Method and device for detecting dialyzer membrane leakage in continuous renal replacement therapy

By using light sources in four bands—blue, green, red, and infrared—and a backpropagation neural network in continuous renal replacement therapy, dialyzer leakage can be accurately detected, solving the problem of inaccurate leakage detection in existing technologies and improving the reliability and safety of the detection.

CN116577045BActive Publication Date: 2026-03-24GUANGDONG BIOLIGHT MEDITECH CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-04-18
Publication Date
2026-03-24

AI Technical Summary

Technical Problem

In continuous renal replacement therapy, the detection of blood leakage caused by dialyzer membrane rupture is difficult to perform accurately, which is prone to false alarms, affecting the treatment effect and endangering patient safety.

Method used

The system uses four light sources—blue, green, red, and infrared—to transmit light through the dialysate waste liquid. Combined with a backpropagation neural network, it calculates the blood concentration in the dialysate by eliminating differences in light absorption and color interference, thus achieving accurate blood leakage detection.

Benefits of technology

It enables accurate detection of dialyzer leakage, reduces false alarms, and improves the safety and reliability of treatment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116577045B_ABST
    Figure CN116577045B_ABST
Patent Text Reader

Abstract

The application discloses a dialyzer blood leakage detection method and device in continuous renal replacement therapy, an electronic equipment and a storage medium, and relates to the technical field of dialyzer blood leakage detection. The method comprises the following steps: emitting light sources of four wave bands of blue light, green light, red light and infrared light through a light emitting module, and making the light sources of the four wave bands pass through a dialysate waste liquid pipe; acquiring signals corresponding to the light sources of the four wave bands after passing through the dialysate waste liquid pipe through a light source receiving module; sampling the signals acquired by the light source receiving module, and sending the sampling data to a processing module, so that the processing module acquires Bb, Gg, Rr, IRir, Bt, Gt, Rt and IRt, and the processing module calculates the blood concentration of the dialysate waste liquid through a BP neural network. According to the dialyzer blood leakage detection method in continuous renal replacement therapy, the blood concentration of the dialysate waste liquid can be accurately detected, and the false alarm phenomenon is reduced.
Need to check novelty before this filing date? Find Prior Art

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of dialyzer blood leakage detection, in particular to a dialyzer blood leakage detection method and device in continuous renal replacement therapy, an electronic device and a storage medium. BACKGROUND

[0002] In continuous renal replacement therapy (CRRT), blood leakage into dialysate caused by dialyzer membrane rupture is an event that is difficult to absolutely avoid. Membrane rupture can cause blood loss in patients, thereby affecting treatment effectiveness, and even possibly endangering the safety of patients, leading to medical accidents and medical disputes. Therefore, accurately detecting whether dialyzer membrane rupture and blood leakage have occurred is of great significance for continuous renal replacement therapy. SUMMARY

[0003] The present application aims to at least solve one of the technical problems existing in the prior art. To this end, the present application provides a dialyzer blood leakage detection method and device in continuous renal replacement therapy, an electronic device and a storage medium, which can accurately detect dialyzer membrane rupture and blood leakage.

[0004] In one aspect, the dialyzer blood leakage detection method in continuous renal replacement therapy according to the present application embodiment comprises the following steps:

[0005] The light-emitting module emits light sources of four wavebands of blue light, green light, red light and infrared light respectively, and the light sources of the four wavebands pass through the dialysate waste liquid pipe;

[0006] The light source receiving module acquires signals corresponding to the light sources of the four wavebands after passing through the dialysate waste liquid pipe;

[0007] The signals acquired by the light source receiving module are sampled, and the sampling data are sent to the processing module, so that the processing module acquires a blue light initial value, a green light initial value, a red light initial value, an infrared light initial value, a blue light instantaneous value, a green light instantaneous value, a red light instantaneous value and an infrared light instantaneous value; wherein the blue light initial value, the green light initial value, the red light initial value and the infrared light initial value correspond to sampling data acquired before treatment, and the blue light instantaneous value, the green light instantaneous value, the red light instantaneous value and the infrared light instantaneous value correspond to sampling data acquired in real time during treatment;

[0008] The processing module calculates the blood concentration of dialysate waste liquid by BP neural network according to the blue light initial value, the green light initial value, the red light initial value, the infrared light initial value, the blue light instantaneous value, the green light instantaneous value, the red light instantaneous value and the infrared light instantaneous value.

[0009] According to some embodiments of the present application, the method further comprises the following steps:

[0010] When the blood concentration is greater than a preset value, the processing module controls the alarm module to perform an alarm action.

[0011] According to some embodiments of the present application, the BP neural network is trained by the following steps:

[0012] A plurality of simulated dialysis solutions corresponding to normal conditions and different blood leakage conditions are obtained;

[0013] The light emitting module emits light sources of four wave bands of blue light, green light, red light and infrared light respectively, and the light sources of the four wave bands pass through each simulated dialysis solution respectively;

[0014] The light source receiving module obtains signals corresponding to the light sources of the four wave bands after passing through the simulated dialysis solution;

[0015] The signals obtained by the light source receiving module are sampled, and the sampling data is sent to the processing module;

[0016] The processing module takes the sampling data as training data to train the weight matrix of the BP neural network.

[0017] On the other hand, according to the dialyzer blood leakage detection device in continuous renal replacement therapy according to the embodiments of the present application, comprising:

[0018] A light emitting module is arranged on one side of the dialysis liquid waste pipe, and the light emitting module is used to emit light sources of four wave bands of blue light, green light, red light and infrared light, and the light sources of the four wave bands pass through the dialysis liquid waste pipe;

[0019] A light source receiving module is arranged on the other side of the dialysis liquid waste pipe, and the light source receiving module is used to obtain signals corresponding to the light sources of the four wave bands after passing through the dialysis liquid waste pipe;

[0020] A sampling module is used to sample the signals obtained by the light source receiving module;

[0021] A processing module is used to obtain the sampling data of the sampling module, so as to obtain a blue light initial value, a green light initial value, a red light initial value, an infrared light initial value, a blue light instantaneous value, a green light instantaneous value, a red light instantaneous value and an infrared light instantaneous value, and calculate the blood concentration of the dialysis liquid waste by a BP neural network according to the blue light initial value, the green light initial value, the red light initial value, the infrared light initial value, the blue light instantaneous value, the green light instantaneous value, the red light instantaneous value and the infrared light instantaneous value.

[0022] The initial values ​​of blue light, green light, red light, and infrared light correspond to the sampling data obtained before treatment, while the instantaneous values ​​of blue light, green light, red light, and infrared light correspond to the sampling data obtained in real time during treatment.

[0023] According to some embodiments of the present invention, the apparatus further includes:

[0024] The driving module is used to drive the light-emitting module to emit a light source of a corresponding wavelength according to the command of the processing module.

[0025] According to some embodiments of the present invention, the apparatus further includes:

[0026] The alarm module is used to execute an alarm action when the blood concentration is greater than a preset value.

[0027] According to some embodiments of the present invention, the device further includes a host computer electrically connected to the processing module.

[0028] According to some embodiments of the present invention, the dialysis waste tube is made of a material that is transparent across the entire wavelength range.

[0029] On the other hand, an electronic device according to an embodiment of the present invention includes:

[0030] Memory, used to store program instructions;

[0031] The processor is used to call the program instructions stored in the memory and execute the dialyzer leakage detection method in continuous renal replacement therapy according to the obtained program instructions.

[0032] On the other hand, according to an embodiment of the present invention, the storage medium stores computer-executable instructions for causing a computer to perform the above-described method for detecting dialyzer leakage in continuous renal replacement therapy.

[0033] The method, apparatus, electronic device, and storage medium for detecting dialyzer leakage in continuous renal replacement therapy according to embodiments of the present invention have at least the following beneficial effects: A light source including four wavelengths—blue, green, red, and infrared—is used to transmit light through the dialysate waste liquid segment. Based on the different absorption rates of substances of different colors and diameters for different wavelengths of light, and by applying a backpropagation neural network to eliminate color interference in the dialysate waste liquid segment due to patient ion poisoning, the corresponding spatial envelope is found in the four-dimensional sampling space and mapped to the blood concentration in the dialysate, thereby achieving more accurate and intelligent leakage detection and reducing false alarms.

[0034] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0035] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which:

[0036] Figure 1 This is a flowchart of the steps in the dialyzer leakage detection method during continuous renal replacement therapy according to an embodiment of the present invention;

[0037] Figure 2 This is a schematic diagram of the structure of a dialyzer leakage detection device in continuous renal replacement therapy according to an embodiment of the present invention;

[0038] Figure 3 This is a schematic diagram of the operation process of the BP neural network in an embodiment of the present invention;

[0039] Figure 4 This is a schematic diagram of the specific process of the dialyzer leakage detection method in continuous renal replacement therapy according to an embodiment of the present invention;

[0040] Figure label:

[0041] The system includes a light-emitting module 100, a dialysis fluid waste pipe 200, a light source receiving module 300, a sampling module 400, a processing module 500, a driving module 600, and a host computer 700. Detailed Implementation

[0042] This section will describe in detail specific embodiments of the present invention. Preferred embodiments of the present invention are shown in the accompanying drawings. The purpose of the drawings is to supplement the textual description with graphics, so that people can intuitively and vividly understand each technical feature and overall technical solution of the present invention, but they should not be construed as limiting the scope of protection of the present invention.

[0043] In the description of this invention, "several" means one or more, "more than" means two or more, "greater than," "less than," and "exceeding" are understood to exclude the stated number, while "above," "below," and "within" are understood to include the stated number. The use of "first" and "second" in the description is merely for distinguishing technical features and should not be construed as indicating or implying relative importance, or implicitly indicating the number of indicated technical features, or implicitly indicating the order of the indicated technical features.

[0044] In the description of this invention, unless otherwise explicitly defined, terms such as "set up," "install," and "connect" should be interpreted broadly, and those skilled in the art can reasonably determine the specific meaning of the above terms in this invention in conjunction with the specific content of the technical solution.

[0045] Currently, the detection method for dialyzer membrane rupture and blood leakage typically employs optical projection detection. This method utilizes the different absorption rates of large molecules and cells in the blood at different wavelengths of light, setting an attenuation ratio of transmitted light flux to assess the presence of blood leakage in the dialysate waste section. This detection method, based on a set attenuation ratio, can only determine whether a predetermined leakage threshold has been reached; it cannot calculate the concentration of leaked blood in the dialysate based on the light attenuation. Furthermore, when color interference exists in the dialysate waste section, this method struggles to filter out color interference, resulting in low detection accuracy and a high likelihood of false alarms. This method is adequate for general hemodialysis treatment applications because in ordinary hemodialysis, the detoxification molecules are mostly small-molecule toxins from uremia patients, and the color interference of toxins in the dialysate waste is relatively small and uniform, thus the traditional detection method is sufficient. This method only triggers an alarm when the alarm concentration threshold is reached and does not reflect the actual leakage concentration in real time. However, during continuous renal replacement therapy, the dialysis waste fluid contains toxic ions with colors that differ greatly from blood. The color of the dialysis waste fluid can cover the spectrum from red to purple. If traditional detection methods are used, false alarms may occur due to color interference.

[0046] Therefore, on the one hand, such as Figure 1 As shown in the figure, this invention provides a method for detecting dialyzer leakage in continuous renal replacement therapy, comprising the following steps:

[0047] Step S100: The light-emitting module 100 emits light sources of four wavelengths: blue light, green light, red light and infrared light, and the light sources of the four wavelengths pass through the dialysis waste liquid pipe 200 respectively.

[0048] Step S200: The light source receiving module 300 acquires the signals corresponding to the four light sources after passing through the dialysis waste liquid tube 200;

[0049] Step S300: Sample the signal acquired by the light source receiving module 300 and send the sampled data to the processing module 500, so that the processing module 500 acquires the initial value of blue light Bb, the initial value of green light Gg, the initial value of red light Rr, the initial value of infrared light IRir, the instantaneous value of blue light Bt, the instantaneous value of green light Gt, the instantaneous value of red light Rt, and the instantaneous value of infrared light IRt; wherein, Bb, Gg, Rr, and IRir correspond to the sampled data acquired before treatment, and Bt, Gt, Rt, and IRt correspond to the sampled data acquired in real time during treatment;

[0050] Step S400: The processing module 500 calculates the blood concentration of the dialysis waste liquid using a BP (back propagation) neural network based on the initial values ​​of blue light (Bb), green light (Gg), red light (Rr), infrared light (IRir), instantaneous values ​​of blue light (Bt), green light (Gt), red light (Rt), and infrared light (IRt).

[0051] Specifically, such as Figure 2 As shown, the light-emitting module 100 and the light source receiving module 300 are respectively disposed on both sides of the dialysis waste pipe 200; wherein, the light-emitting module 100 includes multiple light-emitting diodes capable of emitting four different wavelengths of light: blue light, green light, red light and infrared light; correspondingly, the light source receiving module 300 includes multiple receiving sensors for receiving the above four light sources.

[0052] In this example, the processing module 500 uses an MCU, but it can also be any other processor with control and computation functions. A driver module 600 is also provided between the processing module 500 and the light-emitting module 100. The processing module 500 drives the light-emitting module 100 to emit light of the corresponding wavelength through the driver module 600. The light emitted by the light-emitting module 100 passes through the dialysate waste tube 200 and is received by the light source receiving module 300. The sampling module 400 then processes and samples the data and sends it to the processing module 500. This allows the processing module 500 to collect the digital sample values ​​corresponding to each wavelength of the light source and calculate the blood concentration in the dialysate waste using a BP neural network. This allows it to determine whether dialyzer membrane rupture and blood leakage have occurred. When the blood concentration exceeds a preset value, it indicates that blood leakage has occurred. In this case, the processing module 500 will control the alarm module to execute an alarm action.

[0053] The following is for reference. Figure 3 and Figure 4 This invention provides a detailed description of the specific execution process of the dialyzer leakage detection method in continuous renal replacement therapy according to embodiments of the present invention.

[0054] In practical application and operation, the operator first completes all pre-treatment preparations, confirming that the tubing is installed in place and that the dialysis fluid is properly pre-filled; when the processing module 500 receives the start command from the host computer 700, it will proceed according to... Figure 4 The flowchart shown below will guide you through the following steps:

[0055] Step 1: Perform a self-test on the entire machine. If the self-test fails, the process ends and the processing module 500 reports the error to the host computer 700. If the self-test is normal, proceed to Step 2.

[0056] Step 2: The processing module 500 controls the driving module 600 to drive the light-emitting module 100, so that the light-emitting module 100 emits light sources of four wavelengths: blue light, green light, red light and infrared light, and each light source illuminates for a duration in turn. The specific duration must ensure that the light source receiving module 300 can normally collect a value. During this period, the light source will pass through the dialysis fluid waste pipe 200 and be received by the light source receiving module 300.

[0057] Step 3: The sampling module 400 samples the signal received by the light source receiving module 300 and sends the sampled data to the processing module 500, so that the processing module 500 sequentially receives the digital sampled values ​​of the light source in the corresponding band, namely Rr, Gg, Bb and IRir (Rr, Gg, Bb and IRir correspond to the signals of the four light sources after passing through the dialysis fluid before the start of treatment), uses Rr, Gg, Bb and IRir as initial values ​​and stores them, reports to the host computer 700 to complete the sampling and storage of the initial values, and the host computer 700 begins the formal treatment process;

[0058] Step 4: During treatment, repeat steps 2 and 3, following the same steps as for acquiring Rr, Gg, Bb, and IRir, so that the processing module 500 can acquire the instantaneous values ​​Rt, Gt, Bt, and IRt (Rt, Gt, Bt, and IRt correspond to the signals after the four light sources pass through the dialysis waste liquid generated during treatment) in real time during the treatment process, and use this as one round of sampling. After one round of sampling is completed, the processing module 500 pushes the eight sampled digital values ​​of Rr, Gg, Bb, IRir, Rt, Gt, Bt, and IRt together into the input as shown in the figure. Figure 3 The BP neural network shown is used to perform calculations to obtain the real-time blood concentration Yt of the dialysate corresponding to the sampling values ​​in this round;

[0059] Step 5: Compare the calculated real-time blood concentration Yt with the standard alarm blood leakage concentration Y. If Yt > Y, upload the data to the host computer 700 to trigger a blood leakage alarm and terminate the operation. If Yt ≤ Y, return to step 4 and proceed with the next round of sampling normally to obtain instantaneous values ​​Rt+1, Gt+1, Bt+1, and IRt+1. This cycle continues until the treatment ends, obtaining the real-time blood concentration of the dialysate in each round of sampling.

[0060] In the example of this invention, Figure 3 The BP neural network shown is trained through the following steps:

[0061] Obtain multiple simulated dialysis solutions corresponding to normal conditions and different blood leakage conditions;

[0062] The light-emitting module 100 emits light in four wavelengths: blue, green, red, and infrared, and the light in each wavelength passes through each simulated dialysis solution.

[0063] The light source receiving module 300 acquires the signals corresponding to the four wavebands of the light source after passing through the simulated dialysis solution;

[0064] The signal acquired by the light source receiving module 300 is sampled, and the sampled data is sent to the processing module 500;

[0065] The processing module 500 uses the sampled data as training data to train the weight matrix of the BP neural network.

[0066] Specifically, in practical applications, simulated dialysis solutions with different blood concentrations can be artificially prepared to simulate dialysis waste fluid from actual blood leakage. Alternatively, sensor data collected from various leakage scenarios in clinical practice, including situations with various color interferences, can be used to collect normal values ​​of Rr, Gg, Bb, and IRir, and instantaneous values ​​of Rt, Gt, Bt, and IRt at different leakage concentrations. These collected values ​​are then used as training data to train a backpropagation (BP) neural network. This training produces a weight matrix that can stably eliminate various toxin and color interferences present in CRRT treatment and map Rr, Gg, Bb, IRir, Rt, Gt, Bt, and IRt to actual blood concentrations. During actual blood leakage detection, the blood concentration in the dialysis waste fluid can be obtained by multiplying the vectors of Rr, Gg, Bb, IRir, Rt, Gt, Bt, and IRt with the weight matrix.

[0067] The dialyzer leakage detection method in continuous renal replacement therapy (CRRT) according to embodiments of the present invention employs a light source including four wavelengths: blue, green, red, and infrared light. This light is transmitted through the dialysate waste liquid. Based on the different absorption rates of substances of different colors and diameters for different wavelengths of light, and by applying a backpropagation (BP) neural network to eliminate color interference in the dialysate waste liquid due to patient ion poisoning, the corresponding spatial envelope is found in a four-dimensional sampling space and mapped to the leakage concentration in the dialysate. This achieves more accurate and intelligent leakage detection, reducing false alarms. While infrared light, with its longer wavelength, is less sensitive to leakage components in the waste liquid than shorter wavelengths like blue and green, it is also less sensitive to color interference. The impact of color interference on infrared light is less than that of leakage components in the waste liquid. Therefore, using infrared light as one of the judgment factors for eliminating color interference and detecting leakage in CRRT treatment can reduce the probability of false alarms in CRRT applications. By employing a backpropagation (BP) neural network, leveraging the advantages of multi-layer neural networks in nonlinear mapping, and replacing manual fitting with computer-trained weight matrices to find the spatial envelope corresponding to the light flux of each color and the blood leakage concentration in a multi-dimensional space, the mapping relationship can be more accurate and complex. The collected Rr, Gg, Bb, IRir, Rt, Gt, Bt, and IRt can be mapped to the blood concentration in the detected waste liquid. Regardless of whether the blood concentration in the waste liquid has not reached or exceeded the alarm concentration line, it can be visualized in real time, providing the machine user with more intuitive data.

[0068] On the other hand, such as Figure 2 As shown in the embodiments of the present invention, a dialyzer leakage detection device for continuous renal replacement therapy is also proposed, the device comprising:

[0069] The light-emitting module 100 is disposed on one side of the dialysis waste liquid pipe 200. The light-emitting module 100 is used to emit light sources of four wavelengths: blue light, green light, red light and infrared light, and to allow the light sources of the four wavelengths to pass through the dialysis waste liquid pipe 200.

[0070] The light source receiving module 300 is located on the other side of the dialysate waste pipe 200. The light source receiving module 300 is used to acquire the signals corresponding to the four light sources after passing through the dialysate waste pipe 200.

[0071] The sampling module 400 is used to sample the signal acquired by the light source receiving module 300;

[0072] The processing module 500 is used to acquire the sampling data from the sampling module 400, thereby obtaining the initial values ​​of blue light (Bb), green light (Gg), red light (Rr), infrared light (IRir), instantaneous values ​​of blue light (Bt), green light (Gt), red light (Rt), and infrared light (IRt). Based on Bb, Gg, Rr, IRir, Bt, Gt, Rt, and IRt, the blood concentration Yt of the dialysis waste liquid is calculated using a BP neural network.

[0073] Among them, the initial values ​​of blue light (Bb), green light (Gg), red light (Rr), and infrared light (IRir) correspond to the sampling data obtained before treatment, while the instantaneous values ​​of blue light (Bt), green light (Gt), red light (Rt), and infrared light (IRt) correspond to the sampling data obtained in real time during treatment.

[0074] The dialysis fluid waste tube 200 uses a full-band light-transmitting material to ensure that the blue, green, red, and infrared light emitted by the light source can all pass through the dialysis fluid waste tube 200 and be received by the light source receiving module 300.

[0075] Furthermore, in this example, the dialyzer leakage detection device in continuous renal replacement therapy also includes a drive module 600, which drives the light-emitting module 100 to emit a light source of a corresponding wavelength according to the command of the processing module 500. It should be noted that the drive module 600 can adopt existing common drive circuits, which are well known to those skilled in the art, so the detailed structure of the drive module 600 will not be described here.

[0076] Furthermore, in this example, the dialyzer leakage detection device in continuous renal replacement therapy also includes a host computer 700 electrically connected to the processing module 500. The host computer 700 is used to control the operation of the entire machine during the treatment process and to interact with the processing module 500. The data processed by the processing module 500 can be uploaded to the host computer 700 in real time for display, allowing personnel to intuitively observe the blood concentration in the dialysate waste fluid. In addition, alarm information can also be displayed on the host computer 700.

[0077] Furthermore, in this example, the dialyzer leakage detection device in continuous renal replacement therapy also includes an alarm module. The alarm module is used to trigger an alarm when the blood concentration Yt exceeds a preset value Y. The alarm module can display alarm information on a host computer 700, or it can use an audible and visual alarm or indicator lights to trigger an alarm.

[0078] The dialyzer leakage detection device for continuous renal replacement therapy according to an embodiment of the present invention is used to perform the dialyzer leakage detection method for continuous renal replacement therapy described in the above-described embodiments. The device uses a light source including four wavelengths: blue light, green light, red light, and infrared light, which transmits the dialysate waste liquid. Based on the different absorption amounts of substances of different colors and diameters for different wavelengths of light, and by applying a backpropagation neural network to eliminate color interference in the dialysate waste liquid due to ion poisoning by the patient, the device finds the corresponding spatial envelope in the four-dimensional sampling space and maps the leakage concentration in the dialysate, thereby achieving more accurate and intelligent leakage detection and reducing false alarms.

[0079] It should be noted that the specific functions implemented in this device embodiment are the same as those in the above method embodiment, and the beneficial effects achieved are also the same as those achieved in the above method embodiment.

[0080] On the other hand, embodiments of the present invention also provide an electronic device comprising:

[0081] Memory, used to store program instructions;

[0082] The processor is used to call the program instructions stored in the memory and execute the dialyzer leakage detection method in continuous renal replacement therapy according to the obtained program instructions.

[0083] On the other hand, embodiments of the present invention also propose a storage medium storing computer-executable instructions for causing a computer to execute the above-described method for detecting dialyzer leakage in continuous renal replacement therapy.

[0084] Although specific embodiments are described herein, those skilled in the art will recognize that many other modifications or alternative embodiments are also within the scope of this disclosure. For example, any of the functions and / or processing capabilities described in connection with a particular device or component can be performed by any other device or component. Furthermore, while various exemplary embodiments and architectures have been described according to embodiments of this disclosure, those skilled in the art will recognize that many other modifications to the exemplary embodiments and architectures described herein are also within the scope of this disclosure.

[0085] The foregoing description, with reference to block diagrams and flowcharts of systems, methods, systems, and / or computer program products according to exemplary embodiments, has described certain aspects of this disclosure. It should be understood that one or more blocks in the block diagrams and flowcharts, as well as combinations of blocks in the block diagrams and flowcharts, can be implemented by executing computer-executable program instructions, respectively. Similarly, according to some embodiments, some blocks in the block diagrams and flowcharts may not need to be executed in the order shown, or may not all need to be executed. Furthermore, additional components and / or operations beyond those shown in the blocks in the block diagrams and flowcharts may exist in some embodiments.

[0086] Therefore, blocks in block diagrams and flowcharts support combinations of means for performing a specified function, combinations of elements or steps for performing a specified function, and program instruction means for performing a specified function. It should also be understood that each block in a block diagram and flowchart, and combinations of blocks in block diagrams and flowcharts, can be implemented by a dedicated hardware computer system or a combination of dedicated hardware and computer instructions that performs a specific function, element, or step.

[0087] The program modules, applications, etc., described herein may include one or more software components, including, for example, software objects, methods, data structures, etc. Each such software component may include computer-executable instructions that, in response to execution, cause at least a portion of the functionality described herein (e.g., one or more operations of the exemplary methods described herein) to be performed.

[0088] Software components can be coded using any of a variety of programming languages. An exemplary programming language could be a low-level programming language, such as assembly language associated with a specific hardware architecture and / or operating system platform. Software components including assembly language instructions may need to be converted into executable machine code by an assembler before being executed by the hardware architecture and / or platform. Another exemplary programming language could be a higher-level programming language that is portable across multiple architectures. Software components including higher-level programming languages ​​may need to be converted into an intermediate representation by an interpreter or compiler before execution. Other examples of programming languages ​​include, but are not limited to, macro languages, shell or command languages, job control languages, scripting languages, database query or search languages, or report writing languages. In one or more exemplary embodiments, a software component containing instructions from one of the above-described programming language examples can be executed directly by the operating system or other software components without first being converted into another form.

[0089] Software components can be stored as files or other data storage structures. Software components of similar type or related function can be stored together in a specific directory, folder, or library. Software components can be static (e.g., pre-defined or fixed) or dynamic (e.g., created or modified at runtime).

[0090] The embodiments of the present invention have been described in detail above with reference to the accompanying drawings. However, the present invention is not limited to the above embodiments. Within the scope of knowledge possessed by those skilled in the art, various changes can be made without departing from the spirit of the present invention.

Claims

1. A method for detecting dialyzer leakage in continuous renal replacement therapy, characterized in that, Includes the following steps: The light-emitting module emits light in four wavelengths: blue, green, red, and infrared, and the light in these four wavelengths passes through the dialysis waste liquid pipe. The light source receiving module acquires the signals corresponding to the four light sources after passing through the dialysis waste liquid tube; The signal acquired by the light source receiving module is sampled, and the sampled data is sent to the processing module, so that the processing module obtains the initial values ​​of blue light, green light, red light, and infrared light, as well as the instantaneous values ​​of blue light, green light, red light, and infrared light. The initial values ​​of blue light, green light, red light, and infrared light correspond to the sampled data acquired before treatment, while the instantaneous values ​​of blue light, green light, red light, and infrared light correspond to the sampled data acquired in real time during treatment. The processing module calculates the blood concentration in the dialysis waste fluid using a BP neural network based on the initial values ​​of blue light, green light, red light, and infrared light, as well as the instantaneous values ​​of blue light, green light, red light, and infrared light. The BP neural network is then used to eliminate color interference in the dialysis waste fluid segment, and the corresponding spatial envelope is located in the four-dimensional sampling space and mapped to represent the blood concentration in the dialysis fluid.

2. The method for detecting dialyzer leakage in continuous renal replacement therapy according to claim 1, characterized in that, The method further includes the following steps: When the blood concentration is greater than a preset value, the processing module controls the alarm module to perform an alarm action.

3. The method for detecting dialyzer leakage in continuous renal replacement therapy according to claim 1, characterized in that, The BP neural network is trained through the following steps: Obtain multiple simulated dialysis solutions corresponding to normal conditions and different blood leakage scenarios; The light-emitting module emits light in four wavelengths: blue, green, red, and infrared, and the light in each wavelength passes through each of the simulated dialysis solutions. The light source receiving module acquires the signals corresponding to the four wavebands of the light source after passing through the simulated dialysis solution; The signal acquired by the light source receiving module is sampled, and the sampled data is sent to the processing module; The processing module uses the sampled data as training data to train the weight matrix of the BP neural network.

4. A dialyzer leakage detection device for continuous renal replacement therapy, characterized in that, include: A light-emitting module is disposed on one side of the dialysis waste liquid tube. The light-emitting module is used to emit light sources of four wavelengths: blue light, green light, red light and infrared light, and to allow the light sources of the four wavelengths to pass through the dialysis waste liquid tube. A light source receiving module is located on the other side of the dialysis fluid waste tube. The light source receiving module is used to acquire the signals corresponding to the four light sources after passing through the dialysis fluid waste tube. The sampling module is used to sample the signal acquired by the light source receiving module; The processing module is used to acquire the sampling data from the sampling module, thereby obtaining the initial values ​​of blue light, green light, red light, and infrared light, as well as the instantaneous values ​​of blue light, green light, red light, and infrared light. Based on these initial values, the blood concentration in the dialysis waste liquid is calculated using a BP neural network. The BP neural network is used to eliminate color interference in the dialysis waste liquid segment, and the corresponding spatial envelope is found in the four-dimensional sampling space and mapped to the blood concentration in the dialysis fluid. The initial values ​​of blue light, green light, red light, and infrared light correspond to the sampling data obtained before treatment, while the instantaneous values ​​of blue light, green light, red light, and infrared light correspond to the sampling data obtained in real time during treatment.

5. The dialyzer leakage detection device for continuous renal replacement therapy according to claim 4, characterized in that, The device further includes: The driving module is used to drive the light-emitting module to emit a light source of a corresponding wavelength according to the command of the processing module.

6. The dialyzer leakage detection device for continuous renal replacement therapy according to claim 4, characterized in that, The device further includes: The alarm module is used to execute an alarm action when the blood concentration is greater than a preset value.

7. The dialyzer leakage detection device for continuous renal replacement therapy according to claim 4, characterized in that, The device also includes a host computer electrically connected to the processing module.

8. The dialyzer leakage detection device for continuous renal replacement therapy according to claim 4, characterized in that, The dialysis waste liquid tube is made of a material that is transparent across the entire wavelength range.

9. An electronic device, characterized in that, include: Memory, used to store program instructions; A processor is configured to call program instructions stored in the memory and execute the dialyzer leakage detection method in continuous renal replacement therapy according to any one of claims 1-3.

10. A storage medium, characterized in that, The storage medium stores computer-executable instructions for causing a computer to perform the dialyzer leakage detection method in continuous renal replacement therapy according to any one of claims 1-3.

Citation Information

Patent Citations

  • Optical sensor, method of measuring optical signal, and apparatus for estimating blood concentration

    CN111134688A

  • Digital blood leakage sensor

    CN111442882A