System For Risk Evaluation Research Articles

Weekday and outcomes of elective cardiac surgery in the UK: a large retrospective database analysis.

Several studies have shown worse outcomes in patients operated on later in the week. We tested this hypothesis in a large UK national audit database in elective patients undergoing adult cardiac surgery. We used a generalized additive model to evaluate the effect of the day of the week on the following postoperative outcomes: 30-day mortality, stroke, need for dialysis and return to theatre for bleeding. We have adjusted for the relevant European System for Cardiac Operative Risk Evaluation (EuroSCORE) II covariates, plus responsible consultant, hospital and year of operation and performed subgroup analysis for isolated coronary artery bypass grafting (CABG) procedures. Out of 371500 patients, 60555 (16.3%) underwent AVR, 36553 (9.8%) AVR plus CABG, 238812 (64.3%) isolated CABG, 26517 (7.1%) isolated mitral valve repair or replacement and 9063 (2.4%) mitral valve plus CABG. A total of 13997 (3%) had surgery over the weekend. After covariate adjustment, we found no effect of day of surgery on mortality (P = 0.081), stroke (P = 0.137) and need for postop dialysis (P = 0.732). However, across all operations, there was evidence of a lower rate of return to theatre for bleeding/tamponade at the weekend (P = 0.039). In subgroup analysis of isolated CABG, the day of the week did not affect any outcomes. We found no effect of the day of the week on risk-adjusted short-term mortality, stroke, and the requirement for postoperative dialysis after elective cardiac surgery. Overall, the patients operated on during the weekdays were less likely to return to theatre for bleeding. In isolated CABG, the day of the week did not affect any outcomes.

Short-Term Outcomes After Transcatheter Aortic Valve Replacement in Predominant Aortic Regurgitation with Left Ventricular Dysfunction.

Patients with aortic stenosis and low left ventricular ejection fraction (LVEF) would benefit from transcatheter aortic valve replacement. However, the safety and efficacy of transcatheter aortic valve replacement in patients with aortic regurgitation and left ventricular dysfunction remains unknown.We defined LVEF < 50% as left ventricular dysfunction. A total of 27 symptomatic patients with aortic regurgitation and ejection fraction < 50% underwent transcatheter aortic valve replacement using the J-Valve™ system (JieCheng Medical Technology Co, Ltd, Suzhou, China) in Zhongshan Hospital, Fudan University, from May 2014 to June 2019. Procedural and postoperative clinical outcomes were analyzed according to Valve Academic Research Consortium-2 (VARC-2) criteria.All patients (eight females; 70.6 ± 7.1 years) were considered to be at least intermediate surgical risk and/or severe comorbidity precluding for surgical aortic valve replacement (logistic European System for Cardiac Operative Risk Evaluation, 16.8 ± 9.5%, range 4.6% to 37.9%) by a multidisciplinary heart team. Transapical implantations were successful in 26 (96.3%) patients. All-cause mortality was 3.7% in the latest follow-up (25-590 days, median 369 days). Significant improvements in LVEF, left ventricular end-diastolic, and systolic dimensions were observed after procedure (from 40.3 ± 6.7% to 50.8 ± 10.5%, P < 0.001; from 65.1 ± 8.9 mm to 56.0 ± 9.6 mm, P = 0.002; from 52.2 ± 9.8 mm to 35.9 ± 13.4 mm, P < 0.001, respectively). No patient had aortic stenosis and paravalvular leak more than moderate and heart function improvement was obtained in the majority of patients at 1-year follow-up.Transcatheter aortic valve replacement using the J-Valve™ system is a reasonable alternative for patients with aortic regurgitation and left ventricular dysfunction regarding promising short-term outcomes.

Machine learning for predicting 5-year mortality risks: data from the ESSE-RF study in Primorsky Krai

Aim. To develop and perform comparative assessment of the accuracy of models for predicting 5-year mortality risks according to the Epidemiology of Cardiovascular Diseases and their Risk Factors in Regions of Russian Federation (ESSE-RF) study in Primorsky Krai.Material and methods. The study included 2131 people (1257 women and 874 men) aged 23-67 years with a median of 47 years (95% confidence interval [46; 48]). The study protocol included measurement of blood pressure (BP), heart rate (HR), waist circumference, hip circumference, and waist-to-hip ratio (WHR). The following blood biochemical parameters: total cholesterol (TC), low and high density lipoprotein cholesterol, triglycerides, apolipoproteins AI and B, lipoprotein(a), N-terminal pro-brain natriuretic peptide (NT-proNBP), D-dimer, fibrinogen, C-reactive protein (CRP), glucose, creatinine, uric acid. The study endpoint was 5-year all-cause death (2013-2018). The group of deceased patients during this period consisted of 42 (2%) people, while those continued the study — 2089 (98%). The χ2, Fisher and MannWhitney tests, univariate logistic regression (LR) were used for data processing and analysis. To build predictive models, we used following machine learning (ML) methods: multivariate LR, Weibull regression, and stochastic gradient boosting.Results. The prognostic models developed on the ML basis, using parameters of age, sex, smoking, systolic blood pressure (SBP) and TC level in their structure, had higher quality metrics than Systematic COronary Risk Evaluation (SCORE) system. The inclusion of CRP, glucose, NT-proNBP, and heart rate into the predictors increased the accuracy of all models with the maximum rise in quality metrics in the multivariate LR model. Predictive potential of other factors (WHR, lipid profile, fibrinogen, D-dimer, etc.) was low and did not improve the prediction quality. An analysis of the influence degree of individual predictors on the mortality rate indicated the prevailing contribution of five factors as follows: age, levels of TC, NT-proNBP, CRP, and glucose. A less noticeable effect was associated with the level of HR, SBP and smoking, while the contribution of sex was minimal.Conclusion. The use of modern ML methods increases the accuracy of predictive models and provides a higher efficiency of risk stratification, especially among individuals with a low and moderate death risk from cardiovascular diseases.

The prediction algorithm of credit risk of science and technology finance based on cloud computing

In order to effectively guarantee the effect of credit risk prediction of science and technology finance and improve the ability of risk prediction, a credit risk prediction algorithm of science and technology finance based on cloud computing is proposed. The logistic regression model is used to predict, and the financial indicators of science and technology credit are selected as the model covariates. According to the characteristics and strong correlation of many financial indicators of science and technology credit, this paper constructs the final index system of online supply chain technology credit risk evaluation based on SMEs. Then the principal component analysis method is used to select the principal component. Combined with the penalty method, the data space dimension of financial indicators is further reduced, and the unrelated principal components are obtained. On this basis, a logistic regression model is established to predict the credit risk by taking the selected main components as covariates. The experimental results show that the algorithm has a good fit to the credit risk of 16 science and technology credit enterprises, and the risk prediction ability is significantly improved, which can effectively guarantee the effect of science and technology credit risk prediction.

EuroSCORE II as Predictor of Mortality and Morbidity in Post-CABG Patient in Dr. Soetomo General Academic Hospital

Introduction: European System for Cardiac Operative Risk Evaluation (EuroSCORE) is a scoring system to predict mortality risk after cardiac surgery. EuroSCORE II was introduced to replace and show superiority over EuroSCORE I which tends to overestimate the risk of heart surgery procedures and have a low discrimination ability. Meanwhile, this is the first study to analyze EuroSCORE II as a predictor of mortality and morbidity in Indonesians. Objective: This study aims to analyze EuroSCORE II as a predictor of mortality and morbidity in Indonesians. Materials and Methods: This is a retrospective study using medical records of CABG patients in Dr. Soetomo General Academic Hospital from January 2016 to December 2017. Results and Discussion: Out of 39 Patients who have performed CABG surgery, most were male (89.7%) with the highest age range of 46-65 years (59%). Deceased patients had an average EuroSCORE II of 22.36% and SD±26.97%7%, while 27 patients who survived had an average EuroSCORE II of 6.78% and SD±6.4%. Based on morbidity assessment, EuroSCORE II only accurately predicted the risk of kidney failure and did not properly assess the length of inotropic use, vasopressors, hospitalization time, the risk of arrhythmias, low cardiac output syndrome, Durante-operative bleeding, and the need for blood transfusion. These inaccuracies occurred because the samples that were included varied based on their standard deviation and pattern-less graph. Conclusion: EuroSCORE II is inadequate to predict morbidity and mortality in postoperative patients, therefore, it is considered less effective.

Modified transventricular and transaortic mitral valve edge-to-edge repair mimicking MitraClip overcorrection.

ObjectiveIn the current study, we present our mid-term experience with modified edge-to-edge repair technique through a transventricular and transaortic route in patients requiring left ventricular remodeling or aortic root/valve surgery.MethodsFrom December 2006 through April 2015, 49 high-risk patients (median age: 69 years; median European System for Cardiac Operative Risk Evaluation II: 11.4 [6.54-14.9]) underwent transventricular (N = 7; 14%) or transaortic (N = 42; 86%) edge-to-edge mitral valve repair. The Alfieri stitch technique was modified by MitraClip type overcorrection and solid buttressing behind the posterior leaflet. Indication was grade 2+ functional mitral valve incompetence and dilated or impaired left ventricle (N = 25; 52%), or grade 3+ (N = 22; 45%) and grade 4+ functional mitral valve regurgitation (N = 2; 4%). Surgical procedure included aortic root surgery in 65%, aortic valve replacement with surgical revascularization in 18%, and Dor-plasty with surgical revascularization in 14%.ResultsIntraoperative mortality and early neurologic complications were absent in our series. Ninety-day mortality was 12.2% (N = 6). Median clinical and echocardiographic follow-up-time was 50.7 (21.5-44.1) and 39.2 (33.7-44.1) months, respectively. Median postoperative transvalvular gradient was low (2.72 [1.91-4.22] mm Hg) and did not increase during follow-up (P = .268), although peak gradient rose slightly from 7.41 to 8.12 mm Hg (P = .071). The actuarial reoperation free rate at the index valve was 96.8%.ConclusionsTransventricular or transaortic Alfieri mitral repair mimicking mitral clip overcorrection represents a quick and safe technique in the setting of high-risk patients undergoing left ventricular remodeling or aortic root/valve surgery and can be performed with low risk of creating mitral stenosis at midterm. The technique is straightforward, with reliable identification of the center of the valve leaflets being the limitation.

A Self-Learning BP Neural Network Assessment Algorithm for Credit Risk of Commercial Bank

Commercial banks play an important role in the financial system, and their role in the processes of capital circulation, capital integration, capital resource allocation, and total social demand and supply adjustment is irreplaceable. This paper proposes the idea of constructing a credit risk evaluation system for commercial banks based on BPNN by combining qualitative and quantitative analysis, based on computer technology and management theory. Its main goal is to use a neural network’s self-learning ability to perform complex loan risk assessment. BPNN is capable of self-learning, self-adaptation, and knowledge acquisition, as well as dealing well with uncertainty. It is a nonlinear method that eliminates obvious subjective and artificial factors, resulting in a more objective and effective evaluation result. Experiments show that the established model is effective in regulating personal credit management and reducing investment risks for commercial banks, as well as providing a new decision-making framework for banks’ personal credit business.

Developing a holistic fuzzy hierarchy-cloud assessment model for the connection risk of renewable energy microgrid

Grid-connection of renewable energy microgrids (GCREM) is an important form of promoting the use of clean and renewable energy (RE). However, GCREM will bring huge risks to the power grid. Accurate evaluation and control of risks are critical to the development of GCREM. The existing research is not deep and comprehensive enough to make a reliable evaluation on the risks. The current study proposes a new evaluation framework based on the unit decomposition of the system of GCREM, and then builds a holistic fuzzy hierarchy-cloud assessment model for the risks. The main contributions of this paper are as follows: (1) decomposes GCREM risks to each functional unit of the system, and clarifies the risk transmission between the units within the system; (2) improves the accuracy of weighting risk variables based on interval type-2 fuzzy method; (3) realizes the visibility of risk evaluation and a prior judgment on its effectiveness; (4) establishes a 5-dimensional risk evaluation system of GCREM for the first time, which achieved full coverage of risk variables without the overlap between dimensions. The empirical analyses show that our model can not only assess the overall risk level of GCREM, but also identify key risk sources.

Critical Preoperative Hemoglobin Value to Predict Anemia-Related Complications After Cardiac Surgery

Preoperative anemia is frequent in patients undergoing cardiac surgery and is associated with increased postoperative complications. The purpose of this observational study was to estimate the critical preoperative hemoglobin threshold associated with the occurrence of complications after cardiac surgery. A retrospective observational cohort study. A tertiary-care medical center from January 2019 to April 2020. A total of 1,004 patients undergoing elective cardiac surgery were included. None (observational study). The primary study endpoint was to define the hemoglobin threshold that predicted the occurrence of postoperative major complications after elective cardiac surgery. Postoperative complications were a composite criterion, including transient ischemic attack or stroke, myocardial infarction, acute kidney injury, respiratory failure, mediastinitis, or mesenteric ischemia. A discrimination threshold was determined by using receiver operating characteristic curves. The discrimination threshold for hemoglobin concentration with the best sensitivity/specificity ratio for the occurrence of postoperative complications was 13 g/dL for male patients and 11.8 g/dL for female patients. The incidence of postoperative complications was 17.2% in the total population. Independent risks were preoperative hemoglobin concentration, red blood cell transfusion, European System for Cardiac Operative Risk Evaluation II, and the type of surgery. The critical preoperative hemoglobin thresholds associated with the occurrence of postoperative complications with the best sensitivity/specificity ratio were 13 g/dL for men and 11.8 g/dL for women, which were very similar to the World Health Organization criteria defining anemia.

Ten years after the introduction of the European system for cardiac operative risk evaluation 2: A single center validation

Introduction. The aim of this study was to evaluate the predictive value of the European System for Cardiac Operative Risk Evaluation II in adult patients with acquired heart diseases. Material and Methods. The research included a consecutive series of 6,031 patients who underwent coronary, valvular and combined cardiac surgical interventions in the period from January 15, 2015 to December 31, 2020. Model calibration was assessed by comparing the ratio of actual to expected postoperative mortality and using the Hosmer-Lemeshow test. The discriminative power was examined using the area under the receiver operating characteristic curve. Results. A total of 2,883 patients underwent isolated coronary surgery, 1,841 underwent valvular procedures, while a combined procedure was performed in 1,307 patients. The operative risk was moderately underestimated in the entire group, as well as in the group of patients who underwent surgical revascularization of the coronary arteries. In patients who underwent valvular surgery, the actual mortality rate was slightly overestimated, while in patients with combined procedures it was moderately underestimated. The European System for Cardiac Operative Risk Evaluation II showed excellent discriminative power in the whole group of patients undergoing surgery (area under the curve = 0.825, p &lt; 0.0005). The cut-off value was 2.60, sensitivity 0.757 and specificity 0.750. The discriminative power of the model was excellent in the group of coronary patients (area under the curve = 0.810) as well as in the group with isolated valvular surgery (area under the curve = 0.815). In patients with combined procedures, the discriminatory power was very good (area under the curve = 0.775). Conclusion. The results of our single centre study show that European System for Cardiac Operative Risk Evaluation II predicts hospital mortality with satisfactory results in the entire group, but underestimates it when it comes to combined cardiac surgical procedures. The discriminative power of the model is excellent.

Research on the Construction of Accounting Informatics System and Risk Assessment Method in Big Data’s Era

The traditional financial informatics administration system risk assessment method in the evaluation of system risk can deal with less data throughput, and the system risk assessment effect is not good, so the study of the financial informatics administration system of the risk assessment method under the background of big data is a necessity. The method sets logical nodes according to system modules and builds risk estimation models by finding logical relationships between data. Based on the big data background, according to the utility theory and the risk preference function estimation, choose the big data batch calculation and streaming calculation methods to calculate the system programme risk index and financial data faithless risk index. According to the risk residual value, the probability of a system function failure in the main module and submodule of the system is adjusted, and the risk level is defined by the exponential function to realize the system risk estimation under the background of big data. Experimental results show that compared with the two traditional system risk estimation methods, the proposed method has a larger data throughput and a wider range of risk indicators. It can be seen that the proposed method meets the risk estimation requirements of the enterprise financial informatics administration system.

Risk Investment Decision Making Model Based on Grey Prediction

Market traders frequently buy and sell assets with the goal of maximizing total investment returns. There is usually a commission on each sale. Develop a model with only the daily price stream to date, Use the model to determine whether traders should buy, hold or sell assets in their portfolio on a daily basis. This article a portfolio maximization model is established. In order to develop this model, the Gray Forecast Model is first used to predict the daily transaction price flow of these two assets from the perspective of the day. Then establish a market analysis model, use the form of data segmentation fitting and prediction, select the first 260 days of data from the perspective of the day of purchase to analyze the market conditions (if it is less than 260, try to use all of it), and prepare for the next risk assessment Secondly, a risk evaluation system is established, five evaluation indicators are proposed to use the AHP model to evaluate the risk of gold and bitcoin, and the weights are established and the risk indicator Var is proposed. Finally, according to the triple [C, G, B], an investment income model is established, and the idea of dynamic programming is used to maximize the income C+G+B minus the commission. Finally, the final maximum investment of [1000,0,0] on September 11, 2016 is 154220.6385$, And visualize the daily investment plan and investment curve

Combination of a vascular plug and coiling to treat an ascending aortic pseudoaneurysm following aortic surgery

Combination of a vascular plug and coiling to treat an ascending aortic pseudoaneurysm following aortic surgery

Research on personal credit risk evaluation based on XGBoost

In the current research field of personal credit risk assessment, the existing characteristics and their combination of characteristics have little relationship with the borrower’s default status, and the explanatory ability is not strong. In this paper, feature selection is carried out by Logistc regression, and default discrimination is carried out by XGBoost, and personal credit risk evaluation model is constructed. In addition, 10000 pieces of real credit data of X Bank are demonstrated to test the effectiveness of the model. There are two main tasks in this paper. First, by comparing three feature selection methods, Logistc regression, AIC-Logistic regression and BIC-Logistic regression, the Logistc regression model with the best AUC and accuracy was selected to construct an index system of personal credit risk evaluation. /*Second, by comparing the performance evaluation indexes of XGBoost, decision tree and K-nearest neighbor classification algorithms, XGBoost is selected to build a personal credit risk evaluation model with good performance in AUC, accuracy and Type II error.

Changes in risk factors trends in coronary surgery over the past decade - a single center validation

Introduction/Objective. The risk factors in coronary patients indicated for surgery change during the years. The aim of this study was to analyze the trends of risk factors which enter into the composition of the European System for Cardiac Operative Risk Evaluation (EuroSCORE II). Methods. The research included 3996 patients who underwent coronary surgery from January 2012 to December 2020 at our clinic. For estimation of the risk factors and evaluation of the operative risk, the EuroSCORE II model was used. Kruskal?Wallis H test was used for testing differences of values of numerical variables between years. The calibration and the discriminative power of the EuroSCORE II were assessed by comparing the observed to the expected mortality ratio and by using area under the receiver operating characteristic curve (AUC). Results. Old age has shown a significant increasing trend (p &lt; 0.0005), as well as diabetes mellitus on insulin therapy, before surgery (p = 0.004). The significant declining trend have shown: extracardiac arteriopathy (p = 0.003), critical preoperative condition (p = 0.013), preoperative NYHA Classes III or IV (p &lt; 0.0005) and preoperative angina pectoris CCS Class IV (p &lt; 0.0005). The mean value of the EuroSCORE II decreased from 1.73 to 1.53 (p &lt; 0.0005). The observed mortality was 1.70% and the mean, predicted by the EuroSCORE II, was 1.75%. The O/E mortality ratio was 0.98; 95% confidence interval 0.95?1.03. The AUC was 0.825. Conclusion. Over the past decade the risk profile of patients for coronary surgery has changed. The mean value of the EuroSCORE II has a declining trend with a good predictive and discriminative power.

Is EuroSCORE II still a reliable predictor for cardiac surgery mortality in 2022? A retrospective study study.

The European System for Cardiac Operation Risk Evaluation II (EuroSCORE II) is the most common tool used to evaluate the perioperative risk of mortality after cardiac surgery in Europe, and its use is currently recommended by the relevant guidelines. However, recently, its role has been questioned: Several papers have suggested that these algorithms may no longer be adequate for risk prediction due to an overestimation of adult cardiac surgical risk. Our goal was to validate the EuroSCORE II in the prediction of 30-day in-hospital mortality in patients undergoing open cardiac surgery in a high-volume hospital. In this retrospective cohort study, we included all patients who underwent cardiac surgery from January 2016 to May 2022 within the departments of cardiac surgery of the Monzino Cardiology Centre in Milan, Italy. We evaluated the discrimination power of the EuroSCORE II by using the receiver operating characteristic curve and the corresponding area under the curve. We performed calibration plots to assess the concordance between the model's prediction and the observed outcomes. A total of 4,034 patients were included (mean age = 65.1 years; 68% males), of which 674 (16.7%) underwent isolated coronary artery bypass grafting. The EuroSCORE II showed a good discrimination power in predicting 30-day in-hospital mortality (area under the curve = 0.834). However, for interventions performed in an elective setting, very low values of the EuroSCORE II overestimated the observed mortality, whereas for interventions performed in an emergency setting, EuroSCORE II values above 10 extensively underestimated the observed mortality. Our study suggests that the EuroSCORE II seems not to be a reliable score in estimating the true risk of death, especially in high-risk patients.

Postoperative Mortality in Surgically Treated Infective Endocarditis Patients and Its Correlation with EuroSCORE I

Abstract Introduction Even after advances in medical and surgical treatment, infective endocarditis is associated with substantial morbidity and mortality. The aim of this study was to evaluate postoperative mortality in surgically treated infective endocarditis patients and its correlation with the European System for Cardiac Operative Risk Evaluation (EuroSCORE) I. Methods This retrospective observational study included 43 patients treated surgically for infective endocarditis, between 2014 and 2019, at a tertiary care center. Mortality in surgically treated infective endocarditis patients was determined in terms of frequency (%). Patients were divided into two groups—survivors and nonsurvivors (died within 30 days of surgery). Mean EuroSCORE I of survivors and nonsurvivors was compared using the unpaired t-test with equal variance. A correlation was sought between mortality and EuroSCORE I as well. The prediction ability of EuroSCORE I for mortality was determined by the area under receiver operating characteristic curve. Results Out of 43 patients who underwent surgery for infective endocarditis,11 patients (25.58%) died. Mean EuroSCORE I was 15.90 ± 2.02 in nonsurvivors and 7.84 ± 3.19 in survivors. EuroSCORE I was significantly higher in nonsurvivors (p &lt; 0.05). The area under curve value was 0.9744 (p &lt; 0.001), thus showing that EuroSCORE I predicts mortality in surgically treated infective endocarditis patients. Conclusion The 30-day mortality in patients who underwent surgery for infective endocarditis was 25.58%. There is a significant correlation between EuroSCORE I and mortality. A EuroSCORE I value &gt;14 predicts mortality in surgically treated infective endocarditis patients with sensitivity and specificity of 90.91 and 90.63%, respectively.

Evaluation of associated credit risk in supply chain based on trade credit risk contagion

The evaluation of associated credit risk in supply chain is a difficult problem in the current credit risk management practice. Based on graph theory and fuzzy preference theory, we put forward a new evaluation method of associated credit risk in the supply chain. First, the credit risk of enterprises in supply chain are divided into “self-own credit risk” and “credit risk contagion”. Second, the indicator system of self-own credit risk evaluation of enterprises in the supply chain is designed, and the fuzzy comparative judgment matrix of self-own credit risk evaluation indicator is obtained by using fuzzy preference relation, and the evaluation basic model of “self-own credit risk” is established. On the basis, the evaluation derivative model of “credit risk contagion” is established. Furthermore, by integrating the two kinds of evaluation results, the credit risk of enterprises in supply chain is evaluated comprehensively, and the contagion effect of associated credit risk in supply chain based on trade credit risk contagion (TCRC) is revealed.

Study on quantification scheme of weight coefficient for electrical fire risk assessment of high-rise building

Electrical fire is a very important fire type in high-rise building fire. Therefore, it has high research value for risk assessment of electric fire in high-rise buildings. However, it is difficult to accurately obtain the weight index coefficient of electrical fire risk assessment by single qualitative or quantitative risk assessment method, so the reliability and objectivity of electrical fire risk assessment cannot be guarantee. In order to solve this problem, a method of using numerical simulation to obtain different types of fire risk data is proposed. Then, taking fire risk influencing factors as the research object, a comprehensive fire risk evaluation system is established. Through the comprehensive evaluation system, the electrical fire risk data are evaluated to determine the electrical fire risk weight coefficient. The results show that the fire risk quantification scheme of weight coefficient proposed in this paper can eliminate the subjectivity of traditional expert ratings. The proposed evaluation standard is a comprehensive evaluation system based on the numerical simulation and analytic hierarchy process. Above mentioned method can improve the reliability and accuracy of the weight coefficient of electrical fire risk assessment, and provide a theoretical basis for the research and classification of fire risk.

Study on the comprehensive evaluation of regional financial risk

Since 2011, the Chinese government began to pay attention to the prevention of regional financial risk in the financial field. The effective assessment of regional financial risk is an indispensable link in risk prevention, which is of great significance to maintain economic operation. This paper selects 5 first-level indicators and 15 second-level indicators to build a regional financial risk evaluation system. Based on the economic data of Jiangsu from 2015 to 2020, AHP and entropy weight method are used to calculate the corresponding weights of indicators at all levels. The multi - level fuzzy evaluation model is used to evaluate the financial risk in Jiangsu province. The results show that the membership degree of financial risk to the "general security" level is 0. 5050 at most, among which the proportion of macro environment is 0. 3932 at most, and the degree of external environment is 0. 0625 at least. It can be seen that the economic operation of Jiangsu is relatively stable and the financial risk is small.