoring device 10 for peritoneal dialysis.

[0086] The image acquisition device 20 may be a camera, a video camera, or other acquisition device with a camera head, etc. The specific setting position may be set according to the actual situation, as long as the whole body or part of the body of the object to be measured can be captured.

[0087] For the processes of joint abdominal pressure monitoring, posture recognition, labeling, data analysis, etc. between the image acquisition device 20 and the abdominal pressure monitoring device 10 for peritoneal dialysis, please refer to the explanation in the above-mentioned embodiment of the abdominal pressure monitoring device 10 for peritoneal dialysis, which will not be repeated here.

[0088] In this embodiment, the peritoneal pressure monitoring system for peritoneal dialysis includes an image acquisition device and a peritoneal pressure monitoring device for peritoneal dialysis, wherein the image acquisition device can transmit the acquired image to the peritoneal pressure monitoring device for peritoneal dialysis for posture recognition, and the peritoneal pressure monitoring device for peritoneal dialysis includes a pressure monitoring module, a posture recognition module, a labeling module and a data analysis module, wherein the pressure monitoring module can monitor the peritoneal pressure of the object to be measured in real time during the current pressure monitoring process to obtain real-time first pressure data; the posture recognition module can identify the neutron state of the object to be measured in real time to determine the real-time target posture of the object to be measured; the labeling module can label the first pressure data at the corresponding moment according to the real-time target posture of the object to be measured to determine the labeled second pressure data; the data analysis module can analyze whether the cause of the abnormality is related to the target posture according to the second pressure data when there is an abnormality in the second pressure data. The abdominal pressure monitoring system for peritoneal dialysis of the present invention can identify the real-time posture of the object to be measured and mark the identified posture on the real-time pressure data. In this way, when the abdominal pressure is continuously monitored, the pressure data with the posture marked in real time can be used to quickly analyze whether the cause of the abnormality is related to the posture when there is an abnormality in the abdominal pressure, so that the abdominal pressure data of the object to be measured caused by posture interference can be well interpreted and can be used to guide subsequent diagnosis and treatment, thereby realizing the effective use and accurate analysis of the abdominal pressure data of the object to be measured.

[0089] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0090] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0091] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A peritoneal pressure monitoring device for peritoneal dialysis, characterized in that: include: A pressure monitoring module, used to monitor the abdominal pressure of the subject to be tested in real time during the current pressure monitoring process to obtain real-time first pressure data; A posture recognition module is used to recognize the posture of the object to be measured in real time and determine the real-time target posture of the object to be measured; A labeling module, used for labeling the first pressure data at a corresponding moment according to the real-time target posture of the object to be measured, and determining the labeled second pressure data; The data analysis module is used to analyze whether the cause of the abnormality is related to the target posture according to the second pressure data when the second pressure data is abnormal.

2. The peritoneal pressure monitoring device for peritoneal dialysis according to claim 1, characterized in that: The gesture recognition module is specifically used for Acquire the image to be tested of the object to be tested in real time, classify the posture of the object to be tested in the image to be tested, and determine the initial posture corresponding to the object to be tested; According to the initial posture and the image to be measured, the posture of the object to be measured is identified to determine the target posture corresponding to the object to be measured; The accuracy of the target posture is higher than the accuracy of the initial posture.

3. The peritoneal pressure monitoring device for peritoneal dialysis according to claim 2, characterized in that: The gesture recognition module is specifically used for Using a preset human posture estimation model to identify key points of the object to be measured in the image to be measured, and determining a plurality of key points corresponding to the object to be measured; Determining a plurality of target key points associated with the initial posture from the plurality of key points; The target posture of the object to be measured is determined according to the position information of each target key point.

4. The peritoneal pressure monitoring device for peritoneal dialysis according to claim 3, characterized in that: The initial posture includes any one of a sitting posture, a standing posture and a lying posture, the target key points include a hip key point, a shoulder key point and a knee key point, and the posture recognition module is specifically used for Calculate a first vector according to the position information of the hip key point and the position information of the shoulder key point; and calculate a second vector according to the position information of the hip key point and the position information of the knee key point; Calculating the angle between the first vector and the second vector, and determining the degree of waist bending of the object to be measured according to the angle; The target posture is determined according to the degree of waist bending.

5. The peritoneal pressure monitoring device for peritoneal dialysis according to any one of claims 2 to 4, characterized in that: The gesture recognition module is specifically used for Using a neural network to classify the posture of the object to be measured in the image to be measured, and determine the initial posture corresponding to the object to be measured; The neural network is trained based on a plurality of training images and the annotation posture corresponding to each training image, and the annotation postures corresponding to the training images are not completely the same.

6. The peritoneal pressure monitoring device for peritoneal dialysis according to any one of claims 1 to 4, characterized in that: In the current pressure monitoring process, the target posture of the object to be measured is not completely the same at each moment; The data analysis module is further used to extract the second pressure data belonging to the same target posture at different times from the second pressure data, and determine the change trend of the abdominal pressure under the corresponding target posture according to the second pressure data of each target posture at different times; the change trend of the abdominal pressure under each target posture is different; Furthermore, the changing trends of the abdominal cavity pressure under the target postures are compared, and the optimal posture of the object to be measured in the next pressure monitoring process is determined from the target postures.

7. The peritoneal pressure monitoring device for peritoneal dialysis according to any one of claims 1 to 4, characterized in that: The data analysis module is specifically used to adjust the target posture of the object to be measured at the current moment, and detect whether the second pressure data at the subsequent moment is abnormal after the adjustment; if the second pressure data at the subsequent moment is not abnormal, it is determined that the reason why the second pressure data at the current moment is abnormal is related to the target posture at the current moment; If the second pressure data at the subsequent moment is still abnormal, it is determined that the reason why the second pressure data at the current moment is abnormal is related to the peritoneal dialysis fluid infusion amount or ultrafiltration amount of the subject to be tested.

8. The peritoneal pressure monitoring device for peritoneal dialysis according to any one of claims 1 to 4, characterized in that: Also includes: an alarm module, configured to compare the second pressure data in real time with a preset pressure threshold range, and when the second pressure data at any moment exceeds the pressure threshold range, determine that the second pressure data at any moment is abnormal, and output an alarm message; The alarm information includes the reason why the second pressure data at any moment is abnormal and decision suggestion information determined based on the reason.

9. The peritoneal pressure monitoring device for peritoneal dialysis according to claim 8, characterized in that: Also includes: An auxiliary decision-making module is used to generate a personalized treatment plan corresponding to the subject to be tested based on the second pressure data of the subject to be tested in multiple pressure monitoring processes, the clinical treatment data of the subject to be tested, and the living habit data of the subject to be tested; the clinical treatment data includes an initial treatment plan and / or predicted treatment results.

10. A peritoneal pressure monitoring system for peritoneal dialysis, characterized in that: A device comprising an image acquisition device and a peritoneal pressure monitoring device for peritoneal dialysis according to any one of claims 1 to 9; The image acquisition device is used to acquire the image to be tested of the object to be tested in real time, and transmit the image to be tested to the peritoneal pressure monitoring device for peritoneal dialysis.

Images