CN112837819A - Method for establishing acute kidney injury prediction model after coronary artery bypass grafting - Google Patents
Method for establishing acute kidney injury prediction model after coronary artery bypass grafting Download PDFInfo
- Publication number
- CN112837819A CN112837819A CN202110077761.7A CN202110077761A CN112837819A CN 112837819 A CN112837819 A CN 112837819A CN 202110077761 A CN202110077761 A CN 202110077761A CN 112837819 A CN112837819 A CN 112837819A
- Authority
- CN
- China
- Prior art keywords
- risk factors
- model
- coronary artery
- artery bypass
- establishing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 208000009304 Acute Kidney Injury Diseases 0.000 title claims abstract description 45
- 238000000034 method Methods 0.000 title claims abstract description 37
- 208000033626 Renal failure acute Diseases 0.000 title claims abstract description 32
- 201000011040 acute kidney failure Diseases 0.000 title claims abstract description 32
- 210000004351 coronary vessel Anatomy 0.000 title claims abstract description 27
- 101800000407 Brain natriuretic peptide 32 Proteins 0.000 claims abstract description 24
- 102400000667 Brain natriuretic peptide 32 Human genes 0.000 claims abstract description 24
- 101800002247 Brain natriuretic peptide 45 Proteins 0.000 claims abstract description 24
- HPNRHPKXQZSDFX-OAQDCNSJSA-N nesiritide Chemical compound C([C@H]1C(=O)NCC(=O)N[C@@H](CCCNC(N)=N)C(=O)N[C@@H](CCCCN)C(=O)N[C@@H](CCSC)C(=O)N[C@@H](CC(O)=O)C(=O)N[C@@H](CCCNC(N)=N)C(=O)N[C@H](C(N[C@@H](CO)C(=O)N[C@@H](CO)C(=O)N[C@@H](CO)C(=O)N[C@@H](CO)C(=O)NCC(=O)N[C@@H](CC(C)C)C(=O)NCC(=O)N[C@@H](CSSC[C@@H](C(=O)N1)NC(=O)CNC(=O)[C@H](CO)NC(=O)CNC(=O)[C@H](CCC(N)=O)NC(=O)[C@@H](NC(=O)[C@H](CCSC)NC(=O)[C@H](CCCCN)NC(=O)[C@H]1N(CCC1)C(=O)[C@@H](N)CO)C(C)C)C(=O)N[C@@H](CCCCN)C(=O)N[C@@H](C(C)C)C(=O)N[C@@H](CC(C)C)C(=O)N[C@@H](CCCNC(N)=N)C(=O)N[C@@H](CCCNC(N)=N)C(=O)N[C@@H](CC=1N=CNC=1)C(O)=O)=O)[C@@H](C)CC)C1=CC=CC=C1 HPNRHPKXQZSDFX-OAQDCNSJSA-N 0.000 claims abstract description 24
- 102100036475 Alanine aminotransferase 1 Human genes 0.000 claims abstract description 21
- 108010082126 Alanine transaminase Proteins 0.000 claims abstract description 21
- 206010019280 Heart failures Diseases 0.000 claims abstract description 12
- DDRJAANPRJIHGJ-UHFFFAOYSA-N creatinine Chemical compound CN1CC(=O)NC1=N DDRJAANPRJIHGJ-UHFFFAOYSA-N 0.000 claims description 40
- 239000008280 blood Substances 0.000 claims description 37
- 210000004369 blood Anatomy 0.000 claims description 37
- 238000001356 surgical procedure Methods 0.000 claims description 22
- 229940109239 creatinine Drugs 0.000 claims description 20
- 238000007477 logistic regression Methods 0.000 claims description 20
- 208000010125 myocardial infarction Diseases 0.000 claims description 19
- 206010020772 Hypertension Diseases 0.000 claims description 16
- 238000007675 cardiac surgery Methods 0.000 claims description 10
- 238000012795 verification Methods 0.000 claims description 10
- 206010012601 diabetes mellitus Diseases 0.000 claims description 9
- 208000006545 Chronic Obstructive Pulmonary Disease Diseases 0.000 claims description 8
- 238000011088 calibration curve Methods 0.000 claims description 8
- 238000000611 regression analysis Methods 0.000 claims description 8
- 238000002054 transplantation Methods 0.000 claims description 8
- 230000002861 ventricular Effects 0.000 claims description 8
- 238000013211 curve analysis Methods 0.000 claims description 7
- 230000002980 postoperative effect Effects 0.000 claims description 7
- 208000005764 Peripheral Arterial Disease Diseases 0.000 claims description 6
- 208000030831 Peripheral arterial occlusive disease Diseases 0.000 claims description 6
- -1 cardiac surgery Proteins 0.000 claims description 6
- 238000007619 statistical method Methods 0.000 claims description 4
- 230000008901 benefit Effects 0.000 claims description 3
- 230000001419 dependent effect Effects 0.000 claims description 3
- 238000010200 validation analysis Methods 0.000 claims description 3
- 238000010219 correlation analysis Methods 0.000 claims description 2
- 201000010099 disease Diseases 0.000 claims description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 2
- 238000011119 multifactor regression analysis Methods 0.000 claims description 2
- 210000002966 serum Anatomy 0.000 claims description 2
- 238000011156 evaluation Methods 0.000 abstract description 8
- 230000000630 rising effect Effects 0.000 abstract description 3
- 238000012216 screening Methods 0.000 abstract description 2
- 238000013210 evaluation model Methods 0.000 abstract 2
- 238000013433 optimization analysis Methods 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 12
- 238000004458 analytical method Methods 0.000 description 5
- 230000000747 cardiac effect Effects 0.000 description 4
- 230000003902 lesion Effects 0.000 description 4
- 230000002093 peripheral effect Effects 0.000 description 4
- 206010003658 Atrial Fibrillation Diseases 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000007684 non-elective surgery Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000000391 smoking effect Effects 0.000 description 3
- 210000001685 thyroid gland Anatomy 0.000 description 3
- 108010023302 HDL Cholesterol Proteins 0.000 description 2
- 102000001554 Hemoglobins Human genes 0.000 description 2
- 108010054147 Hemoglobins Proteins 0.000 description 2
- 108010028554 LDL Cholesterol Proteins 0.000 description 2
- 210000000709 aorta Anatomy 0.000 description 2
- 230000001746 atrial effect Effects 0.000 description 2
- 230000003416 augmentation Effects 0.000 description 2
- 210000004204 blood vessel Anatomy 0.000 description 2
- 230000007213 cerebrovascular event Effects 0.000 description 2
- HVYWMOMLDIMFJA-DPAQBDIFSA-N cholesterol Chemical compound C1C=C2C[C@@H](O)CC[C@]2(C)[C@@H]2[C@@H]1[C@@H]1CC[C@H]([C@H](C)CCCC(C)C)[C@@]1(C)CC2 HVYWMOMLDIMFJA-DPAQBDIFSA-N 0.000 description 2
- 208000029078 coronary artery disease Diseases 0.000 description 2
- 238000000556 factor analysis Methods 0.000 description 2
- 238000002513 implantation Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012502 risk assessment Methods 0.000 description 2
- UFTFJSFQGQCHQW-UHFFFAOYSA-N triformin Chemical compound O=COCC(OC=O)COC=O UFTFJSFQGQCHQW-UHFFFAOYSA-N 0.000 description 2
- 206010002383 Angina Pectoris Diseases 0.000 description 1
- 206010003662 Atrial flutter Diseases 0.000 description 1
- 206010010071 Coma Diseases 0.000 description 1
- 208000032928 Dyslipidaemia Diseases 0.000 description 1
- 208000031226 Hyperlipidaemia Diseases 0.000 description 1
- 208000017170 Lipid metabolism disease Diseases 0.000 description 1
- 208000005736 Nervous System Malformations Diseases 0.000 description 1
- 208000011623 Obstructive Lung disease Diseases 0.000 description 1
- 208000001647 Renal Insufficiency Diseases 0.000 description 1
- 206010042434 Sudden death Diseases 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 210000003169 central nervous system Anatomy 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 235000012000 cholesterol Nutrition 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000035487 diastolic blood pressure Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 201000005577 familial hyperlipidemia Diseases 0.000 description 1
- 230000004217 heart function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 201000006370 kidney failure Diseases 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000008383 multiple organ dysfunction Effects 0.000 description 1
- 210000003516 pericardium Anatomy 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000035488 systolic blood pressure Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 210000002700 urine Anatomy 0.000 description 1
- 208000003663 ventricular fibrillation Diseases 0.000 description 1
- 206010047302 ventricular tachycardia Diseases 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention discloses a method for establishing a prediction model of acute kidney injury after coronary artery bypass grafting, which is characterized in that a risk evaluation model is established by collecting and sorting a large amount of hospital information of patients in China, combining direct single-factor and indirect single-factor regression screening and a multi-factor regression optimization analysis method, and the accuracy and reliability of the evaluation model are effectively improved by increasing the sample size and bringing in new risk factors, particularly the rising of alanine aminotransferase and the introduction of two risk factors of brain natriuretic peptide, so that an effective evaluation prediction method is provided for the risk evaluation of acute kidney injury of coronary artery bypass grafting of patients with heart failure in China, and the method has important significance for the healthy development of the medical level in China.
Description
Technical Field
The invention belongs to the field of biomedicine, and particularly relates to a method for establishing a model for predicting acute renal injury after coronary artery bypass grafting.
Background
Coronary heart disease is the most common cause of heart failure, and Coronary Artery Bypass Graft (CABG) surgery is one of the important methods for surgical treatment of coronary heart disease complicated with cardiac insufficiency. However, due to the high requirements of the surgical technique and the complexity of the perioperative management, the perioperative serious complications of the patients are high, the incidence of Acute Kidney Injury (AKI) is high in a plurality of complications, and postoperative multiple organ dysfunction, most commonly cardiac insufficiency combined with AKI, is closely related to perioperative death and postoperative life quality reduction. Currently, many predictive scoring systems for renal insufficiency after cardiac surgery have been established, and more commonly used are the criveland ARF score, Mehta score, SRI score and the like. However, these models were designed primarily for all patient populations with cardiac surgery and were mostly based on clinical data 10 years ago, with data collected primarily from western national populations. There may be bias in the evaluation of patients today who receive pure CABG, especially cardiac insufficiency. Therefore, a risk assessment model considering both the specificity and the accuracy of Chinese population is established, the adverse events after operation can be accurately predicted, the risk factors are layered, high-risk patients are identified, and perioperative risk factors are controlled, so that the aims of reducing complications and improving the medical quality are fulfilled, and the clinical significance is important.
Disclosure of Invention
The invention aims to provide a method for establishing a model for predicting acute kidney injury after coronary artery bypass transplantation, which can more accurately evaluate the risk of acute kidney injury after coronary artery bypass transplantation of a heart failure patient, is a model more suitable for risk prediction of Chinese population, and is suitable for popularization and application in clinical practice.
In order to achieve the purpose, the invention adopts the following technical scheme:
a method for establishing a prediction model of acute renal injury after coronary artery bypass transplantation is characterized in that the model firstly adopts direct single-factor regression analysis on risk factors of acute renal injury after coronary artery bypass transplantation, then obtains combined risk factors through the indirect single-factor regression analysis method, finally further screens the combined risk factors through multi-factor regression analysis to obtain final risk factors, and determines a line chart prediction model.
Further, the establishment of the model comprises the following steps:
(1) collecting clinical data of patients with cardiac insufficiency before statistical operation and patients who undergo coronary artery bypass graft operation to establish a disease database;
(2) respectively carrying out correlation analysis on the 27 possible risk factors, firstly carrying out direct single-factor logistic regression analysis, and determining the direct risk factors which are ranked in the front relative to the acute renal injury;
(3) taking the risk factors ranked in the front in the step (2) as dependent variables respectively, carrying out indirect single-factor logistic regression analysis on the remaining variables, and determining the indirect risk factors ranked in the front again;
(4) combining the risk factors ranked in the step (2) and the step (3) to obtain combined risk factors;
(5) performing multi-factor logistic regression analysis on the combined risk factors, and deleting the co-linear variables to obtain final risk factors related to postoperative acute kidney injury;
(6) assigning values to the final risk factors based on the regression coefficients of the final risk factors, establishing a line chart prediction model equation, and calculating the incidence rate of acute kidney injury: p (t) ═ λ0(t)exp(β1x1+β2x2+…+βkxk)；
(7) The model is externally verified by a verification group.
Further, the 27 possible risk factor variables in step (2) are all classified variables, and are expressed by frequency (percentage).
Further, the direct risk factors of step (2) are 3: serum creatinine, history of myocardial infarction and perioperative blood transfusion.
Further, the indirect risk factors in step (3) are 10: gender, diabetes, elevated alanine aminotransferase, cardiac surgery, brain natriuretic peptide, peripheral arterial disease, left ventricular ejection fraction, hypertension, chronic obstructive pulmonary disease, and extracorporeal circulation surgery.
Further, the combined risk factors in step (4) are 13: blood creatinine, history of myocardial infarction, perioperative blood transfusion, sex, diabetes, elevated alanine aminotransferase, cardiac surgery, brain natriuretic peptide, peripheral arterial disease, left ventricular ejection fraction, hypertension, chronic obstructive pulmonary disease, and extracorporeal circulation surgery, and the final risk factors of step (5) are 9: gender, elevated alanine aminotransferase, brain natriuretic peptide, blood creatinine, left ventricular ejection fraction, history of myocardial infarction, hypertension, extracorporeal circulation surgery, and perioperative blood transfusion.
Further, according to the direct single-factor Logistic regression analysis in the step (2) and the indirect single-factor Logistic regression analysis in the step (3), the significance of the risk factors is sorted according to the absolute value of the accuracy.
Further, the multi-factor Logistic regression analysis in the step (5) adopts an "Enter" method, and a line chart is established based on a Logistic regression equation.
Further, the external verification in the step (7) includes performing discrimination evaluation by using AUC values, performing model calibration evaluation by using a calibration curve, and performing net gain evaluation by using decision curve analysis.
Further, all statistical analyses were done using the R language (version 3.5).
Compared with other existing models, the model establishing process takes Chinese patients as research objects, the base number of the sick population searched and researched is large, the database samples are rich, and the risk factors searched and researched are more, so that the model is more suitable for Chinese populations and higher in prediction accuracy compared with other existing prediction models, and is suitable for evaluating the risk of postoperative acute renal injury in clinical practice.
The multi-step regression analysis method not only fully retains the integrity of the risk factors, but also ensures the correlation between the screened risk factors and the prediction result, greatly improves the prediction accuracy of the prediction model, and has important significance for risk evaluation in clinical practice.
Particularly, independent risk factors alanine aminotransferase and brain natriuretic peptide are introduced into the prediction model through the step-by-step screening method, so that the model shows better discrimination, calibration and net gain rate, and has important significance for improving the prediction accuracy of the model; the improvement of the prediction accuracy indirectly proves that the increase of alanine aminotransferase and the direct risk relationship between brain natriuretic peptide and perioperative acute kidney injury exist, thereby providing more references and evaluation basis for perioperative risk assessment of coronary artery bypass grafting of heart failure patients; meanwhile, two risk factors, namely alanine aminotransferase rising and brain natriuretic peptide, are introduced and proposed, so that the method has important guidance and reference significance for deeply researching the risk reason and mechanism of acute renal injury in the perioperative period of coronary artery bypass transplantation of a heart failure patient.
Drawings
FIG. 1 is a schematic illustration of a nomogram prediction model in accordance with the present invention;
FIG. 2 is a schematic diagram showing a comparison of calibration curves of models of the building block according to the present invention;
FIG. 3 is a schematic diagram showing comparison of Receiver Operating Curves (ROC) of models of the modeling system according to the present invention;
FIG. 4 is a comparison of Receiver Operating Curves (ROC) for each model of the validation set of the present invention;
FIG. 5 is a schematic diagram illustrating the analysis and comparison of decision curves of the models of the building block set according to the present invention;
FIG. 6 is a schematic diagram illustrating a decision curve analysis of each model of the validation set according to the present invention;
fig. 7 is a schematic flow chart of the method for establishing the acute kidney injury prediction model after coronary artery bypass grafting.
Detailed Description
The invention discloses a method for establishing a prediction model of acute kidney injury after coronary artery bypass grafting, and the flow schematic diagram of the method is shown in figure 7, and the invention is further described and explained below by combining the figure.
Example 1
In the management and collection from 2010 to 2019, 3659 patients with complete clinical data who receive coronary artery bypass grafting due to heart failure serve as modeling study objects, and the collection and collection of the patients in the management comprises the following steps: gender, hyperlipidemia, brain natriuretic peptide, thyroid function, hemoglobin, alanine aminotransferase, hypertension, body mass index, history of myocardial infarction, diabetes, stenting of cardiac vessels, elevated blood creatinine, cardiac surgery, history of smoking, peripheral arterial disease, cerebrovascular events, pre-operative critical status, CCS4 grade, pre-operative atrial fibrillation or atrial flutter, NYHA cardiac function grade III or IV, left ventricular ejection fraction (LVEF < 35%), incorporated valve surgery, incorporated aortic surgery, non-elective surgery, chronic obstructive pulmonary disease, 27 risk factors including extracorporeal circulation surgery and perioperative blood transfusion were used as subjects.
Acute kidney injury is defined by the fact that the following three criteria are met to diagnose acute kidney injury: (1) an increase in blood creatinine (SCR) of greater than or equal to 0.3mg/dL within 48 hours; (2) the increase of the SCR is more than or equal to 1.5 times of the basic value within 7 days; (3) urine volume was less than 0.5ml/kg/h for 6 consecutive hours.
The standard for judging hyperlipemia can diagnose dyslipidemia when the test index of the fasting plasma meets the following item of more than or equal to 1, the Total Cholesterol (TC) is more than or equal to 6.2mmol/L, the low-density lipoprotein cholesterol (LDL-C) is more than or equal to 4.1mmol/L, the Triglyceride (TG) is more than or equal to 2.3mmol/L, and the high-density lipoprotein cholesterol (HDL-C) is less than 1.0 mmol/L; the brain natriuretic peptide classification criteria were: less than 50 years old, brain natriuretic peptide > 450pg/ml, between 50 and 75 years old, brain natriuretic peptide > 900pg/ml, greater than 75 years old, brain natriuretic peptide greater than 1800 pg/ml; thyroid function, whether there is a history of thyroid abnormality; hemoglobin, with < 90g/L as a demarcation point; alanine aminotransferase, whether or not there is an increase in alanine aminotransferase; hypertension, whether systolic pressure is more than 140mmHg or diastolic pressure is more than 90 mmHg; myocardial infarction, whether or not there is a history of myocardial infarction; diabetes, whether there is a history of diabetes; the stent implantation of the cardiac blood vessel, namely whether the stent implantation operation of the cardiac blood vessel exists or not; blood creatinine, preoperative blood creatinine > 176 umol/L; cardiac surgery, whether there is cardiac surgery that has been done to open the pericardium; smoking history, whether there is a history of smoking; peripheral arterial lesions, whether or not peripheral arterial lesions exist in the past; cerebrovascular events, with or without coma for more than 24 hours or central nervous system abnormalities for more than 72 hours; preoperative critical state, whether any one of ventricular tachycardia or ventricular fibrillation or sudden death caused by rescue exists; CCS4 grade, CCS angina grade 4 grade; performing atrial fibrillation or atrial augmentation before an operation, wherein the preoperative atrial fibrillation or atrial augmentation is performed within two weeks; left ventricular ejection fraction (LVEF < 35%); merging valve surgery, whether any valve surgery is merged; merging aorta surgery, whether any merging aorta surgery exists; non-elective surgery, whether or not there is a non-elective surgery; chronic obstructive pulmonary disease, whether or not there is too slow obstructive pulmonary disease; extracorporeal circulation operation, whether extracorporeal circulation operation exists or not; perioperative blood transfusion, whether perioperative blood transfusion exists or not; gender and body mass index are also included. And (4) collating the patient data information and establishing a patient data database.
Example 2
Statistical analysis: all variables are classified variables and are expressed by frequency (percentage), in single-factor analysis, the significance of risk factors is sorted according to the absolute value of the accuracy, and the P value is required to be less than 0.1. The multi-factor Logistic regression analysis adopts an 'Enter' method, the 'Enter' method is an optional analysis method in a regression analysis method column, and a line chart prediction model is established based on a Logistic regression equation.
3659 patients are divided into two groups according to the ages, the sexes and the body quality index indexes, wherein one group serves as a modeling group, the other group serves as a verification group, the number of the modeling group is 2365, the number of the verification group is 1294, and the ages, the sexes and the body quality index indexes of the modeling group and the verification group are basically consistent in distribution.
In a modeling group (n ═ 2365), through the combination of previous research and clinical experience, 27 risk factors are included in the research, firstly, direct single-factor logistic regression analysis is carried out, the correlation between the 27 risk factors and acute kidney injury is directly analyzed, the correlation significance of the risk factors is sorted according to the absolute value of the accuracy, the P value is required to be less than 0.1, and 3 direct risk factors which are sorted in the front relative to the acute kidney injury are obtained: blood creatinine, history of myocardial infarction and perioperative blood transfusion, then indirect single-factor logistic regression analysis is carried out, respectively taking blood creatinine, myocardial infarction history and perioperative period blood transfusion as dependent variables, performing indirect single-factor regression analysis on the remaining 24 variables, sorting the significance of risk factors according to the absolute value of the accuracy, requiring the P value to be less than 0.1, selecting 4 corresponding indirect risk factors with front sorting after the regression analysis of each variable is finished, wherein four risk factors of diabetes, alanine aminotransferase rising, peripheral arterial lesion and brain natriuretic peptide are obtained according to the analysis result of the blood creatinine, analyzing the history of myocardial infarction to obtain four risk factors of LVEF less than 35 percent, chronic obstructive pulmonary disease, extracorporeal circulation operation and peripheral arterial lesion, analyzing the perioperative blood transfusion result to obtain four risk factors of cardiac operation, sex, hypertension and brain natriuretic peptide. A total of 10 indirect risk factors were screened by the above analysis: sex, diabetes, elevated alanine aminotransferase, cardiac surgery, brain natriuretic peptide, peripheral arterial disease, LVEF < 35%, hypertension, chronic obstructive pulmonary disease, and extracorporeal circulation surgery. The above 10 indirect risk factors together with the blood creatinine, the history of myocardial infarction and 3 direct risk factors of perioperative blood transfusion yield 13 combined risk factors: the 13 combined risk factors are subjected to multi-factor logistic regression analysis, the collinearity variable is deleted, and 9 final risk factors related to postoperative acute kidney injury are determined: sex, elevated alanine aminotransferase, brain natriuretic peptide, blood creatinine, LVEF < 35%, history of myocardial infarction, hypertension, extracorporeal circulation surgery and perioperative blood transfusion. The weights and coefficients for the 9 final risk factors are shown in table 1.
TABLE 1 Risk factors and weights
Establishing independent risk factors selected on the basis of multi-factor analysis, assigning values based on regression coefficients of each independent risk factor, and establishing a linear-series chart prediction model (figure 1) by using a logistic regression method according to table 1, wherein the incidence rate of acute renal injury is as follows: p (t) ═ λ0(t)exp(β1x1+β2x2+…+βkxk) Wherein P (t) is the incidence of acute renal injury, λ0(t) is a function for calculating AKI, x1、x2...xkAs covariate, betaiIs xiFor predicting the incidence of postoperative acute kidney injury.
The model was evaluated for calibration, discrimination and net benefit by plotting calibration curves (calibration curve), ROC subject working curves and Decision Curve Analysis (DCA). And compared to the current clinofland ARF score, Mehta score, and SRI score used clinically.
The model calibration degree is evaluated by adopting a calibration curve, the discrimination degree is evaluated by adopting an AUC (AUC) value, the net gain rate is evaluated by adopting a DCA (data center analysis) curve, all statistical analysis is completed by adopting an R language (version3.5), and the P value less than 0.05 is considered to have statistical significance.
The comparison of the calibration curves of the models of the building module with the schematic diagram (fig. 2) shows that the calibration curves of the line chart prediction model and the other three models show that the line chart prediction model has better calibration degree (fig. 2) than the other models, and particularly has very high calibration degree in the range of the predicted incidence rate of AKI being lower than 30%.
The model object working curve (ROC) comparison schematic diagram (figure 3) of each model object of the modeling group is established, wherein the AUC value of the prediction model of the line chart is 0.807, the AUC value of the Cleveland ARF score is 0.638, the AUC value of the Mehta score is 0.597, the AUC value of the SRI score is 0.600, the comparison schematic diagram (figure 4) of the operation curve (ROC) of each model object of the verification group is established, wherein the AUC value of the prediction model of the line chart is 0.815, the AUC value of the Cleveland ARF score is 0.612, the AUC value of the Mehta score is 0.620, and the AUC value of the SRI score is 0.572, and the AUC value under the working curve (AUC) of the prediction model object of the line chart is higher than that of other 3 common models, the AUC is the area enclosed by the coordinate axis under the ROC curve, the AUC is closer to 1.0, the detection method is higher.
The decision curve analysis comparison schematic diagram (figure 5) of each model of the building module group and the decision curve analysis schematic diagram (figure 6) of each model of the verification group show that the decision curve analysis DCA curve shows that the line list diagram prediction model shows higher net gain rate in the building module group and the verification group than other three models.
2365 patients are established in total, wherein 205 patients (8.67%) have AKI after operation, and the prediction model of the line chart incorporates 9 independent risk factors such as sex, alanine aminotransferase, brain natriuretic peptide, preoperative blood creatinine increase, LVEF < 35%, previous myocardial infarction, hypertension, extracorporeal circulation operation, perioperative blood transfusion and the like. 1294 patients in the verified group, wherein 119 patients (9.19%) have AKI after operation, the line graph prediction model shows better discrimination, calibration and net benefit rate than other 3 models, and the line graph prediction model has higher prediction accuracy on acute renal injury after coronary artery bypass transplantation of patients with cardiac insufficiency.
Example 3
Independent risk factors alanine aminotransferase and brain natriuretic peptide influence the experiment on the line chart prediction model, the verification object is the group of people in the modeling group, when the line chart prediction model incorporates gender, preoperative blood creatinine is increased, LVEF is less than 35%, the past myocardial infarction, hypertension, extracorporeal circulation surgery, perioperative blood transfusion and other 7 independent risk factors, the area under the subject working curve (AUC) is 0.738; when the model incorporates gender, preoperative blood creatinine is increased, LVEF is less than 35%, 8 independent risk factors such as previous myocardial infarction, hypertension, extracorporeal circulation surgery, perioperative blood transfusion, alanine aminotransferase and the like are adopted, and the area under the working curve (AUC) of a subject is 0.762; when the model incorporates gender, preoperative blood creatinine is increased, LVEF is less than 35%, 8 independent risk factors such as previous myocardial infarction, hypertension, extracorporeal circulation surgery, perioperative blood transfusion, brain natriuretic peptide and the like are included, and the area under the working curve (AUC) of a subject is 0.751; when the model incorporates gender, preoperative blood creatinine is increased, LVEF is less than 35%, 9 independent risk factors such as previous myocardial infarction, hypertension, extracorporeal circulation surgery, perioperative blood transfusion, alanine aminotransferase, brain natriuretic peptide and the like are adopted, and the area under the working curve (AUC) of a subject is 0.807; therefore, in the process of establishing the model, the inclusion of independent risk factors alanine aminotransferase and brain natriuretic peptide has important significance for better discrimination, calibration and net gain rate displayed by the line diagram prediction model.
The present invention is further illustrated and described in the above embodiments, which are only used to help understand the method and the core idea of the present application, and the content of the present specification should not be construed as limiting the present application since the skilled person can change the specific implementation and application scope according to the idea of the present application.
Claims (10)
1. The method for establishing the acute kidney injury prediction model after the coronary artery bypass transplantation is characterized in that the model firstly adopts direct single-factor regression analysis on risk factors of the acute kidney injury after the coronary artery bypass transplantation, then obtains combined risk factors by the indirect single-factor regression analysis method, finally further screens the combined risk factors by multi-factor regression analysis to obtain final risk factors, and determines a line chart prediction model.
2. The method for establishing a model for predicting acute renal injury after coronary artery bypass graft according to claim 1, wherein the model is established by the steps of:
(1) collecting clinical data of patients with cardiac insufficiency before statistical operation and patients who undergo coronary artery bypass graft operation to establish a disease database;
(2) respectively carrying out correlation analysis on the 27 possible risk factors, firstly carrying out direct single-factor logistic regression analysis, and determining the direct risk factors which are ranked in the front relative to the acute renal injury;
(3) taking the risk factors ranked in the front in the step (2) as dependent variables respectively, carrying out indirect single-factor logistic regression analysis on the remaining variables, and determining the indirect risk factors ranked in the front again;
(4) combining the direct risk factors and the indirect risk factors in the step (2) and the step (3) to obtain combined risk factors;
(5) performing multi-factor logistic regression analysis on the combined risk factors, and deleting the co-linear variables to obtain final risk factors related to postoperative acute kidney injury;
(6) assigning values to the final risk factors based on the regression coefficients of the final risk factors, establishing a line chart prediction model equation, and calculating the incidence rate of acute kidney injury: p (t) ═ λ0(t)exp(β1x1+β2x2+…+βkxk)；
(7) The model is externally verified by a verification group.
3. The method for establishing a model for the prediction of acute renal injury after coronary artery bypass graft as claimed in claim 2, wherein the 27 possible risk factor variables of step (2) are all classified variables and are expressed by frequency (percentage).
4. The method for establishing a model for predicting acute renal injury after coronary artery bypass graft as claimed in claim 2, wherein the direct risk factors in step (2) are 3: serum creatinine, history of myocardial infarction and perioperative blood transfusion.
5. The method for establishing a model for predicting acute renal injury after coronary artery bypass graft as claimed in claim 2, wherein the indirect risk factors in step (3) are 10: gender, diabetes, elevated alanine aminotransferase, cardiac surgery, brain natriuretic peptide, peripheral arterial disease, left ventricular ejection fraction, hypertension, chronic obstructive pulmonary disease, and extracorporeal circulation surgery.
6. The method for establishing a model for predicting acute renal injury after coronary artery bypass graft as claimed in claim 2, wherein the combined risk factors in step (4) are 13: blood creatinine, history of myocardial infarction, perioperative blood transfusion, sex, diabetes, elevated alanine aminotransferase, cardiac surgery, brain natriuretic peptide, peripheral arterial disease, left ventricular ejection fraction, hypertension, chronic obstructive pulmonary disease, and extracorporeal circulation surgery, and the final risk factors of step (5) are 9: gender, elevated alanine aminotransferase, brain natriuretic peptide, blood creatinine, left ventricular ejection fraction, history of myocardial infarction, hypertension, extracorporeal circulation surgery, and perioperative blood transfusion.
7. The method according to claim 2, wherein the significance of risk factors is ranked according to the absolute value of the accuracy in the direct one-factor Logistic regression analysis in step (2) and the indirect one-factor Logistic regression analysis in step (3).
8. The method for establishing a model for predicting acute renal injury after coronary artery bypass graft according to claim 2, wherein the multi-factor Logistic regression analysis in step (5) adopts an "Enter" method, and a line chart is established based on Logistic regression equation.
9. The method of claim 2, wherein the external validation of step (7) comprises using AUC values for discrimination assessment, using calibration curve to assess model calibration, and using decision curve analysis for net benefit assessment.
10. The method for establishing a model for the prediction of acute renal injury after coronary artery bypass graft according to claim 2, wherein all statistical analyses are performed using R language (version 3.5).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110077761.7A CN112837819B (en) | 2021-01-20 | 2021-01-20 | Method for establishing acute kidney injury prediction model after coronary artery bypass grafting operation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110077761.7A CN112837819B (en) | 2021-01-20 | 2021-01-20 | Method for establishing acute kidney injury prediction model after coronary artery bypass grafting operation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112837819A true CN112837819A (en) | 2021-05-25 |
| CN112837819B CN112837819B (en) | 2024-04-16 |
Family
ID=75929197
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110077761.7A Active CN112837819B (en) | 2021-01-20 | 2021-01-20 | Method for establishing acute kidney injury prediction model after coronary artery bypass grafting operation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112837819B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112820397A (en) * | 2021-01-20 | 2021-05-18 | 尹丽君 | Method for establishing perioperative risk prediction model for coronary artery bypass grafting |
| CN113409945A (en) * | 2021-07-02 | 2021-09-17 | 上海市第一人民医院 | Model capable of predicting acute kidney injury caused by sepsis |
| CN113591582A (en) * | 2021-07-01 | 2021-11-02 | 山东科技大学 | Character recognition device and method based on resting state functional magnetic resonance data |
| CN113782211A (en) * | 2021-10-27 | 2021-12-10 | 首都医科大学附属北京地坛医院 | Establishment method and prediction method of risk early warning model for chronic kidney disease of hepatitis B cirrhosis patients |
| CN113921136A (en) * | 2021-09-13 | 2022-01-11 | 吾征智能技术(北京)有限公司 | System for fusing multi-source data to intelligently evaluate and predict chronic disease risk |
| CN114974595A (en) * | 2022-05-13 | 2022-08-30 | 江苏省人民医院（南京医科大学第一附属医院） | Crohn's disease patient mucosa healing prediction model and method |
| CN115910365A (en) * | 2022-11-16 | 2023-04-04 | 华中科技大学同济医学院附属同济医院 | Construction method and prediction system of Eos-CRSwNP preoperative intractable assessment model |
| CN117894466A (en) * | 2024-03-15 | 2024-04-16 | 四川大学华西医院 | Continuous acute nephritis risk prediction method and system based on recurrent neural network |
| CN118430836A (en) * | 2024-07-02 | 2024-08-02 | 天津医科大学总医院 | Construction method and application of early-stage acute kidney injury prediction model after cardiac arrest resuscitation |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101689220A (en) * | 2007-04-05 | 2010-03-31 | 奥利安实验室有限公司 | The system and method that be used for the treatment of, diagnosis and prospective medicine illness takes place |
| CN110827992A (en) * | 2019-11-15 | 2020-02-21 | 袁洪 | Preoperative prediction method for acute renal injury after hypertension operation |
| CN111613334A (en) * | 2020-06-01 | 2020-09-01 | 广东省心血管病研究所 | Method for establishing acute kidney injury probability prediction model after aortic arch replacement |
| CN112017783A (en) * | 2020-09-14 | 2020-12-01 | 华中科技大学同济医学院附属协和医院 | Prediction model for pulmonary infection after heart operation and construction method thereof |
-
2021
- 2021-01-20 CN CN202110077761.7A patent/CN112837819B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101689220A (en) * | 2007-04-05 | 2010-03-31 | 奥利安实验室有限公司 | The system and method that be used for the treatment of, diagnosis and prospective medicine illness takes place |
| US20100088264A1 (en) * | 2007-04-05 | 2010-04-08 | Aureon Laboratories Inc. | Systems and methods for treating diagnosing and predicting the occurrence of a medical condition |
| CN110827992A (en) * | 2019-11-15 | 2020-02-21 | 袁洪 | Preoperative prediction method for acute renal injury after hypertension operation |
| CN111613334A (en) * | 2020-06-01 | 2020-09-01 | 广东省心血管病研究所 | Method for establishing acute kidney injury probability prediction model after aortic arch replacement |
| CN112017783A (en) * | 2020-09-14 | 2020-12-01 | 华中科技大学同济医学院附属协和医院 | Prediction model for pulmonary infection after heart operation and construction method thereof |
Non-Patent Citations (2)
| Title |
|---|
| 席雷;王正清;刘志刚;梁少杰;滕磊;: "体外循环对冠状动脉旁路移植术后患者早期急性肾损伤的影响", 第三军医大学学报, no. 12 * |
| 杨立猛等: "冠状动脉旁路移植术后急性肾损伤的发生情况与危险因素分析", 中国血液净化, no. 11, pages 738 - 741 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112820397B (en) * | 2021-01-20 | 2024-04-05 | 中国医学科学院阜外医院 | Method for establishing peri-operative risk prediction model of coronary artery bypass grafting |
| CN112820397A (en) * | 2021-01-20 | 2021-05-18 | 尹丽君 | Method for establishing perioperative risk prediction model for coronary artery bypass grafting |
| CN113591582A (en) * | 2021-07-01 | 2021-11-02 | 山东科技大学 | Character recognition device and method based on resting state functional magnetic resonance data |
| CN113591582B (en) * | 2021-07-01 | 2024-05-31 | 山东科技大学 | Character recognition device and method based on resting state functional magnetic resonance data |
| CN113409945A (en) * | 2021-07-02 | 2021-09-17 | 上海市第一人民医院 | Model capable of predicting acute kidney injury caused by sepsis |
| CN113921136A (en) * | 2021-09-13 | 2022-01-11 | 吾征智能技术(北京)有限公司 | System for fusing multi-source data to intelligently evaluate and predict chronic disease risk |
| CN113782211A (en) * | 2021-10-27 | 2021-12-10 | 首都医科大学附属北京地坛医院 | Establishment method and prediction method of risk early warning model for chronic kidney disease of hepatitis B cirrhosis patients |
| CN114974595A (en) * | 2022-05-13 | 2022-08-30 | 江苏省人民医院（南京医科大学第一附属医院） | Crohn's disease patient mucosa healing prediction model and method |
| CN115910365A (en) * | 2022-11-16 | 2023-04-04 | 华中科技大学同济医学院附属同济医院 | Construction method and prediction system of Eos-CRSwNP preoperative intractable assessment model |
| CN115910365B (en) * | 2022-11-16 | 2024-02-13 | 华中科技大学同济医学院附属同济医院 | Construction method and prediction system of Eos-CRSwNP preoperative refractory evaluation model |
| CN117894466A (en) * | 2024-03-15 | 2024-04-16 | 四川大学华西医院 | Continuous acute nephritis risk prediction method and system based on recurrent neural network |
| CN117894466B (en) * | 2024-03-15 | 2024-05-17 | 四川大学华西医院 | Continuous acute nephritis risk prediction method and system based on recurrent neural network |
| CN118430836A (en) * | 2024-07-02 | 2024-08-02 | 天津医科大学总医院 | Construction method and application of early-stage acute kidney injury prediction model after cardiac arrest resuscitation |
| CN118430836B (en) * | 2024-07-02 | 2024-09-06 | 天津医科大学总医院 | Construction method and application of early-stage acute kidney injury prediction model after cardiac arrest resuscitation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112837819B (en) | 2024-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112837819A (en) | Method for establishing acute kidney injury prediction model after coronary artery bypass grafting | |
| Bundy et al. | Serum calcification propensity and coronary artery calcification among patients with CKD: the CRIC (Chronic Renal Insufficiency Cohort) study | |
| Wu et al. | An artificial intelligence approach to early predict non-ST-elevation myocardial infarction patients with chest pain | |
| CN115019919B (en) | Deep learning-based method for establishing function prediction model after early recovery of stroke | |
| CN113327679A (en) | Pulmonary embolism clinical risk and prognosis scoring method and system | |
| CN112420196A (en) | Prediction method and system for survival rate of acute myocardial infarction patient within 5 years | |
| Shu et al. | Clinical application of machine learning-based artificial intelligence in the diagnosis, prediction, and classification of cardiovascular diseases | |
| CN112820397B (en) | Method for establishing peri-operative risk prediction model of coronary artery bypass grafting | |
| CN114898873A (en) | Method and system for predicting cardiovascular disease risk of diabetes mellitus pre-stage patient | |
| CN106980757A (en) | The concurrent coronary artery pathological changes hazards management system of Kawasaki disease and method for digging | |
| Zhou et al. | Prediction of 1-year mortality after heart transplantation using machine learning approaches: A single-center study from China | |
| Salvioni et al. | The MECKI score initiative: Development and state of the art | |
| Luo et al. | Machine learning–based risk model for predicting early mortality after surgery for infective endocarditis | |
| CN113640516A (en) | Application of peripheral blood EPCs (Epiches sinensis) as life time prediction marker for old people | |
| WO2018223832A1 (en) | Use of plasma s100a12 in early diagnosis of st-segment elevation myocardial infarction | |
| Wang et al. | The predictive value of CatLet© angiographic scoring system for long-term prognosis in patients with acute myocardial infarction presenting> 12 h after symptom onset | |
| Farzi et al. | Predicting serious diabetic complications using hidden pattern detection | |
| Kasama et al. | Prognostic value of myocardial perfusion single photon emission computed tomography for major adverse cardiac cerebrovascular and renal events in patients with chronic kidney disease: results from first year of follow-up of the Gunma-CKD SPECT multicenter study | |
| CN114864097A (en) | Method and device for establishing aorta dissection patient postoperative death prediction model | |
| Gualano et al. | Renal function–based contrast threshold predicts kidney injury in transcatheter aortic valve replacement | |
| Zhou et al. | A novel laboratory-based model to predict the presence of obstructive coronary artery disease comparison to coronary artery disease consortium 1/2 score, duke clinical score and diamond-forrester score in china | |
| CN115479934B (en) | Aortic dissection combined prognosis evaluation system based on markers and imaging | |
| CN114400094A (en) | Construction method and application of myocardial infarction risk prediction model after percutaneous coronary intervention treatment for multi-disease co-morbid old patients | |
| Cherbi et al. | One-year outcomes in cardiogenic shock triggered by ventricular arrhythmia: an analysis of the FRENSHOCK multicenter prospective registry | |
| Kong et al. | Evaluation of the prognostic role of the wall motion score index and the SYNTAX score II in patients with acute coronary syndrome following percutaneous coronary intervention by evaluation of major adverse cardiovascular events at 12-month follow-up |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210903 Address after: 100037 Beijing City, Xicheng District No. 167 North Applicant after: FUWAI HOSPITAL, CHINESE ACADEMY OF MEDICAL SCIENCES Address before: 6-3, 417 Hengshan street, Lushunkou District, Dalian, Liaoning, 116041 Applicant before: Yin Lijun |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |