AI & machine learning models for cloud security risk assessment

Credit risk assessment is a critical task for financial institutions to determine the creditworthiness of their potential customers. Business intelligence (BI) and machine learning (ML) techniques have gained popularity in recent years as effective tools for credit risk assessment. In this paper, we propose a decision support system (DSS) for credit risk assessment that integrates BI and ML techniques. The proposed DSS employs BI tools to extract and transform data from various sources, and ML techniques to analyze the data and generate predictive models for credit risk assessment. We evaluate the proposed DSS using a real-world dataset of a financial institution. The results show that the proposed DSS achieves a high level of accuracy in credit risk assessment. The results showed that the system was able to accurately predict credit risk, with an accuracy of 88%. The system also outperformed traditional credit scoring models, which highlights the potential of our system for credit risk assessment. The system provides decision-makers with actionable insights to make informed decisions, thereby reducing the risk of default and increasing the profitability of the financial institution.

The introduction of Electronic Health Records (EHRs) is causing fast transformation in healthcare. EHR contains the patient private information and health history in digital form. Hence, EHR data cannot be shared due to privacy concerns to the Machine Learning(ML) research community, through which we can make the healthcare system smarter and provide quality healthcare services to the patients. As a result, synthetic data is utilised as a backup when real-world data (such as EHR data) is unavailable. Synthetic data can be shared without revealing any private information of the patient. This paper focuses on generating synthetic data from the real dataset. As a use case, we have selected Chronic Kidney Disease(CKD) dataset (real) and generated three datasets – real, synthetic, and a combination of real + synthetic. To test the accuracy of the synthetic data, we ran six supervised machine learning algorithms on these three datasets with all characteristics and reduced features to see if the patient had CKD or not. Supervised ML algorithms on the three datasets are assessed based on the following performance metrics - Confusion Matrix, Accuracy, Recall, Precision, and F1-Score. According to the results, XGBoost surpasses with 100 percent accuracy on all three datasets with full features and a 100 percent accuracy on the mix of real and synthetic datasets with feature reduction.

PurposeAssessment of cardiovascular risk is the keystone of prevention in cardiovascular disease. The objective of this pilot study was to estimate the cardiovascular risk score (American Hospital Association [AHA] risk score, Syntax risk, and SCORE risk score) with machine learning (ML) model based on retinal vascular quantitative parameters.MethodsWe proposed supervised ML algorithm to predict cardiovascular parameters in patients with cardiovascular diseases treated in Dijon University Hospital using quantitative retinal vascular characteristics measured with fundus photography and optical coherence tomography – angiography (OCT-A) scans (alone and combined). To describe retinal microvascular network, we used the Singapore “I” Vessel Assessment (SIVA), which extracts vessel parameters from fundus photography and quantitative OCT-A retinal metrics of superficial retinal capillary plexus.ResultsThe retinal and cardiovascular data of 144 patients were included. This paper presented a high prediction rate of the cardiovascular risk score. By means of the Naïve Bayes algorithm and SIVA + OCT-A data, the AHA risk score was predicted with 81.25% accuracy, the SCORE risk with 75.64% accuracy, and the Syntax score with 96.53% of accuracy.ConclusionsPerformance of these algorithms demonstrated in this preliminary study that ML algorithms applied to quantitative retinal vascular parameters with SIVA software and OCT-A were able to predict cardiovascular scores with a robust rate. Quantitative retinal vascular biomarkers with the ML strategy might provide valuable data to implement predictive model for cardiovascular parameters.Translational RelevanceSmall data set of quantitative retinal vascular parameters with fundus and with OCT-A can be used with ML learning to predict cardiovascular parameters.

This study investigates the integration of Earth Observation (EO) data and Machine Learning (ML) techniques for classifying volcanic activity states at Mount Etna, one of the world’s most active and monitored volcanoes. Using satellite data, including ground deformation, radiance, land surface temperature, sulfur dioxide emissions, and gravity anomalies, five volcanic activity states were identified: Quiet, Preparatory, Unrest, Eruption, and Cooling. Supervised ML algorithms, such as random forest, support vector machines, decision trees, and k-nearest neighbors, were employed to classify these states. Random forest achieved the highest accuracy, demonstrating its robustness for this application.The study addresses challenges like temporal and spatial disparities and class imbalances through data preprocessing, ensuring a reliable dataset for training and validation. A k-fold cross-validation approach was used to evaluate model performance systematically. The results underline the potential of ML techniques combined with EO data for volcanic hazard monitoring, with implications for improving risk assessment and early-warning systems. This methodology, tested on a well-instrumented volcano like Mount Etna, provides a foundation for extending the approach to other less-monitored volcanoes.These findings are one of the first attempts of integrating satellite data with Artificial Intelligence (AI) to enhance the accuracy of volcanic state predictions and mitigate risks associated with eruptions, while emphasizing the need for rigorous validation against well-documented case studies.

Stroke remains one of the challenging health conditions worldwide. To date, an intelligent decision support system for stroke risk assessment and prediction are developed to aid in healthcare planning, control, and prevention of diseases. However, beyond the use of innovative technologies to assess and predict stroke, user acceptance is still underrepresented in the literature. Thus, this study aims to empirically examine the users' acceptance of decision support system for stroke risk assessment and prediction using an extended technology acceptance model, through a survey conducted among healthcare professionals in the Philippines. Results show the significance of perceived compatibility, perceived complexity, perceived security, and trust in perceived usefulness and perceived ease of use. However, context has no significant positive effect on perceived ease of use as well as trust in perceived usefulness. This study is the first empirical evidence of understanding healthcare professionals' acceptance of health information systems with decision support for stroke risk assessment and prediction in the Philippines. Practical and research implications are presented.

Conceptual framework of a cloud-based decision support system for arsenic health risk assessment

Aim of the paper is the development of a Fuzzy Decision Support System (FDSS) for the Environmental Risk Assessment (ERA) of the deliberate release of genetically modified plants. The evaluation process permits identifying potential impacts that can achieve one or more receptors through a set of migration paths. ERA process is often performed in presence of incomplete and imprecise data and is generally yielded using the personal experience and knowledge of the human experts. Therefore the risk assessment in the FDSS is obtained by using a Fuzzy Inference System (FIS), performed using jFuzzyLogic library. The decisions derived by FDSS have been validated on real world cases by the human experts that are in charge of ERA. They have confirmed the reliability of the fuzzy support system decisions.

Venous thromboembolism (VTE) is a major contributor to maternal morbidity and mortality worldwide. Pregnancy is associated with the development of a baseline hypercoagulable state. The two strongest risk factors for pregnancy-associated VTE are previous VTE and/or high risk thrombophilia. The others risk factors for VTE during pregnancy are well known such as maternal, pregnancy and delivery characteristics. Considering the variation in recommendation in guidelines and low-quality evidence on the prevention, diagnosis and treatment, practice differs between countries and clinical institutions. Some authors developed risk scores, enabling individualized estimation of thrombotic risk during pregnancy, and permitting implementation of a risk-adapted strategy for thromboprophylaxis during pregnancy and postpartum. This review describes the existing VTE risk scores during the antenatal and postnatal period. The important message beyond the score used is that all women should undergo VTE risk factor assessment. The use of a Computerized Clinical Decision Support System for VTE risk assessment should be explored in obstetrics.

The problem raised is how to build a web-based decision support system for village apparatus performance assessment using the profile matching method, Kashus study at the Wee Limbu village office, southwest Sumba district. help carry out assessments using the profile matching method which is carried out to determine the apparatus' recommendations in the assessment system based on behavioral aspects, this decision making process is assisted by a decision support system. One of the methods used is Profile Matching, which is a method that compares the criteria for which alternative candidate places are selected. The road is suitable to be built according to the criteria determined by the Verification Body so that a difference value is obtained which is usually called the gap value. The decision support system designed is a web-based decision support system for assessing apparatus performance using the profile matching method

Dairy and dairy processing industries are included in the group of food products and high-risk industries. Decision making in relation to risk management in dairy industry supply chain is significant. This study aimed at designing a Intelligent decision support system (DSS) for risk assessment of dairy agroindustry supply chain and the estimation of dairy price in the risk-based farmer level. The risk assessment is analyzed by fuzzy logic approach which is Fuzzy Inference System (FIS) and Fuzzy Assosiative Memories (FAMs). The basic knowledge of this system is obtained through the preparation of rule base of risk assessment and the relation of production cost and risks at the farm based on the expert arguments variables. There are six outputs yielded from RSDA, that is risk assessment in accordance with priority issue, risk assessment for delivery activity, risk source exploration, risk performance, risk management partially and the estimation of production cost and price with risks. The system provides several alternatives which will help decision making in preparing risk management in dairy agroindustry supply chain. Moreover, this system also provides several scenarios of dairy price estimation at the level of farmer who includes risk factor in the farmer. By this system, it is expected that the opportunity of risk and risk impact of dairy agroindustry supply chain can be minimized.

Non-communicable diseases (NCDs) are among the leading causes of deaths worldwide. Early detection and management could mitigate NCD-related complications. The Philippine Package for Essential NCD Interventions (PhilPEN) is a set of protocols to identify the risk level of developing NCD among at-risk patients and recommend an action plan based on a clinical service pathway. This paper proposes a framework in building a rule-based decision support system for risk assessment and management of NCDs following the PhilPEN and a decision tree derived from the risk prediction chart. It is demonstrated through a prototype application called App. BlockNCD App maintains a registry of enrolled clients for risk assessment and screening. Variables such as age, gender, lifestyle and laboratory results are processed by the application and calculates the NCD risk level of the client. Depending on the NCD risk level, BlockNCD App recommends appropriate medical intervention. The use of an automated decision support systems can help in managing NCD cases better through early intervention and treatment and by minimizing errors that arise from manual interpretation of risk prediction charts and clinical pathways.

BackgroundIntelligent decision support systems (IDSS) have been applied to tasks of disease management. Deep neural networks (DNNs) are artificial intelligent techniques to achieve high modeling power. The application of DNNs to large-scale data for estimating stroke risk needs to be assessed and validated. This study aims to apply a DNN for deriving a stroke predictive model using a big electronic health record database.Methods and resultsThe Taiwan National Health Insurance Research Database was used to conduct a retrospective population-based study. The database was divided into one development dataset for model training (~70% of total patients for training and ~10% for parameter tuning) and two testing datasets (each ~10%). A total of 11,192,916 claim records from 840,487 patients were used. The primary outcome was defined as any ischemic stroke in inpatient records within 3 years after study enrollment. The DNN was evaluated using the area under the receiver operating characteristic curve (AUC or c-statistic). The development dataset included 672,214 patients (a total of 8,952,000 records) of whom 2,060 patients had stroke events. The mean age of the population was 35.5±20.2 years, with 48.5% men. The model achieved AUC values of 0.920 (95% confidence interval [CI], 0.908–0.932) in testing dataset 1 and 0.925 (95% CI, 0.914–0.937) in testing dataset 2. Under a high sensitivity operating point, the sensitivity and specificity were 92.5% and 79.8% for testing dataset 1; 91.8% and 79.9% for testing dataset 2. Under a high specificity operating point, the sensitivity and specificity were 80.3% and 87.5% for testing dataset 1; 83.7% and 87.5% for testing dataset 2. The DNN model maintained high predictability 5 years after being developed. The model achieved similar performance to other clinical risk assessment scores.ConclusionsUsing a DNN algorithm on this large electronic health record database is capable of obtaining a high performing model for assessment of ischemic stroke risk. Further research is needed to determine whether such a DNN-based IDSS could lead to an improvement in clinical practice.

During the Coronavirus Disease 2019 (COVID-19) epidemic, the massive spread of the disease has placed an enormous burden on the world's healthcare and economy. The early risk assessment system based on a variety of machine learning (ML) algorithms may be able to provide more accurate advice on the classification of COVID-19 patients, offering predictive, preventive, and personalized medicine (PPPM) solutions in the future. In this retrospective study, we divided a portion of the data into training and validation cohorts in a 7:3 ratio and established a model based on a combination of two ML algorithms first. Then, we used another portion of the data as an independent testing cohort to determine the most accurate and stable model and compared it with other scoring systems. Finally, patients were categorized according to risk scores and then the correlation between their clinical data and risk scores was studied. The elderly accounted for the majority of hospitalized patients with COVID-19. The C-index of the model constructed by combining the stepcox[both] and survivalSVM algorithms was 0.840 in the training cohort and 0.815 in the validation cohort, which was calculated to have the highest C-index in the testing cohort compared to the other 119 ML model combinations. Compared with current scoring systems, including the CURB-65 and several reported prognosis models previously, our model had the highest AUC value of 0.778, representing an even higher predictive performance. In addition, the model's AUC values for specific time intervals, including days 7,14 and 28, demonstrate excellent predictive performance. Most importantly, we stratified patients according to the model's risk score and demonstrated a difference in survival status between the high-risk, median-risk, and low-risk groups, which means a new and stable risk assessment system was built. Finally, we found that COVID-19 patients with a history of cerebral infarction had a significantly higher risk of death. This novel risk assessment system is highly accurate in predicting the prognosis of patients with COVID-19, especially elderly patients with COVID-19, and can be well applied within the PPPM framework. Our ML model facilitates stratified patient management, meanwhile promoting the optimal use of healthcare resources.

Supervised machine learning (ML) offers an exciting suite of algorithms that could benefit research in sport science. In principle, supervised ML approaches were designed for pure prediction, as opposed to explanation, leading to a rise in powerful, but opaque, algorithms. Recently, two subdomains of ML–explainable ML, which allows us to “peek into the black box,” and interpretable ML, which encourages using algorithms that are inherently interpretable–have grown in popularity. The increased transparency of these powerful ML algorithms may provide considerable support for the hypothetico-deductive framework, in which hypotheses are generated from prior beliefs and theory, and are assessed against data collected specifically to test that hypothesis. However, this paper shows why ML algorithms are fundamentally different from statistical methods, even when using explainable or interpretable approaches. Translating potential insights from supervised ML algorithms, while in many cases seemingly straightforward, can have unanticipated challenges. While supervised ML cannot be used to replace statistical methods, we propose ways in which the sport sciences community can take advantage of supervised ML in the hypothetico-deductive framework. In this manuscript we argue that supervised machine learning can and should augment our exploratory investigations in sport science, but that leveraging potential insights from supervised ML algorithms should be undertaken with caution. We justify our position through a careful examination of supervised machine learning, and provide a useful analogy to help elucidate our findings. Three case studies are provided to demonstrate how supervised machine learning can be integrated into exploratory analysis. Supervised machine learning should be integrated into the scientific workflow with requisite caution. The approaches described in this paper provide ways to safely leverage the strengths of machine learning—like the flexibility ML algorithms can provide for fitting complex patterns—while avoiding potential pitfalls—at best, like wasted effort and money, and at worst, like misguided clinical recommendations—that may arise when trying to integrate findings from ML algorithms into domain knowledge.Key PointsSome supervised machine learning algorithms and statistical models are used to solve the same problem, y = f(x) + ε, but differ fundamentally in motivation and approach.The hypothetico-deductive framework—in which hypotheses are generated from prior beliefs and theory, and are assessed against data collected specifically to test that hypothesis—is one of the core frameworks comprising the scientific method. In the hypothetico-deductive framework, supervised machine learning can be used in an exploratory capacity. However, it cannot replace the use of statistical methods, even as explainable and interpretable machine learning methods become increasingly popular.Improper use of supervised machine learning in the hypothetico-deductive framework is tantamount to p-value hacking in statistical methods.

Machine learning (ML), particularly, Automated machine learning (AutoML) offers a range of possibilities for analysing large volumes of historical maritime accidents data with advanced algorithms for integrating predictive analytics in operational and policy decision-making for improving maritime safety. This study explores historical data of maritime accidents in Norwegian waters over 40 years. The data has been utilised for analysing five major maritime accident categories: grounding, contact damage, fire or explosion, collision, and heavy weather damage. A total of 29 classification ML algorithms were trained, and the Light Gradient Boosted Trees Classifier was found to be the best-performing with the highest predictive accuracy. The three most impactful factors for accident risk are the category of navigation waters, phase of operation, and gross tonnage of the vessel. Based on the feature effect results, vessels sailing in narrow coastal waters, in the along-the-way operational phase, and fishing vessels are highly vulnerable to grounding relative to other types of accidents. The results can be used as input for the entire procedure of risk analysis, from hazard identification to quantification of accident consequences, and the best-performing ML algorithm can be utilized in developing a decision support system for real-time maritime accident risk assessment.