A method for predicting cardiovascular and cerebrovascular events in end-stage renal disease based on plasma lipidomics and red blood cell lipidomics

Abstract

The present invention discloses a method for predicting cardiovascular and cerebrovascular events in end-stage renal disease based on plasma lipidomics and red blood cell lipidomics, specifically involving biomarkers PC42:6, PC42:7, and SM d18:1 / 14:0. The biomarkers also include age, gender, and dialysis years, indicators of new cardiovascular and cerebrovascular events. The present invention provides the use of reagents for detecting the above biomarkers in the preparation of products for assisting in the diagnosis or prediction of whether end-stage renal disease is complicated by cardiovascular and cerebrovascular diseases. The present invention provides products for assisting in the diagnosis or prediction of whether end-stage renal disease is complicated by cardiovascular and cerebrovascular diseases. The present invention also provides the application and construction method of related computer models. The present invention also provides the application of the above biomarkers in a system for automated auxiliary diagnosis or prediction of whether end-stage renal disease is complicated by cardiovascular and cerebrovascular diseases. The present invention also provides the application of the above biomarkers in the preparation of products for end-stage renal disease typing and the construction method.

Description

Technical Field

[0001] The present invention belongs to the field of biotechnology and relates to a method for predicting cardiovascular and cerebrovascular events in end-stage renal disease based on plasma lipidomics and red blood cell lipidomics, and specifically relates to biomarkers PC42:6, PC42:7, and SM d18:1 / 14:0. Background Art

[0002] End-stage renal disease (ESRD) refers to the terminal stage of various chronic kidney diseases. It has a high incidence and heavy disease burden and is currently a major global public health issue. ESRD patients experience severe electrolyte and hemodynamic disorders in their bodies, and their risk of cardiovascular and cerebrovascular disease (CVD) increases accordingly. Hemodialysis is an important treatment for ESRD patients. The hemodialysis process causes drastic changes in electrolytes and hemodynamics, which ultimately further increases the risk of various cardiovascular and cerebrovascular diseases and even sudden death. Therefore, predicting the CVD risk of ESRD patients is crucial. Currently, there is no good method to predict whether ESRD patients on dialysis will develop CVD. Summary of the Invention

[0003] In order to solve the technical problems existing in the prior art, the present invention provides the following technical solutions:

[0004] The present invention provides the use of a reagent for detecting biomarkers in a sample in the preparation of a product for auxiliary diagnosis or prediction of whether end-stage renal disease is complicated by cardiovascular and cerebrovascular diseases. The biomarkers include PC42:6, PC42:7, and SM d18:1 / 14:0.

[0005] Furthermore, the biomarkers include a combination of PC42:6, PC42:7, and SM d18:1 / 14:0.

[0006] Furthermore, the biomarkers also include prediction / diagnosis indicators for new cardiovascular and cerebrovascular events, and the indicators include age, gender, and dialysis years.

[0007] Furthermore, the biomarkers also include prediction / diagnosis indicators for new cardiovascular and cerebrovascular events, and the indicators include a combination of age, gender, and dialysis years.

[0008] Sphingomyelin (d18:1 / 14:0), or SM (d18:1 / 14:0), is a sphingolipid found in animal cell membranes, particularly in the myelin sheath that surrounds the axons of some nerve cells. It is typically composed of phosphorylcholine and ceramide. SM (d18:1 / 14:0) consists of a sphingosine backbone and myristic acid chains. In humans, sphingomyelin is the only membrane phospholipid not derived from glycerol. Like all sphingolipids, SM has a ceramide core (sphingosine bound to a fatty acid via an amide bond). It also contains a polar head group, either phosphorylcholine or phosphoethanolamine.

[0009] PC42:6 and PC42:7 are phosphatidylcholines (PC or GPCho), a type of phospholipid with a choline head group and a key component of biological membranes. Like diacylglycerol, glycerophosphocholine can have many different combinations of fatty acids of varying lengths and degrees of saturation attached to the C-1 and C-2 positions. PC42:6 has a total fatty acid chain length of 42 and a total degree of unsaturation of 6, while PC42:7 has a total fatty acid chain length of 42 and a total degree of unsaturation of 7.

[0010] Furthermore, the end-stage renal disease includes the terminal stages of the following chronic kidney diseases, and the chronic kidney diseases include primary glomerulonephritis, hypertensive arteriosclerosis, diabetic nephropathy, secondary glomerulonephritis, tubulointerstitial lesions, ischemic nephropathy, and hereditary kidney diseases.

[0011] Furthermore, the tubulointerstitial lesions include acute and chronic interstitial nephritis, chronic pyelonephritis, chronic uric acid nephropathy, obstructive nephropathy, and drug-induced nephropathy.

[0012] Furthermore, the hereditary kidney disease includes polycystic kidney disease and hereditary nephritis.

[0013] Furthermore, the cardiovascular and cerebrovascular diseases include cardiovascular diseases and cerebrovascular diseases.

[0014] Furthermore, the cardiovascular diseases include atherosclerosis, ischemic heart disease, coronary heart disease, heart failure, peripheral artery disease, coronary artery bypass grafting, unstable angina, unstable refractory angina, stable angina, chronic stable angina, acute coronary syndrome, and myocardial infarction.

[0015] Furthermore, the myocardial infarction includes single or recurrent myocardial infarction, myocardial infarction without Q wave, non-ST-segment elevation myocardial infarction, and ST-segment elevation myocardial infarction.

[0016] The term "cardiovascular disease" refers to diseases that affect the heart, blood vessels, or both. In particular, cardiovascular disease includes arrhythmias (atrial, ventricular, or both); atherosclerosis and its sequelae; angina pectoris; heart rhythm disturbances; myocardial ischemia; myocardial infarction; cardiac or vascular aneurysms; stroke; peripheral occlusive arterial disease of a limb, organ, or tissue; ischemic reperfusion injury to the brain, heart, kidney, or other organs or tissues; endotoxic, surgical, or traumatic shock; hypertension, valvular heart disease, heart failure, abnormal blood pressure; vasoconstriction (including vasoconstriction associated with migraine); and vascular abnormalities, inflammation, or dysfunction limited to a single organ or tissue.

[0017] Furthermore, the cerebrovascular diseases include acute cerebral infarction, cerebral hemorrhage, cerebral stroke, lacunar infarction, cerebral microbleeding, and white matter lesions.

[0018] Furthermore, the sample includes tissue samples, primary or cultured cells or cell lines, cell supernatants, cell lysates, platelets, serum, plasma, blood, vitreous humor, lymph fluid, synovial fluid, follicular fluid, semen, amniotic fluid, milk, whole blood, blood-derived cells, urine, cerebrospinal fluid, saliva, sputum, tears, sweat, mucus, ascites, pelvic washing fluid, gynecological fluid, pleural fluid, tumor lysate, thyroid tissue, tissue culture fluid, tissue extract, homogenized tissue, tumor tissue, cell extract.

[0019] Furthermore, the sample includes serum, plasma, blood, blood-derived cells, and platelets.

[0020] Furthermore, the sample includes serum, blood, and plasma.

[0021] Furthermore, the sample is blood.

[0022] The term "sample" is used in its broadest sense. In one sense, it can refer to animal cells or tissues. In another sense, it is meant to include samples or cultures obtained from any source, as well as biological and environmental samples. Biological samples can be obtained from plants or animals (including humans) and include fluids, solids, tissues, and gases. In some embodiments, the sample is a blood sample.

[0023] Furthermore, the reagents include reagents for detecting the expression levels of biomarkers by western blotting, ELISA, radioimmunoassay, radioimmunodiffusion, octotron immunodiffusion, rocket electrophoresis, tissue immunostaining, immunoprecipitation assay, complement fixation assay, FACS, and protein chip detection.

[0024] Furthermore, the products include test kits, chips, test papers, nucleic acid membrane strips, antibodies, and ligands.

[0025] The term "biomarker" refers to a factor that is a unique indicator of a biological process, biological event and / or pathological condition, and the term biomarker encompasses both clinical markers and biomarkers. Therefore, in the context of the present invention, the term "biomarker" encompasses, for example, "biological biomarkers", and the biomarkers disclosed herein also include genes encoding those proteins (DNA and / or RNA) and metabolites. The term "biomarker" also encompasses "clinical biomarkers" (also referred to as "clinical status markers") that can predict the response to biological therapy, such as sex, age, concomitant medication, smoking status, body mass index (BMI) etc. See, for example, U.S. Patents US20150065530, US20140141990, US20130005596, US20090233304, US20140199709, US20130303398, US20110212104, which are incorporated herein by reference in their entirety.

[0026] The present invention provides a product for assisting in the diagnosis or prediction of whether end-stage renal disease is complicated by cardiovascular and cerebrovascular diseases. The product comprises the aforementioned reagent for detecting biomarkers in a sample, wherein the biomarkers include PC42:6, PC42:7, and SM d18:1 / 14:0.

[0027] Furthermore, the biomarkers include a combination of PC42:6, PC42:7, and SM d18:1 / 14:0.

[0028] Furthermore, the biomarkers also include prediction / diagnosis indicators for new cardiovascular and cerebrovascular events, and the indicators include age, gender, and dialysis years.

[0029] Furthermore, the biomarkers also include prediction / diagnosis indicators for new cardiovascular and cerebrovascular events, and the indicators include a combination of age, gender, and dialysis years.

[0030] Furthermore, the newly-occurring cardiovascular and cerebrovascular events include newly-occurring cardiovascular events and newly-occurring cerebrovascular events.

[0031] Furthermore, the newly-occurring cardiovascular events include atherosclerosis, ischemic heart disease, coronary heart disease, heart failure, peripheral artery disease, coronary artery bypass grafting, unstable angina, unstable refractory angina, stable angina, chronic stable angina, acute coronary syndrome, and myocardial infarction.

[0032] Furthermore, the myocardial infarction includes single or recurrent myocardial infarction, myocardial infarction without Q wave, non-ST-segment elevation myocardial infarction, and ST-segment elevation myocardial infarction.

[0033] Furthermore, the newly-occurring cerebrovascular events include cerebral hemorrhage, cerebral infarction, lacunar infarction, cerebral microbleeding, and white matter lesions.

[0034] The term "diagnosis" refers to detecting a disease or determining the stage or degree of a disease. Typically, the diagnosis of a disease is based on the evaluation of one or more factors and / or symptoms of a predicted disease. That is, the presence, absence or amount of a factor that indicates the presence or absence of a predicted disease or condition can be used for diagnosis. It is believed that each factor or symptom indicating the diagnosis of a specific disease does not need to be exclusively related to the specific disease. For example, there may be a differential diagnosis that can be inferred from the diagnostic factor or symptom. Similarly, there may be a situation where the factor or symptom indicating a specific disease is present in an individual without a specific disease. The term "diagnosis" also encompasses determining the therapeutic effect of a drug therapy, or predicting a response pattern to a drug therapy. Diagnostic methods can be used independently or in combination with other diagnostic and / or staging methods known in the medical field for specific diseases.

[0035] The present invention provides the use of biomarkers in constructing a computer model for assisting diagnosis or predicting whether end-stage renal disease is complicated by cardiovascular and cerebrovascular diseases, wherein the biomarkers include the biomarkers described above.

[0036] The present invention provides a method for constructing an auxiliary diagnosis or prediction model for whether end-stage renal disease is complicated by cardiovascular and cerebrovascular diseases based on biomarkers of plasma lipidomics and red blood cell lipidomics. The construction method includes using a machine learning method to train the model to construct a prediction model, and the biomarkers include the biomarkers described above.

[0037] Furthermore, the construction method includes the steps of collecting and processing biomarker samples.

[0038] Furthermore, the biomarker samples are from patients with end-stage renal disease who have cardiovascular and cerebrovascular diseases and patients with end-stage renal disease who do not have cardiovascular and cerebrovascular diseases.

[0039] Furthermore, the machine learning method includes a decision tree model, a random forest model, a K-nearest neighbor algorithm model, a naive Bayes model, a support vector machine model, and a neural network model.

[0040] Furthermore, the machine learning method uses the expression levels of biomarkers as features.

[0041] The present invention provides the use of biomarkers in a system for automated auxiliary diagnosis or prediction of whether end-stage renal disease is complicated by cardiovascular and cerebrovascular diseases, wherein the biomarkers include PC42:6, PC42:7, and SM d18:1 / 14:0.

[0042] Furthermore, the biomarkers include a combination of PC42:6, PC42:7, and SM d18:1 / 14:0.

[0043] Furthermore, the biomarkers also include prediction / diagnosis indicators for new cardiovascular and cerebrovascular events, and the indicators include age, gender, and dialysis years.

[0044] Furthermore, the biomarkers also include prediction / diagnosis indicators for new cardiovascular and cerebrovascular events, and the indicators include a combination of age, gender, and dialysis years.

[0045] The present invention provides a system for automated auxiliary diagnosis or prediction of whether end-stage renal disease is complicated by cardiovascular and cerebrovascular diseases. The system includes a result judgment module for analyzing whether a subject's end-stage renal disease is complicated by cardiovascular and cerebrovascular diseases based on the expression levels of the aforementioned biomarkers.

[0046] Furthermore, the system includes an input module for inputting the expression levels of the aforementioned biomarkers.

[0047] Furthermore, the system includes an output module for outputting the analysis result of the result judgment module.

[0048] The term "automated" refers to a situation where any one or more steps of a procedure or method (e.g., cell collection) do not need to be performed "by hand" (i.e., manually), but wherein the desired step or procedure (e.g., cell collection) can be performed by one or more suitable devices or systems such as one or more robots, liquid handling robots and / or other (e.g., solvent preparation) liquid transfer devices, which are programmed before performing one or more steps so that the corresponding steps and modes (particularly the collection step) are performed in an automated manner according to the programmed content.

[0049] The term "system" refers not only to a system having a structure in which multiple computers, pieces of hardware, devices, etc. are connected to each other via a communication unit such as a network (including communication connections established in a one-to-one manner), but also to a system implemented by one computer, one piece of hardware, one device, etc.

[0050] The term "subject" or "patient" includes any human or non-human animal. The term "non-human animal" includes all vertebrates, e.g., mammals and non-mammals, such as non-human primates, sheep, dogs, cats, horses, cows, bears, chickens, amphibians, reptiles, etc.

[0051] In some embodiments, the implementation of the system includes performing or completing selected tasks manually, automatically, or a combination thereof. Furthermore, depending on the actual use of instruments and equipment of embodiments of the system of the present invention, the system can be used to implement multiple program tasks by means of hardware, software, firmware, or a combination thereof.

[0052] The present invention provides the use of biomarkers in preparing products for end-stage renal disease typing, wherein the end-stage renal disease typing includes end-stage renal disease combined with cardiovascular and cerebrovascular diseases, and end-stage renal disease without cardiovascular and cerebrovascular diseases.

[0053] The biomarkers include PC42:6, PC42:7, and SM d18:1 / 14:0.

[0054] Furthermore, the biomarkers include a combination of PC42:6, PC42:7, and SM d18:1 / 14:0.

[0055] Furthermore, the biomarkers also include prediction / diagnosis indicators for new cardiovascular and cerebrovascular events, and the indicators include age, gender, and dialysis years.

[0056] Furthermore, the biomarkers also include prediction / diagnosis indicators for new cardiovascular and cerebrovascular events, and the indicators include a combination of age, gender, and dialysis years.

[0057] The present invention provides a method for constructing a product for end-stage renal disease typing, the method comprising:

[0058] 1) Collect samples from patients with end-stage renal disease and detect the expression levels of biomarkers in them;

[0059] 2) comparing the test results in step 1) with the critical expression level of the biomarker, and classifying the end-stage renal disease patients as end-stage renal disease with cardiovascular and cerebrovascular diseases or end-stage renal disease without cardiovascular and cerebrovascular diseases based on the results;

[0060] The biomarkers include PC42:6, PC42:7, and SM d18:1 / 14:0.

[0061] Furthermore, the biomarkers include a combination of PC42:6, PC42:7, and SM d18:1 / 14:0.

[0062] Furthermore, the biomarkers also include prediction / diagnosis indicators for new cardiovascular and cerebrovascular events, and the indicators include age, gender, and dialysis years.

[0063] Furthermore, the biomarkers also include prediction / diagnosis indicators for new cardiovascular and cerebrovascular events, and the indicators include a combination of age, gender, and dialysis years. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 This is the ROC curve of whether end-stage renal disease is complicated with cardiovascular and cerebrovascular diseases using the control basic model and the experimental lipid model in the test set;

[0065] Figure 2 This is the ROC curve diagram of the diagnosis of whether end-stage renal disease is complicated with cardiovascular and cerebrovascular diseases using the control basic model and the experimental lipid model in the validation set. DETAILED DESCRIPTION

[0066] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the invention belongs. Although any methods and materials similar or equivalent to those described herein can be used in the practice or testing of the present invention, preferred methods and materials are described herein.

[0067] The logarithmic function for associating the marker combination with the disease preferably uses an algorithm developed and obtained by applying statistical methods. For example, suitable statistical methods are discriminant analysis (DA) (i.e., linear, quadratic, regular DA), kernel methods (i.e., SVM), non-parametric methods (i.e., k-nearest neighbor classifiers), PLS (partial least squares), tree-based methods (i.e., logistic regression, CART, random forest methods), generalized linear models (i.e., logarithmic regression), principal component-based methods (i.e., SIMCA), generalized superposition models, fuzzy logic-based methods, neural network-based and genetic algorithm-based methods. Skilled technicians will have no problem selecting suitable statistical methods to evaluate the marker combination of the present invention and thereby obtain suitable mathematical algorithms.

[0068] The receiver operating characteristic (ROC) curve is a curve plotted based on a series of different binary classification methods (cutoff values ​​or decision thresholds), with sensitivity (true positive rate) on the vertical axis and 1-specificity (false positive rate) on the horizontal axis. The area under the ROC curve is an important indicator of test accuracy; the larger the area under the ROC curve, the greater the diagnostic value of the test.

[0069] The term "AUC" is an abbreviation for "area under the curve". In particular, it refers to the area under the receiver operating characteristic (ROC) curve. The ROC curve is a plot of the true positive rate versus the false positive rate for different possible cut-off points of a diagnostic test. It shows that the trade-off between sensitivity and specificity depends on the cut-off point chosen (any increase in sensitivity is accompanied by a decrease in specificity). The area under the ROC curve (AUC) is a measure of the accuracy of a diagnostic test (the larger the area, the better; the optimal value is 1; the ROC curve for a randomized test is located on the diagonal with an area of ​​0.5; see JPEgan. (1975) Signal Detection Theory and ROC Analysis, Academic Press, New York). Example Biomarkers are associated with the diagnosis and prediction of whether end-stage renal disease is accompanied by cardiovascular and cerebrovascular diseases

[0070] 1. Experimental subjects

[0071] In this experiment, the sample sources for both the test and validation sets were clinically collected samples from patients with end-stage renal disease (ESRD), and all samples were blood samples. The test set contained 58 samples, while the validation set contained 59 samples. Both the significant difference analysis and receiver operating characteristic (ROC) analysis were performed.

[0072] The inclusion and exclusion criteria for patients with end-stage renal disease are as follows:

[0073] Patients with CKD stage 4-5 and regular maintenance dialysis treatment were enrolled from Peking Union Medical College Hospital between July 2013 and July 2014.

[0074] Inclusion criteria: (1) aged 17 years or older; (2) maintenance dialysis patients requiring regular dialysis for more than 2 months; (3) agreed and signed the informed consent form.

[0075] Exclusion criteria: (1) patients with systemic infection, acute cardiovascular events, malignant tumors, surgical operations, or trauma in the month before inclusion in the study; (2) patients with mental illness, mood disorders, long-term use of psychiatric medications, epilepsy, or diagnosed dementia; (3) patients with metabolic encephalopathy; (4) patients with a history of non-atherosclerotic vascular disease (such as Takayasu arteritis).

[0076] The basic information of 117 patients with end-stage renal disease is shown in Table 1:

[0077] Table 1

[0078]

[0079]

[0080] 2. Experimental methods

[0081] 1) Experimental sample extraction principle: repeated 2000 random samplings were used to divide the samples into two groups, each accounting for 50%, and finally 58 samples were obtained in the test set and 59 samples in the validation set.

[0082] 2) Control base model composition: `New-onset cardio-cerebrovascular events` ~ Age + Gender + `Dialysis vintage` (i.e., "new-onset cardio-cerebrovascular events" ~ Age + Gender + "dialysis vintage")

[0083] The experimental lipid model consists of the following components: `New-onset cardio-cerebrovascular events` ~ Age + Gender + Dialysis vintage + PC42:6 + PC42:7 + SM d18:1 / 14:0` (i.e., "new-onset cardio-cerebrovascular events" ~ Age + Gender + Dialysis vintage + PC42:6 + PC42:7 + SM d18:1 / 14:0)

[0084] 3) Blood lipidomics methods

[0085] Lipids were extracted from blood samples using a modified Bligh / Dyer extraction method (two extractions): 750 μL of chloroform:methanol (1:2) (v / v) was added to the blood sample and incubated at 4°C, 1500 rpm for 30 min. After incubation, 350 μL of deionized water and 250 μL of chloroform were added to induce phase separation. The lower organic phase containing lipids was extracted into a clean tube. The lipid extraction was repeated once, and 450 μL of chloroform was added to the remaining aqueous phase. The two lipid extracts were combined into a single tube and dried in the OH mode of a SpeedVac. The samples were stored at -80°C until further analysis.

[0086] The samples were reconstituted in an isotope standard mixture, and all analyses were performed using an Exion UPLC-QTRAP 6500 Plus (Sciex) liquid chromatography-mass spectrometer in electrospray ionization (ESI) mode under the following conditions: curtain gas = 20, ion spray voltage = 5500 V, temperature = 400°C, ion source gas 1 = 35, ion source gas 2 = 35.

[0087] Polar lipids were separated using a Phenomenex Luna silica 3μm column (150x2.0mm inner diameter) under the following mobile phase conditions: mobile phase A (chloroform:methanol:ammonia 89.5:10:0.5) and mobile phase B (chloroform:methanol:ammonia:water 55:39:0.5:5.5). A gradient of mobile phase A was applied starting at 95% for 5 minutes, then linearly decreased to 60% over 7 minutes and held for 4 minutes. The mobile phase A was then further decreased to 30% and held for 15 minutes. Finally, the initial gradient was maintained for 5 minutes. Mass spectrometry multiple reaction monitoring (MRM) was established for the identification and quantification of various lipids. Lipid species were quantified using an internal standard.

[0088] 4) Differential expression analysis

[0089] The test set and validation set were differentially expressed based on the blood lipidomics detection results of biomarkers to obtain the model regression coefficients of the test set and validation set respectively.

[0090] 5) Diagnostic efficacy analysis

[0091] The R package "pROC" was used to draw the receiver operating characteristic (ROC) curve, and the AUC values ​​of the screened biomarkers in the test set and validation set were analyzed to determine their diagnostic efficacy for whether end-stage renal disease was complicated with cardiovascular and cerebrovascular diseases.

[0092] 6) Statistical analysis methods

[0093] The Wilcoxon signed-rank test was used to evaluate the differences in expression of the biomarkers. The remaining data were analyzed using the Student's t-test (normally distributed variables) or the Wilcoxon rank-sum test (non-normally distributed variables). All statistical tests were performed using R (version: 3.6.3), and the significance threshold was set at 0.05.

[0094] 3. Experimental results

[0095] 1) The results of differential expression analysis of the test set are shown in Table 2:

[0096] Table 2

[0097]

[0098]

[0099] 2) The results of differential expression analysis of the validation set are shown in Table 3:

[0100] Table 3

[0101] Group estimate std.error statistic p.value Experimental lipid models -6.153320878 2.923819682 -2.104548689 0.035330612 age 0.059568104 0.040691942 1.463879615 0.143226844 gender 1.199998623 0.873752889 1.373384441 0.169632864 Dialysis year 0.004911842 0.007549016 0.650659931 0.515266034 `PC42:6` 0.909318077 0.688092678 1.321505236 0.186332958 `PC42:7` 0.504923033 0.609230856 0.828787689 0.407224556 `SM d18:1 / 14:0` 0.540634757 0.428701899 1.261097182 0.207273836

[0102] 3) ROC curve analysis of biomarkers for diagnosing or predicting whether end-stage renal disease is complicated by cardiovascular and cerebrovascular diseases

[0103] Using the control basic model and experimental lipid model as variables, and using the sample data of the test set, the ROC curves of the control basic model and experimental lipid model were drawn to determine whether end-stage renal disease was complicated with cardiovascular and cerebrovascular diseases. The results are as follows: Figure 1 As shown, the results showed that the AUC value of the ROC curve obtained by the control basic model was 0.70, and the AUC value of the ROC curve obtained by the experimental lipid model was 0.85, and there was a significant difference between the two (p = 0.022), indicating that the experimental lipid model can improve the accuracy of diagnosing or predicting whether end-stage renal disease is complicated by cardiovascular and cerebrovascular diseases, indicating that the biomarkers of the experimental lipid model can become biomarkers for diagnosing or predicting whether end-stage renal disease is complicated by cardiovascular and cerebrovascular diseases.

[0104] Using the control basic model and experimental lipid model as variables, and using the sample data of the validation set, the ROC curves of the control basic model and experimental lipid model were drawn to determine whether end-stage renal disease was complicated with cardiovascular and cerebrovascular diseases. The results are as follows: Figure 2 As shown, the results showed that the AUC value of the ROC curve obtained by the control basic model was 0.65, and the AUC value of the ROC curve obtained by the experimental lipid model was 0.85, and there was a significant difference between the two (p = 0.013), verifying that the experimental lipid model can improve the accuracy of diagnosing or predicting whether end-stage renal disease is complicated by cardiovascular and cerebrovascular diseases, and proving that the biomarkers of the experimental lipid model can become biomarkers for diagnosing or predicting whether end-stage renal disease is complicated by cardiovascular and cerebrovascular diseases.

[0105] The above embodiments are only provided for understanding the method and core concept of the present invention. It should be noted that, without departing from the principles of the present invention, a number of improvements and modifications may be made to the present invention by a person skilled in the art, and such improvements and modifications shall fall within the scope of protection of the claims of the present invention.

Claims

1. The application of biomarkers in constructing a computer model for assisting in the diagnosis of whether end-stage renal disease is complicated by cardiovascular and cerebrovascular diseases, characterized in that: The biomarkers were a combination of PC42:6, PC42:7, SM d18:1 / 14:0, age, sex, and year of dialysis.

2. Application of biomarkers in the construction of an automated system for assisting in the diagnosis of whether end-stage renal disease is complicated by cardiovascular and cerebrovascular diseases, including: The biomarkers were a combination of PC42:6, PC42:7, SM d18:1 / 14:0, age, sex, and year of dialysis.

3. A system for automated auxiliary diagnosis of whether end-stage renal disease is complicated by cardiovascular and cerebrovascular diseases, characterized in that: The system includes a result judgment module for analyzing whether the subject's end-stage renal disease is complicated with cardiovascular and cerebrovascular diseases based on the biomarker data according to claim 2; The system comprises an input module for inputting the data of the biomarker as claimed in claim 2; The system includes an output module for outputting the analysis result of the result judgment module.

4. Use of a biomarker in the preparation of a diagnostic kit for end-stage renal disease typing, characterized in that: The classification of end-stage renal disease includes end-stage renal disease combined with cardiovascular and cerebrovascular diseases, and end-stage renal disease without cardiovascular and cerebrovascular diseases; The biomarkers were a combination of PC42:6, PC42:7, SM d18:1 / 14:0, age, sex, and year of dialysis.

Images