Markers of early chronic kidney disease and their uses

Abstract

The present invention belongs to the field of biomedicine technology, and discloses markers for early chronic kidney disease and their uses. A marker for diagnosing and / or predicting early chronic kidney disease, the marker is selected from one or more of 4-heptanone, 2-methyl-2-butanol, o-xylene, n-octane, m-xylene, n-nonane, n-dodecane, n-tetradecane and styrene. The marker of the present invention can accurately distinguish between healthy people and patients with early chronic kidney disease, which is conducive to clinical treatment of the disease, and the marker is derived from exhaled breath. Because sampling has the advantages of being convenient, immediate and non-invasive, the present invention has important application value.

Description

Technical Field

[0001] The present invention belongs to the field of biomedicine technology, and specifically relates to markers of early chronic kidney disease and uses thereof. Background Art

[0002] Chronic kidney disease seriously endangers human health. According to statistics, the prevalence of chronic kidney disease worldwide is as high as 10-15%, and the mortality rate is about 1.5%.

[0003] Chronic kidney disease is a clinical general term for the vast majority of kidney diseases, such as glomerulonephritis, latent nephritis, pyelonephritis, Henoch-Schönlein purpura nephritis, lupus erythematosus nephritis, gouty kidney, IgA nephropathy, nephrotic syndrome, membranous nephropathy, diabetic nephropathy, hypertensive nephropathy, and polycystic kidney disease. It can lead to chronic kidney structural and functional disorders, such as pathological damage to the glomerular filtration rate, abnormal blood or urine components, and abnormal imaging examinations, or decreased glomerular filtration rate.

[0004] Chronic kidney disease is divided into five stages based on glomerular filtration rate (GFR): stage 1, stage 2, stage 3, stage 4, and stage 5, with increasing severity. The unit of GFR is mL / (min·1.73m 2 ), when GFR ≥ 90, it is stage 1, when GFR is 60-89, it is stage 2, when GFR is 30-59, it is stage 3, when GFR is 15-29, it is stage 4, and when GFR is <15, it is stage 5. Early diagnosis and treatment can help slow down and avoid its progression to end-stage renal disease, thereby improving treatment efficacy and reducing treatment costs. Currently, the diagnosis of chronic kidney disease is mainly based on blood and urine analysis, but the collection of blood and urine is inconvenient, and the pre-treatment process is complicated, making it difficult to perform high-frequency testing. In addition, the markers in blood and urine have problems with insufficient sensitivity and specificity.

[0005] Compared with blood and urine testing, breath testing is convenient for multiple collections and easier to pre-process. If stage 1 chronic kidney disease can be diagnosed in time, it will be beneficial for early treatment of chronic kidney disease and improve the cure rate. However, there is currently no exhaled breath marker that can identify stage 1 chronic kidney disease. Summary of the invention

[0006] In view of the above-mentioned shortcomings of the prior art, the purpose of the present invention is to provide a marker for early chronic kidney disease and a use thereof, in order to solve the problems existing in the prior art.

[0007] To achieve the above purpose, the present invention specifically adopts the following technical solutions.

[0008] The purpose of the present invention is to protect a marker for diagnosing and / or predicting early chronic kidney disease, wherein the marker is selected from one or more of 4-heptanone, 2-methyl-2-butanol, o-xylene, n-octane, m-xylene, n-nonane, n-dodecane, n-tetradecane and styrene.

[0009] In certain embodiments of the present invention, the marker comprises a combination of 4-heptanone and n-dodecane.

[0010] In certain embodiments of the present invention, the marker is selected from a combination of 4-heptanone, 2-methyl-2-butanol and o-xylene.

[0011] In certain embodiments of the present invention, the marker is selected from a combination of 4-heptanone, 2-methyl-2-butanol and n-octane.

[0012] In certain embodiments of the present invention, the marker is selected from a combination of 4-heptanone, 2-methyl-2-butanol, o-xylene and n-octane.

[0013] In certain embodiments of the present invention, the volatility marker is selected from a combination of 4-heptanone, 2-methyl-2-butanol, n-tetradecane and styrene.

[0014] In certain embodiments of the present invention, the marker is selected from a combination of 4-heptanone, o-xylene, m-xylene and n-nonane.

[0015] In certain embodiments of the present invention, the marker is selected from a combination of 4-heptanone, 2-methyl-2-butanol, o-xylene, n-octane and m-xylene.

[0016] In certain embodiments of the present invention, the marker is selected from a combination of 4-heptanone, 2-methyl-2-butanol, o-xylene, n-octane, m-xylene and n-nonane.

[0017] In certain embodiments of the present invention, the marker is selected from a combination of 4-heptanone, 2-methyl-2-butanol, o-xylene, n-octane, m-xylene, n-nonane and n-dodecane.

[0018] In certain embodiments of the present invention, the marker is selected from a combination of 4-heptanone, 2-methyl-2-butanol, o-xylene, n-octane, m-xylene, n-nonane, n-dodecane and n-tetradecane.

[0019] In certain embodiments of the present invention, the marker is selected from a combination of 4-heptanone, 2-methyl-2-butanol, o-xylene, n-octane, m-xylene, n-nonane, n-dodecane, n-tetradecane and styrene.

[0020] In certain embodiments of the present invention, the marker is derived from exhaled air, preferably alveolar exhaled air.

[0021] The present invention also aims to protect the use of a substance for detecting the markers as described above in the preparation of a product for diagnosing and / or predicting early chronic kidney disease.

[0022] In certain embodiments of the present invention, the substance for detecting a marker refers to a substance with a volume or mass concentration of the marker.

[0023] The present invention also aims to protect a product for in vitro diagnosis and / or prediction of early chronic kidney disease, which comprises the substance for detecting markers as described above.

[0024] In certain embodiments of the present invention, the product comprises at least one of a kit, a membrane strip, a chip and a detection system.

[0025] Preferably, the detection system is selected from a gas sensing system or a gas chromatograph.

[0026] The present invention also aims to protect a method for screening a marker as described above, comprising the following steps:

[0027] Detecting the types and amounts of compounds in samples from subjects, including patients with stage 1 chronic kidney disease and healthy subjects;

[0028] The test results are analyzed to obtain compounds that are different between stage 1 chronic kidney disease patients and healthy people, namely the markers.

[0029] In certain embodiments of the present invention, the analysis method includes t-test or z-test analysis, and the P value is calculated. The compound with a P value < 0.05 is the marker.

[0030] In certain embodiments of the present invention, the sample is exhaled air, preferably alveolar exhaled air.

[0031] In certain embodiments of the present invention, the method for detecting the compound is:

[0032] Adsorbents are used to enrich the exhaled breath of the subjects;

[0033] A thermal desorber is used to perform thermal desorption on the adsorbent after enriching the exhaled air, and then a gas chromatography-mass spectrometry method is used for detection. The detection results are qualitatively and quantitatively analyzed. The type of the compound is obtained according to the qualitative analysis, and the content of the compound is obtained according to the quantitative analysis.

[0034] The present invention also aims to protect a method for constructing an early chronic kidney disease risk prediction model, the method comprising the following steps:

[0035] 1) constructing a sample data set based on the detection amounts of the markers described above in the samples of the subjects, wherein the subjects include patients with confirmed clinical stage 1 chronic kidney disease and healthy people;

[0036] 2) randomly dividing the sample data set into a test set and a training set, using a machine learning method to learn the training set to obtain the early chronic kidney disease prediction model.

[0037] In certain embodiments of the present invention, the machine learning method is selected from at least one of a random forest algorithm, a support vector machine algorithm, a decision tree algorithm, a K nearest neighbor algorithm, a logistic regression algorithm, and a neural network algorithm. In certain preferred embodiments, it is a decision tree algorithm.

[0038] In certain embodiments of the present invention, the split ratio of the test set to the training set is 1:(1-3). In certain preferred embodiments, it is 1:2.

[0039] In certain embodiments of the present invention, the step 3) is also included in which the chronic kidney disease clinical staging prediction model is tested using a test set.

[0040] The present invention also aims to protect a device for diagnosing early chronic kidney disease, the device comprising:

[0041] A data module, used to obtain the detection amount data of the markers as described above in the sample of the subject;

[0042] The evaluation module processes the detection data using the chronic kidney disease clinical staging prediction model obtained by the construction method described above to output the chronic kidney disease clinical staging results.

[0043] The present invention also aims to protect a method for screening early chronic kidney disease, comprising the following steps:

[0044] S1. Obtaining the detection amount data of the markers as described above in the sample of the subject;

[0045] S2. Using the early chronic kidney disease prediction model obtained by the construction method described above to process the detection data to output a chronic kidney disease diagnosis result.

[0046] In certain embodiments of the present invention, the sample is exhaled air, preferably alveolar exhaled air.

[0047] The object of the present invention is also to protect a device, comprising a processor and a memory, wherein the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory so that the device performs the screening method as described above or the construction method as described above.

[0048] The object of the present invention also lies in protecting a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the screening method or the construction method as described above.

[0049] In the present invention, through large-scale screening of organic compounds in the exhaled breath of stage 1 chronic kidney disease patients and healthy people, it is found that there are significant differences in the contents of 9 volatile organic compounds, namely 4-heptanone, 2-methyl-2-butanol, o-xylene, n-octane, m-xylene, n-nonane, n-dodecane, n-tetradecane and styrene, between stage 1 chronic kidney disease patients and healthy people. Therefore, these 9 compounds in the exhaled breath are used as markers for predicting the early diagnosis or prediction of chronic kidney disease. The present invention also establishes an early chronic kidney disease risk prediction model, and the sensitivity of the model is greater than or equal to 86%, the specificity is greater than or equal to 67%, and the accuracy is greater than or equal to 74%, which can accurately distinguish healthy people from chronic kidney disease patients. Compared with blood and urine tests, the present invention uses compounds in the exhaled breath as markers to diagnose or predict early chronic kidney disease, which has the advantages of convenient multiple collection and easier pretreatment. In addition, it will be beneficial to determine clinical treatment methods, prescribe the right medicine, and improve the cure rate. Therefore, the present invention has important application value.

[0050] Compared with the prior art, the present invention has the following beneficial effects:

[0051] 1) The marker combination involved in the present invention can be applied to large-scale primary screening of stage 1 chronic kidney disease.

[0052] 2) Compared with blood and urine analysis, the sampling of exhaled breath analysis has the advantages of convenience and immediacy. Therefore, diagnosing chronic kidney disease through exhaled breath will greatly improve the compliance and comfort of the tested person; the collection process is non-invasive, simple and fast. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 It shows a schematic structural diagram of the CO2-controlled exhaled breath collection device used in the present invention. (A) The figure shows that when the CO2 in the exhaled breath < C50, the exhaled breath is not collected; (B) The figure shows that when the CO2 in the exhaled breath ≥ C50, the exhaled breath is collected in the air bag.

[0054] Figure 2 It shows a schematic diagram of the early chronic kidney disease risk prediction model of Example 2 of the present invention.

[0055] Figure 3 It shows a schematic diagram of the early chronic kidney disease risk prediction model of Example 3 of the present invention.

[0056] Figure 4 It shows a schematic diagram of the early chronic kidney disease risk prediction model of Example 4 of the present invention.

[0057] Figure 5 Shown is a schematic diagram of the early chronic kidney disease risk prediction model of Example 5 of the present invention.

[0058] Figure 6 Shown is a schematic diagram of the early chronic kidney disease risk prediction model of Example 6 of the present invention. DETAILED DESCRIPTION

[0059] The following is a description of the implementation of the present invention by means of specific embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification.

[0060] Before further describing the specific embodiments of the present invention, it should be understood that the scope of protection of the present invention is not limited to the specific embodiments described below; it should also be understood that the terms used in the examples of the present invention are intended to describe specific embodiments, rather than to limit the scope of protection of the present invention. The test methods in the following examples without specifying specific conditions are generally carried out under conventional conditions or under conditions recommended by the manufacturers.

[0061] When the embodiments give numerical ranges, it should be understood that, unless otherwise specified in the present invention, both endpoints of each numerical range and any numerical value between the two endpoints can be selected. Unless otherwise defined, all technical and scientific terms used in the present invention have the same meaning as those generally understood by those skilled in the art. In addition to the specific methods, equipment, and materials used in the embodiments, according to the grasp of the prior art by those skilled in the art and the record of the present invention, any methods, equipment, and materials of the prior art similar or equivalent to the methods, equipment, and materials described in the embodiments of the present invention can also be used to realize the present invention.

[0062] Currently, the diagnosis of chronic kidney disease mainly relies on blood and urine analysis. However, the collection of blood and urine is inconvenient, and the pre-treatment process is complicated, making it difficult to perform high-frequency testing. In addition, the markers in blood and urine have insufficient sensitivity and specificity. Therefore, this patent application is proposed.

[0063] The underlying principle of the present invention is that after a pathological change occurs in human tissue, it will cause changes in human metabolism, resulting in changes in the concentration of some volatile organic compounds in the blood. Volatile organic compounds can pass through the blood-air barrier in the lungs, so their concentration in the exhaled breath will change. Therefore, diseases can be identified by detecting changes in the concentration of certain volatile organic compounds in the exhaled breath.

[0064] To achieve the above-mentioned purpose, one of the objects of the present invention is to protect a marker for diagnosing and / or predicting early chronic kidney disease, wherein the marker is selected from one or more of 4-heptanone, 2-methyl-2-butanol, o-xylene, n-octane, m-xylene, n-nonane, n-dodecane, n-tetradecane and styrene.

[0065] In certain embodiments of the present invention, the marker comprises a combination of 4-heptanone and n-dodecane.

[0066] In certain embodiments of the present invention, the marker is selected from a combination of 4-heptanone, 2-methyl-2-butanol and o-xylene.

[0067] In certain embodiments of the present invention, the marker is selected from a combination of 4-heptanone, 2-methyl-2-butanol and n-octane.

[0068] In certain embodiments of the present invention, the marker is selected from a combination of 4-heptanone, 2-methyl-2-butanol, o-xylene and n-octane.

[0069] In certain embodiments of the present invention, the marker is selected from a combination of 4-heptanone, 2-methyl-2-butanol, n-tetradecane and styrene.

[0070] In certain embodiments of the present invention, the marker is selected from a combination of 4-heptanone, o-xylene, m-xylene and n-nonane.

[0071] In certain embodiments of the present invention, the volatile organic compound is selected from the group consisting of 4-heptanone, 2-methyl-2-butanol, o-xylene, n-octane and m-xylene.

[0072] In certain embodiments of the present invention, the volatile organic compound is selected from the group consisting of 4-heptanone, 2-methyl-2-butanol, o-xylene, n-octane, m-xylene and n-nonane.

[0073] In certain embodiments of the present invention, the volatile organic compound is selected from the group consisting of 4-heptanone, 2-methyl-2-butanol, o-xylene, n-octane, m-xylene, n-nonane and n-dodecane.

[0074] In certain embodiments of the present invention, the volatile organic compound is selected from the group consisting of 4-heptanone, 2-methyl-2-butanol, o-xylene, n-octane, m-xylene, n-nonane, n-dodecane and n-tetradecane.

[0075] In certain embodiments of the present invention, the volatile organic compound is selected from the group consisting of 4-heptanone, 2-methyl-2-butanol, o-xylene, n-octane, m-xylene, n-nonane, n-dodecane, n-tetradecane and styrene.

[0076] In order to achieve the above-mentioned purpose, the second object of the present invention is to protect the use of substances for detecting markers as described above in the preparation of products for diagnosing and / or predicting early chronic kidney disease.

[0077] In certain embodiments of the present invention, the substance for detecting a marker includes a substance for detecting the volume or mass concentration of the marker.

[0078] In order to achieve the above objectives, the third objective of the present invention is to protect a product for in vitro diagnosis and / or early prediction of chronic kidney disease, which comprises a substance for detecting markers for the use described above.

[0079] In certain embodiments of the present invention, the product comprises at least one of a kit, a membrane strip, a chip and a detection system.

[0080] For the above purpose, the fourth object of the present invention is to protect a method for screening a marker as described above, comprising the following steps:

[0081] Detecting the types and amounts of compounds in samples from subjects, including patients with stage 1 chronic kidney disease and healthy subjects;

[0082] The test results are analyzed to obtain compounds that are different between stage 1 chronic kidney disease patients and healthy people, namely the markers.

[0083] In certain embodiments of the present invention, the sample is exhaled air, preferably alveolar exhaled air.

[0084] In certain embodiments of the present invention, the analysis method includes t-test or z-test analysis, and the P value is calculated. The compound with a P value < 0.05 is the marker.

[0085] In certain embodiments of the present invention, the method for detecting the compound is:

[0086] Adsorbents are used to enrich the exhaled breath of the subjects;

[0087] A thermal desorber is used to perform thermal desorption on the adsorbent after enriching the exhaled air, and then a gas chromatography-mass spectrometry method is used for detection. The detection results are qualitatively and quantitatively analyzed. The type of the compound is obtained according to the qualitative analysis, and the content of the compound is obtained according to the quantitative analysis.

[0088] As a preferred embodiment, the adsorbent is selected from one or more of Tenax, Carbograph, Chromosorb and PoraPak.

[0089] As a preferred embodiment, the thermal desorption conditions are:

[0090] The primary desorption temperature is 280-320°C, and the desorption time is 5-15 min;

[0091] The secondary desorption temperature is 300-340°C and the desorption time is 2-8 min;

[0092] Transmission line temperature: 180~220℃;

[0093] No diversion.

[0094] As a preferred embodiment, the gas chromatography measurement conditions are:

[0095] Chromatographic column: HP-5ms, length 30m×inner diameter 0.25mm×film thickness 0.25μm;

[0096] Carrier gas: Helium purity ≥ 99.999%;

[0097] Carrier gas pressure: (5~15) psi;

[0098] Heating procedure: initial temperature 30-50°C, maintained for 2-8 min; then raised to 250-290°C at a rate of 5-15°C / min, maintained for 2-8 min.

[0099] As a preferred embodiment, the mass spectrometry conditions are:

[0100] Transmission line temperature: 220~260℃;

[0101] Ionization method: electron impact (EI);

[0102] Ionization voltage: 60-80 eV;

[0103] Ion source temperature: 210~250℃;

[0104] Quadrupole temperature: 130~170℃;

[0105] Detection mode: qualitative analysis by full scan total ion current (TIC), semi-quantitative analysis by peak area method;

[0106] Mass range: 35~390amu.

[0107] For the above purpose, the fifth purpose of the present invention is to protect a method for constructing an early chronic kidney disease risk prediction model, the construction method comprising the following:

[0108] 1) constructing a sample data set based on the detection amounts of the markers described above in the samples of the subjects, wherein the subjects include patients with confirmed clinical stage 1 chronic kidney disease and healthy people;

[0109] 2) randomly dividing the sample data set into a test set and a training set, using a machine learning method to learn the training set to obtain the early chronic kidney disease prediction model.

[0110] In certain embodiments of the present invention, the machine learning method is selected from at least one of a random forest algorithm, a support vector machine algorithm, a decision tree algorithm, a K nearest neighbor algorithm, a logistic regression algorithm, and a neural network algorithm. In certain preferred embodiments, it is a decision tree algorithm.

[0111] In certain embodiments of the present invention, the split ratio of the test set to the training set is 1:(1-3). In certain preferred embodiments, it is 1:2.

[0112] In certain embodiments of the present invention, the construction method further comprises step 3) testing the chronic kidney disease clinical staging prediction model using a test set.

[0113] Exemplarily, the early chronic kidney disease risk prediction model is as follows: model<-rpart(formula,train_data), where formula represents the modeling formula and train_data represents the training set data.

[0114] If you want to check whether each sample is chronic kidney disease, you can enter the code: rpart_pred<-predict(model,test_data,type="class"), where model represents the model, test_data represents the test set data, and type="class" represents whether it is chronic kidney disease.

[0115] The early chronic kidney disease risk prediction model of the present invention has a sensitivity greater than or equal to 86%, a specificity greater than or equal to 67%, and an accuracy greater than or equal to 74%, showing good predictive ability.

[0116] In order to achieve the above-mentioned purpose, the sixth object of the present invention is to protect a device for diagnosing early chronic kidney disease, the device comprising:

[0117] A data module, used to obtain the detection amount data of the markers as described above in the sample of the subject;

[0118] The evaluation module processes the detection data using the chronic kidney disease clinical staging prediction model obtained by the construction method described above to output the chronic kidney disease clinical staging results.

[0119] For the above purpose, the seventh object of the present invention is to protect a method for early chronic kidney disease screening, comprising the following steps:

[0120] S1. Obtaining the detection amount data of the markers as described above in the sample of the subject;

[0121] S2. Using the early chronic kidney disease prediction model obtained by the construction method described above to process the detection data to output a chronic kidney disease diagnosis result.

[0122] In certain embodiments of the present invention, the sample is exhaled air, preferably alveolar exhaled air.

[0123] To achieve the above-mentioned objectives, an eighth object of the present invention is to protect a device comprising a processor and a memory, wherein the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory so that the device performs the screening method as described above or the construction method as described above.

[0124] For the above-mentioned purpose, the ninth object of the present invention is to protect a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the screening method as described above or the construction method as described above.

[0125] Figure 1 The diagram is a schematic diagram of the structure of the exhaled air collection device used in the present invention. The exhaled air analysis device used in the present invention includes an exhaled air collection device, an adsorption tube, a thermal desorber and a gas chromatograph-mass spectrometer. The specific method of use is to use CO2 to control the exhaled air collection device to collect the alveolar exhaled air of the subject in a Teflon air bag, and then transfer the exhaled air in the air bag to an adsorption tube filled with Tenax TA adsorption material for enrichment, and put the adsorption tube enriched with exhaled air components into the thermal desorber for heating to desorb the exhaled air components, and the desorbed exhaled air components are delivered to a gas chromatograph-mass spectrometer with a chromatographic column of HP-5ms for detection. The exhaled air collection device, adsorption tube and thermal desorber used are all existing devices on the market.

[0126] In the following examples of the present application, UNITY-xr TD thermal desorber (Markes International, UK); 8890 / 5977B gas chromatograph-mass spectrometer (Agilent, USA);

[0127] The conditions for thermal desorption are:

[0128] The primary desorption temperature was 300 °C and the desorption time was 10 min;

[0129] The secondary desorption temperature was 320 °C and the desorption time was 3 min;

[0130] Transmission line temperature: 200°C;

[0131] No diversion.

[0132] The gas chromatography conditions are:

[0133] Chromatographic column: Chromatographic column: Chromatographic column HP-5ms, length 30m × inner diameter 0.25mm × film thickness 0.25μm;

[0134] Carrier gas: Helium purity ≥ 99.999%;

[0135] Carrier gas pressure: 10psi;

[0136] Heating program: initial temperature 40°C, maintained for 5 min; then increased to 270°C at a rate of 10°C / min, maintained for 5 min.

[0137] The mass spectrometry conditions are:

[0138] Transmission line temperature: 240°C;

[0139] Ionization method: electron impact (EI);

[0140] Ionization voltage: 70 eV;

[0141] Ion source temperature: 230°C;

[0142] Quadrupole temperature: 150℃;

[0143] Detection mode: qualitative analysis by full scan total ion current (TIC), semi-quantitative analysis by peak area method;

[0144] Mass range: 35~390amu.

[0145] All materials, reagents and instruments used in the present invention are well known in the art, but do not limit the implementation of the present invention. Other reagents and equipment well known in the art can be applied to the implementation of the following embodiments of the present invention.

[0146] Example 1

[0147] In this embodiment, the Figure 1 The CO2 controlled exhaled air collection device shown collects the alveolar exhaled air of the subject, analyzes the collected alveolar exhaled air, and screens out compounds with significant differences in content between chronic kidney disease patients and healthy people as markers. Including the following:

[0148] Subject groups: including chronic kidney disease patient group and healthy control group. The chronic kidney disease patient group consisted of 21 stage 1 chronic kidney disease patients, and the healthy control group consisted of 36 healthy people.

[0149] Both the chronic kidney disease group and the healthy control group rinsed their mouths with pure water before collecting exhaled breath.

[0150] Method design: Exhaled breath was collected from the chronic kidney disease patient group and the healthy control group. After pretreatment, the exhaled breath was analyzed by gas chromatography-mass spectrometry to obtain the chromatographic peak area of ​​the compounds. The chromatographic peak area of ​​the exhaled breath compounds of the chronic kidney disease patient group and the healthy control group was analyzed univariately to screen out the compounds with significant differences between the chronic kidney disease patient group and the control group.

[0151] 1.1 Exhaled breath collection

[0152] Based on the Fowler model, the exhaled gas CO2 concentration is increased by 50% (C50) to distinguish between anatomical dead space exhaled gas and alveolar exhaled gas. When the exhaled gas is lower than C50, the collection device does not collect this part of the exhaled gas; when the exhaled gas is higher than C50, the collection device collects this part of the exhaled gas in a Teflon air bag, and the exhaled gas collection volume is 3L.

[0153] 1.2 Exhaled breath detection

[0154] The exhaled breath was transferred to an adsorption tube filled with Tenax TA adsorbent for enrichment, and then detected by gas chromatography-mass spectrometry through thermal desorption injection to obtain the test results.

[0155] 1.3 Analysis of test results

[0156] According to the NIST14 database and the retention time of the standard substances, the test results obtained in step 1.2 were qualitatively and quantitatively analyzed, and a total of 16 compounds in the exhaled breath were identified.

[0157] 1.4 Screening of Volatile Organic Compounds as Biomarkers

[0158] The t-test method was used to compare the chromatographic peak areas of the 16 compounds identified between the chronic kidney disease group and the healthy control group. The compounds with significant differences (P<0.05) between the two groups were used as markers. A total of 9 volatile organic compounds were screened out, including 4-heptanone, 2-methyl-2-butanol, o-xylene, n-octane, m-xylene, n-nonane, n-dodecane, n-tetradecane and styrene. The contents of these 9 volatile organic compounds in the exhaled breath of the chronic kidney disease group were significantly lower than those in the healthy control group. The names, retention times, chromatographic peak areas and t-test analysis results of the compounds in the exhaled breath are shown in Table 1.

[0159] Table 1

[0160]

[0161]

[0162] Example 2

[0163] In this embodiment, a sample data set is constructed based on the detection amount of the markers of the subjects in Example 1, and a decision tree algorithm is used to learn and construct an early chronic kidney disease risk prediction model. It includes the following:

[0164] 1) The exhaled breath samples of 57 subjects were randomly divided into 3 groups, 2 groups of samples were used as training sets, and 1 group of samples was used as a test set. The characteristics of the training set and the test set were the contents of 4-heptanone and n-dodecane.

[0165] 2) The decision tree model is used to learn the data in the training set to obtain the early chronic kidney disease risk prediction model. Figure 2 .

[0166] 3) The early chronic kidney disease risk prediction model was evaluated using the test set data. The evaluation indicators included sensitivity, specificity and accuracy. The results are shown in Table 2.

[0167] Sensitivity: The proportion of patients with stage 1 CKD correctly identified among all patients with stage 1 CKD.

[0168] Specificity: The proportion of healthy people correctly identified among all healthy people.

[0169] Accuracy: The proportion of correctly identified stage 1 CKD patients and healthy subjects among all subjects.

[0170] The caret package (6.0-92) of R software (version 4.1.3) was used to construct an early chronic kidney disease risk prediction model and validated using a test set.

[0171] a) Use the decision tree model to learn the training set and obtain the early chronic kidney disease risk prediction model.

[0172] Use the following command line: model<-rpart(formula,train_data), where formula represents the modeling formula and train_data represents the training set data.

[0173] b) Substitute the test set into the early chronic kidney disease risk prediction model for evaluation.

[0174] Use the following command line:

[0175] rpart_pred<-predict(model,test_data,type="class")where model represents the model, test_data represents the test set data, and type="class" represents whether it is chronic kidney disease.

[0176] As can be seen from Table 2, the sensitivity of the chronic kidney disease diagnostic model of the present invention for distinguishing between healthy people and patients with stage 1 chronic kidney disease is 86%, the specificity is 67%, and the accuracy is 74%.

[0177] Example 3

[0178] In this embodiment, a sample data set is constructed based on the detection amount of the markers of the subjects in Example 1, and a decision tree algorithm is used for learning to construct an early chronic kidney disease risk prediction model. It includes the following:

[0179] 1) The exhaled breath samples of 57 subjects were randomly divided into 3 groups, 2 groups of samples were used as training sets, and 1 group of samples was used as a test set. The characteristics of the training set and the test set were the contents of 4-heptanone, 2-methyl-2-butanol and o-xylene.

[0180] 2) The decision tree model was used to learn the training set and obtain the early chronic kidney disease risk prediction model. Figure 3 .

[0181] 3) The early chronic kidney disease risk prediction model was evaluated using the test set. The evaluation indicators included sensitivity, specificity and accuracy. The results are shown in Table 2.

[0182] As can be seen from Table 2, the sensitivity of the early chronic kidney disease risk prediction model of the present invention for healthy people and patients with stage 1 chronic kidney disease is 86%, the specificity is 83%, and the accuracy is 84%.

[0183] Example 4

[0184] In this embodiment, a sample data set is constructed based on the detection amount of the markers of the subjects in Example 1, and a decision tree algorithm is used to learn and construct an early chronic kidney disease risk prediction model. It includes the following:

[0185] 1) The exhaled breath samples of 57 subjects were randomly divided into 3 groups, 2 groups of samples were used as training sets, and 1 group of samples was used as a test set. The characteristics of the training set and the test set were the contents of 4-heptanone, 2-methyl-2-butanol and n-octane.

[0186] 2) The decision tree model was used to learn the training set and obtain the early chronic kidney disease risk prediction model. Figure 4 .

[0187] 3) The early chronic kidney disease risk prediction model was evaluated using the test set. The evaluation indicators included sensitivity, specificity and accuracy. The results are shown in Table 2.

[0188] As can be seen from Table 2, the sensitivity, specificity and accuracy of the early chronic kidney disease risk prediction model of the present invention for distinguishing between healthy people and patients with stage 1 chronic kidney disease are 86%, 83% and 84%.

[0189] Example 5

[0190] In this embodiment, a sample data set is constructed based on the detection amount of the markers of the subjects in Example 1, and a decision tree algorithm is used to learn and construct an early chronic kidney disease risk prediction model. It includes the following:

[0191] 1) The exhaled breath samples of 57 subjects were randomly divided into 3 groups, 2 groups of samples were used as training sets, and 1 group of samples was used as a test set. The characteristics of the training set and the test set were the contents of 4-heptanone, 2-methyl-2-butanol, n-tetradecane and styrene.

[0192] 2) The decision tree model was used to learn the training set and obtain the early chronic kidney disease risk prediction model. Figure 5 .

[0193] 3) The early chronic kidney disease risk prediction model was evaluated using the test set. The evaluation indicators included sensitivity, specificity and accuracy. The results are shown in Table 2.

[0194] As can be seen from Table 2, the sensitivity of the early chronic kidney disease risk prediction model of the present invention for distinguishing between healthy people and patients with stage 1 chronic kidney disease is 86%, the specificity is 75%, and the accuracy is 79%.

[0195] Example 6

[0196] In this embodiment, a sample data set is constructed based on the detection amount of the markers of the subjects in Example 1, and a decision tree algorithm is used to learn and construct an early chronic kidney disease risk prediction model. It includes the following:

[0197] 1) The exhaled breath samples of 57 subjects were randomly divided into 3 groups, 2 groups of samples were used as training sets, and 1 group of samples was used as a test set. The characteristics of the training set and the test set were the contents of 4-heptanone, o-xylene, m-xylene and n-nonane.

[0198] 2) The decision tree model is used to learn the training set and obtain the chronic kidney disease diagnosis model. Figure 6 .

[0199] 3) The early chronic kidney disease risk prediction model was evaluated using the test set. The evaluation indicators included sensitivity, specificity and accuracy. The results are shown in Table 2.

[0200] As can be seen from Table 2, the sensitivity of the early chronic kidney disease risk prediction model of the present invention for distinguishing between healthy people and patients with stage 1 chronic kidney disease is 86%, the specificity is 75%, and the accuracy is 79%.

[0201] Table 2

[0202] Volatile organic compounds Sensitivity (%) Specificity (%) Accuracy (%) 1、7 86 67 74 1、2、3 86 83 84 1、2、4 86 83 84 1、2、8、9 86 75 79 1、3、5、6 86 75 79

[0203] Among them, the volatile organic compound combinations 1 and 7 in Table 2 are the compositions numbered 1 and 7 in Table 1, that is, the combination of 4-heptanone and n-dodecane; 1, 2, 3 are the compositions numbered 1, 2, 3 in Table 1, that is, the combination of 4-heptanone, 2-methyl-2-butanol and o-xylene; 1, 2, 4 are the compositions numbered 1, 2, 4 in Table 1, that is, the combination of 4-heptanone, 2-methyl-2-butanol and n-octane; 1, 2, 8, 9 are the compositions numbered 1, 2, 8, 9 in Table 1, that is, the combination of 4-heptanone, 2-methyl-2-butanol, n-tetradecane and styrene; 1, 3, 5, 6 are the compositions numbered 1, 3, 5, 6 in Table 1, that is, the combination of 4-heptanone, o-xylene, m-xylene and n-nonane.

[0204] As can be seen from Table 2, the sensitivity of the constructed early chronic kidney disease risk prediction model is greater than or equal to 86%, the specificity is greater than or equal to 67%, and the accuracy is greater than or equal to 74%, indicating that the decision tree model constructed with the screened markers as features can accurately distinguish between healthy people and patients with stage 1 chronic kidney disease.

[0205] Conclusions: A combination of nine markers, including 4-heptanone, 2-methyl-2-butanol, o-xylene, n-octane, m-xylene, n-nonane, n-dodecane, n-tetradecane, and styrene, can identify stage 1 chronic kidney disease.

[0206] In summary, the present invention conducts large-scale screening of organic matter in the exhaled breath of patients with stage 1 chronic kidney disease and healthy people, and finds that the contents of 9 volatile organic compounds, including 4-heptanone, 2-methyl-2-butanol, o-xylene, n-octane, m-xylene, n-nonane, n-dodecane, n-tetradecane and styrene, are significantly different between patients with stage 1 chronic kidney disease and healthy people, so these 9 compounds in the exhaled breath are used as markers for early diagnosis or prediction of chronic kidney disease. The present invention also establishes an early chronic kidney disease risk prediction model, the sensitivity of the model is greater than or equal to 86%, the specificity is greater than or equal to 67%, and the accuracy is greater than or equal to 74%, which can accurately distinguish healthy people from patients with chronic kidney disease. Compared with blood and urine tests, the present invention uses compounds in exhaled breath as markers to diagnose or predict early chronic kidney disease, which has the advantages of convenient multiple collection and easier pretreatment. In addition, it will be beneficial to determine clinical treatment methods, prescribe the right medicine for the right disease, and improve the cure rate, so the present invention has important application value.

[0207] The above embodiments are merely illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. Anyone familiar with the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by a person of ordinary skill in the art without departing from the spirit and technical concept disclosed by the present invention shall still be covered by the claims of the present invention.

Claims

1. A marker for diagnosing and / or predicting early chronic kidney disease, characterized in that: The marker is derived from exhaled breath, and the marker is selected from one or more of 4-heptanone, 2-methyl-2-butanol, o-xylene, n-octane, m-xylene, n-nonane, n-dodecane, n-tetradecane and styrene; and the marker is selected from at least one of the following technical features: 1) The marker is selected from a combination of 4-heptanone and n-dodecane; 2) The marker is selected from a combination of 4-heptanone, 2-methyl-2-butanol and o-xylene; 3) The marker is selected from a combination of 4-heptanone, 2-methyl-2-butanol and n-octane; 4) The marker is selected from a combination of 4-heptanone, 2-methyl-2-butanol, o-xylene and n-octane; 5) The marker is selected from a combination of 4-heptanone, 2-methyl-2-butanol, n-tetradecane and styrene; 6) The marker is selected from a combination of 4-heptanone, o-xylene, m-xylene and n-nonane; 7) The marker is selected from a combination of 4-heptanone, 2-methyl-2-butanol, o-xylene, n-octane and m-xylene; 8) The marker is selected from the group consisting of 4-heptanone, 2-methyl-2-butanol, o-xylene, n-octane, m-xylene and n-nonane; 9) The marker is selected from the group consisting of 4-heptanone, 2-methyl-2-butanol, o-xylene, n-octane, m-xylene, n-nonane and n-dodecane; 10) The marker is selected from the group consisting of 4-heptanone, 2-methyl-2-butanol, o-xylene, n-octane, m-xylene, n-nonane, n-dodecane and n-tetradecane; 11) The marker is selected from the group consisting of 4-heptanone, 2-methyl-2-butanol, o-xylene, n-octane, m-xylene, n-nonane, n-dodecane, n-tetradecane and styrene.

2. Use of a substance for detecting the marker as claimed in claim 1 in the preparation of a product for diagnosing and / or predicting early chronic kidney disease.

3. The use according to claim 2, characterized in that The substance for detecting a marker includes a substance for detecting the volume or mass concentration of the marker.

4. A product for in vitro diagnosis and / or prediction of early chronic kidney disease, characterized in that: The product comprises the substance for detecting a marker for use as claimed in claim 2 or 3.

5. Use of the marker according to claim 1 or the product according to claim 4 in screening drugs for treating and / or preventing chronic kidney disease.

6. A method for constructing a risk prediction model for early chronic kidney disease, characterized in that: The construction method includes the following: 1) constructing a sample data set based on the detection amount of the marker as claimed in claim 1 in the subject sample, wherein the subject includes patients with confirmed clinical stage 1 chronic kidney disease and healthy people; 2) Randomly dividing the sample data set into a test set and a training set, using a machine learning method to learn the training set to obtain the early chronic kidney disease prediction model.

7. The construction method according to claim 6, characterized in that: The sample is selected from exhaled breath; And / or, the machine learning method is selected from at least one of a random forest algorithm, a support vector machine algorithm, a decision tree algorithm, a K nearest neighbor algorithm, a logistic regression algorithm, and a neural network algorithm; And / or, the split ratio of the test set to the training set is 1:(1-3); And / or, the method further includes step 3) testing the chronic kidney disease clinical staging prediction model using a test set.

8. A method for screening early chronic kidney disease, characterized in that: The steps include: S1. Obtaining the detection amount data of the marker according to claim 1 in the sample of the subject; S2. Using the early chronic kidney disease prediction model obtained by the construction method as described in claim 6 or 7 to process the detection data to output a chronic kidney disease diagnosis result.

9. A device for diagnosing early chronic kidney disease, characterized in that: The device comprises: A data module, used to obtain the detection amount data of the marker according to claim 1 in the sample of the subject; An evaluation module processes the detection data using the chronic kidney disease clinical staging prediction model obtained by the construction method as described in claim 6 or 7 to output a chronic kidney disease diagnosis result.

10. A device comprising a processor and a memory, wherein the memory is used to store a computer program, characterized in that: The processor is used to execute the computer program stored in the memory so as to enable the device to perform the screening method according to claim 8 or the construction method according to claim 6 or 7.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the screening method according to claim 8 or the construction method according to claim 6 or 7 is implemented.

Images