Wireless urine oxygen partial pressure monitoring device and monitoring method

Abstract

The invention discloses a wireless urine oxygen partial pressure monitoring device and method. The monitoring device comprises a multi-cavity catheter, a temperature sensor, an optical fiber oxygen sensitive sensor, a flow sensor, a main control circuit, a wireless data receiving and transmitting module, an intelligent terminal and a urine bag. The monitoring method comprises the following steps: installing the monitoring device; collecting data; establishing a prediction model and carrying out training and verification; model prediction and result output; the monitoring device is externally arranged, the risk of damage to the bladder of a patient does not need to be considered, a temperature sensor can be easily introduced, whether the kidney is infected or has other abnormal conditions or not is judged through urine temperature assistance, a flow sensor is introduced, the urination capacity of the kidney is monitored, and on the basis of the urine oxygen partial pressure index in combination with the flow sensor, the monitoring accuracy is improved. And through multi-parameter comprehensive analysis, the degree and the property of the renal injury are evaluated more accurately.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical devices, and in particular relates to a wireless urine oxygen partial pressure monitoring device and a monitoring method. Background Art

[0002] Acute kidney injury (AKI) is a clinical syndrome in which renal function decreases sharply in a short period of time due to damage to renal structure or function. Its pathogenesis is complex, with high morbidity and mortality. The treatment of AKI mainly includes symptomatic, supportive and renal replacement therapy. There is no effective treatment to promote or accelerate renal recovery. Existing methods strive to identify people at high risk of AKI, identify AKI in the early stages and make treatment plans to prevent progression to more serious stages. At present, the clinical diagnosis of AKI usually adopts the AKI diagnostic criteria established in the Kidney Disease Improving Global Outcomes (KDIGO) acute kidney injury guidelines, that is, the serum creatinine level increases by ≥0.3 mg / dL (≥26.5 μmol / L) within 48 hours or exceeds 1.5 times the baseline value or more, and it is clear or inferred that the above situation occurs within 7 days; or the urine volume is <0.5 mL / (kg·h) for 6 hours, which can predict the risk of AKI. However, these two tests are time-consuming and usually lead to delayed diagnosis results. In addition, an extracorporeal circulation of biomarkers can be established to assist in diagnosis, but this method requires expensive diagnostic equipment and is time-consuming.

[0003] Ischemia-reperfusion injury (IRI) is one of the main causes of acute kidney injury (AKI). Ischemia-reperfusion injury can cause hypoxia and oxidative stress in the donor kidney, which can further trigger a series of cell and tissue damage, such as lipid peroxidation of cell membranes, activation of inflammatory responses, and apoptosis. Studies have reported that when renal injury during reperfusion has a significant heterogeneous response, the effect is most obvious at the cortical medullary junction, and the limited tissue oxygen supply and high oxygen demand in the medulla are considered to be the main reasons for the kidney's susceptibility to acute ischemic injury. In the absence of other confounding factors, the oxygen partial pressure in urine is a good and almost immediate substitute for the oxygen partial pressure in the renal medulla. The basis for this is that the rectus vessels are a network of post-glomerular peritubular capillaries located in the medulla close to the urinary collecting ducts, and when urine is first discharged, the urine oxygen partial pressure is similar to that in the renal medulla.

[0004] Based on the above analysis, continuous urine oxygen partial pressure measurement can be used as a real-time monitoring method for renal hypoxia and injury risk. Real-time monitoring of oxygen in urine can help evaluate the oxygenation status of tissues during donor renal ischemia and reperfusion. It has been reported that polarographic electrodes are placed in the bladder to measure urine oxygen partial pressure, thereby monitoring the patient's postoperative AKI risk. However, installing a detection probe in the bladder not only increases the economic burden on the patient, but also easily increases the risk of bladder injury, and only a single urine oxygen partial pressure indicator cannot fully evaluate the health of the kidneys. Based on the problems existing in the prior art, it is necessary to propose a wireless urine oxygen partial pressure monitoring device and monitoring method. Summary of the invention

[0005] The present invention provides a wireless urine oxygen partial pressure monitoring device and a monitoring method thereof, so as to solve the problem that the polarographic electrode is placed in the bladder to measure the urine oxygen partial pressure, which has a high cost and a risk of damaging the patient's bladder.

[0006] To solve the above problems, the technical solution provided by the present invention is as follows:

[0007] The embodiment of the present invention provides a wireless urine oxygen partial pressure monitoring device, comprising a multi-lumen urinary catheter (3), a temperature sensor (4), an optical fiber oxygen sensitive sensor (5), a flow sensor (6), a main control circuit (7), a wireless data transceiver module (8), an intelligent terminal (9) and a urine bag (10); the multi-lumen urinary catheter (3) comprises a urine storage chamber (31), and the urine storage chamber (31) is provided with a left joint (32), three top joints (33) and a right joint (34); the left joint (32) is connected to the bladder of a patient (1) through a first urinary catheter (21), and the right joint (34) is connected to the urine bag (10) through a second urinary catheter (22);

[0008] One end of the temperature sensor (4) is connected to the urine storage chamber (31) through a first top connector (33), and the other end is connected to the main control circuit (7) through a data line; the optical fiber oxygen sensitive sensor (5) comprises an optical fiber oxygen sensitive sensing probe (51) and a Y-type optical fiber (53) connected through an SMA interface (52); the optical fiber oxygen sensitive sensing probe (51) is connected to the urine storage chamber (31) through a second top connector (33); the Y-type optical fiber (53) is connected to the main control circuit (7); one end of the flow sensor (6) is connected to the urine storage chamber (31) through a third top connector (33), and the other end is connected to the main control circuit (7) through a data line; the wireless data transceiver module (8) is connected to the main control circuit (7), and is also connected to the intelligent terminal (9), and the intelligent terminal (9) comprises a terminal processor (91) and a user interface (92);

[0009] The Y-shaped optical fiber (53) is connected to a blue light signal transmitting port (54) after one branch, and is connected to a fluorescent signal receiving port (55) after another branch of the Y-shaped optical fiber (53); the main control circuit (7) comprises a filter (74), a photoelectric conversion circuit (75), a phase-locked amplifier circuit (76), an analog-to-digital conversion circuit (77), an MCU chip (71), a signal generating circuit (72), and a blue light LED (73) which are connected in sequence; the blue light LED (73) is connected to the blue light signal transmitting port (54), and the filter (74) is connected to the fluorescent signal receiving port (55); the photoelectric conversion circuit (75) is connected to the MCU chip (71), and the MCU chip (71) is also connected to a wireless data transceiver circuit (78); and the signal generating circuit (72) is also connected to the phase-locked amplifier circuit (76).

[0010] In an optional embodiment of the present invention, the phase-locked amplifier circuit (76) comprises an AD630 modulation circuit (763), a low-pass filter circuit (764) and a DC bias circuit (765) which are connected in sequence; the DC bias circuit (765) is connected to the analog-to-digital conversion circuit (77); the AD630 modulation circuit (763) is connected to the signal processing circuit (724) of the signal generating circuit (72), and the signal processing circuit (724) is also connected to the blue light LED (73) and the MCU chip (71), respectively.

[0011] The embodiment of the present invention further provides a wireless urine oxygen partial pressure monitoring method, which is implemented by using a wireless urine oxygen partial pressure monitoring device of the above embodiment, and includes the following steps:

[0012] Step S1, installing the wireless urine oxygen partial pressure monitoring device, connecting the circuit, and then debugging to ensure that the circuit is correct and the signal transmission is normal;

[0013] Step S2, data collection: After processing the sensing signal using the intelligent terminal (9), the urine oxygen partial pressure monitored by the optical fiber oxygen sensitive sensor (5), the urine temperature monitored by the temperature sensor (4), and the urine flow rate monitored by the flow sensor (6) can be directly read;

[0014] Step S3, establishing a prediction model and performing training and verification: using the Logistic regression analysis method, constructing a big data analysis model for predicting the probability of AKI in patients, training and verifying the model so that the model can analyze and process the patient data collected by the wireless urine oxygen partial pressure monitoring device, and give the probability of AKI in patients;

[0015] Step S4, model prediction and result output: The patient data collected in step S2 is sent to the big data analysis and prediction model trained in step S3 in real time to evaluate the risk of AKI in the current patient, that is, the monitoring data is predicted using the trained big data analysis and prediction model.

[0016] In an optional embodiment of the present invention, in step S1, the bladder of the patient (1) is connected to the left connector (32) of the multi-lumen urinary catheter (3) through the first urinary catheter (21) to ensure that the bladder of the patient (1) is connected to the urine storage chamber (31), and then the other end of the multi-lumen urinary catheter (3) is connected to the urine bag (10) through the second urinary catheter (22);

[0017] A temperature sensor (4), an optical fiber oxygen sensitive sensor (5), and a flow sensor (6) are installed; and the three are connected to a main control circuit (7); a wireless data transceiver module (8) is integrated on the main control circuit (7); and the wireless data transceiver module (8) is connected to a debugging intelligent terminal (9) through wireless communication.

[0018] In an optional embodiment of the present invention, the optical fiber oxygen sensitive sensor (5) in step S2 uses the fluorescence quenching effect to detect the change in oxygen concentration. This process is described using the Stern-Volmer equation, as shown in formula (1):

[0019] In the formula: I0 is the initial intensity of the fluorescence signal emitted by the optical fiber oxygen sensitive sensor probe (51) in an oxygen-free environment; I is the fluorescence signal intensity after fluorescence quenching of the optical fiber oxygen sensitive sensor probe (51); τ0 is the initial lifetime of the fluorescence signal emitted by the optical fiber oxygen sensitive sensor probe (51) in an oxygen-free environment; τ is the fluorescence signal lifetime after fluorescence quenching of the optical fiber oxygen sensitive sensor probe (51); K is the Stern-Volmer constant; x9O2) is the oxygen concentration.

[0020] In an optional embodiment of the present invention, step S3 specifically includes the following steps:

[0021] Step S31, data pre-processing: read the collected data of the patient's urine oxygen partial pressure level, urine temperature, urine flow rate, etc. and analyze and process them, and remove abnormal data; manually enter the patient's age, gender, weight, historical medical condition, AKI occurrence, etc. through the intelligent terminal; use the above data as a data set, and use 80% of the patient data in the data set as a training set and 20% of the patient data as a test set;

[0022] Step S32, constructing a connection function: using the sigmoid function to construct a connection function, mapping the binary variable of whether the patient has AKI to a continuous variable, and constructing a multivariate ordered logistic regression model fitting function f(z), the expression of which is as follows:

[0023] The calculated value of f9z) is the probability of the patient developing AKI calculated by the model, and Z is the situation of the patient developing AKI. When Z=1, it means that the patient has AKI, and when Z=0, it means that the patient does not have AKI. In formula (2), z is the multivariate linear regression fitting function, and the expression is as follows: z=w1x1+w2x2+w3x3+b(3); In the formula: b is the intercept; x1, x2, and x3 are the patient's urine oxygen partial pressure data, urine temperature data, and urine flow rate data, respectively; w1, w2, and w3 are the corresponding independent variables x i weights; let W = [w1,w2,w3],X = [x1,x2,x3], we get Z = WX T +b;

[0024] Step S33, deriving the probability of whether AKI occurs by the model: deriving the probability of whether AKI occurs by the model through fitting function f(z() of the multivariate ordered logistic regression model, which is expressed as follows:

[0025]

[0026] Formula (4) represents the probability of AKI occurring predicted by the model; Formula (5) represents the probability of AKI not occurring predicted by the model;

[0027] According to formulas (3), (4), and (5), we can obtain the likelihood term of the i-th sample point:

[0028]

[0029] Then the maximum likelihood function lnL(W,b) can be expressed as:

[0030] Step S34, constructing the cost function of the multivariate ordered logistic regression model: using the cross entropy loss function Lloss(W, b) to construct the cost function of the multivariate ordered logistic regression model, the cross entropy loss function expression is as follows: Let y represent the actual sample value, Representing the model prediction output, the cost function is obtained:

[0031] Step S35, construct a gradient descent algorithm to solve the model parameters: use the gradient descent method SGD to solve the cross entropy loss function, and the gradient G of the cross entropy loss function is expressed as follows:

[0032]

[0033]

[0034] The iterative formula of the stochastic gradient descent algorithm is:

[0035] W:=W-αG w (12); b: = b-αG b (13); where: α is the learning rate, which controls the speed of gradient descent, and the convergence condition is set to the difference between two consecutive gradient calculation values ​​less than 0.001;

[0036] The model parameters W and b were solved by gradient descent method on the training set to obtain a big data analysis model for predicting the probability of AKI in patients.

[0037] Step S36, model verification: input the data used as the test set into the model constructed in step S35, calculate the probability of the patient's AKI risk, and analyze the model calculation results with the actual results to calculate the accuracy of the big data analysis model for predicting the probability of AKI in patients.

[0038] In an optional embodiment of the present invention, the abnormal data eliminated in step S31 include: abnormal data with a urine oxygen partial pressure level greater than 250 mmHg or less than 1 mmHg, a urine temperature higher than 45°C or lower than 25°C, and a urine flow rate greater than 10 mL / min or less than 0.1 mL / min; after elimination, the missing data are replaced with the average value of the urine oxygen partial pressure level of 80 mmHg, the urine temperature of 35°C, and the urine flow rate of 1 mL / min.

[0039] In an optional embodiment of the present invention, the accuracy in step S36 represents the accuracy of the prediction result of the established model, and the calculation formula is as follows:

[0040] Wherein: TP is the result when both the predicted result and the true value are “positive”, and the “positive” case indicates that the patient has AKI; TN is the result when both the predicted result and the true value are “negative”, and the “negative” case indicates that the patient does not have AKI; FP is the result when the predicted result is “positive” and the true value is “negative”; FN is the result when the predicted result is “negative” and the true value is “positive”.

[0041] In an optional embodiment of the present invention, in step S4, a threshold value of 0.5 is set for the multivariate ordered logistic regression model; when the prediction result is greater than 0.5, it is determined that the patient has AKI; when the prediction result is less than 0.5, it is determined that the patient does not have AKI;

[0042] Furthermore, the model prediction results were classified: when the prediction result was less than 0.3, the model outputted a low-risk warning for AKI; when the prediction result was between 0.3 and 0.6, the model outputted a medium-risk warning for AKI; when the prediction result was greater than 0.6, the model outputted a high-risk warning for AKI;

[0043] The model prediction results are sent to the user interface (92) of the intelligent terminal (9) in real time for the user to view. The user can view the patient's blood pressure, urine oxygen partial pressure level, urine temperature, urine flow rate, AKI risk prediction results, and prediction probability information from the display interface.

[0044] Compared with the prior art, the embodiment of the present invention provides a wireless urine oxygen partial pressure monitoring device and a monitoring method thereof, which have the following beneficial effects:

[0045] (1) The monitoring device of the present invention utilizes time-division multiplexing technology, uses AD630 and a low-pass filter circuit to form a single-channel phase-locked amplifier structure, and generates a high-precision orthogonal reference signal through the MCU chip in a time-sharing manner, and sends it to the single-channel phase-locked amplifier circuit for modulation operation with the input signal, which can effectively avoid the error caused by the inability to achieve complete parameter symmetry in the dual-channel phase-locked amplifier structure. After experimental testing, the phase accuracy of the input signal detected by the single-channel phase-locked amplifier structure using time-division multiplexing technology is improved by 30%, and real-time, continuous and accurate monitoring of the patient's urine oxygen partial pressure level can be achieved. The device is small in size and easy to install; the monitoring data is sent to the intelligent terminal through a wireless data transceiver module, avoiding the disadvantages of foreign body sensation and restricted movement caused by complex line connections to the patient, and is suitable for monitoring the patient's urine oxygen partial pressure level in various occasions.

[0046] Since the monitoring device is external, there is no need to consider the risk of damage to the patient's bladder. A temperature sensor can be easily introduced to assist in determining whether the kidneys have infection or other abnormalities based on the urine temperature. A flow sensor is introduced to monitor the kidney's urination ability. Combined with the flow sensor, based on the urine oxygen partial pressure index, a multi-parameter comprehensive analysis is performed to more accurately assess the degree and nature of kidney damage, thereby providing a more reliable basis for clinical decision-making.

[0047] (2) The monitoring method of the present invention provides a big data analysis model for predicting the risk of AKI in patients based on the logistic regression method. The model adopts a multivariate ordered logistic regression model, and the independent variables are the patient's urine oxygen partial pressure level, urine temperature, urine flow rate and other information; the dependent variable is the risk of AKI in patients, which is divided into three categories: low risk, medium risk and high risk. The model independent variable data comes from the collection results of the wireless urine oxygen partial pressure monitoring device and the clinical patient information collection. The data is transmitted to the intelligent terminal through the wireless data transceiver module and classified and stored; the actual AKI occurrence of the object monitored by the wireless urine oxygen partial pressure monitoring device is input by the intelligent terminal data input function and classified and stored; the model can predict the probability of AKI in patients based on the patient's urine oxygen partial pressure level, urine flow rate, urine temperature and other indicators. The use of this model can provide assistance for the prevention and treatment of AKI in clinical patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0049] Figure 1 A schematic diagram of the structure of a wireless urine oxygen partial pressure monitoring device provided in an embodiment of the present application.

[0050] Figure 2 A schematic diagram of the structure of a multi-lumen urinary catheter in a wireless urine oxygen partial pressure monitoring device provided in an embodiment of the present application.

[0051] Figure 3 A circuit connection block diagram of a phase modulator and demodulator in a wireless urine oxygen partial pressure monitoring device provided in an embodiment of the present application.

[0052] Figure 4 A circuit connection block diagram of a phase-locked amplifier in a wireless urine oxygen partial pressure monitoring device provided in an embodiment of the present application.

[0053] Figure 5 This is a waveform diagram of a blue light LED driving signal and a fluorescent voltage signal in a wireless urine oxygen partial pressure monitoring device provided in an embodiment of the present application.

[0054] Figure 6 A flowchart of a wireless urine oxygen partial pressure monitoring method provided in an embodiment of the present application.

[0055] Figure 7 This is a linear relationship diagram between the urine oxygen partial pressure data measured by a wireless urine oxygen partial pressure monitoring device and the phase difference of the fluorescent voltage signal provided in an embodiment of the present application.

[0056] Figure 8 A wireless urine oxygen partial pressure monitoring device provided in an embodiment of the present application is used to clinically measure urine oxygen partial pressure data of patients.

[0057] Fig. 9 A flowchart for constructing a patient AKI risk prediction model in a wireless urine oxygen partial pressure monitoring device provided in an embodiment of the present application.

[0058] Fig.10 This is a diagram of parameter weight calculation results for a patient AKI risk prediction model in a wireless urine oxygen partial pressure monitoring device provided in an embodiment of the present application.

[0059] Fig.11 This is a graph showing the accuracy calculation results of a patient AKI risk prediction model used in a wireless urine oxygen partial pressure monitoring device provided in an embodiment of the present application.

[0060] Fig.12 A wireless urine oxygen partial pressure monitoring device provided in an embodiment of the present application is used for a patient AKI risk prediction model, and a logistic regression model output result diagram of urine oxygen partial pressure and patient AKI risk.

[0061] Fig.13 A schematic diagram of a user terminal interface of a wireless urine oxygen partial pressure monitoring device provided in an embodiment of the present application.

[0062] Fig.14 A circuit structure diagram of a wireless urine oxygen partial pressure monitoring device provided in an embodiment of the present application.

[0063] Fig.15 This is a circuit diagram of a wireless urine oxygen partial pressure monitoring device provided in an embodiment of the present application.

[0064] Fig.16 A physical diagram of a wireless urine oxygen partial pressure monitoring device provided in an embodiment of the present application.

[0065] The accompanying drawings are marked as follows: 1-patient; 2-catheter; 3-multi-lumen catheter; 31-urine storage chamber; 32-connector; 33-threaded interface; 4-temperature sensor; 5-fiber optic oxygen sensitive sensor; 51-fiber optic oxygen sensitive sensor probe; 52-SMA interface; 53-Y-type optical fiber; 54-blue light signal transmitting port; 55-fluorescent signal receiving port; 6-flow sensor; 7-main control circuit; 71-MCU chip; 72-signal generating circuit; 721-PWM drive signal; 722-reference signal X; 723-reference Signal Y; 724-signal processing circuit; 725-blue light LED driving signal; 73-blue light LED; 74-filter; 75-photoelectric conversion circuit; 76-phase-locked amplifier circuit; 761-time-sharing reference signal; 762-fluorescence voltage signal; 763-AD630 modulation circuit; 764-low-pass filter circuit; 765-DC bias circuit; 77-analog-to-digital conversion circuit; 78-wireless data transceiver circuit; 8-wireless data transceiver module; 9-intelligent terminal; 91-terminal processor; 92-user interface; 10-urine bag. DETAILED DESCRIPTION

[0066] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application for which protection is claimed, but merely represents the selected embodiments of the present application.

[0067] like Figure 1 , Figure 2 and Figure 3 As shown, an embodiment of the present invention provides a wireless urine oxygen partial pressure monitoring device, including a multi-lumen urinary catheter 3, a temperature sensor 4, an optical fiber oxygen sensitive sensor 5, a flow sensor 6, a main control circuit 7, a wireless data transceiver module 8, an intelligent terminal 9 and a urine bag 10; the multi-lumen urinary catheter 3 includes a urine storage chamber 31, and the urine storage chamber 31 is provided with a left joint 32, three top joints 33 and a right joint 34; the left joint 32 is connected to the bladder of the patient 1 through the first urinary catheter 21, and the right joint 34 is connected to the urine bag 10 through the second urinary catheter 22. The three top joints 33 are all threaded interfaces.

[0068] One end of the temperature sensor 4 is connected to the urine storage chamber 31 through the first top connector 33, and the other end is connected to the main control circuit 7 through the data line, and its function is to monitor the urine temperature and transmit the fluorescence signal generated by the probe of the temperature sensor 4 to the receiving end of the phase modulator through the data line. The optical fiber oxygen sensitive sensor 5 includes an optical fiber oxygen sensitive sensing probe 51 and a Y-type optical fiber 53 connected through an SMA interface 52; the optical fiber oxygen sensitive sensing probe 51 is connected to the urine storage chamber 31 through the second top connector 33; the Y-type optical fiber 53 is connected to the main control circuit 7, and its function is to monitor the urine oxygen partial pressure near one end of the bladder of the patient 1.

[0069] One end of the flow sensor 6 is connected to the urine storage chamber 31 through the third top connector 33, and the other end is connected to the main control circuit 7 through a data line; it is used to monitor the urine flow and transmit the fluorescent signal generated by the probe of the flow sensor to the receiving end of the main control circuit through the data line. The wireless data transceiver module 8 is connected to the main control circuit 7 and is also connected to the smart terminal 9 to send the collected urine oxygen partial pressure, urine temperature, and urine flow information to the smart terminal 9. The smart terminal 9 includes a terminal processor 91 and a user interface 92.

[0070] The Y-type optical fiber 53 is branched into a blue light signal transmitting port 54, which is used to transmit the blue light excitation signal generated by the main control circuit 7 to the optical fiber oxygen sensitive sensor probe 51. The Y-type optical fiber 53 is branched into a fluorescence signal receiving port 55, which is used to transmit the fluorescence emission signal generated by the optical fiber oxygen sensitive sensor probe 53 to the receiving end of the main control circuit.

[0071] like Figure 3 and Figure 4 As shown, the main control circuit 7 includes a filter 74, a photoelectric conversion circuit 75, a phase-locked amplifier circuit 76, an analog-to-digital conversion circuit 77, an MCU chip 71, a signal generating circuit 72, and a blue light LED 73 connected in sequence; the blue light LED 73 is connected to the blue light signal transmitting port 54, and the filter 74 is connected to the fluorescent signal receiving port 55; the photoelectric conversion circuit 75 is connected to the MCU chip 71, and the MCU chip 71 is also connected to a wireless data transceiver circuit 78; the signal generating circuit 72 is also connected to the phase-locked amplifier circuit 76. The phase-locked amplifier circuit 76 includes an AD630 modulation circuit 763, a low-pass filter circuit 764, and a DC bias circuit 765 connected in sequence; the DC bias circuit 765 is connected to the analog-to-digital conversion circuit 77; the AD630 modulation circuit 763 is connected to the signal processing circuit 724 of the signal generating circuit 72, and the signal processing circuit 724 is also connected to the blue light LED 73 and the MCU chip 71, respectively.

[0072] The signal flow of a wireless urine oxygen partial pressure monitoring device is as follows:

[0073] The MCU chip 71 generates a PWM drive signal 721, which is biased by the signal generating circuit 72 to generate a blue light LED drive signal 725, and is transmitted to the blue light LED 73. The blue light LED 73 generates a blue light excitation signal, which is transmitted to the optical fiber oxygen sensitive sensor probe 51 through the blue light signal transmitting port 54 and one branch of the Y-type optical fiber 53 in turn, so that the optical fiber oxygen sensitive sensor probe generates a fluorescence emission signal; the fluorescence emission signal is transmitted to the filter 74 through another branch of the Y-type optical fiber 53 and the fluorescence signal receiving port 55 in turn, and the fluorescence emission signal is filtered out of the blue light excitation signal and then transmitted to the photoelectric conversion circuit 75, which converts the fluorescence emission signal into a fluorescence voltage signal 762, and the fluorescence voltage signal 762 is sent to the phase-locked amplifier circuit 76. At this time, there are also two orthogonal reference signals generated by the control signal generating circuit of the MCU chip 71 in time-sharing, which will be merged in parallel with the fluorescence voltage signal in time-sharing, and the two signals are modulated. The voltage waveforms of the blue light LED drive signal 725 and the fluorescence voltage signal 762 are as follows: Figure 5 As shown, the frequency of the blue LED driving signal 725 and the fluorescent voltage signal 762 are both 40KHZ. Finally, the processed signal is converted into a digital signal by the analog-to-digital conversion circuit 77 and sent to the MCU chip 71 for data processing. The processing result is sent to the wireless data transceiver module 8 through the wireless data transceiver circuit 78, and finally sent to the terminal processor 91 for data analysis and displayed through the user interface 92.

[0074] In order to clarify the specific process of signal processing in the phase-locked amplifier circuit 76, its structure and signal flow are described in detail: The structure of the phase-locked amplifier circuit 76 is as follows: Figure 4 As shown, it includes: AD630 modulation circuit 763, low-pass filter circuit 764, DC bias circuit 765, and the signal flow is as follows:

[0075] The MCU chip 71 generates a PWM drive signal 721, which is biased by the signal processing circuit 724 to obtain a blue light LED drive signal 725, and the blue light LED drive signal is sent to the blue light LED 73 to generate a blue light excitation signal; at the same time, the MCU chip 71 generates an orthogonal reference signal X722 and an orthogonal reference signal Y723 in a time-sharing manner, and biases them respectively through the signal processing circuit 724; the processed time-sharing reference signal 761 will be sent to the AD630 modulation circuit 763 in a time-sharing manner, wherein the signal flow of the blue light LED 73 has been described in the previous text and will not be repeated; and in the AD630 modulation circuit 763, the time-sharing reference signal 761 and the fluorescent voltage signal 762 finally input by the photoelectric conversion circuit 75 are modulated, and the operation result is sent to the low-pass filter circuit 764 for filtering, and the filtered DC signal is forward biased by the DC bias circuit 765, and the processed signal will be sent to the analog-to-digital conversion circuit 77.

[0076] like Figure 6 As shown, an embodiment of the present invention further provides a wireless urine oxygen partial pressure monitoring method, which is implemented by using a wireless urine oxygen partial pressure monitoring device of the above embodiment, and includes the following steps:

[0077] Step S1, installing the wireless urine oxygen partial pressure monitoring device, connecting the circuit, and then debugging to ensure that the circuit is correct and the signal transmission is normal;

[0078] Step S2, data collection: After processing the sensing signal using the intelligent terminal 9, the urine oxygen partial pressure monitored by the optical fiber oxygen sensitive sensor 5, the urine temperature monitored by the temperature sensor 4, and the urine flow rate monitored by the flow sensor 6 can be directly read;

[0079] Step S3, establishing a prediction model and performing training and verification: using the Logistic regression analysis method, constructing a big data analysis model for predicting the probability of AKI in patients, training and verifying the model so that the model can analyze and process the patient data collected by the wireless urine oxygen partial pressure monitoring device, and give the probability of AKI in patients;

[0080] Step S4, model prediction and result output: The patient data collected in step S2 is sent to the big data analysis and prediction model trained in step S3 in real time to evaluate the risk of AKI in the current patient, that is, the monitoring data is predicted using the trained big data analysis and prediction model.

[0081] In step S1, the bladder of the patient 1 is connected to the left connector 32 of the multi-lumen urinary catheter 3 through the first urinary catheter 21 to ensure that the bladder of the patient 1 is connected to the urine storage chamber 31, and then the other end of the multi-lumen urinary catheter 3 is connected to the urine bag 10 through the second urinary catheter 22; the temperature sensor 4, the optical fiber oxygen sensitive sensor 5, and the flow sensor 6 are installed; and the three are connected to the main control circuit 7, and the wireless data transceiver module 8 is integrated on the main control circuit 7, and the wireless data transceiver module 8 is connected to the debugging intelligent terminal 9 through wireless communication. After all the equipment is installed, it is debugged, and the line is correct and the signal transmission is normal. Then enter the monitoring link.

[0082] In step S2, the optical fiber oxygen sensitive sensor 5 uses the fluorescence quenching effect to detect the change in oxygen concentration. This process is described by the Stern-Volmer equation, as shown in formula (1):

[0083] In the formula: I0 is the initial intensity of the fluorescence signal emitted by the optical fiber oxygen sensitive sensor probe 51 in an oxygen-free environment; I is the fluorescence signal intensity after fluorescence quenching of the optical fiber oxygen sensitive sensor probe 51; τ0 is the initial lifetime of the fluorescence signal emitted by the optical fiber oxygen sensitive sensor probe 51 in an oxygen-free environment; τ is the fluorescence signal lifetime after fluorescence quenching of the optical fiber oxygen sensitive sensor probe 51; K is the Stern-Volmer constant; x(O2) is the oxygen concentration.

[0084] The phase value of the fluorescence signal emitted by the optical fiber oxygen sensitive sensor probe 51 is different under different oxygen concentrations. The phase change of the fluorescence signal emitted by the optical fiber oxygen sensitive sensor probe 51 is measured based on the phase-sensitive detection technology. After the sensor signal is processed by the terminal data processing system, the oxygen concentration of the urine to be tested can be directly output.

[0085] Figure 7 The linear fitting diagram of the measured data of urine oxygen partial pressure and the phase of the fluorescence signal. From the fitting results, it can be seen that the linear correlation between the urine oxygen partial pressure and the phase of the fluorescence signal measured by the urine oxygen partial pressure detection device of the present invention is greater than 98.9%, which can achieve accurate measurement of urine oxygen partial pressure. The actual clinical test sample data of some patients are as follows Figure 8 shown.

[0086] The construction flow chart of the big data analysis model is as follows: Fig. 9 As shown, step S3 specifically includes the following steps:

[0087] Step S31, data pre-processing: read the collected data of the patient's urine oxygen partial pressure level, urine temperature, urine flow rate, etc. and analyze and process them, and remove abnormal data; manually enter the patient's age, gender, weight, historical medical condition, AKI occurrence, etc. through the intelligent terminal; use the above data as a data set, and use 80% of the patient data in the data set as a training set and 20% of the patient data as a test set;

[0088] Step S32, constructing a connection function: using the sigmoid function to construct a connection function, mapping the binary variable of whether the patient has AKI to a continuous variable, and constructing a multivariate ordered logistic regression model fitting function f(z), the expression of which is as follows:

[0089] The calculated value of f(z) is the probability of the patient developing AKI calculated by the model. Z is the situation of the patient developing AKI. When Z=1, it means that the patient has AKI, and when Z=0, it means that the patient does not have AKI. In formula (2), z is the multivariate linear regression fitting function, which is expressed as follows: z=w1x1+w2x2+w3x3+b(3); where b is the intercept; x1, x2, and x3 are the patient's urine oxygen partial pressure data, urine temperature data, and urine flow rate data, respectively; w1, w2, and w3 are the corresponding independent variables x i weights; let W = [w1,w2,w3],X = [x1,x2,x3], we get Z = WX T +b;

[0090] Step S33, deriving the probability of whether AKI occurs by the model: deriving the probability of whether AKI occurs by the model through the multivariate ordered logistic regression model fitting function f(z), which is expressed as follows:

[0091]

[0092] Formula (4) represents the probability of AKI occurring predicted by the model; Formula (5) represents the probability of AKI not occurring predicted by the model;

[0093] According to formulas (3), (4), and (5), we can obtain the likelihood term of the i-th sample point:

[0094]

[0095] Then the maximum likelihood function lnL(W,b) can be expressed as:

[0096] Step S34, constructing the cost function of the multivariate ordered logistic regression model: using the cross entropy loss function Lloss(W, b) to construct the cost function of the multivariate ordered logistic regression model, the cross entropy loss function expression is as follows: Let y represent the actual sample value, Representing the model prediction output, the cost function is obtained:

[0097] Step S35, construct a gradient descent algorithm to solve the model parameters: use the gradient descent method SGD to solve the cross entropy loss function, and the gradient G of the cross entropy loss function is expressed as follows:

[0098]

[0099] The iterative formula of the stochastic gradient descent algorithm is:

[0100] W:=W-αG w (12); b: = b-αG b (13); where: α is the learning rate, which controls the speed of gradient descent, and the convergence condition is set to the difference between two consecutive gradient calculation values ​​less than 0.001;

[0101] The model parameters W and b were solved by the gradient descent method on the training set to obtain a big data analysis model for predicting the probability of AKI in patients. The parameter weight calculation results of the big data analysis model are shown in Figure 2. Fig.10 As shown in Figure 2, urine oxygen partial pressure has the greatest impact on whether a patient develops AKI. The output of the logistic regression model of urine oxygen partial pressure and the risk of AKI in patients is as follows: Fig.11 shown.

[0102] Step S36, model verification: input the data used as the test set into the model constructed in step S35, calculate the probability of the patient's AKI risk, and analyze the model calculation results with the actual results to calculate the accuracy of the big data analysis model for predicting the probability of AKI in patients.

[0103] The abnormal data eliminated in step S31 include: urine oxygen partial pressure level greater than 250 mmHg or less than 1 mmHg, urine temperature higher than 45°C or lower than 25°C, urine flow rate greater than 10 mL / min or less than 0.1 mL / min; after elimination, the missing data are replaced with the average value of urine oxygen partial pressure level 80 mmHg, urine temperature 35°C, and urine flow rate 1 mL / min.

[0104] The accuracy in step S36 represents the accuracy of the prediction results of the established model, and the calculation formula is as follows:

[0105] Wherein: TP is the result when both the predicted result and the true value are “positive”, and the “positive” case indicates that the patient has AKI; TN is the result when both the predicted result and the true value are “negative”, and the “negative” case indicates that the patient does not have AKI; FP is the result when the predicted result is “positive” and the true value is “negative”; FN is the result when the predicted result is “negative” and the true value is “positive”.

[0106] The accuracy of the trained big data analysis prediction model was calculated using the test set. In this embodiment, the initial accuracy of the model test was 87.71%. On the one hand, it was verified that the use of this model can provide an auxiliary means for the early prevention of AKI; on the other hand, the value of 87.71% in this embodiment is only the accuracy of the initial test of the model. As the amount of data on monitored patients continues to increase in the later application process, the various parameters of the model will be corrected and optimized, and the prediction accuracy will be further improved.

[0107] In step S4, a threshold of 0.5 is set for the multivariate ordered logistic regression model; when the prediction result is greater than 0.5, it is determined that the patient has AKI; when the prediction result is less than 0.5, it is determined that the patient does not have AKI;

[0108] Furthermore, the model prediction results were classified: when the prediction result was less than 0.3, the model outputted a low-risk warning for AKI; when the prediction result was between 0.3 and 0.6, the model outputted a medium-risk warning for AKI; when the prediction result was greater than 0.6, the model outputted a high-risk warning for AKI;

[0109] The model prediction results are sent to the user interface 92 of the smart terminal 9 in real time for the user to view. The user can view the patient's blood pressure, urine oxygen partial pressure level, urine temperature, urine flow rate, AKI risk prediction results, prediction probability and other information from the display interface.

[0110] Fig.12 A wireless urine oxygen partial pressure monitoring device provided in an embodiment of the present application is used for a patient AKI risk prediction model, and a logistic regression model output result diagram of urine oxygen partial pressure and patient AKI risk. Fig.13 A schematic diagram of a user terminal interface of a wireless urine oxygen partial pressure monitoring device provided in an embodiment of the present application. Fig.14 A circuit structure diagram of a wireless urine oxygen partial pressure monitoring device provided in an embodiment of the present application. Fig.15 This is a circuit diagram of a wireless urine oxygen partial pressure monitoring device provided in an embodiment of the present application. Fig.16 A physical diagram of a wireless urine oxygen partial pressure monitoring device provided in an embodiment of the present application.

[0111] In summary, although the present invention has been disclosed as above in terms of preferred embodiments, the above preferred embodiments are not intended to limit the present invention. A person skilled in the art may make various changes and modifications without departing from the spirit and scope of the present invention. Therefore, the scope of protection of the present invention shall be based on the scope defined in the claims.

Claims

1. A wireless urine oxygen partial pressure monitoring device, characterized in that: The invention comprises a multi-lumen urinary catheter (3), a temperature sensor (4), an optical fiber oxygen sensitive sensor (5), a flow sensor (6), a main control circuit (7), a wireless data transceiver module (8), an intelligent terminal (9) and a urine bag (10); the multi-lumen urinary catheter (3) comprises a urine storage chamber (31), and the urine storage chamber (31) is provided with a left joint (32), three top joints (33) and a right joint (34); the left joint (32) is connected to the bladder of the patient (1) through a first urinary catheter (21), and the right joint (34) is connected to the urine bag (10) through a second urinary catheter (22); One end of the temperature sensor (4) is connected to the urine storage chamber (31) through a first top connector (33), and the other end is connected to the main control circuit (7) through a data line; the optical fiber oxygen sensitive sensor (5) comprises an optical fiber oxygen sensitive sensing probe (51) and a Y-type optical fiber (53) connected through an SMA interface (52); the optical fiber oxygen sensitive sensing probe (51) is connected to the urine storage chamber (31) through a second top connector (33); the Y-type optical fiber (53) is connected to the main control circuit (7); one end of the flow sensor (6) is connected to the urine storage chamber (31) through a third top connector (33), and the other end is connected to the main control circuit (7) through a data line; the wireless data transceiver module (8) is connected to the main control circuit (7), and is also connected to an intelligent terminal (9), and the intelligent terminal (9) comprises a terminal processor (91) and a user interface (92); The Y-shaped optical fiber (53) is connected to a blue light signal transmitting port (54) after one branch, and is connected to a fluorescent signal receiving port (55) after another branch of the Y-shaped optical fiber (53); the main control circuit (7) comprises a filter (74), a photoelectric conversion circuit (75), a phase-locked amplifier circuit (76), an analog-to-digital conversion circuit (77), an MCU chip (71), a signal generating circuit (72), and a blue light LED (73) which are connected in sequence; the blue light LED (73) is connected to the blue light signal transmitting port (54), and the filter (74) is connected to the fluorescent signal receiving port (55); the photoelectric conversion circuit (75) is connected to the MCU chip (71), and the MCU chip (71) is also connected to a wireless data transceiver circuit (78); and the signal generating circuit (72) is also connected to the phase-locked amplifier circuit (76).

2. A wireless urine oxygen partial pressure monitoring device according to claim 1, characterized in that: The phase-locked amplifier circuit (76) comprises an AD630 modulation circuit (763), a low-pass filter circuit (764) and a DC bias circuit (765) which are connected in sequence; the DC bias circuit (765) is connected to the analog-to-digital conversion circuit (77); the AD630 modulation circuit (763) is connected to the signal processing circuit (724) of the signal generating circuit (72); and the signal processing circuit (724) is also respectively connected to the blue light LED (73) and the MCU chip (71).

3. A wireless urine oxygen partial pressure monitoring method, implemented by using a wireless urine oxygen partial pressure monitoring device as claimed in any one of claim 2, characterized in that: The following steps are involved: Step S1, installing the wireless urine oxygen partial pressure monitoring device, connecting the circuit, and then debugging to ensure that the circuit is correct and the signal transmission is normal; Step S2, data collection: After processing the sensing signal using the intelligent terminal (9), the urine oxygen partial pressure monitored by the optical fiber oxygen sensitive sensor (5), the urine temperature monitored by the temperature sensor (4), and the urine flow rate monitored by the flow sensor (6) can be directly read; Step S3, establishing a prediction model and performing training and verification: using the Logistic regression analysis method, constructing a big data analysis model for predicting the probability of AKI in patients, training and verifying the model so that the model can analyze and process the patient data collected by the wireless urine oxygen partial pressure monitoring device, and give the probability of AKI in patients; Step S4, model prediction and result output: The patient data collected in step S2 is sent to the big data analysis and prediction model trained in step S3 in real time to evaluate the risk of AKI in the current patient, that is, the monitoring data is predicted using the trained big data analysis and prediction model.

4. A wireless urine oxygen partial pressure monitoring method according to claim 3, characterized in that: In step S1, the bladder of the patient (1) is connected to the left connector (32) of the multi-lumen urinary catheter (3) through the first urinary catheter (21) to ensure that the bladder of the patient (1) is connected to the urine storage chamber (31), and then the other end of the multi-lumen urinary catheter (3) is connected to the urine bag (10) through the second urinary catheter (22); A temperature sensor (4), an optical fiber oxygen sensitive sensor (5), and a flow sensor (6) are installed; and the three are connected to a main control circuit (7); a wireless data transceiver module (8) is integrated on the main control circuit (7); and the wireless data transceiver module (8) is connected to a debugging intelligent terminal (9) through wireless communication.

5. A wireless urine oxygen partial pressure monitoring method according to claim 3, characterized in that: In step S2, the optical fiber oxygen sensitive sensor (5) uses the fluorescence quenching effect to detect the change in oxygen concentration. This process is described by the Stern-Volmer equation, as shown in formula (1): Wherein: I0 is the initial intensity of the fluorescence signal emitted by the optical fiber oxygen sensitive sensor probe (51) in an oxygen-free environment; I is the fluorescence signal intensity of the optical fiber oxygen sensitive sensor probe (51) after fluorescence quenching; τ0 is the initial lifetime of the fluorescence signal emitted by the optical fiber oxygen sensitive sensor probe (51) in an oxygen-free environment; τ is the fluorescence signal lifetime of the optical fiber oxygen sensitive sensor probe (51) after fluorescence quenching; K is the Stern-Volmer constant; x ( O 2) is the oxygen concentration.

6. A wireless urine oxygen partial pressure monitoring method according to claim 3, characterized in that: Step S3 specifically includes the following steps: Step S31, data pre-processing: reading the collected data of the patient's urine oxygen partial pressure level, urine temperature, urine flow rate, etc. and analyzing and processing them, and eliminating abnormal data; The patient's age, gender, weight, medical history, AKI occurrence and other data were manually entered through the smart terminal; the above data was used as a data set, 80% of the patient data in the data set was used as a training set, and 20% of the patient data in the data set was used as a test set; Step S32, constructing a connection function: Use the sigmoid function to construct a connection function, map the binary variable of whether the patient has AKI to a continuous variable, and construct a multivariate ordered logistic regression model fitting function f ( z ) , which is expressed as follows: f ( z ) The calculated value is the probability of the patient developing AKI calculated by the model, and Z is the situation of the patient developing AKI. When Z = 1, it means that the patient has AKI, and when Z = 0, it means that the patient does not have AKI. In formula (2), z is the multivariate linear regression fitting function, and the expression is as follows: z = w1x1 + w2x2 + w3x3 + b (3); In the formula: b is the intercept; x1, x2, and x3 are the patient's urine oxygen partial pressure data, urine temperature data, and urine flow rate data, respectively; w1, w2, and w3 are the corresponding independent variables x i weights; let W = [w1,w2,w3],X = [x1,x2,x3], we get Z = WX T +b; Step S33, deriving a model to predict the probability of AKI occurrence: fitting function f by multivariate ordered logistic regression model ( z ) The probability of whether AKI occurs is derived from the model, and its expression is as follows: Formula (4) represents the probability of AKI occurring predicted by the model; Formula (5) represents the probability of AKI not occurring predicted by the model; According to formulas (3), (4), and (5), we can obtain the likelihood term of the i-th sample point: Then the maximum likelihood function lnL ( W,b ) It can be expressed as: Step S34, construct the cost function of the multivariate ordered logistic regression model: using the cross entropy loss function Lloss ( W,b ) The cost function of the multivariate ordered logistic regression model is constructed, and the cross entropy loss function expression is as follows: Let y represent the actual sample value, Representing the model prediction output, the cost function is obtained: Step S35, construct a gradient descent algorithm to solve the model parameters: use the gradient descent method SGD to solve the cross entropy loss function, and the gradient G of the cross entropy loss function is expressed as follows: The iterative formula of the stochastic gradient descent algorithm is: W:=W-αG w (12); b: = b-αG b (13); where: α is the learning rate, which controls the speed of gradient descent, and the convergence condition is set to the difference between two consecutive gradient calculation values ​​less than 0.001; The model parameters W and b were solved by gradient descent method on the training set to obtain a big data analysis model for predicting the probability of AKI in patients. Step S36, model verification: input the data used as the test set into the model constructed in step S35, calculate the probability of the patient's AKI risk, and analyze the model calculation results with the actual results to calculate the accuracy of the big data analysis model for predicting the probability of AKI in patients.

7. A wireless urine oxygen partial pressure monitoring method according to claim 3, characterized in that: The abnormal data eliminated in step S31 include: urine oxygen partial pressure level greater than 250 mmHg or less than 1 mmHg, urine temperature higher than 45°C or lower than 25°C, urine flow rate greater than 10 mL / min or less than 0.1 mL / min; after elimination, the missing data are replaced with the average value of urine oxygen partial pressure level 80 mmHg, urine temperature 35°C, and urine flow rate 1 mL / min.

8. A wireless urine oxygen partial pressure monitoring method according to claim 6, characterized in that: The accuracy in step S36 represents the accuracy of the prediction results of the established model, and the calculation formula is as follows: Wherein: TP is the result in which both the predicted result and the true value are "positive", "positive" means that the patient has AKI; TN is the result in which both the predicted result and the true value are "negative", "negative" means that the patient does not have AKI; FP is the result in which the predicted result is "positive" and the true value is "negative"; FN is the result in which the predicted result is "negative" and the true value is "positive".

9. A wireless urine oxygen partial pressure monitoring method according to claim 6, characterized in that: In step S4, a threshold of 0.5 is set for the multivariate ordered logistic regression model; when the prediction result is greater than 0.5, it is determined that the patient has AKI; when the prediction result is less than 0.5, it is determined that the patient does not have AKI; Furthermore, the model prediction results were classified: when the prediction result was less than 0.3, the model outputted a low-risk warning for AKI; when the prediction result was between 0.3 and 0.6, the model outputted a medium-risk warning for AKI; When the prediction result is greater than 0.6, the model outputs a high-risk warning for AKI; The model prediction results are sent in real time to the user interface (92) of the smart terminal (9) for the user to view. The user can view the patient's blood pressure, urine oxygen partial pressure level, urine temperature, urine flow rate, AKI risk prediction results, and prediction probability information from the display interface.

Images