Automated Risk Assessment Research Articles

Natural Language Processing Risk Assessment Application Developed for Marble Quarries

In this study, by using the texts describing the hazards and precautions taken during text mining, the necessary processes were carried out to first estimate the probability value and severity value of the risk and then calculate the risk values by Natural Language Processing analysis. In order to be used within the scope of the study, two data sets were generated from the data in the risk assessment report prepared by applying the L-type matrix risk assessment in marble quarries between 2015 and 2021. Stochastic Gradient Descent (SGD) was used for classification and prediction by analyzing text data. One data set was used to analyze the probability value of the risk and the other was used to analyze the severity value of the risk. In light of the results, when a text containing hazard and precaution information was entered, a system was developed that analyzed this text, estimated the probability and severity values, and calculated the risk assessment score. The application of the SGD algorithm to learning models developed on text data yielded an accuracy rate of 91.2% in the risk probability data set and 97.5% in the risk severity data set. The results indicated that the models were capable of conducting automatic risk assessment on text data and of effectively predicting the requisite probability and severity values. Due to the high accuracy rates obtained during the study, this risk assessment software was recommended for use in marble quarries.

Investigation of bias in the automated assessment of school violence

ObjectivesNatural language processing and machine learning have the potential to lead to biased predictions. We designed a novel Automated RIsk Assessment (ARIA) machine learning algorithm that assesses risk of violence and aggression in adolescents using natural language processing of transcribed student interviews. This work evaluated the possible sources of bias in the study design and the algorithm, tested how much of a prediction was explained by demographic covariates, and investigated the misclassifications based on demographic variables. MethodsWe recruited students 10–18 years of age and enrolled in middle or high schools in Ohio, Kentucky, Indiana, and Tennessee. The reference standard outcome was determined by a forensic psychiatrist as either a “high” or “low” risk level. ARIA used L2-regularized logistic regression to predict a risk level for each student using contextual and semantic features. We conducted three analyses: a PROBAST analysis of risk in study design; analysis of demographic variables as covariates; and a prediction analysis. Covariates were included in the linear regression analyses and comprised of race, sex, ethnicity, household education, annual household income, age at the time of visit, and utilization of public assistance. ResultsWe recruited 412 students from 204 schools. ARIA performed with an AUC of 0.92, sensitivity of 71%, NPV of 77%, and specificity of 95%. Of these, 387 students with complete demographic information were included in the analysis. Individual linear regressions resulted in a coefficient of determination less than 0.08 across all demographic variables. When using all demographic variables to predict ARIA’s risk assessment score, the multiple linear regression model resulted in a coefficient of determination of 0.189. ARIA performed with a lower False Negative Rate (FNR) of 15.2% (CI [0 – 40]) for the Black subgroup and 12.7%, CI [0 – 41.4] for Other races, compared to an FNR of 26.1% (CI [14.1 – 41.8]) in the White subgroup. ConclusionsBias assessment is needed to address shortcomings within machine learning. In our work, student race, ethnicity, sex, use of public assistance, and annual household income did not explain ARIA’s risk assessment score of students. ARIA will continue to be evaluated regularly with increased subject recruitment.

Resilient cloud cluster with DevSecOps security model, automates a data analysis, vulnerability search and risk calculation

Automated, secure software development is an important digitalization task, solved with the DevSecOps approach. An important part of the DevSecOps approach is continuous risk assessment, which is necessary to identify and evaluate risk factors. Combining the development cycle with continuous risk assessment creates software development and operation synergies and minimizes vulnerabilities. The article presents the main methods of deploying web applications and ways to increase information security at all stages of product development. It also compares different types of infrastructures and cloud computing providers and analyzes modern tools used to automate processes. The cloud cluster was deployed using Terraform and the Jenkins pipeline, written in the Groovy programming language, which checks program code for vulnerabilities and allows you to fix violations at the earliest stages of developing secure web applications. The developed cluster implements the proposed algorithm for automated risk assessment based on the calculation (modeling) of cloud infrastructure threats and vulnerabilities, which operates in real-time, periodically collecting all information and adjusting the system according to the risk and applied controls. The algorithm for calculating risk and losses is based on statistical data and FAIR information risk assessment methodology. The risk value obtained using the proposed method is quantitative, which allows more efficient forecasting of information security costs in software development.

RiskTree: Decision Trees for Asset and Process Risk Assessment Quantification in Big Data Platforms

The inherent characteristics of big data lies in its voluminous scale, varied data formats, and swift processing velocity. The intrinsic characteristics of big data undermine the efficacy of conventional data security techniques and data management standards, consequently compromising the security of big data. As a consequence, big data possesses susceptibilities to security incidents, including unauthorized data access, data manipulation, and data compromise throughout the transmission, storage, and processing stages. Conventional information system security risk assessment methodologies are constrained by human resources and computational techniques, rendering them unsuitable for direct application to big data platforms. Consequently, there is an urgent necessity to develop a risk assessment framework tailored specifically for big data environments, capable of quantifying potential risks and losses. In response to this need, we have devised an automated risk assessment theory that assimilates the unique characteristics of big data with traditional quantitative methods, introducing a risk metric system suited to the big data context. Utilizing the risk-related data generated during operations on the big data platform, we train a decision tree model to derive the weights for each risk indicator. These weights are then employed to conduct a weighted summation of the operational risk indicators, thereby achieving a quantitative evaluation of the platform's risk profile. To substantiate the proposed framework, experiments were conducted on a simulated big data platform. The experimental outcomes demonstrate that, compared to existing quantitative risk assessment methodologies, our approach enables an automatic, objective, and efficient assessment and quantification of the risks associated with tangible assets and data processing operations within the big data platform.

Perspectives on Artificial Intelligence in Nursing in Asia.

Artificial intelligence (AI) is reshaping health care, including nursing, across Asia, presenting opportunities to improve patient care and outcomes. This viewpoint presents our perspective and interpretation of the current AI landscape, acknowledging its evolution driven by enhanced processing capabilities, extensive data sets, and refined algorithms. Notable applications in countries such as Singapore, South Korea, Japan, and China showcase the integration of AI-powered technologies such as chatbots, virtual assistants, data mining, and automated risk assessment systems. This paper further explores the transformative impact of AI on nursing education, emphasizing personalized learning, adaptive approaches, and AI-enriched simulation tools, and discusses the opportunities and challenges of these developments. We argue for the harmonious coexistence of traditional nursing values with AI innovations, marking a significant stride toward a promising health care future in Asia.

Abstract 7669: Use of computational pathology to predict biochemical recurrence in prostate cancer (Pca) (Rp) patients following radical prostatectomy: Evaluation in low decipher risk category

Abstract Background: Current tools for predicting prostate cancer biochemical recurrence (BCR) after RP often depend on parameters determined by pathologists, such as tumor grade, which is known to vary between reviewers. Genomic risk classifiers provide useful information but require substantial tissue, are costly, and are not commonly accessible in many medical centers. The study presents an artificial intelligence (AI) model for automated risk assessment of biochemical recurrence (BCR) by analyzing nuclear morphologic patterns from Pca archival H&E slides. Nuclear morphometric features are essential for disease diagnosis and gaining insights into cellular functions. Specifically, we sought to evaluate whether the computational pathology approach could provide additional granular risk stratification within the low-risk group identified by Decipher. Methods: The study employed two cohorts from the University of Pennsylvania D1 and D2. D1 comprised 180 patients, while D2 comprised 175 patients, including 63 individuals from the Decipher low-risk group. None of the patients in either cohort had received any pre-operative treatments. Within the Decipher cohort, a tumor segmentation model was created using the U-net deep learning network. The HoVer-Net model was used to both segment and classify nuclei. The feature extracted included a combination of nuclear texture and quantitative measurements of the spatial arrangement of nuclei. The eleven most significant features, selected via the least absolute shrinkage and selection operator (LASSO), were utilized to build a Cox regression model for predicting the risk of BCR in D1. In D2, patients were classified as either low-risk or high-risk for BCR based on the median risk score derived from D1. Results: Patients from D1 identified as high risk by the AI model experienced shorter survival, with a median BCR time of 27 months, in contrast to 55 months for those classified as low risk. The AI model demonstrated significant prognostic value for BCR in both D1 (HR = 6.82, 95% confidence interval [CI]: 3.54-13.12, p < 0.0019), and D2 (HR = 2.72, 95% CI: 1.53-4.82, p < 0.0032). Furthermore, the model effectively stratified the Decipher low-risk group in D2 into distinct low and high-risk categories (HR = 4.52, 95% confidence interval [CI]: 1.70-12.05, p < 0.0085). The most prognostic features identified included five related to nuclei shape diversity (Minor Axis Length, Eccentricity, Equivalent Diameter, Solidity, and Circularity) in conjunction with nine nuclear texture features. Conclusions: The AI model's findings suggest that a digital image-based prognostic classifier for prostate cancer could serve as an alternative or complementary method to molecular-based companion risk tests. Additional, independent multi-site and prospective validation of these findings are warranted. Citation Format: Kamal Hammouda, Tilak Pathak, Tuomas Mirtti, Priti Lal, Shilpa Gupta, Anant Madabhushi. Use of computational pathology to predict biochemical recurrence in prostate cancer (Pca) (Rp) patients following radical prostatectomy: Evaluation in low decipher risk category [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 7669.

Limits to discretion and automated risk assessments in EU border control: Recognising the political in the technical

AbstractThis article analyses how the automation of border control challenges the rule of law requirement on sufficient limits to discretion by using the idea expressed by the Court of Justice of the European Union (CJEU) non‐delegation doctrine that it is possible to make a clear distinction between technically complex assessments and political discretion. To illustrate these challenges, the article uses the examples of the European Travel Information and Authorisation System (ETIAS) and the conferral of discretionary powers to EU agency Frontex to establish pre‐determined risk criteria. The article argues that not recognising the inherent political aspects of exercising technical powers leads to insufficient limits to discretionary powers in the context of automated risk assessments. Beyond raising serious rule of law concerns of arbitrary exercise of power, the idea that technical assessments and policy choices can be clearly separated enables ‘algorithmic discretion’ as a new form of administrative discretion.

Automated Risk Assessment in SAP Financial Modules through Machine Learning

Automated Risk Assessment in SAP Financial Modules through Machine Learning

Anticipating multisectoral use of services with the support of AI

Introduction: This paper presents the preliminary results of a collaborative R&D project which aims at developing artificial intelligence (AI) supported anticipation of multisectoral use of services. If we were able to predict the escalation of health and social problems of clients and the use of several different services, we could plan and offer them early preventive services with the objective of improving the quality of life and reducing the costs of service provision in the longer term.
 Approach and methods: The multidisciplinary project in progress collaborates at four spheres of research and development within the elderly care of one welfare region in Finland.
 1) Anticipatory management practices concerning risk client groups and anticipatory case management practices concerning individual clients in risk are being developed supported by predictive AI technology. The requirements concerning the information the AI based prediction model should produce to the managers and to the case managers have provisionally been defined. The current practices are co-studied, and the new practices supported by AI are co-designed by involving the “relevant” health and social care managers and practitioners in the welfare region.
 2) A machine learning (ML) predictive model based on health and social care data is being developed. The prediction model will be developed based on retrospective analysis of health and social data of the welfare region. The available data includes clinical data recorded during healthcare encounters, decisions, and usage of social services as well as physical function assessments. The data is used to train and test potential machine learning algorithms for predicting future service use of the elderly individuals based on their current health status and past use of services.
 3) The implementation of the AI/ML model within the IT infrastructure and information systems (IS) in use will be supported and investigated. The developed ML model would eventually be integrated into the IT/IS environment of the case organization. That entails connecting the specific data sources, running the model computations, and passing the results to the digital workflow of the care production management for knowledge management.
 
 4) The EU and Finnish legislation that regulate the use of personal health and social data in the development and use of AI based predictive models is being analyzed. Requirements and potential limitations imposed by current legislation on the use of predictive models are identified. In particular, the strict conditions applicable to making automated risk assessments of individuals for purposes of taking anticipatory measures are analyzed and avenues for meeting them by health and social care organizations are discussed.
 Results and outputs: Working on these four spheres, the project produces a generic model on developing the anticipation practices of multisectoral use of services with the help of AI technology. The model will available to all the organizations which are developing AI based anticipation of multisectoral use of services.
 Key words: Anticipation, prediction, health and social services usage, machine learning model, AI software, legislation, elderly care

1.2 Forecasting Best Performance with Incomplete Resources: Automated Risk Assessment of School Violence

1.2 Forecasting Best Performance with Incomplete Resources: Automated Risk Assessment of School Violence

The Automated Information System “Perimeter” is a Tool for the Modernization of Information and Technical Support of Sanitary and Quarantine Control

Sanitary and quarantine control (SQC) at the state border of the Russian Federation is the first barrier to the importation and subsequent spread of diseases on the territory of the country. Every year the number of registered outbreaks of infectious diseases in the countries of the world increases, which entails an increase in published information, some of which is unreliable and requires verification. At the same time, against the background of the development of international tourism, increase in passenger traffic, the risk of infectious diseases importation into the territory of Russia rises manifold, which creates the need for modernization of information and technical support of the SQC. In connection with the above, the aim of the work was to develop a scientifically substantiated system of informatization and digitalization of SQC, which resulted in the introduction of an automated risk assessment system as regards importation of dangerous infectious diseases (AIS “Perimeter”) at all sanitary-quarantine checkpoints (SQP). Materials and methods. The information system was created using the following software platforms: Laravel, VueJs. The official websites of the Ministries of Health of the respective countries, data from the official regional websites of WHO, regional centers for disease control and prevention (CDC), and data from the ProMED-mail system were used as sources of information on infectious morbidity in the countries of the world. Results and discussion. Implementation of AIS “Perimeter” has brought about the maximum possible efficiency in the targeted informing of SQP officials about the current epidemiological situation in the countries of the world; an effective tool for monitoring the situation at the federal level in real-time mode. It facilitates the work of SQP, staff related to conducting standard operational procedures, due to considerable decrease in the volume of routine activities to keep records. The proposed in the AIS expert risk assessment as regards importation of infectious diseases allows SQP employees, based on reliable information, to make timely decisions on the need to conduct SQC and exclude erroneous actions in the essential set of measures within the framework of SQC implementation, while minimizing subjectivity with respect to decision making.

An automatic risk assessment system for sudden cardiac death using look ahead pattern

An automatic risk assessment system for sudden cardiac death using look ahead pattern

Towards automated risk assessments for modular manufacturing systems

Abstract Manufacturing systems based on Industry 4.0 concepts provide a greater availability of data and have modular characteristics enabling frequent changes. This raises the need for new security engineering concepts that cover the increasing complexity and frequency of mandatory security risk assessments. In contrast, the current standardization landscape used for the assessment of these systems only offers abstract, static, manual, and resource-intensive procedures. Therefore, this work proposes a method that further specifies the IEC 62443 aiming to automate the security risk assessments in such a way that manual efforts can be reduced and a consistent quality can be achieved. The methodology is presented using network segmentation as a guiding example and consists of four main steps: Information collection based on a process analysis, information formalisation with a semi-formal model, information usage applying first order logic to extract expert knowledge, and information access using the concept of the digital twin. In addition, the applicability of the IEC 62443 standard to the risk assessment of modular manufacturing systems is evaluated.

Automated cardiovascular risk categorization through AI-driven coronary calcium quantification in cardiac PET acquired attenuation correction CT

BackgroundWe present an automatic method for coronary artery calcium (CAC) quantification and cardiovascular risk categorization in CT attenuation correction (CTAC) scans acquired at rest and stress during cardiac PET/CT. The method segments CAC according to visual assessment rather than the commonly used CT-number threshold. MethodsThe method decomposes an image containing CAC into a synthetic image without CAC and an image showing only CAC. Extensive evaluation was performed in a set of 98 patients, each having rest and stress CTAC scans and a dedicated calcium scoring CT (CSCT). Standard manual calcium scoring in CSCT provided the reference standard. ResultsThe interscan reproducibility of CAC quantification computed as average absolute relative differences between CTAC and CSCT scan pairs was 75% and 85% at rest and stress using the automatic method compared to 121% and 114% using clinical calcium scoring. Agreement between automatic risk assessment in CTAC and clinical risk categorization in CSCT resulted in linearly weighted kappa of 0.65 compared to 0.40 between CTAC and CSCT using clinically used calcium scoring. ConclusionThe increased interscan reproducibility achieved by our method may allow routine cardiovascular risk assessment in CTAC, potentially relieving the need for dedicated CSCT.

A review of cyber security risk assessment for web systems during its deployment and operation

This paper presents the state of the arts in security risk assessment of web systems. The process of assessing security risks and the process of developing and operating information systems in general, web systems in particular, are depicted step by step, showing how the risk assessment is performed during the deployment and the operation of web systems. Based on this analysis, different methods related to the manual and automatic risk assessment are reviewed, focusing on the methods using probability theory and Bayesian networks. The techniques developed for quantitative and qualitative assessment are presented and compared in terms of their objectives, scopes, and results to pick out advantages and limits. Finally, the approaches dedicated to assessing the risks of web systems are presented.

A dual-channel biomarker detection based on spatiotemporal upconversion-linked immunosorbent assay

Multiplexed detection of different but clinically relevant low-abundance biomarkers is of paramount importance for early-stage disease diagnosis. Herein, we have developed a simple, yet versatile and sensitive upconversion-based sensing platform that leverages the excitation-controlled switchable optical properties of upconversion nanoparticles to achieve the simultaneous detection of α-fetoprotein (AFP) and human chorionic gonadotropin (hCG) biomarkers. The assay yielded a limit of detection of 7.81 pg/mL for AFP and 1.02 × 10−4 IU/mL for hCG in spiked serum. By utilizing the dual-channel luminescent signals as dual input, we have further developed an open-source software for automatic risk assessment of testicular cancer based on a dual-input logic OR gate. Due to the high optical tunability of upconversion luminescence, the technique and software present in this work should inspire new ideas for the early diagnosis of a wide range of diseases.

Automatic Risk Assessment for an Industrial Asset Using Unsupervised and Supervised Learning

Monitoring the condition of industrial equipment is fundamental to avoid failures and maximize uptime. The present work used supervised and unsupervised learning methods to create models for predicting the condition of an industrial machine. The main objective was to determine when the asset was either in its nominal operation or working outside this zone, thus being at risk of failure or sub-optimal operation. The results showed that it is possible to classify the machine state using artificial neural networks. K-means clustering and PCA methods showed that three states, chosen through the Elbow Method, cover almost all the variance of the data under study. Knowing the importance that the quality of the lubricants has in the functioning and classification of the state of machines, a lubricant classification algorithm was developed using Neural Networks. The lubricant classifier results were 98% accurate compared to human expert classifications. The main gap identified in the research is that the found classification works only carried out classifications of present, short-term, or mid-term failures. To close this gap, the work presented in this paper conducts a long-term classification.

2.7 Automated Detection of School Violence Using Linguistic Features

On average, there are 52 violent incidents per school per year. Early identification of high-risk students prior to aggression or violence could help prevent future episodes. While there has been progress in violence prevention, most research still relies on specialized, manual, and time-intensive risk assessments. There are no automated risk-assessment scales to guide risk prevention. Our objective is to develop an Automated RIsk Assessment (ARIA) tool that uses machine learning to predict the risk of violence and aggression using structured interview transcripts from students.

A Data Driven Approach for Automated Risk Assessment and Survival Prediction of Coronavirus Using Artificial Neural Networks

Coronavirus is proved to be a severe epidemic diseasethroughout the world. Despite of endeavoring lot of medicalfacilities for mitigating with this pandemic, still the number ofinfected cases increased rapidly, which leads to lack of healthcareresources (i.e. hospitals, doctors and other healthcare amenities). Early stage risk prediction by analyzing several clinical andbehavioral risk factors is considered to be a promising solutionfor prescribing appropriate triage to patients and to reduce themortality rate due to this fetal disease. To cope up with thisproblem, in our study we have proposed a deep learning basedapproach for the early stage prediction of risk of infection andrisk of mortality in individuals possessing certain risk factors. Wehave utilized a publically available covid-19 dataset incorporatingseveral risk factors that may cause this infection. For the selectionof most significant risk factors i.e. with respect to their level ofimportance in risk prediction, we have employed three featuresselection techniques (i.e. f_classif, PCA and Tree). The set ofextracted features are the utilized for the training of proposed ANN for the prediction of infection risk and mortality risk due tocovid-19. For the performance analysis of proposed method, fourdifferent evaluation metrics are being employed including: MSE,MAE, ME and EV. The proposed model has achieved a minimum loss (MSE) of 0.00137 for infection risk prediction and MSE of0.000012 for mortality risk prediction.

Automated risk assessment of newly detected atrial fibrillation poststroke from electronic health record data using machine learning and natural language processing.

BackgroundTimely detection of atrial fibrillation (AF) after stroke is highly clinically relevant, aiding decisions on the optimal strategies for secondary prevention of stroke. In the context of limited medical resources, it is crucial to set the right priorities of extended heart rhythm monitoring by stratifying patients into different risk groups likely to have newly detected AF (NDAF). This study aimed to develop an electronic health record (EHR)-based machine learning model to assess the risk of NDAF in an early stage after stroke.MethodsLinked data between a hospital stroke registry and a deidentified research-based database including EHRs and administrative claims data was used. Demographic features, physiological measurements, routine laboratory results, and clinical free text were extracted from EHRs. The extreme gradient boosting algorithm was used to build the prediction model. The prediction performance was evaluated by the C-index and was compared to that of the AS5F and CHASE-LESS scores.ResultsThe study population consisted of a training set of 4,064 and a temporal test set of 1,492 patients. During a median follow-up of 10.2 months, the incidence rate of NDAF was 87.0 per 1,000 person-year in the test set. On the test set, the model based on both structured and unstructured data achieved a C-index of 0.840, which was significantly higher than those of the AS5F (0.779, p = 0.023) and CHASE-LESS (0.768, p = 0.005) scores.ConclusionsIt is feasible to build a machine learning model to assess the risk of NDAF based on EHR data available at the time of hospital admission. Inclusion of information derived from clinical free text can significantly improve the model performance and may outperform risk scores developed using traditional statistical methods. Further studies are needed to assess the clinical usefulness of the prediction model.