Machine Learning-Based Decision-Making Mechanism for Risk Assessment of Cardiovascular Disease

Cardiovascular disease(CVD)has gradually become one of the main causes of harm to the life and health of residents.Exploring the influencing factors and risk assessment methods of CVD has become a general trend.In this paper,a machine learning-based decision-making mechanism for risk assessment of CVD is designed.In this mechanism,the logistics regression analysismethod and factor analysismodel are used to select age,obesity degree,blood pressure,blood fat,blood sugar,smoking status,drinking status,and exercise status as the main pathogenic factors of CVD,and an index systemof risk assessment for CVD is established.Then,a two-stage model combining K-means cluster analysis and random forest(RF)is proposed to evaluate and predict the risk of CVD,and the predicted results are compared with the methods of Bayesian discrimination,K-means cluster analysis and RF.The results show that thepredictioneffect of theproposedtwo-stagemodel is better than that of the comparedmethods.Moreover,several suggestions for the government,the medical industry and the public are provided based on the research results.

Health risk assessment of trace metal(loid)s in agricultural soils based on Monte Carlo simulation coupled with positive matrix factorization model in Chongqing, southwest China

This study aimed to investigate the pollution characteristics, source apportionment, and health risks associated with trace metal(loid)s(TMs) in the major agricultural producing areas in Chongqing, China. We analyzed the source apportionment and assessed the health risk of TMs in agricultural soils by using positive matrix factorization(PMF) model and health risk assessment(HRA) model based on Monte Carlo simulation. Meanwhile, we combined PMF and HRA models to explore the health risks of TMs in agricultural soils by different pollution sources to determine the priority control factors. Results showed that the average contents of cadmium(Cd), arsenic (As), lead(Pb), chromium(Cr), copper(Cu), nickel(Ni), and zinc(Zn) in the soil were found to be 0.26, 5.93, 27.14, 61.32, 23.81, 32.45, and 78.65 mg/kg, respectively. Spatial analysis and source apportionment analysis revealed that urban and industrial sources, agricultural sources, and natural sources accounted for 33.0%, 27.7%, and 39.3% of TM accumulation in the soil, respectively. In the HRA model based on Monte Carlo simulation, noncarcinogenic risks were deemed negligible(hazard index <1), the carcinogenic risks were at acceptable level(10^(-6)<total carcinogenic risk ≤ 10^(-4)), with higher risks observed for children compared to adults. The relationship between TMs, their sources, and health risks indicated that urban and industrial sources were primarily associated with As, contributing to 75.1% of carcinogenic risks and 55.7% of non-carcinogenic risks, making them the primary control factors. Meanwhile, agricultural sources were primarily linked to Cd and Pb, contributing to 13.1% of carcinogenic risks and 21.8% of non-carcinogenic risks, designating them as secondary control factors.

Construction and validation of a risk-prediction model for anastomotic leakage after radical gastrectomy: A cohort study in China

Objectives:Anastomotic leakage(AL)stands out as a prevalent and severe complication following gastric cancer surgery.It frequently precipitates additional serious complications,significantly influencing the overall survival time of patients.This study aims to enhance the risk-assessment strategy for AL following gastrectomy for gastric cancer.Methods:This study included a derivation cohort and validation cohort.The derivation cohort included patients who underwent radical gastrectomy at Sir Run Run Shaw Hospital,Zhejiang University School of Medicine,from January 1,2015 to December 31,2020.An evidence-based predictor questionnaire was crafted through extensive literature review and panel discussions.Based on the questionnaire,inpatient data were collected to form a model-derivation cohort.This cohort underwent both univariate and multivariate analyses to identify factors associated with AL events,and a logistic regression model with stepwise regression was developed.A 5-fold cross-validation ensured model reliability.The validation cohort included patients from August 1,2021 to December 31,2021 at the same hospital.Using the same imputation method,we organized the validation-queue data.We then employed the risk-prediction model constructed in the earlier phase of the study to predict the risk of AL in the subjects included in the validation queue.We compared the predictions with the actual occurrence,and evaluated the external validation performance of the model using model-evaluation indicators such as the area under the receiver operating characteristic curve(AUROC),Brier score,and calibration curve.Results:The derivation cohort included 1377 patients,and the validation cohort included 131 patients.The independent predictors of AL after radical gastrectomy included age65 y,preoperative albumin<35 g/L,resection extent,operative time240 min,and intraoperative blood loss90 mL.The predictive model exhibited a solid AUROC of 0.750(95%CI:0.694e0.806;p<0.001)with a Brier score of 0.049.The 5-fold cross-validation confirmed these findings with a calibrated C-index of 0.749 and an average Brier score of 0.052.External validation showed an AUROC of 0.723(95%CI:0.564e0.882;p?0.006)and a Brier score of 0.055,confirming reliability in different clinical settings.Conclusions:We successfully developed a risk-prediction model for AL following radical gastrectomy.This tool will aid healthcare professionals in anticipating AL,potentially reducing unnecessary interventions.

Coastal erosion risk assessment of Hainan Island, China

Coastal erosion on islands is increasing due to sea level rise,frequent extreme events,and anthropogenic activities.However,studies on the multifactorial coastal erosion risk and the vulnerability of islands are limited.In this study,the Coastal Erosion Risk Assessment(CERA)method was applied for the first time to the study area in China to assess the erosion risk on the coast of Hainan Island;to explore the effects of coastal ocean dynamics,sediment movement characteristics,and anthropogenic construction;and to discuss the suitability of the method and countermeasures for coastal protection.The results show that the coast of Hainan Island shows high sensitivity,high value,low exposure,and moderate erosion.The whole island showed high vulnerability but low erosion risk,with the eastern region being more affected by erosion,particularly the eastern side of Wulong Port and Yalin Bay in Wenchang,and the shore section of Yalong Bay in Sanya,having a very high risk of coastal erosion.In addition,Monte Carlo simulation was used to check the applicability of the CERA method,and it was found that the rate of shoreline change,population density,and number of storms significantly contributed to coastal erosion,but only the short-term effects of sea level rise were considered.The effects of sea level rise and sediment grain size were primarily analyzed as influencing factors.The effects of sea level rise continue to strengthen,with coastal retreat expected to be greater than 2 m by the mid-21st century.Moreover,Hainan Island is primarily composed of the fine and medium sand types,which have little resistance to coastal erosion.Currently,the impact of sediment grain size is rarely considered in coastal erosion risk assessment studies.However,it can be incorporated into the indicator system in the future,and the spatial variation of indicators can be fully considered to strengthen the refinement study.

Research on Risk Assessment Method of Long-Tube Trailer Road Transportation

Road transport safety has always been paid attention to by the safety production managers of enterprises. In this study, cloud model and analytic hierarchy process were applied to the safety of long-tube trailer transport. The opinions of 30 experts were analyzed, from which 29 key parameters were selected. The study addressed the relevance of the parameters and the possibility of automatic collection and transmission to obtain 12 core risk factors. The macro-safety risk indicator system for long-tube trailers was established based on the identified risk indicators. Finally, a risk assessment model for road transport of long tube trailers consisting of 3 dimensions of likelihood, severity and sensitivity was constructed. This model provides a technical method for strengthening the risk control of road transport of long-tube trailers.

Landslide Hazard and Risk Assessment on the Northern Slope of Mt. Changbai, China

摘要：昌拜山，的北斜坡上的山崩危险和风险评价向北朝鲜汉语的边阶附近的一个著名旅游胜地，被估计。也就是，这研究被划分成二部分山崩危险带状配列和风险评价。山崩危险带状配列(LHZ ) 的 1992 Anbalagan 和 Singh 方法在这个区域被修改并且使用。这样，一个联合分析方法在代表性的区域被使用为控制因素(斜坡坡度，相对消除，植被，地质学，断绝发展，弱层厚度和地面水) 得到一项措施。为到斜坡失败的因素的会员度，有限价值的中间的范围被用来计算 LHZ。从斜坡失败基于潜在的损坏的一个评价，一张合理风险评价地图用潜在的损坏和可能的危险的关系被获得帮助未来计划和预言并且避免生活的损失。

Arsenic in Drinking Water Toxicological Risk Assessment in the North Region of Burkina Faso

Human health risks assessment were estimated by determining the nature and probability of adverse health effects in the North region’s populations who are now exposed to arsenic from drinking water or will be exposed in the future. Several questions were addressed in this study: what types of health problems may be caused by arsenic from drinking water? What is the chance that people will experience health problems when exposed to different levels of arsenic? What arsenic level are people exposed to and for how long? To answers these questions we have first identified the hazard by evaluating arsenic concentration in thirty-four (34) bore-hole water points among the region based on the assumption of clinical cases related to drinking water. Arsenic concentration ranged from 0 up to 87.8 micrograms per liter. Next we assessed the dose-response of exposure to arsenic. Dose-response relationship describes how the likelihood and severity of adverse health effects are related to the amount and condition of exposure to arsenic. This required us to choose toxicity reference values (TRVs) above which adverse effects may occur for noncarcinogenic and for carcinogenic effects. Exposure factors have been calculated in two scenarios: people from 0 to 14 years old and people from 15 to 70 years. Exposure has been estimated indirectly through consideration of measured concentrations of arsenic in drinking water. This study show that people in the Yatenga, Zondoma and Passore provinces are at very high risk for developing several pathologies such as hyper pigmentation, keratosis, cancer, etc. due by chronic exposure to arsenic in drinking water.

A Simplified ArcGIS Approach for Landslides Risk Assessment in the Province of Bergamo

The paper describes a simplified GIS approach, for landslides risk assessment in the Province of Bergamo, developed for a GIS degree thesis at the faculty of Engineering of the University of Bergamo. The subject has been and still is largely studied by many researchers with the aid of rigorous mathematical/statistical analysis tools. This work follows some procedures carried out by other studies, but at the end it has been decided to adopt a simple, fast and not rigorous way to find a solution. A following analysis, on the higher risk areas identified, has also been performed to test their reliability, allowing achieving satisfactory results. It has been planned to study the risk model more thoroughly, by taking into account other triggering causes for landslide susceptibility and to try also a rigorous approach, so as to get a better idea of the results achieved so far and how to improve them.

Establishment of a Risk Assessment Framework for Analysis of the Spread of Highly Pathogenic Avian Influenza

To evaluate the risk of highly pathogenic avian influenza (HPAI) in China's Mainland, a risk assessment framework was built. Risk factors were determined by analyzing the epidemic data using the brainstorming method; the analytic hierarchy process was designed to weigh risk factors, and the integrated multicriteria analysis was used to evaluate the final result. The completed framework included the risk factor system, data standards for risk factors, weights of risk factors, and integrated assessment methods. This risk assessment framework can be used to quantitatively analyze the outbreak and spread of HPAI in China's Mainland.

Fuzzy Risk Assessment Model of Power Transformer Based on Borda Number Theory

The power transformer is the key equipment of transforming voltage and exchanging power in the power system.It's safe and reliable operation directly influences the safe level of the power system.To study the risk assessment of power transformer which is very significant to improve the reliability of the power system,a fuzzy comprehensive risk assessment model of power transformer based on Borda number theory is proposed in this paper.At first,the fault types and risk factors of the power transformer are analyzed.Secondly,the basic framework of the fuzzy comprehensive evaluation is applied to quantify the risk factors.And then,Borda number theory is employed to analyze influence degree and occurrence probability of power transformer.At last,the various risk factors impact index and fuzzy comprehensive evaluation index of power transformer can be easily obtained.Applying this model,the relative importance degree of the risk factors can be horizontally compared according to the numerical index,the engineering staff can directly get the parameters of the transformer risk level and get a good description of the visual expression through using 5 score and similar visual language.

Diagnostic value of ABCD2 and ABCD3-Ⅰ risk scoring systems in determining one-month risk of stroke in patients with transient ischemic attack: An observational study

Objective:To compare the diagnostic value of the ABCD2 and ABCD3-栺scoring systems in predicting the development of a 30-day neurological event in adult patients with transient ischemic attack(TIA)presenting to the emergency department.Methods:The study was observational and prospective and was conducted in a single center.The diagnostic values of the ABCD2 and ABCD3-栺scores in predicting a neurological event within one month were compared in patients diagnosed with TIA in the emergency department.Results:A statistically significant difference was observed between groups with or without stroke within one month in terms of both the ABCD2 and ABCD3-栺scores(P=0.044 and P=0.029,respectively).There was no statistically significant difference between the patients with and without a recurrent TIA within one month in relation to the ABCD2 score(P=0.934),but a statistically significant difference was found in the ABCD3-栺scores of these groups(P<0.001).Conclusions:Both the ABCD2 and ABCD3-栺scoring systems could predict ischemic stroke within 30 days of TIA,the ABCD3-栺score is more effective than the ABCD2 score in the prediction of TIA recurrence.

Landslide susceptibility assessment in Western Henan Province based on a comparison of conventional and ensemble machine learning

Landslide is a serious natural disaster next only to earthquake and flood,which will cause a great threat to people’s lives and property safety.The traditional research of landslide disaster based on experience-driven or statistical model and its assessment results are subjective,difficult to quantify,and no pertinence.As a new research method for landslide susceptibility assessment,machine learning can greatly improve the landslide susceptibility model’s accuracy by constructing statistical models.Taking Western Henan for example,the study selected 16 landslide influencing factors such as topography,geological environment,hydrological conditions,and human activities,and 11 landslide factors with the most significant influence on the landslide were selected by the recursive feature elimination(RFE)method.Five machine learning methods[Support Vector Machines(SVM),Logistic Regression(LR),Random Forest(RF),Extreme Gradient Boosting(XGBoost),and Linear Discriminant Analysis(LDA)]were used to construct the spatial distribution model of landslide susceptibility.The models were evaluated by the receiver operating characteristic curve and statistical index.After analysis and comparison,the XGBoost model(AUC 0.8759)performed the best and was suitable for dealing with regression problems.The model had a high adaptability to landslide data.According to the landslide susceptibility map of the five models,the overall distribution can be observed.The extremely high and high susceptibility areas are distributed in the Funiu Mountain range in the southwest,the Xiaoshan Mountain range in the west,and the Yellow River Basin in the north.These areas have large terrain fluctuations,complicated geological structural environments and frequent human engineering activities.The extremely high and highly prone areas were 12043.3 km^(2)and 3087.45 km^(2),accounting for 47.61%and 12.20%of the total area of the study area,respectively.Our study reflects the distribution of landslide susceptibility in western Henan Province,which provides a scientific basis for regional disaster warning,prediction,and resource protection.The study has important practical significance for subsequent landslide disaster management.

Research on Assessment Model of Information System Security Based on Various Security Factors

With the rapid development of network technology, the meaning of layers and attributes in respect of information system security must be extended based on the understanding of the concept of information system security. The layering model (LM) of information system security and the five-attribute model (FAM) based on security factors were put forward to perfect the description and modeling of the information system security framework. An effective framework system of risk calculation and assessment was proposed, which is based on FAM.

A Review of Research on Risk Assessment of Fresh Agricultural Product Supply Chain

With the establishment of a well-off society in an all-round way,Chinese residents have put forward higher requirements for the quality and safety of fresh agricultural products.In recent years,domestic and foreign academic circles have also paid more and more attention to the risk of fresh agricultural product supply chain.This article collects and sorts out the research findings of domestic and foreign scholars on the risk assessment of fresh agricultural product supply chain in recent years,and summarizes and discusses from three aspects:supply chain risk factors,risk assessment indicator selection,and risk assessment methods.It is intended to provide a reference for future new research ideas and research perspectives.

Psychological Risk Factors of Terrorist Offenders in Indonesia

Psychological criminogenic factors for identifying terrorist offenders at risk of recidivism in Indonesia remain unclear;hence the adequate assessment to those involved with terrorism and measurement of effective terrorism rehabilitation are questioned.‘MIKRA’Risk Assessment was developed to identify individual criminogenic risk factors and needs of terrorist offenders in Indonesia.It is formulated to set up future parameters of effective terrorism rehabilitation.MIKRA study involved thirty-two eminent Indonesian counterterrorism experts and practitioners in semi-structured interviews and qualitative data analysis.The study identifies 18 individual risk factors and needs of ideology-based terrorist offenders that are grouped into one of three higher order domains:Motivation,Ideology,and Capability.

Classifying risk level of gastric cancer: Evaluation of questionnaire-based prediction model

Objective: This study aimed at evaluating the efficacy of the questionnaire-based prediction model in an independent prospective cohort.Methods: A cluster-randomized controlled trial was conducted in Changsha, Harbin, Luoshan, and Sheyang in eastern China in 2015-2017. A total of 182 villages/communities were regarded as clusters, and allocated to screening arm or control arm randomly. Face-to-face interview through a questionnaire interview, including of relevant risk factors of gastric cancer, was administered for each subject. Participants were further classified into high-risk or low-risk groups based on their exposure to risk factors. All participants were followed up until December 31, 2019. Cumulative incidence rates from gastric cancer between high-risk and low-risk groups were calculated and compared using the log-rank test. Cox proportional hazard regression models were applied to estimate hazard ratio(HR) and 95% confidence interval(95% CI).Results: Totally, 89,914 residents were recruited with a mean follow-up of 3.47 years. And 42,015(46.73%)individuals were classified into high-risk group and 47,899(53.27%) subjects were categorized into low-risk group.Gastric cancer was diagnosed in 131 participants, of which 91 were in high-risk group. Compared with the low-risk participants, high-risk individuals were more likely to develop gastric cancer(adjusted HR=2.15, 95% CI,1.23-3.76). The sensitivity of the questionnaire-based model was estimated at 61.82%(95% CI, 47.71-74.28) in a general population.Conclusions: Our questionnaire-based model is effective at identifying high-risk individuals for gastric cancer.

Analysis of Risks in Hainan Island Typhoon Hazard Factor Based on GIS

[Objective] The aim of this paper was to analyze the risks in the typhoon hazard factors in Hainan Island. [Method] Taking the theory and method of natural disasters evaluation as starting point and supporting point, and selecting Hainan province as the research target, where the typhoon disaster occurred relatively serious, based on the typhoon data during 1958-2008, with happening frequency of typhoon hazard-formative factors, maximum rainfall, potentially devastating effects of typhoon winds as evaluation indexes, the typhoon disaster risk evaluation index system and evaluation model were established. And by dint of GIS technique, Hainan island typhoon disaster risk zoning of hazard-formative factors and grading were prepared. [Result] Typhoon occurred frequently in Hainan and there were no certain rules of its annual changes. The monthly changes mainly happed during July to October. The highly dangerous area of typhoon mainly distributed in east coast area. The annual daily precipitation decreased from central mountainous area to the surroundings; typhoon hided in the destructive highly risked area in east, south and west area; low disastrous area occurred in the middle area; the risks of disastrous factors weakened from east area to west area. The distribution area of each level was that low dangerous area>mild dangerous area>highly dangerous area>secondary low dangerous area>highly dangerous area. [Conclusion] The study supplied scientific reference for the government in the united organization and direction of disaster relief work.

The Use of Low Molecular Weight Heparin for Venous Thromboembolism Prophylaxis in Medical Patients: How Much Are We Adherent to the Guidelines?

Background: Venous thromboembolism (VTE) is a common complication seen during or after hospitalization that manifests as deep venous thrombosis (DVT) and/or pulmonary embolism (PE). PE is considered the commonest preventable cause of death during and/or after hospitalization. Thus, pharmacological and mechanical methods are used to prevent VTE in hospitalized patients. Despite the availability of guidelines for VTE prophylaxis, it is crucial to assess the adherence and adaptation of the institution to these guidelines. Purpose: This study aimed to investigate adherence to the American College of Chest Physicians (ACCP) 2012 VTE prophylaxis guidelines in hospitalized medical patients in a tertiary care hospital in the United Arab Emirates. Methods: An observational prospective design was utilized in this study. To achieve the purpose, primary and secondary end points were identified to be the core of the investigation. The primary end points were: the incidence of bleeding, VTE, and cardiovascular events. While the secondary end points were: dose and indication validity for prophylaxis, VTE and bleeding risk assessments, adverse drug events (ADE) other than bleeding, appropriate monitoring when on low molecular weight heparin (LMWH) and the presence of contraindication at the time of prescribing LMWH. Results: 16 patients (20%) out of the total 80 met one or more of the primary end points. The vast majority of patients (81.25%) developed bleeding, while VTE was seen in one case only during hospitalization. 11 patients (13.75%) received LMWH while a contraindication was present. 15 patients (18.75%) who were prescribed LMWH had an International Medical Prevention Registry on Venous Thromboembolism (IMPROVE) bleeding risk score of ≥7. However, 5 out of 13 patients (38.46%) who developed bleeding had a bleeding score of ≥7, and the relationship between bleeding score of ≥7 and the development of bleeding was statistically significant (p = 0.047). When investigating the doses that were utilized, 40% were prescribed an inappropriate dose. Conclusion: Various factors played a role in the inappropriateness of VTE prophylaxis such as;poor adherence to VTE guidelines, inappropriate dosing and monitoring, and not evaluating the bleeding risk. Hence, to be able to achieve effective VTE prophylaxis, these factors need to be addressed through adherence to and adaptation of the ACCP 2012 VTE prophylaxis guidelines.

Variability of Pesticide Residues in Vegetables from the Marketplaces in Jinan City

In order to provide technological support for risk estimation of pesticide residues taken from vegetables, the residues of pesticide in vegetables in Jinan City, China, were investigated. Moreover, the variability of pesticide residues in vegetables was explored, and the variability factor was calculated. The level of pesticide residue was studied by statistical method. The variability factor was calculated using the Harrell-Davis method in accordance with principles recommended by the JMPR. In addition, the procedure of evaluation was validated according to the principles laid down by the JMPR (Joint Meeting on Pesticide Residues). The detection rate of pesticide residues in all marketplace samples was less than 20% in Jinan City. The unqualified rate of vegetables was low (0.6%). The chlorothalonil was found as the pesticide with the highest rate of detection. The vegetables with the highest rate of pesticide residues detected were leafy vegetables. The relationship between variability factor and mean value of concentrations of contaminations was expressed by the formula, v=4.9×Cmean. The pesticide residues in vegetables from Jinan City is low. The evaluated variability factor is larger than that the value recommended by the JMPR, however, less than the default value used for acute intake assessment of pesticide residues in UK in most cases.