Postoperative risk assessment system, device, storage medium and program product

Abstract

The invention provides a postoperative risk assessment system and device, a storage medium and a program product, and relates to the technical field of computers, and the system comprises an extraction module which is used for extracting independent risk factors of early decline of a vascular bridge from postoperative data of a patient; the score determination module is used for determining the score of each factor in the independent risk factors based on a score scale in the column graph model; the column graph model is constructed based on independent risk factors; and the prediction module is used for predicting risk information of early decline of the vascular bridge after coronary artery bypass transplantation based on the risk coefficient corresponding to the total score of each factor in the independent risk factors. Based on Lasso regression analysis and Logistic regression analysis results, a vascular bridge early decline prediction model with risk factors such as QFR greater than 0.80, PI greater than 3.0, complications and non-left trunk stenosis as main bodies is constructed, so that the accuracy of risk assessment of vascular bridge early decline of postoperative patients is improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a postoperative risk assessment system, device, storage medium and program product. Background Art

[0002] Coronary artery bypass grafting (CABG) is a common surgical procedure for the treatment of patients with complex coronary heart disease. Among them, vascular grafts are widely used in CABG surgery because their long-term patency rate is significantly higher than that of venous grafts and they can improve the long-term survival rate of patients. However, a small number of patients experience early failure of vascular grafts within 1 year after surgery (stenosis ≥ 50% or complete occlusion), which may significantly affect the quality of life and medium- and long-term prognosis of patients. Therefore, determining the risk factors for early failure of vascular grafts after surgery is of great clinical significance for evaluating the benefits of bypass surgery, optimizing postoperative management, reducing the restenosis rate, and improving the long-term survival rate of patients. Therefore, how to achieve risk assessment after CABG surgery has become an urgent problem to be solved. Summary of the invention

[0003] The present invention provides a postoperative risk assessment system, device, storage medium and program product, which are used to solve the defects of CABG postoperative risk assessment in the prior art, realize the risk assessment of early decay of vascular bridges of postoperative patients, and improve the accuracy of the assessment.

[0004] The present invention provides a postoperative risk assessment system, comprising the following contents: An extraction module is used to extract independent risk factors for early failure of vascular grafts from postoperative data of patients; the independent risk factors include non-left main stem stenosis, complications, quantitative blood flow fraction and pulsatility index; A score determination module, used to determine the score of each factor in the independent risk factors based on the scoring scale in the nomogram model; the nomogram model is constructed based on the independent risk factors; A prediction module, used to predict the risk information of early failure of vascular graft after coronary artery bypass grafting based on the risk coefficient corresponding to the total score of each factor in the independent risk factors; The independent risk factors are determined by performing minimum absolute value shrinkage and selection operator Lasso regression analysis and multivariate logistic regression analysis on the data set of potential risk factors for cardiovascular disease, and combining the results of Lasso regression analysis and logistic regression analysis.

[0005] According to a postoperative risk assessment system provided by the present invention, the independent risk factors are determined in the following manner: Lasso regression analysis was performed on the data set to obtain the first risk factor for early failure of vascular grafts; Logistic regression analysis was performed on the data set to obtain the second type of risk factors for early failure of vascular grafts; rank the first-category risk factors and the second-category risk factors in terms of importance; The common risk factors in the ranking results of the first category of risk factors and the ranking results of the second category of risk factors are selected as the independent risk factors.

[0006] According to a postoperative risk assessment system provided by the present invention, the prediction module is further used for: Based on the ranking results of the weight coefficients of the first and second risk factors, a target risk factor is selected; wherein the target risk factor includes the independent risk factor; Determine the score of each factor in the target risk factor based on the scoring scale in the nomogram model constructed for the target risk factor; Based on the risk coefficient corresponding to the total score of each factor in the target risk factors, the risk information of early failure of the vascular graft after coronary artery bypass grafting is predicted.

[0007] According to a postoperative risk assessment system provided by the present invention, the first type of risk factors is determined by the following method: Construct the objective function of the Lasso regression model; Determining the optimal regularization parameter of the objective function based on a cross-validation method; Using the data set, training the objective function after determining the optimal regularization parameter to determine the regression coefficient of each variable; the variable is a risk factor in the data set; The first category of risk factors is determined based on the regression coefficient of each of the variables.

[0008] According to a postoperative risk assessment system provided by the present invention, the second type of risk factors is determined by: Build a Logistic regression model; Based on the Logistic regression model, a univariate analysis is performed on the data set to screen out candidate risk factors; Perform a multifactor analysis on the candidate risk factors to obtain the second type of risk factors.

[0009] According to a postoperative risk assessment system provided by the present invention, the prediction module is further used for: Determining a risk factor risk score based on the independent risk factors and their weight coefficients; Dividing risk groups based on the risk scores of the risk factors; Based on the risk groups, major adverse cardiovascular and cerebrovascular events are predicted.

[0010] According to a postoperative risk assessment system provided by the present invention, the weight ranking of each factor in the independent risk factors is quantitative blood flow fraction, complications, pulsatility index and non-left main coronary artery stenosis.

[0011] According to a postoperative risk assessment system provided by the present invention, the quantitative blood flow fraction is greater than 0.8, and the pulsatility index is greater than 3.0.

[0012] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements a method in any of the above-mentioned postoperative risk assessment systems when executing the computer program.

[0013] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method in any of the above-mentioned postoperative risk assessment systems is implemented.

[0014] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method in any one of the above-mentioned postoperative risk assessment systems is implemented.

[0015] The postoperative risk assessment system, device, storage medium and program product provided by the present invention include: an extraction module for extracting independent risk factors for early vascular graft failure from the patient's postoperative data; a score determination module for determining the score of each factor in the independent risk factors based on the scoring scale in the nomogram model; the nomogram model is constructed based on the independent risk factors; a prediction module for predicting the risk information of early vascular graft failure after coronary artery bypass grafting based on the risk coefficient corresponding to the total score of each factor in the independent risk factors. Based on the results of Lasso regression analysis and Logistic regression analysis, the present invention constructs a prediction model for early vascular graft failure with risk factors such as QFR>0.80, PI>3.0, complications and non-left main trunk stenosis as the main body, thereby improving the accuracy of risk assessment of early vascular graft failure in postoperative patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0017] Figure 1 It is a module schematic diagram of the postoperative risk assessment system provided by the present invention.

[0018] Figure 2 This is one of the schematic diagrams of the Lasso regression analysis of risk factors for early failure of vascular bridges provided by the present invention.

[0019] Figure 3 This is the second schematic diagram of the Lasso regression analysis of risk factors for early failure of vascular bridges provided by the present invention.

[0020] Figure 4 This is the third schematic diagram of the Lasso regression analysis of risk factors for early failure of vascular bridges provided by the present invention.

[0021] Figure 5 This is one of the schematic diagrams for constructing a new model of risk factors for early failure of vascular bridges provided by the present invention.

[0022] Figure 6 This is the second schematic diagram of constructing a new model of risk factors for early failure of vascular bridges provided by the present invention.

[0023] Figure 7 This is the third schematic diagram of constructing a new model of risk factors for early failure of vascular bridges provided by the present invention.

[0024] Figure 8 This is one of the schematic diagrams for validating the effectiveness of the early-stage decay prediction model for vascular bridges provided by the present invention.

[0025] Fig. 9 This is the second schematic diagram of the effectiveness verification of the early-stage decay prediction model of vascular bridge provided by the present invention.

[0026] Fig.10 This is the third schematic diagram of the effectiveness verification of the early-stage decay prediction model of vascular bridge provided by the present invention.

[0027] Fig.11 It is a schematic diagram for comparing the cumulative MACCE-free event rates after CABG surgery provided by the present invention.

[0028] Fig.12 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0030] The influencing factors of early vascular graft failure are complex and diverse, including traditional cardiovascular risk factors such as hypertension, diabetes, and smoking history, as well as intraoperative hemodynamic parameters and complications. In related technologies, the nomogram prediction model constructed with traditional cardiovascular risk factors such as smoking and hypertension has a certain ability to predict the risk of vascular graft stenosis. However, with the in-depth study of hemodynamic and wall compliance evaluation tools such as coronary artery quantitative flow ratio (QFR) and pulsatility index (PI), more and more evidence shows that blood flow parameters play an important role in evaluating the long-term prognosis of CABG patients. However, in related technologies, there has been no research on the association between these influencing factors and early vascular graft failure.

[0031] Based on this, the present invention explored the potential risk factors for early failure of vascular grafts after CABG surgery through the Least Absolute Shrinkage and Selection Operator (Lasso) regression model and the multifactorial logistic regression model, constructed and evaluated a risk prediction model for early failure of vascular grafts, and provided a new basis for risk assessment and individualized treatment of postoperative patients.

[0032] The present invention provides a postoperative risk assessment system, specifically a postoperative vascular bridge early decay assessment system for coronary artery bypass grafting.

[0033] Combine the following Figure 1-Figure 12 The postoperative risk assessment system, device, storage medium and program product of the present invention are described.

[0034] Figure 1 Schematic diagram of the module of the postoperative risk assessment system provided by the present invention. Figure 1 As shown, the system may include the following modules: An extraction module is used to extract independent risk factors for early failure of vascular grafts from patients' postoperative data; A score determination module is used to determine the score of each factor in the independent risk factor based on the scoring scale in the nomogram model; the nomogram model is constructed based on the independent risk factors; A prediction module is used to predict the risk information of early failure of vascular graft after coronary artery bypass grafting based on the risk coefficient corresponding to the total score of each factor in the independent risk factors; Among them, independent risk factors were determined by performing least absolute shrinkage and selection operator Lasso regression analysis and multivariate logistic regression analysis on the data set of potential risk factors for cardiovascular disease, and combining the results of Lasso regression analysis and logistic regression analysis.

[0035] In the embodiment of the present invention, the vascular graft may be an internal mammary artery graft; early failure of the vascular graft after coronary artery bypass grafting refers to a graft stenosis degree of ≥50% (including complete occlusion) assessed by CCTA (Coronary Computed Tomography Angiography).

[0036] Independent risk factors include non-left main stenosis, complications (also known as in-hospital complications), quantitative blood flow fraction and pulsatility index; the weight ranking of each factor in the independent risk factors is quantitative blood flow fraction, complications, pulsatility index and non-left main stenosis. Among them, the quantitative blood flow fraction is greater than 0.8 (i.e., QFR>0.80) and the pulsatility index is greater than 3.0 (i.e., PI>3.0).

[0037] Pre-constructing a dataset of potential risk factors for cardiovascular disease can, for example, be achieved by: Baseline clinical data of all patients were collected, including demographic characteristics, intraoperative data of CABG, and imaging data (including coronary angiography and postoperative follow-up CCTA images), etc. Coronary angiography was performed using standard percutaneous femoral or radial artery access with a 6F or 7F guiding catheter.

[0038] All patients underwent CCTA follow-up to evaluate graft patency 1 year after surgery (12±3 months), and were divided into a non-fading group and a failing group. Among them, the clinical baseline data of patients in the non-fading group and the failing group showed that the proportion of patients with preoperative QFR>0.80, non-left main stem disease or in-hospital complications in the early failing group of vascular grafts was higher (P<0.01), see Tables 1 and 2.

[0039] Table 1 Comparison of clinical baseline characteristics between the non-failure group and the failure group Table 2 Comparison of clinical baseline characteristics between the non-failure group and the failure group In Tables 1 and 2, the failure group was defined as vascular graft stenosis ≥50% diameter (including complete occlusion) 1 year after surgery; BMI: body-mass index; PCI: percutaneous coronary intervention; LVEF: left ventricular ejection fraction; non-left main disease was defined as left main stenosis <50%; other concomitant surgeries: including left atrial appendectomy, ventricular aneurysm resection, carotid endarterectomy and arteriovenous fistula surgery; number of arterial graft anastomoses: including the number of anastomoses between the left internal mammary artery, right internal mammary artery or radial artery graft and the diseased coronary artery; in-hospital complications included postoperative respiratory tract, surgical site, catheter-related bloodstream infection or infectious endocarditis and other infection symptoms; postoperative bleeding (chest drainage volume ≥7 mL / Kg / h for 2 consecutive hours within the first 12 hours after surgery or a total of ≥84 mL / kg within the first 24 hours); newly diagnosed heart failure by cardiac ultrasound and laboratory examination after surgery; reoperation after surgery; : t-test; #: chi-square test; : Mann-Whitney U test; ▲: Fisher exact probability method.

[0040] Tables 1 and 2 include potential risk factors for cardiovascular disease, such as traditional cardiovascular disease risk factors, including age, sex, BMI, ejection fraction, diabetes, hypertension, hyperlipidemia, peripheral vascular disease, smoking, previous myocardial infarction and PCI history, and time from preoperative angiography to surgery; potential intraoperative risk factors, including non-left main stem stenosis, QFR>0.80, graft material, and PI; postoperative risk factors, including postoperative complications (such as infection, bleeding, heart failure, and reoperation) and length of hospital stay.

[0041] In one embodiment, independent risk factors are determined in the following manner: performing Lasso regression analysis on the data set to obtain the first category of risk factors for early decline of vascular grafts; performing Logistic regression analysis on the data set to obtain the second category of risk factors for early decline of vascular grafts; ranking the first category of risk factors and the second category of risk factors in terms of importance; and selecting the common risk factors from the ranking results of the first category of risk factors and the ranking results of the second category of risk factors as independent risk factors.

[0042] In order to screen out the most significant factors affecting the early decay of vascular grafts and improve the prediction ability of the model, the embodiment of the present invention uses Lasso regression to introduce a regularization parameter ( λ ) to reduce overfitting, such as Figures 2 to 3 The factors included in the model included all potential risk factors for cardiovascular disease in Tables 1 and 2. The model adopted binomial distribution and determined the optimal parameters (such as when λ=0.018, the prediction error of the model was the lowest). At this time, the variables included in the model included: non-left main stenosis, hypertension, hyperlipidemia, complications (i.e., in-hospital complications), QFR>0.80, and PI>3.0. The importance ranking analysis of the relevant factors showed that QFR>0.80 (weighted coefficient 0.152) and in-hospital complications (weighted coefficient 0.114) were the two most important risk factors, followed by PI>3.0 (weighted coefficient 0.063) and non-left main stenosis (weighted coefficient 0.038), suggesting that these factors may have an important impact on the prediction of early failure of vascular grafts, such as Figure 4 shown.

[0043] In one embodiment, the first category of risk factors is determined in the following manner: constructing an objective function of a Lasso regression model; determining an optimal regularization parameter of the objective function based on a cross-validation method; using a data set to train the objective function after determining the optimal regularization parameter to determine the regression coefficient of each variable; the variables are risk factors in the data set; and determining the first category of risk factors based on the regression coefficient of each variable.

[0044] For example, setting the objective function of the Lasso regression model, its general form is: ; in, y i It is i The early decay of vascular grafts in samples (target variable), x ij It is i The sample j potential risk factors, β j is the corresponding regression coefficient, n is the sample size, p is the number of potential risk factors, λ is the regularization parameter.

[0045] Since the model adopts binomial distribution, the output of the model is a probability value indicating the probability of early failure of the vascular graft, which matches the binary nature of the target variable.

[0046] Furthermore, the optimal regularization parameter of the objective function is determined by cross-validation. For example, the 10-fold cross-validation method is used as an example for analysis. The data set is divided into 10 parts. λValue: Use nine of them as training sets. Based on the principle of minimizing the objective function, use an optimization algorithm (such as coordinate descent) to update the regression coefficients so that the model can fit the training data and is subject to regularization constraints. Use the remaining one as a test set and calculate the prediction performance indicators of the model on the test set, such as accuracy, recall, F1-score or logarithmic loss. Traverse different values ​​and repeat the above process to select the model with the best average prediction performance on the test set of ten-fold cross validation. λ as the optimal parameter, that is, the optimal regularization parameter.

[0047] In determining the optimal λ Finally, the Lasso regression model was retrained using the entire data set. In this process, due to the effect of L1 regularization, the regression coefficients of some variables will be compressed to 0, while variables whose regression coefficients are not compressed to 0, such as non-left main stenosis, hypertension, hyperlipidemia, complications, QFR>0.80, and PI>3.0, are considered to have a significant impact on the early decline of vascular grafts and are therefore included in the final model. Based on this, the first category of risk factors can include QFR>0.80, complications, PI>3.0, non-left main stenosis, hypertension, and hyperlipidemia.

[0048] Optionally, the variables finally retained in the Lasso regression model can be sorted according to their absolute values ​​of regression coefficients. The larger the absolute value of the regression coefficient, the more important the role of the variable in the model.

[0049] To further control for confounding factors, a logistic regression model was constructed to control: 1) traditional cardiovascular risk factors, including age, sex, BMI, ejection fraction, diabetes, hypertension, hyperlipidemia, peripheral vascular disease, smoking, previous myocardial infarction and PCI history, and time from preoperative angiography to surgery; 2) potential intraoperative risk factors, including non-left main stenosis, QFR>0.80, graft material, and PI; 3) postoperative risk factors, including postoperative complications (such as infection, bleeding, heart failure, and reoperation) and length of hospital stay, as shown in Tables 3 and 4 . Figure 5 shown.

[0050] Table 3 Logistic regression analysis of influencing factors of vascular graft failure 1 year after CABG surgery In Table 3, PI: pulsatility index; QFR: quantitative flow fraction; PCI: percutaneous coronary intervention; the unlisted potential risk factors for cardiovascular disease and intraoperative related factors had P values ​​> 0.05 and were included in the multivariate analysis with univariate logistic regression analysis P < 0.2.

[0051] Multivariate logistic regression analysis was performed on the data set to obtain the second-category risk factors for early failure of vascular grafts. Among them, the second-category risk factors may include non-left main stenosis, complications, QFR>0.80 and PI>3.0. Optionally, the second-category risk factors may also include risk factors such as hypertension and hyperlipidemia.

[0052] In one embodiment, the second category of risk factors is determined by: constructing a Logistic regression model; performing univariate analysis on the data set based on the Logistic regression model to screen out candidate risk factors; and performing multivariate analysis on the candidate risk factors to obtain the second category of risk factors.

[0053] For example, the Logistic regression model is used for binary classification problems. In the context of studying early failure of vascular grafts, assuming that the dependent variable Y (Whether the vascular bridge decays) follows the Bernoulli distribution, and its probability function is: ; in, X =( x 1 , x 2 , ..., x p ) is a vector containing all the predictive variables that may affect the early failure of vascular grafts (such as the patient's age, gender, disease indicators, etc.), β =( β 0 , β 1 , ..., β p ) is the regression coefficient vector.

[0054] In the univariate analysis, each risk factor was analyzed with simple logistic regression to calculate the odds ratio (OR) and its confidence interval for each factor. p-value ( P value), β The odds ratio indicates the relative probability change of an event (early failure of vascular graft) when the factor increases by one unit (for continuous variables) or changes from one category to another (for categorical variables) when other factors remain unchanged. Then, based on the results of univariate analysis, candidate risk factors are screened. For example, in Table 3, select P Factors with a value of <0.2 (i.e., candidate risk factors) were subjected to subsequent multivariate analysis.

[0055] In the multivariate analysis, the candidate risk factors screened out in the univariate analysis were simultaneously included in the multivariate logistic regression model. In the multivariate model, the model will take into account the interaction and combined impact of these factors, so as to more accurately evaluate the independent contribution of each factor to the early decline of vascular grafts. For example, the Wald statistic or likelihood ratio statistic of each factor is calculated and compared with the corresponding distribution (such as chi-square distribution) to obtain p-value ( P value). p-value ( P The value is used to test the significance of the factor in the model. p-value ( P If the value is less than 0.05, the factor is considered to have a statistically significant impact on the early failure of the vascular graft. For example, in Table 3, p-value ( P Value) < 0.05 includes non-left main stenosis, complications, QFR> 0.80, and PI> 3.0. The multivariate analysis results in Table 3 show that QFR> 0.80 (OR = 5.57, 95% CI: 2.98-10.41) and in-hospital complications (OR = 4.02, 95% CI: 1.59-10.19) are strong predictors of failure risk. The results of Logistic regression analysis are consistent with those of Lasso regression analysis, indicating the importance of hemodynamics and complication management in reducing the risk of graft failure. In addition, the significance of non-left main stenosis in both models indicates that the risk of vascular graft stenosis in this type of patients may increase, which requires clinical attention.

[0056] Based on the results of Logistic regression analysis, the importance of the first category of risk factors is ranked as QFR>0.80, complications, PI>3.0, non-left main stenosis, hypertension and hyperlipidemia. Based on the results of Lasso regression analysis, the importance of the second category of risk factors is ranked as QFR>0.80, complications, PI>3.0 and non-left main stenosis. Then, multiple risk factors with the highest ranking are selected, such as the top 4 risk factors; further, common risk factors are extracted from the selected first and second category risk factors as independent risk factors, that is, QFR>0.80, complications, PI>3.0 and non-left main stenosis are taken as independent risk factors.

[0057] It is understandable that the purpose of selecting common risk factors for two regression analyses is to find factors that are considered to have a significant impact on early failure of vascular grafts under different analysis models. These factors have higher reliability and importance because they have been screened by two different analysis ideas and model mechanisms, and can provide stronger evidence support for clinical decision-making, risk prediction, etc. At the same time, these common risk factors showed a significant impact on early failure of vascular grafts in two different statistical analysis models, indicating that they may play a core role in the occurrence of early failure of vascular grafts. Compared with factors screened out in only one model, common risk factors are more likely to be real and stable risk factors, and their relationship with early failure of vascular grafts is closer and more reliable. In subsequent research and practice, in-depth research, monitoring or intervention on these common risk factors can more effectively reduce the risk of early failure of vascular grafts, or more accurately predict the occurrence of early failure of vascular grafts.

[0058] Furthermore, based on the independent risk factors, a nomogram model was constructed, such as Figure 6 As shown in Figure 3, the nomogram model was used to predict the risk of early failure of vascular grafts after coronary artery bypass grafting.

[0059] After determining the independent risk factors and nomogram model, the independent risk factors for early failure of vascular grafts were extracted from the patients' postoperative data. Based on the scoring scale in the nomogram model, the scores of each factor in the independent risk factors were determined. Finally, based on the risk coefficient corresponding to the total score of each factor in the independent risk factors, the risk information of early failure of vascular grafts after coronary artery bypass grafting was predicted.

[0060] For example, in Figure 6 In the analysis, based on the scoring scale, the score of each independent risk factor can be determined, such as PI>3.0 is scored as 55, QFR>0.80 is scored as 98, complications are scored as 85, and non-left main stem stenosis is scored as 69; assuming that PI>3.0 does not meet the condition, the score is 0, and the total score of all risk factors is 0+98+85+69=252. The risk coefficient corresponding to this total score is 252 / 350=0.72. At this time, it can be predicted that the risk of early failure of the vascular graft after coronary artery bypass grafting is relatively high.

[0061] Compared with the old model that included factors such as smoking, hypertension, LAD stenosis <75% and coronary flow, the nomogram model provided in the embodiment of the present invention included four new key variables: non-left main stenosis, QFR>0.80, PI>3.0 and complications. The AUC of the new model was 0.758 (95% CI: 0.694~0.820), which was significantly higher than the old model (AUC=0.632, 95% CI: 0.561~0.694) and the new and old mixed model (AUC=0.672, 95% CI: 0.577~0.758). The results showed that the new model showed a higher ability to predict early failure of vascular bridges, especially in the identification and early intervention of high-risk patients, and has important application value, such as Figure 7 shown.

[0062] Optionally, binary logistic regression was used to evaluate the model performance, and the data was randomly split into a training set and a test set with a test ratio of 0.70. The ROC (Receiver Operating Characteristic Curve) curve and calibration curve of the training set and the test set showed that the actual performance of the prediction model was highly consistent with the ideal performance, indicating that the model has a high clinical application value and can provide effective support for clinical decision-making, such as Figures 8 to 10 Further calculations of the net reclassification index (NRI) and integrated discrimination improvement index (IDI) showed that the classification accuracy of the new model increased by 27.2% (NRI=0.272, 95% CI: 0.18-0.37; IDI=0.109, 95% CI: 0.059-0.158, P<0.05).

[0063] The postoperative risk assessment system provided by the embodiment of the present invention comprises an extraction module for extracting independent risk factors for early failure of vascular grafts from postoperative data of patients; independent risk factors include non-left main trunk stenosis, complications, quantitative blood flow fraction and pulsatility index; a score determination module for determining the score of each factor in the independent risk factors based on the scoring scale in the nomogram model; the nomogram model is constructed based on independent risk factors; a prediction module for predicting the risk information of early failure of vascular grafts after coronary artery bypass grafting based on the risk coefficient corresponding to the total score of each factor in the independent risk factors; wherein the independent risk factors are determined by performing minimum absolute value shrinkage and selection operator Lasso regression analysis and multifactor logistic regression analysis on the data set of potential risk factors for cardiovascular disease, and combining the results of Lasso regression analysis and Logistic regression analysis. Based on the results of Lasso regression analysis and multifactor logistic regression analysis, the present invention constructs a prediction model for early failure of vascular grafts with risk factors such as QFR>0.80, PI>3.0, complications and non-left main trunk stenosis as the main body, thereby improving the accuracy of risk assessment of early failure of vascular grafts in postoperative patients.

[0064] Based on the above embodiment, the prediction module is also used to: select target risk factors based on the weight coefficient ranking results of the first category risk factors and the second category risk factors; wherein the target risk factors include independent risk factors; determine the score of each factor in the target risk factors based on the scoring scale in the nomogram model constructed based on the target risk factors; and predict the risk information of early failure of the vascular bridge after coronary artery bypass grafting based on the risk coefficient corresponding to the total score of each factor in the target risk factors.

[0065] For example, based on the results of Logistic regression analysis, the weight coefficients of the first category of risk factors are ranked as QFR>0.80, complications, PI>3.0, non-left main stenosis, hypertension, and hyperlipidemia. Based on the results of Lasso regression analysis, the weight coefficients of the second category of risk factors are ranked as QFR>0.80, complications, PI>3.0, and non-left main stenosis. Based on this, QFR>0.80, complications, PI>3.0, non-left main stenosis, hypertension, and hyperlipidemia can be selected as target risk factors. Then, based on the scoring scale in the nomogram model constructed based on the target risk factor, the score of each factor in the target risk factor is determined, and finally, based on the risk coefficient corresponding to the total score of each factor in the target risk factor, the risk information of early failure of the vascular graft after coronary artery bypass grafting is predicted.

[0066] Based on the results of Lasso regression analysis and multivariate logistic regression analysis, the embodiment of the present invention constructs a prediction model for early vascular graft failure with risk factors such as QFR>0.80, PI>3.0, complications, non-left main trunk stenosis, hypertension and hyperlipidemia as the main body, thereby improving the accuracy of risk assessment of early vascular graft failure in postoperative patients.

[0067] Based on the above embodiment, the prediction module is also used to: determine the risk score of risk factors based on independent risk factors and their weight coefficients; divide risk groups based on the risk score of risk factors; and predict major adverse cardiovascular and cerebrovascular events based on the risk groups.

[0068] In the embodiment of the present invention, major adverse cardiac and cerebrovascular events refer to MACCE (major adverse cardiac and cerebrovascular events), wherein MACCE events include all-cause death, myocardial infarction, stroke, and revascularization due to angina pectoris or other reasons.

[0069] Based on each risk factor and its weight coefficient, the risk factor risk score is determined. Among them, the risk factor risk score is to comprehensively evaluate the risk of early vascular graft failure in individual patients. By combining multiple risk factors and their weight coefficients, a quantitative risk score can be obtained. For example, the weight coefficient of QFR>0.80 is 0.152, the weight coefficient of in-hospital complications is 0.114, the weight coefficient of PI>3.0 is 0.063, and the weight coefficient of non-left main stenosis is 0.038. The risk factor risk score is: The risk factor score = (QFR>0.80×0.152) + (in-hospital complications×0.114) + (PI>3.0×0.063) + (non-left main coronary artery stenosis×0.038).

[0070] Optionally, the risk factor risk score can also be calculated based on the binary classification results (0 or 1) of each risk factor and its weight coefficient. For example, assuming that the binary classification result of QFR>0.80 is 1, the weight coefficient is 0.152, the binary classification result of in-hospital complications is 1, the weight coefficient is 0.114, the binary classification result of PI>3.0 is 0, the weight coefficient is 0.063, and the binary classification result of non-left main stenosis is 1, the weight coefficient is 0.038, then the risk factor risk score is: The risk score of hazard factors = 1×0.152+1×0.114+0×0.063+1×0.038.

[0071] Furthermore, based on the risk scores of risk factors, risk groups are divided, such as high-risk group, medium-risk group and low-risk group; finally, major adverse cardiovascular and cerebrovascular events are predicted based on the risk groups.

[0072] Specifically, the coronary risk score of the followed-up patients was calculated according to the weighted coefficient of the importance of risk factors. The total risk scores of four risk factors, including QFR, PI, non-left main lesions and in-hospital complications, were grouped and statistically tested by enumeration method. For example, the grouped statistical test can be implemented using X-tile software. Based on the results of the grouped statistical test, the optimal cutoff value related to MACCE was obtained to maximize the difference in survival patterns. According to the risk score of risk factors, patients were divided into a low-risk group (score <0.16), a medium-risk group (score ≥0.16 and <0.25) and a high-risk group (score ≥0.25). The Kaplan-Meier survival curve showed that there were significant differences in the cumulative MACCE-free survival rates among different risk groups (Log rank P=0.001). Fig.11 In the low-risk group, the incidence of MACCE events was 5.85% (10 / 171), in the medium-risk group it was 13.30% (31 / 233), and in the high-risk group it was significantly increased to 17.06% (43 / 209). The difference between the two groups was statistically significant (P=0.003), which further verified the risk stratification ability of risk factor scores such as QFR, PI, non-left main lesions and in-hospital complications in clinical practice, and helped to strengthen the follow-up and management of high-risk patients after surgery.

[0073] The embodiment of the present invention divides risk groups by risk score of risk factors, and then predicts MACCE events by risk groups, which helps to strengthen follow-up and management of high-risk patients after surgery.

[0074] Fig.12 An example of a physical structure diagram of an electronic device is shown in FIG. Fig.12 As shown, the electronic device may include: a processor 1210, a communications interface 1220, a memory 1230, and a communication bus 1240, wherein the processor 1210, the communications interface 1220, and the memory 1230 communicate with each other via the communication bus 1240. The processor 1210 may call the logic instructions in the memory 1230 to execute the method in the postoperative risk assessment system.

[0075] In addition, the logic instructions in the above-mentioned memory 1230 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0076] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the method in the above-mentioned postoperative risk assessment system.

[0077] In yet another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, can execute the method in the above-mentioned postoperative risk assessment system.

[0078] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0079] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0080] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A postoperative risk assessment system, characterized in that: include: An extraction module is used to extract independent risk factors for early failure of vascular grafts from postoperative data of patients; the independent risk factors include non-left main stem stenosis, complications, quantitative blood flow fraction and pulsatility index; A score determination module, used to determine the score of each factor in the independent risk factors based on the scoring scale in the nomogram model; the nomogram model is constructed based on the independent risk factors; A prediction module, used to predict the risk information of early failure of vascular graft after coronary artery bypass grafting based on the risk coefficient corresponding to the total score of each factor in the independent risk factors; The independent risk factors are determined by performing minimum absolute value shrinkage and selection operator Lasso regression analysis and multivariate logistic regression analysis on the data set of potential risk factors for cardiovascular disease, and combining the results of Lasso regression analysis and logistic regression analysis.

2. The postoperative risk assessment system according to claim 1, characterized in that: The independent risk factors were determined by: Lasso regression analysis was performed on the data set to obtain the first risk factor for early failure of vascular grafts; Logistic regression analysis was performed on the data set to obtain the second type of risk factors for early failure of vascular grafts; rank the first-category risk factors and the second-category risk factors in terms of importance; The common risk factors in the ranking results of the first category of risk factors and the ranking results of the second category of risk factors are selected as the independent risk factors.

3. The postoperative risk assessment system according to claim 2, characterized in that: The prediction module is further used for: Based on the ranking results of the weight coefficients of the first and second risk factors, a target risk factor is selected; wherein the target risk factor includes the independent risk factor; Determine the score of each factor in the target risk factor based on the scoring scale in the nomogram model constructed for the target risk factor; Based on the risk coefficient corresponding to the total score of each factor in the target risk factors, the risk information of early failure of the vascular graft after coronary artery bypass grafting is predicted.

4. The postoperative risk assessment system according to claim 2 or 3, characterized in that: The first category of risk factors is determined by: Construct the objective function of the Lasso regression model; Determining the optimal regularization parameter of the objective function based on a cross-validation method; Using the data set, training the objective function after determining the optimal regularization parameter to determine the regression coefficient of each variable; The variables are risk factors in the data set; The first category of risk factors is determined based on the regression coefficient of each of the variables.

5. The postoperative risk assessment system according to claim 2 or 3, characterized in that: The second category of risk factors is determined by: Build a Logistic regression model; Based on the Logistic regression model, a univariate analysis is performed on the data set to screen out candidate risk factors; Perform a multifactor analysis on the candidate risk factors to obtain the second type of risk factors.

6. The postoperative risk assessment system according to claim 1, characterized in that: The prediction module is further used for: Determining a risk factor risk score based on the independent risk factors and their weight coefficients; Dividing risk groups based on the risk scores of the risk factors; Based on the risk groups, major adverse cardiovascular and cerebrovascular events are predicted.

7. The postoperative risk assessment system according to claim 1, characterized in that: The weight ranking of each factor in the independent risk factors is quantitative blood flow fraction, complications, pulsatility index and non-left main coronary artery stenosis.

8. The postoperative risk assessment system according to claim 1, characterized in that: The quantitative blood flow fraction is greater than 0.8, and the pulsatility index is greater than 3.

0.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the method in the postoperative risk assessment system according to any one of claims 1 to 8 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method in the postoperative risk assessment system according to any one of claims 1 to 8 is implemented.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method in the postoperative risk assessment system according to any one of claims 1 to 8 is implemented.

Images