Diagnostic system for urinary tract infection and construction method thereof

Abstract

The invention discloses a diagnostic system for urinary tract infection and a construction method thereof. The diagnostic system comprises a urinary tract infection detector and an optical detection system, the urinary tract infection detector comprises a plurality of groups of graphdiyne detection arrays containing functionalized graphdiyne, and the functionalized graphdiyne is graphdiyne modified by heme and titanium dioxide; the urinary tract infection detector is used for reacting with the pretreated urine sample, and the optical detection system is used for determining absorbance value data of the urinary tract infection detector. The functionalized graphdiyne is used for constructing the urinary tract infection detector, the multichannel colorimetric detection array is constructed according to the peroxidase activity difference of the functionalized graphdiyne under different acidity conditions, the operation is convenient, and the determination result is accurate and reliable.

Description

Technical Field

[0001] The present invention relates to the technical field of diagnostic devices, and in particular to a diagnostic system for urinary tract infection and a construction method thereof. Background Art

[0002] Urinary tract infection is a common infectious disease that can lead to pyelonephritis, uremia, and even death. Traditional diagnostic strategies for urinary tract infection, such as urine culture and flow cytometry, are costly and require professional operation, which hinders their home use. A large number of extracellular vesicles secreted by pathogens carry the main pathogenic components and can be used as new markers for rapid and accurate diagnosis of urinary tract infections. However, the specific recognition components in bacterial exosomes are mostly lacking or not obvious, which hinders the application and development of efficient recognition methods. Therefore, the development of new methods that can capture and identify bacterial exosomes still faces huge challenges for the rapid diagnosis, timely intervention, and precise treatment of urinary tract infections.

[0003] With the rapid development of artificial intelligence, the integration of machine learning and array sensors has provided a new strategy for disease diagnosis. Machine learning algorithms can analyze the multidimensional data generated by sensors, explore the relationship between data and diseases, and improve the diagnostic performance of sensors. The core of array sensing technology lies in the design of sensor units. Currently, in the field of urinary tract infection disease diagnosis, there is still a lack of intelligent sensor arrays that use bacterial exosomes as diagnostic markers. Summary of the invention

[0004] The object of the present invention is to provide a more convenient, accurate and reliable diagnostic system for urinary tract infection and a method for constructing the same.

[0005] To achieve the above purpose, the technical solution provided by the present invention is:

[0006] The present invention is achieved through the following technical solutions:

[0007] A first aspect of the present application provides a diagnostic system for urinary tract infection, comprising a urinary tract infection detector and an optical detection system;

[0008] The urinary tract infection detector comprises a plurality of groups of graphyne detection arrays containing functionalized graphyne, wherein the functionalized graphyne is graphyne modified by heme and titanium dioxide;

[0009] The urinary tract infection detector is used to react with the pre-treated urine sample, and the optical detection system is used to measure the absorbance value data of the urinary tract infection detector.

[0010] To optimize the above technical solutions, the specific measures taken also include:

[0011] The urinary tract infection detector comprises multiple groups of graphyne detection arrays, each group of graphyne detection arrays has a different pH, forming a multi-channel colorimetric detection array that can detect simultaneously; the detection wavelength of the optical detection system is 300-700nm.

[0012] In the graphyne detection array, hydrogen peroxide, peroxidase substrate and buffered salt solution are added to the functionalized graphyne.

[0013] Hydrogen peroxide, peroxidase substrate, and buffered saline solution are added to the functionalized graphene and incubated with the pretreated urine sample for 20-40 minutes.

[0014] The method for pretreatment of urine samples is: first centrifuge to obtain the supernatant, collect the bacterial exosomes in the urine by ultrafiltration and wash them with urea solution, and finally ultrasonicate and centrifuge.

[0015] It also includes a mathematical model classifier, which is a machine learning model for processing absorbance value data obtained by the optical detection system and outputting the results; the machine learning model supports at least one machine learning algorithm selected from the group consisting of a vector machine, a multivariate linear regression, an artificial neural network, a decision tree, and a random forest.

[0016] Furthermore, the machine learning model uses a multivariate linear regression algorithm to perform weighted multiplication on the absorbance, and the calculation formula is:

[0017] F n =A n ×W n

[0018] T=F1+F2+…+F n +m

[0019] Where n=1, 2, ..., represents different groups of graphyne detection arrays, W n represents the predetermined weights of different groups of graphyne detection arrays in the mathematical model classifier, F n Represents the weighted multiplication of different groups of graphyne detection arrays, A n represents the absorbance values ​​of different groups of graphyne detection arrays, T represents the output value of the diagnostic system for urinary tract infection, and m is a constant.

[0020] The second aspect of the present application provides a method for constructing a diagnostic system for urinary tract infection, comprising:

[0021] Functionalized graphyne modified by heme and titanium dioxide is prepared, and multiple groups of graphyne detection arrays with different pH values ​​are combined into a multi-channel colorimetric detection array as a urinary tract infection detector; the urinary tract infection detector and an optical detection system are combined into a diagnostic system for urinary tract infection.

[0022] The heme and titanium dioxide functionalized graphyne is prepared by mixing graphyne with heme and titanium dioxide for reaction.

[0023] Furthermore, the measurement data of the optical detection system is transmitted to a machine learning model for processing the measurement data, and the machine learning model evaluates the data processing results through evaluation indicators, and the evaluation indicators include accuracy, sensitivity, specificity, ROC curve and AUC value.

[0024] Compared with the prior art, the present invention has the following beneficial effects:

[0025] The present invention utilizes functionalized graphene to construct a urinary tract infection detector using bacterial exosomes as diagnostic markers. The modification of hemin molecules can endow the functionalized graphene with excellent peroxidase activity in a wide range of pH values, providing a detection basis for the construction of a urinary tract infection detector. The modification of titanium dioxide can enhance the functionalized graphene's ability to capture bacterial exosomes. Studies have shown that based on the interaction between titanium dioxide and the exosome phospholipid bilayer, rapid capture of bacterial exosomes can be achieved.

[0026] The present invention constructs a multi-channel colorimetric detection array based on the difference in peroxidase activity of functionalized graphene under different acidity conditions; when bacterial exosomes are adsorbed to the surface of functionalized graphene, the catalytic activity of functionalized graphene is inhibited, resulting in a decrease in the absorbance of the color developer; due to the differences in the types and concentrations of exosomes secreted by bacteria in the urine of healthy people and patients with urinary tract infections, their absorbance values ​​at different pH values ​​are also different, and rapid and accurate identification of exosomes in the urine of healthy / urinary tract infection patients can be achieved in a short time.

[0027] After simple pretreatment of urine samples, the diagnostic system of the present invention can be used for identification and determination. It only needs to collect bacterial exosomes in urine by ultrafiltration, and select a suitable pore size to intercept exosomes according to the size of the exosomes. Compared with other complex separation techniques such as ultracentrifugation and density gradient centrifugation, the operation is simpler and can be carried out under general laboratory conditions without the need for expensive ultracentrifuges. In addition, the sample processing method is carried out under relatively low pressure. This mild condition helps to maintain the integrity and biological activity of the exosomes, making the determination results accurate and reliable.

[0028] The present invention constructs a multi-channel colorimetric detection array with buffer solutions of different pH values, uses exosomes in urine of healthy people / urinary tract infection patients as data sets, and adopts machine learning algorithms to construct a digital diagnostic model; by collecting the absorbance values ​​of bacterial exosomes in urine of healthy people / urinary tract infection patients after reacting with the sensor system, a mathematical diagnostic model is constructed with the help of machine learning algorithms for the accurate diagnosis of urinary tract infection diseases; this method does not require the use of large-scale precision instruments, and can also achieve rapid and accurate diagnosis of urinary tract infection diseases in an environment with limited resources.

[0029] Compared with traditional methods for diagnosing urinary tract infections, the diagnostic system of the present invention is more convenient to operate, and the materials involved can be synthesized under laboratory conditions, with low toxicity and environmental friendliness. This method does not require professional operation and large-scale precision instruments, and can be used in areas with limited resources. It has excellent detection capabilities for the diagnosis of urinary tract infections, and is expected to promote the application of this technology in the typing diagnosis of other types of infectious diseases. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 The figure is a schematic diagram of a method for using the diagnostic system of the present invention to diagnose urinary tract infection.

[0031] Figure 2 These are high-resolution transmission electron microscopy and scanning electron microscopy characterization images of functionalized graphyne in an embodiment of the present invention.

[0032] Figure 3 This is the XPS characterization diagram of functionalized graphyne in an embodiment of the present invention.

[0033] Figure 4 The UV absorption spectra of the functionalized Graphene in the embodiments of the present invention under different pH buffer salts.

[0034] Figure 5 This is an NTA picture of bacterial exosomes in an embodiment of the present invention.

[0035] Figure 6 TEM image of bacterial exosomes in an embodiment of the present invention.

[0036] Figure 7 The inhibition of different bacterial exosomes on functionalized graphene under different pH conditions in the implementation of the present invention.

[0037] Figure 8 DFT simulation calculation diagram of different binding sites of functionalized graphene with Escherichia coli exosomes.

[0038] Fig. 9 This is a diagram showing the working principle of the mathematical model classifier for diagnosing urinary tract infection diseases.

[0039] Fig.10This is an evaluation chart of the diagnostic classification of urinary tract infection diseases by the diagnostic system of the present invention. DETAILED DESCRIPTION

[0040] The above contents of the present invention are further described in detail below in the form of embodiments, but this should not be understood as the scope of the above subject matter of the present invention being limited to the following embodiments, and all technologies realized based on the above contents of the present invention belong to the scope of the present invention.

[0041] The experimental methods used in the following examples are all conventional methods unless otherwise specified, and the reagents, methods and equipment used are all conventional reagents, methods and equipment in the technical field unless otherwise specified.

[0042] Unless otherwise specified, the terms used in this application have the commonly known meanings generally understood by those skilled in the art. Unless otherwise specified, the numerical values ​​of the parameters mentioned in this application can be measured using various measurement methods commonly used in the art.

[0043] The present invention constructs a more convenient, accurate and reliable diagnostic system for urinary tract infection. Figure 1 The present invention utilizes the ability of functionalized Graphene to have peroxidase activity in a wide range of pH values. By regulating the pH of the reaction system, a multi-channel sensor array can be constructed. Based on the difference in the binding of functionalized Graphene to urine bacterial exosomes, the inhibition of the catalytic activity of functionalized Graphene is different. By analyzing the value of the output signal absorbance, accurate diagnosis of healthy people and urinary tract infection diseases can be achieved.

[0044] In some embodiments, the peroxidase substrate is selected from at least one of tetramethylbenzidine, o-phenylenediamine, 2,2-azobis(3-ethyl-benzothiazole-6-sulfonic acid) diammonium salt and 4-aminoantipyrine; the buffered salt solution is selected from at least one of phosphate buffer, acetate buffer, citric acid buffer and phthalic acid buffer.

[0045] The method for pretreatment of urine samples is to first centrifuge to obtain the supernatant, collect the bacterial exosomes in the urine by ultrafiltration and wash them with urea solution, and finally ultrasonicate and centrifuge; the centrifuge tube with a suitable molecular weight cutoff can be selected according to the size and concentration of the exosomes to improve the recovery rate of exosomes in urine.

[0046] Preferably, a refrigerated centrifuge is used to separate cells and bacterial exosomes in urine under low temperature conditions, which is simpler to operate and can be performed under general laboratory conditions.

[0047] In some embodiments, the pretreated urine sample is incubated in the urinary tract infection detector for 20-40 minutes.

[0048] The optical detection system of the present invention is an ultraviolet spectrophotometer and an enzyme marker detection system for detecting ultraviolet absorption spectra.

[0049] In some embodiments, the detection wavelength of the optical detection system is 300-700 nm.

[0050] The method for constructing a diagnostic system for urinary tract infection of the present invention is to form a multi-channel colorimetric detection array with multiple groups of graphyne detection arrays with different pH values ​​as a urinary tract infection detector; the urinary tract infection detector and an optical detection system form a diagnostic system for urinary tract infection, and the measurement data of the optical detection system is transmitted to a machine learning model for processing the measurement data. In the present invention, 3 to 5 groups of graphyne detection arrays are preferred.

[0051] The method for constructing graphyne functionalized with heme and titanium dioxide is to mix graphyne with heme and titanium dioxide to obtain the result.

[0052] In some embodiments, the above reaction is a mixed light-protected reaction, and the precipitate is dissolved with a solvent to obtain a functionalized graphyne solution, which is stored in a dark place at 4° C. for later use.

[0053] In some embodiments, the concentration of functionalized Graphyne is 0.01-0.25 mg / mL; the concentration of hydrogen peroxide is 5-50 mM, the concentration of peroxidase substrate is 1-10 mM, and the concentration of buffered saline is 10-100 mM; the reaction volume ratio of functionalized Graphyne to hydrogen peroxide, peroxidase substrate, and buffered saline is 1-3: 1-3: 1-3: 11-17. Different Graphyne detection arrays are formed by adjusting the pH of the buffered saline.

[0054] In some embodiments, the pH adjustment range of the graphyne detection array is 3.0-8.0, and the pH interval can be 0.2-2.0.

[0055] Machine Learning Models At least one machine learning algorithm from the group consisting of support vector machine, multiple linear regression, artificial neural network, decision tree, and random forest.

[0056] In some embodiments, 60-80% of the data set is used as a training set for the construction of a mathematical diagnosis model, and 20-40% of the data is used as a test set. The accuracy, sensitivity, specificity, ROC curve, AUC value and other indicators of the mathematical diagnosis model are measured to evaluate the diagnostic performance of the classification model for urinary tract infection diseases.

[0057] When the present invention is applied, the output result of the mathematical model classifier of the urinary tract infection disease can be compared with a threshold value. If the output result is greater than the threshold value, the patient is a urinary tract infection patient, and if the output result is less than the threshold value, the patient is a healthy person.

[0058] The diagnostic system of the present invention can be used at room temperature.

[0059] The present invention is further described in detail below in conjunction with specific embodiments:

[0060] Example 1 Preparation of Graphene Detection Array for Detecting Bacterial Exosomes

[0061] Graphdine solution, titanium dioxide solution and hemin solution were used as the reaction stock solution. After the reaction was completed in the dark, methanol was used as a solvent to dissolve the centrifugal precipitate to obtain a functionalized Graphdine solution. The functionalized Graphdine solution was mixed with hydrogen peroxide, peroxidase substrate and buffered salt solution to obtain the sensor element of the sensor array. 10 μL of 0.05 mg / mL functionalized Graphdine solution was mixed with 10 μL of 50 mM hydrogen peroxide and 10 μL of 10 mM 3,3',5,5'-tetramethylbenzidine (TMB) and 150 μL of 100 mM phosphate buffer (pH = 4, 5, 6) to obtain a Graphdine detection array with different pH.

[0062] like Figure 1 , Figure 2 , Figure 3 and Figure 4 shown. Figure 1 A schematic diagram showing the use of the diagnostic system for diagnosing urinary tract infection diseases.

[0063] Figure 2 The scanning electron microscope and transmission electron microscope characterization images of functionalized graphyne are shown. Figure 3 These are the XPS characterization pictures of graphyne (GDY), graphyne modified with titanium dioxide (GDY / TiO2), heme and functionalized graphyne modified with titanium dioxide (GDY / Hem / TiO2). Both Fe and Ti elements show characteristic absorption peaks, indicating that Hem / TiO2 has been successfully modified on the surface of GDY. Figure 4 The catalytic color development and UV absorption spectra of functionalized graphyne on TMB under different pH conditions indicate that functionalized graphyne can exhibit excellent POD activity over a wide range of pH values.

[0064] Example 2 Collection of exosomes secreted by bacteria and cells in urine

[0065] The urine sample was transferred to a 50 mL centrifuge tube, centrifuged at 3000 g for 15 min (4 ° C), and at 12000 g for 15 min (4 ° C), and the supernatant was taken. The supernatant of each tube was transferred to an ultrafiltration tube with a molecular weight cutoff of 100 KDa in batches, and 10 mL of supernatant was transferred to each tube, and centrifuged at 5000 g for 10 min (4 ° C). 5 mL of 8 mM urea solution was added for washing, and centrifuged at 5000 g for 10 min (4 ° C), and washed three times in total. The solution in the ultrafiltration tube was collected in a 1.5 mL centrifuge tube, and 200 μL of 8 mM urea was used to repeatedly blow the exosomes on the membrane to complete the collection of bacterial exosomes in urine. The collected bacterial exosome solution was vortexed, ultrasonicated 10 times (2s, 2s, 200W), and then centrifuged at 14000 g for 15 min to take the supernatant, and the bacterial exosomes separated from urine were obtained.

[0066] Figure 5 and Figure 6 This indicates that this method can successfully obtain bacterial exosomes in urine. Figure 5 As shown in Figure 2, the size and concentration of isolated urinary bEVs were characterized using nanoparticle tracking analysis. Figure 6 As shown, the morphology of bacterial exosomes was characterized by transmission electron microscopy.

[0067] Example 3 Diagnostic system for detecting bacterial exosomes in urine

[0068] When detecting the absorbance of bacterial exosomes in urine in Example 1, the main chemical reagents used, such as 3,3',5,5'-tetramethylbenzidine (TMB), hydrogen peroxide (H2O2), hemin chloride (Hemin), titanium dioxide (TiO2), N-methylpyrrolidone, etc., were all analytically pure and purchased from Sinopharm Chemical Reagent Co., Ltd. (Shanghai, China).

[0069] The functionalized graphene solution was incubated with urine bacterial exosomes, buffer solutions of different pH values, TMB and hydrogen peroxide to form a multi-channel colorimetric detection array. For the collection of colorimetric absorbance of the multi-channel colorimetric detection array, the absorbance of the sensing system at 652 nm was collected using an ELISA instrument to construct a data set for the diagnosis of urinary tract infections.

[0070] Specifically, 10 μL of functionalized graphene solution, 20 μL of bacterial exosome solution, 10 μL of 50 mM hydrogen peroxide, 10 μL of 10 mM TMB and 150 μL of 100 mM phosphate buffer (pH = 4, 5, 6) were added to a 96-well plate to form a mixed solution, incubated for 25 min, and the ultraviolet absorption value at 652 nm was detected using an ELISA detection system to form a three-dimensional array * urine exosomes * matrix data set of different human samples.

[0071] Gram-negative bacteria E. coli and Gram-positive bacteria S. aureus were selected as representative strains to investigate the detection of bacterial exosomes by the sensor array; the concentration of bacterial exosomes was adjusted to 10 9 particles / mL for subsequent experimental analysis; e.g. Figure 7 It can be clearly seen that the functionalized graphyne solution can detect bacterial exosomes under different pH conditions; and different bacteria E. coli and S. aureus have different catalytic inhibition on functionalized graphyne, indicating that the system can realize the diagnosis of different levels of urinary tract infection.

[0072] Taking E. coli as a representative of Gram-negative bacteria, proteinase K and ethylenediaminetetraacetic acid (EDTA) were used to remove proteins and lipopolysaccharides on exosomes, and the binding of functionalized Graphyne to exosomes with removed surface proteins and lipopolysaccharides was investigated. The results showed that the functionalized Graphyne was more inclined to bind to lipopolysaccharides. DFT calculation was used to explore the binding site of functionalized Graphyne with E. coli exosomes. Lipopolysaccharide is composed of core polysaccharide, O-antigen and lipids. Density functional theory (DFT) was used to calculate the free binding energy of functionalized Graphyne with antigens, polysaccharides and lipids. Figure 8 As shown in the figure, the binding free energies are -1.19eV (antigen), -0.99eV (polysaccharide) and -0.90eV (lipid), respectively. The measurement results show that functionalized Graphene is more inclined to bind to the O-antigen in lipopolysaccharide. DFT is used to further characterize the binding mechanism between functionalized Graphene and lipopolysaccharide. The intermolecular forces between functionalized Graphene and O-antigen mainly include hydrogen bonds, covalent bonds and electrostatic effects. Through DFT calculation and analysis, the binding free energies of the three are -0.74eV (hydrogen bonds), -0.31eV (covalent bonds) and -0.14eV (electrostatic effects), respectively. The results show that the binding between functionalized Graphene and O-antigen mainly depends on hydrogen bonds, indicating that the capture ability of bacterial exosomes can be improved through surface interface molecular modification.

[0073] Example 4

[0074] For the diagnosis of urinary tract infections:

[0075] The urethra is a common site of bacterial infection in adults. The urine composition of healthy people and patients with urinary tract infection is very different. Healthy urine contains a small amount of white blood cells and red blood cells, and no pathogenic bacteria; on the contrary, the urine of patients with urinary tract infection contains pathogenic bacteria such as Escherichia coli, Klebsiella and Staphylococcus aureus. Therefore, based on the differences in exosomes secreted by cells and bacteria in urine, it can be used for the diagnosis of urinary tract infection diseases. The present invention combines the constructed multi-channel colorimetric detection array with a machine learning algorithm to construct a mathematical model for the diagnosis of urinary tract infection diseases.

[0076] In the embodiment, a multivariate linear regression algorithm (MLR) is selected as a classification diagnosis model for urinary tract infection diseases. Fig. 9 The method of constructing the intelligent diagnosis model is shown in the figure. The intelligent mathematical model classifier can perform arithmetic operations such as weighting, summation, and subtraction.

[0077] Taking the three different pH values ​​of the Graphene detection array of the embodiment of the present invention as an example, firstly, the three-dimensional data, i.e., the absorbance A at three different pH values, is converted into n Perform weighted multiplication, A n Including A1, A2 and A3, representing the absorbance of the graphyne detection array at different pH values, the specific multiplication calculation formula is:

[0078] F n =A n ×W n

[0079] Among them, W n represents the predetermined weights of the Graphene detection array at different pH values ​​in the mathematical model classifier, F n Represents the weighted multiplication of the Graphene Oxide Detection Array at different pH values, A n Represents the absorbance of the Graphdine detection array at different pH values.

[0080] Add the obtained data F1, F2 and F3 and compare them:

[0081] T=F1+F2+F3+m

[0082] Among them, T represents the output value of the diagnostic system for urinary tract infection, m is a constant, and the diagnostic result is output according to the T value. The threshold of the intelligent diagnostic system is usually set to 0. The classification results below 0 are healthy, and those above 0 are patients with urinary tract infection.

[0083] 60 healthy urine samples and 60 urinary tract infection disease samples were collected, and 150 μL 100 mM phosphate buffer with pH = 4, 5, and 6, 10 μL 50 mM hydrogen peroxide, and 10 μL 10 mM TMB were added in sequence, and mixed evenly to form a mixed solution; the mixed solution was incubated at 25°C for 30 min, transferred to a 96-well plate, and the ultraviolet absorption value at 652 nm was detected by an ELISA detection system to form a training data matrix of 3 arrays × 2 types × 60 samples; the obtained training data matrix was analyzed by MLR using SPSS Statistics 27 software to obtain a mathematical diagnostic model; Fig.10As shown, only one healthy sample was misidentified, and the remaining 39 clinical samples were correctly classified; the confusion matrix showed that the sensitivity, specificity, accuracy and precision of the mathematical model classifier were 95.0%, 100.0%, 97.5% and 100.0%, respectively; the AUC of the sensing system was 0.99.

[0084] Compared with existing urinary tract infection diagnostic strategies, the mathematical model classifier constructed in the present invention has the advantages of fast detection speed, low cost and simple operation; in addition, the detection method does not require direct contact with pathogens and is therefore more friendly to laboratory operators; these results demonstrate the application potential of the mathematical model classifier based on the multivariate linear regression algorithm (MLR) in the diagnosis of uremia in clinical applications.

[0085] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in any form. Any technician familiar with the profession, without departing from the scope of the technical solution of the present invention and based on the technical essence of the present invention, may make any simple modifications, equivalent substitutions and improvements to the above embodiments, which are still within the protection scope of the technical solution of the present invention.

Claims

1. A diagnostic system for urinary tract infection, characterized in that: Includes urinary tract infection detector and optical detection system; The urinary tract infection detector comprises a plurality of groups of graphyne detection arrays containing functionalized graphyne, wherein the functionalized graphyne is graphyne modified by heme and titanium dioxide; The urinary tract infection detector is used to react with the pre-treated urine sample, and the optical detection system is used to measure the absorbance value data of the urinary tract infection detector.

2. The diagnostic system for urinary tract infection according to claim 1, characterized in that: The urinary tract infection detector comprises multiple groups of graphyne detection arrays, each group of graphyne detection arrays has a different pH, forming a multi-channel colorimetric detection array that can detect simultaneously; the detection wavelength of the optical detection system is 300-700nm.

3. The diagnostic system for urinary tract infection according to claim 1, characterized in that: In the graphyne detection array, hydrogen peroxide, peroxidase substrate and buffered salt solution are added to the functionalized graphyne.

4. The diagnostic system for urinary tract infection according to claim 3, characterized in that: Hydrogen peroxide, peroxidase substrate, and buffered saline solution are added to the functionalized graphene and incubated with the pretreated urine sample for 20-40 minutes.

5. The diagnostic system for urinary tract infection according to claim 1, characterized in that: The method for pretreatment of urine samples is: first centrifuge to obtain the supernatant, collect the bacterial exosomes in the urine by ultrafiltration and wash them with urea solution, and finally ultrasonicate and centrifuge.

6. The diagnostic system for urinary tract infection according to claim 1, characterized in that: It also includes a mathematical model classifier, which is a machine learning model for processing absorbance value data obtained by the optical detection system and outputting the results; the machine learning model supports at least one machine learning algorithm selected from the group consisting of a vector machine, a multivariate linear regression, an artificial neural network, a decision tree, and a random forest.

7. The diagnostic system for urinary tract infection according to claim 6, characterized in that: The machine learning model uses a multivariate linear regression algorithm to perform weighted multiplication on the absorbance, and the calculation formula is: F n =A n ×W n T=F1+F2+…+F n +m Where n=1, 2, ..., represents different groups of graphyne detection arrays, W n represents the predetermined weights of different groups of graphyne detection arrays in the mathematical model classifier, F n Represents the weighted multiplication of different groups of graphyne detection arrays, A n represents the absorbance values ​​of different groups of graphyne detection arrays, T represents the output value of the diagnostic system for urinary tract infection, and m is a constant.

8. The method for constructing a diagnostic system for urinary tract infection according to claim 1, characterized in that: include: Functionalized graphyne modified by heme and titanium dioxide is prepared, and multiple groups of graphyne detection arrays with different pH values ​​are combined into a multi-channel colorimetric detection array as a urinary tract infection detector; the urinary tract infection detector and an optical detection system are combined into a diagnostic system for urinary tract infection.

9. The method for constructing a diagnostic system for urinary tract infection according to claim 8, characterized in that: The heme and titanium dioxide functionalized graphyne is prepared by mixing graphyne with heme and titanium dioxide for reaction.

10. The method for constructing a diagnostic system for urinary tract infection according to claim 8, characterized in that: The measurement data of the optical detection system is transmitted to a machine learning model for processing the measurement data. The machine learning model evaluates the data processing results through evaluation indicators, and the evaluation indicators include accuracy, sensitivity, specificity, ROC curve and AUC value.

Images