Risk Assessment Practices Research Articles

Assessment of environmental risk areas based on airborne pollen patterns as a response to land use and land cover distribution

Allergic respiratory diseases are considered to be among the most important public health concerns, and pollen is the main cause of allergic respiratory diseases worldwide. However, the biological component of air quality is largely underestimated, and there is an important gap in the legislation in this area. The aims of this study were to characterise the occurrence and incidence of pollen exposure in relation to potential pollen sources and to delineate the main areas of aerobiological risk in the Madrid Autonomous Region based on homogeneous patterns of pollen exposure. This study uses the historical aerobiological database of the Madrid Region Palynological Network (central Spain) from ten pollen stations from 1994 to 2022, and the land-use information from the Corine Land Cover. Multiple clustering approaches were followed to group the sampling stations and subsequently all the 1 × 1km pixels for the Madrid Autonomous Region. The clustering dendrogram for land-use distribution was compared to the dendrogram for historical airborne pollen data. The two dendrograms showed a good alignment with a very high correlation (0.95) and very low entanglement (0.15), which indicates a close correspondence between the distribution of the potential pollen sources and the airborne pollen dynamics. Based on this knowledge, the Madrid Autonomous Region was divided into six aerobiological risk areas following a clear anthropogenic gradient in terms of the potential pollen sources that determine pollen exposure in the Madrid Region. Spatial regionalisation is a common practice in environmental risk assessment to improve the application of management plans and optimise the air quality monitoring networks. The risk areas proposed by scientific criteria in the Madrid Autonomous Region can be adjusted to other operational criteria following a framework equivalent to other air quality networks.

Patterns of referrals to regional clinical genetics services for women potentially at above-population level risk of breast cancer

BackgroundThe National Institute for Health and Care Excellence (NICE) recommends that women in England at above-population risk be offered additional breast screening and, depending on the level of risk, risk-reducing medication or surgery.MethodsWe reviewed the hospital records of GP referrals made to two large genetics services in England between 01/12/2021-30/11/2022 for women aged 18–49 years and suspected to be at above-population level risk for breast cancer. We compared the women referred with the wider population and estimates of the number of women at above-population level risk using published data.ResultsUp to 20% of women referred did not provide sufficient information for a complete risk assessment and over 25% were considered at near-population level risk after assessment. We estimate that only a small fraction (<10%) of those above population level risk are identified and women in areas of lower deprivation are disproportionately represented amongst referrals.ConclusionsMany women are missing out on potential preventative and risk-reducing interventions for breast cancer and current pathways may be exacerbating existing health inequalities. Better systems for collecting data on family history, improved methods for risk assessment in general practice and more systematic risk assessment of women prior to population-based screening are needed.

Procedural concept for complex risk assessment in a multinational company in Romania

Globally, the process of assessing the risks to the health and safety of workers is implemented through the use of hundreds of dedicated tools, used in a flexible and complementary way, according to clearly specified criteria. Unfortunately, in the national practice of occupational risk assessment, only one method has become generalized, which is used in a proportion of 90-95%, and the major problem is that often it is not even applied only formally. This paper has an ambitious goal, aiming to offer practitioners in our country a case study on good practice on the procedural structure for achieving and capitalizing on the results of risk assessment, in a manner that is both complex and pragmatic. The concept proposed and successfully implemented at the investigated multinational company, offers a major potential to improve the management of occupational safety and health in economic organizations, regardless of their size, form of ownership or other categories of conditioning.

АНАЛИЗ МЕТОДОВ ОЦЕНКИ РИСКОВ В ОБЛАСТИ ПРОИЗВОДСТВЕННОЙ БЕЗОПАСНОСТИ НА АВИАПРЕДПРИЯТИИ

The article discusses various methods of risk assessment in the field of of process safety at an airline. The purpose of the study is to determine the most appropriate risk assessment method to increase the level of safety at work and reduce the probability of dangerous situations. When analyzing the methods for detecting and identifying hazardous events and negative situations, we have highlighted the most effective ones. Based on this, the authors have created diagrams such as the "tree of incidents" and the "tree of events" has been developed for the event: industrial injury. The article considers the matrix method as one of the most common methods in the practice of professional risk assessment.

Fluorescence spectroscopic profiling of urine samples for predicting kidney transplant rejection

Rejection is the primary factor affecting the functionality of a kidney post-transplant, where its prompt prediction of risk significantly influences therapeutic strategies and clinical outcomes. Current graft health assessment methods, including serum creatinine measurements and transplant kidney puncture biopsies, possess considerable limitations. In contrast, urine serves as a direct indicator of the graft's degenerative stage and provides a more accurate measure than peripheral blood analysis, given its non-invasive collection of kidney-specific metabolite. This research entailed collecting fluorescent fingerprint data from 120 urine samples of post-renal transplant patients using hyperspectral imaging, followed by the development of a learning model to detect various forms of immunological rejection. The model successfully identified multiple rejection types with an average diagnostic accuracy of 95.56 %.Beyond proposing an innovative approach for predicting the risk of complications post-kidney transplantation, this study heralds the potential introduction of a non-invasive, rapid, and accurate supplementary method for risk assessment in clinical practice.

Use of Fracture Risk Assessment Tool in clinical practice and Fracture Risk Assessment Tool future directions.

Fracture Risk Assessment Tool is a free, online fracture risk calculator which can be used to predict 10-year fracture risk for women and men over age 50 years. It incorporates seven clinical risk factors and bone density to give a 10-year risk of major osteoporotic fracture and hip fracture. This dynamic tool can be used with patients at the bedside to help guide treatment decisions. There are some limitations to Fracture Risk Assessment Tool, with the most central limitation being the fact that inputs are binary. Much research has been done to try to refine Fracture Risk Assessment Tool to allow for more accurate risk prediction, and this article describes the data for adjusting Fracture Risk Assessment Tool depending on the clinical scenario such as the dose of glucocorticoid use, presence of diabetes and others. Recently, the new FRAXplus tool has been developed to address many of these concerns and will likely replace the old Fracture Risk Assessment Tool in the future. At the current time, it is available in beta form.

Malcoda: Practical and Stochastic Security Risk Assessment for Enterprise Networks

Malcoda: Practical and Stochastic Security Risk Assessment for Enterprise Networks

Integrating Resilience into Risk Matrices: A Practical Approach to Risk Assessment with Empirical Analysis

The changing and intensifying landscape of global, national, and local disaster risks, driven by socio-political, environmental, and technological shifts, underscores the critical need for risk assessment by international agencies and governments. The Risk Matrix, introduced in 1995, has been widely used for risk assessment in different contexts, lauded for its simplicity and effectiveness. This model relies on the core risk components of consequence and likelihood, making it a favored tool for risk managers. To enhance the precision of risk assessment, various adaptations and extensions of the risk matrix have emerged; while some indirectly address resilience aspects, none explicitly integrate resilience into the matrix. This paper explores the risk matrix and its extensions, advocating for the inclusion of resilience in risk assessment. It introduces an empirical approach to quantify resilience, through a survey targeting small and medium-sized businesses in Southern Ontario, Canada. By developing two types of risk matrices—one with resilience considerations and one without—our work demonstrates how resilience alters risk prioritization, highlighting the importance of preparedness. This research underscores the pivotal role of resilience in risk assessment and urges its explicit integration into risk matrices to enhance accuracy and efficacy. Through practical examples and empirical data, the paper builds a compelling case for the central role of resilience in modern risk assessment practices.

Qualitative and quantitative concentration-response modelling of gene co-expression networks to unlock hepatotoxic mechanisms for next generation chemical safety assessment.

Next generation risk assessment of chemicals revolves around the use of mechanistic information without animal experimentation. In this regard, toxicogenomics has proven to be a useful tool to elucidate the underlying mechanisms of adverse effects of xenobiotics. In the present study, two widely used human in vitro hepatocyte culture systems, namely primary human hepatocytes (PHH) and human hepatoma HepaRG cells, were exposed to liver toxicants known to induce liver cholestasis, steatosis or necrosis. Benchmark concentration-response modelling was applied to transcriptomics gene co-expression networks (modules) to derive benchmark concentrations (BMCs) and to gain mechanistic insight into the hepatotoxic effects. BMCs derived by concentration-response modelling of gene co-expression modules recapitulated concentration-response modelling of individual genes. Although PHH and HepaRG cells showed overlap in deregulated genes and modules by the liver toxicants, PHH demonstrated a higher responsiveness, based on the lower BMCs of co-regulated gene modules. Such BMCs can be used as transcriptomics point of departure (tPOD) for assessing module-associated cellular (stress) pathways/processes. This approach identified clear tPODs of around maximum systemic concentration (Cmax) levels for the tested drugs, while for cosmetics ingredients the BMCs were 10-100-fold higher than the estimated plasma concentrations. This approach could serve next generation risk assessment practice to identify early responsive modules at low BMCs, that could be linked to key events in liver adverse outcome pathways. In turn, this can assist in delineating potential hazards of new test chemicals using in vitro systems and used in a risk assessment when BMCs are paired with chemical exposure assessment.

A CNN-based strategy to automate contour detection of the hip and proximal femur using DXA hip images from longitudinal databases (CLSA and CaMos)

ABSTRACT Hip fractures contribute significantly to mortality in older adults. New methods to identify those at risk use dual-energy X-ray absorptiometry (DXA) images and advanced image processing. However, DXA images have an overlapping femur and pelvis and may contain boundary lines, making automation challenging. Herein, a 5-layer U-net convolutional neural network (CNN) was developed to segment the femur from hip DXA images. Images were used from the Canadian Longitudinal Study on Aging (CLSA, N=104) and Canadian Multicentre Osteoporosis Study (CaMos, N=105) databases for training, with manual contour drawing defining the ‘true output’ of each image. An algorithm was then developed to mask each hip image, and trained to predict subsequent masks. The CNN was tested with 44 additional CLSA images and 42 CaMos images. This proposed approach had an accuracy and intersection over union (IoU) of 97% and 0.57, and 93% and 0.51, for CaMos and CLSA scans, respectively. Furthermore, a series of augmentation techniques was applied to increase the data size, with accuracies of 96% and 94%, and IoU of 0.53 and 0.50. Overall, our strategy automatically determined the contour of the proximal femur using various clinical DXA images, a key step to automate fracture risk assessment in clinical practice.

Combined storm surge and wave overtopping inundation based on fully coupled storm surge-wave-tide model

Inundations in low-lying coastal areas are commonly caused by compound flooding due to the combination of surge overflow and wave overtopping. The increasing frequency of strong tropical cyclones accompanied by high waves is exacerbating flooding risks. In recent studies, wave-induced flooding (i.e., wave run-up and overtopping) has been reported as a critical component of coastal inundations. However, no clear standard has been established for estimating compound flooding caused by the nonlinear interactions of each component. The present study developed a fully coupled model of surge, wave, tide, and wave overtopping to propose a framework for assessing compound coastal inundations. A series of numerical experiments were conducted in an idealized coastal area to analyze flooding risk comprehensively. The experimental results revealed that the conventional decoupled calculation processes for wave overtopping/run-up tend to overestimate the inundation. The advanced approaches provided stable estimations of offshore wave characteristics that change dynamically under extreme wave conditions, resulting in a reliable wave overtopping calculation. Furthermore, a considerable amount of inundation can occur even when typhoons make landfall during low tidal conditions due to the prolonged occurrence of wave overtopping. The proposed framework can be considered an optimal method for practical flooding risk assessments in coastal areas by estimating compound inundations and including transition processes of surge overflow and wave overtopping/run-up.

Exploring Counselor Practices and Risk Assessment in a Proactive Digital Intervention Through Instagram in Young People: Qualitative Study.

Suicide is one of the leading causes of preventable death in young people, and the way young people are communicating suicidality has evolved to include web-based disclosures and help-seeking. To date, mental health intervention services, both on the web and in person, have been conceived in the traditional model, whereby support is provided if a young person (or their family) actively seeks out that support when distressed. On the other hand, proactive outreach is an innovative approach to intervention that has been shown to be effective in other areas of health care. Live for Tomorrow chat was delivered on Instagram and comprised of counselors who reach out to provide brief person-centered intervention to young people who post content indicating distress or suicidality. Our aim was to explore how counselors engaged young people in a proactive digital intervention and how risk assessment was conducted in this context. We analyzed 35 transcripts of conversations between counselors and young people aged 13-25 years using the 6-step approach of Braun and Clarke's reflexive thematic analysis. These transcripts included a counseling intervention and a follow-up chat that was aimed at collecting feedback about the counseling intervention. A total of 7 themes emerged: using microskills to facilitate conversations, building confidence and capacity to cope with change, seeking permission when approaching conversations about suicidality or self-harm, conversations about suicidality following a structured approach, providing assurances of confidentiality, validation of the experience of suicidality, and using conversations about suicidality to identify interventions. Counselors were able to translate counseling microskills and structured questioning regarding suicidality into a digital context. In particular, in the digital context, counselors would use the young person's post and emojis to further conversations and build rapport. The findings highlight the importance of the counselor's role to listen, empathize, validate, and empower young people and that all these skills can be transferred to a digital text counseling intervention. Counselors used a structured approach to understanding suicidality in a permission-seeking, validating, and confidential manner to identify interventions with the young person. These practices allowed the conversation to move beyond traditional risk assessment practices to meaningful conversations about suicidality. Moving beyond traditional risk assessment practices and into conversations about suicidality allowed for the validation of the young person's experience and exploration of interventions and support that made sense and were seen to be helpful to the young person. This study highlighted the benefits of a proactive digital chat-based intervention, which is a novel approach to engaging with young people experiencing psychological distress and suicidality. Furthermore, this research demonstrates the feasibility and benefit of moving mental health intervention and support to a medium where young people are currently disclosing distress and intervening proactively.

Early-career school psychologists’ risk assessment self-efficacy: An Australian perspective

Assessment and management of youth suicide risk is a key role for school psychologists. However, prior research indicates that psychologists commonly lack confidence and feel unprepared when they graduated to conduct risk assessments. This qualitative study explored nine Victorian early-career school psychologists’ role in risk assessment, and their self-perceived preparedness, self-efficacy, postgraduate training experiences and methods used to assess risk. Results identified that the frequency of student suicidal ideation and acute mental health presentations exceeded participants’ expectations. Participants identified confidence in assessing risk, but less confidence in the follow-up actions. Participants reported employing comprehensive risk assessment practices and most received exposure to risk assessment during training. Key factors identified for building risk assessment preparedness and confidence were supervision, experience, professional development and research. As participants identified core risk assessment competencies that may require further coverage in curricula, these findings have important implications for universities to maximise graduates’ risk assessment preparedness.

Unveiling the Discrepancy in Multiple Myeloma Risk Classification between Clinical Practice and SKY92 Test and the Impact on Survival

Introduction:Despite the advancements in therapeutic approaches for multiple myeloma (MM), which have led to improve the survival rates, a subset of high-risk patients still faces limited benefits from current treatments. Therefore, it is crucial to accurately identify specific patient groups who would benefit from tailored therapies through risk stratification. In this study, we aim to assess the risk classification of patients based on conventional risk markers currently used in clinical practices and with the gene expression profiling (GEP)-based SKY92 risk classifier (SkylineDx, San Diego). This approach could provide further insights for optimizing risk-adapted treatment compared to the standard guidelines used in clinical practice. Methods: The PRospective Observational Multiple Myeloma Impact Study (PROMMIS; NCT02911571) trial, a prospective US multicenter study, enrolled a total of 251 newly diagnosed MM patients (NDMM). The patients underwent risk stratification using two distinct approaches. Firstly, physicians assessed their risk of progression at the time of diagnosis according to their routine practice guidelines. Then, the patients were classified into risk groups using the SKY92 molecular test. The analysis involved the processing of RNA extracted from CD138-positive plasma cells (≥80% purity), which were isolated through immunomagnetic separation. SKY92 test was carried out either at the enrolling institute or by sending samples to a central laboratory. For 221 patients, progression-free survival (PFS) and overall survival (OS) data were available, with measurements taken from date of diagnosis; the median follow-up period was 38 months. Survival analysis was performed utilizing Cox proportional hazards model. Results: Based on conventional risk classification, 123 (49%) NDMM were classified as standard-risk and 128 (51%) patients as high-risk. However, SKY92 yielded a noticeable difference in classification, with 179 (71%) patients being categorized as standard-risk and 72 (29%) patients as high-risk. In specific 23 standard-risk and 79 high-risk (n=102, 41%) patients accordingly with clinical practice assessment were classified differently by the SKY92 test. Standard-risk and high-risk groups identified by current clinical practice classification showed a significant difference in PFS (HR: 1.6, 95%CI 1.0-2.4, p=0.031), but not in OS (HR: 1.9, 95%CI 0.9-4.0, p=0.10). With SKY92 risk stratification, instead, a significant difference was observed between the two risk groups in both PFS (HR: 2.1, 95%CI 1.4-3.1, p&amp;lt;0.001) and OS (HR: 3.7, 95%CI 1.8-7.6, p&amp;lt;0.001); furthermore, the median PFS for standard-risk and high-risk patients was, respectively, 50 and 26 months. The median OS was not reached within the 60-month timeframe for both groups. For the n=221 MM patients with survival data, we observed that most patients classified as standard-risk based on clinical practice classification were also categorized as standard-risk according to SKY92 analysis (83 out of 105, 79%). However, among those initially identified as high-risk by conventional risk classification, 71 out of 116 (61%) patients exhibit no significant difference in PFS (HR: 1.1, 95%CI 0.6-1.8, p=0.8) and OS (HR: 0.6, 95%CI 0.2-1.9, p=0.4) when compared to standard-risk patients, as determined by both risk classification methods ( Figure 1). Conversely, only 22 out of 72 (30%) patients initially identified as high-risk by SKY92 and as standard-risk by clinical practice show no significance difference for PFS (HR: 1.1, 95%CI 0.5-2.4, p=0.8) and OS (HR: 0.9, 95%CI 0.2-4.1, p=0.9) compared with standard-risk patients determined by both tests. Forty-five patients identified as HR by both risk classification methods show highly significant differences for PSF (HR: 2.9, 95%CI 1.7-4.9, p&amp;lt;0.001) and OS (HR: 4.1, 95%CI 1.8-9.6, p&amp;lt;0.001) compare with standard-risk group. Conclusions: These findings based on prospective real-world clinical data, collected in a prospective US multicenter trial confirm the effectiveness of the GEP SKY92 on risk stratification both for PFS and OS. These results support the added value of integrating SKY92 into clinical practice for precise risk assessment of patients. Figure1: PFS and OS based on the combination of the clinical risk assessment (CRA) and the SKY92 risk.

Developing the Form and Content of Implementation Strategies to Prevent Venous Thromboembolism for Ambulatory Patients with Cancer

Introduction To prevent venous thromboembolism (VTE) in people with cancer, guidelines recommend risk-assessment for those receiving systemic therapy and anticoagulation (AC) prophylaxis for those at high risk of VTE. However, these recommendations are significantly underused in clinical practice. Our prior work demonstrated barriers and facilitators contributing to this underuse and identified potential implementation strategies to address these barriers. The objective of this study was to develop the form and content of targeted implementation strategies promoting the uptake in clinical practice of guideline-recommendations for VTE prevention for ambulatory patients with cancer. Methods We conducted multidisciplinary stakeholder focus group discussions and semi-structured patient interviews to iteratively design the form and content of five implementation strategies (Table 1): (1) Conduct clinician education and training on risk-assessment models and anticoagulation thromboprophylaxis; (2) Adapt electronic health records (EHR) to provide interactive assistance; (3) Develop and distribute educational materials for clinicians about the Khorana score, VTE risk, and AC counseling; (4) Develop and distribute educational materials for patients; and (5) Audit and feedback. Stakeholders included oncologists, classical hematologists, an oncology clinical pharmacist, oncology advanced practice providers, and oncology patients, in academic and community-based settings within a single health care system. We conducted the clinician focus groups iteratively: in the first session we reviewed guidelines and evidence to support the use of risk assessment and AC prophylaxis in patients with cancer and shared barriers and facilitators identified in our earlier work. During subsequent sessions, we iteratively designed the form and content of the implementation strategies. In the final session, clinicians were presented a finalized prototype of the implementation strategies and asked to perform exploratory usability testing through simulated patient care encounters. Individual semi-structured interviews were conducted with patients to obtain feedback on the design of the implementation strategies and patient-education resources. Results A workflow for integration of risk-assessment and relevant prophylaxis in clinical practice was created based on participant feedback. Details for selected implementation strategies are shown in Table 1. For EHR support, stakeholders recommended the risk-assessment component be integrated within chemotherapy order sets. In addition, they recommended incorporating aid for AC management within the EHR, including a method to assess bleeding risk, pre-populated options for AC thromboprophylaxis, provision of easily accessible links to resources for peri-operative/procedure AC management, and a list of interactions between anticoagulants and common drugs used in oncology practice. Clinician stakeholders also recommended - and subsequently approved - standard phrases available to incorporate into the EHR documentation, both to guide decision-making and to serve as a reminder to re-assess in future visits. For education resources (clinician and patient), clinicians wanted education resources to be concise, and for the patient-facing resource, to be provided to patients both in existing “chemotherapy education” booklets and sent in after-visit appointment instructions. Regarding audit and feedback, clinicians recommended a personalized report card comparing their use of appropriate VTE prevention to their peers. After reviewing the patient-facing education documents, patients recommended simpler, straightforward language and clarifications for the VTE and AC patient education resources based on their past experiences. Conclusions With multidisciplinary stakeholder input from clinicians and patients, we developed a set of implementation strategies designed to address barriers to uptake of VTE prevention recommendations in oncology clinics. Next steps are to test the implementation strategies in clinical practice to measure impact on increasing these evidence-based interventions.

Noise risk assessment practices of four South African manufacturing and utilities companies.

The South African Noise Induced Hearing Loss (NIHL) Regulations, mandates employers to conduct a noise risk assessment, which records specific variables for determining the status of exposure and the need for implementation of control measures. The study evaluated company noise risk assessment practices for alignment with legal requirements and specific risk assessment guidelines. Convenience sampling was used to select the four manufacturing and utilities companies that participated in the study. The participating companies submitted latest noise risk assessment records for evaluation through the READ approach. The noise risk assessment records of three of the four companies omitted the recording of factors such as the reasonable deterioration in or failure of control measures, adequate control and formalisation of hearing conservation programmes (HCPs). When evaluated against the South African National Standard 31000 Risk Assessment guidelines, the risk assessment processes of the respective companies were lacking in addressing aspects related to establishing communication and consultation, evaluation, adapting, continually improving, leadership and commitment, and integration. The recorded information on the noise risk assessment reports from the four participating companies were incomplete, negatively affecting subsequent HCP management processes and decision-making. Future studies should investigate other aspects such as the implementation status of recommended noise controls as well as their effectiveness as recorded in the noise risk assessment records.Contribution:This study provided firsthand insights of company noise risk assessment practices, specifically identifying functional and technical areas requiring improvement to enhance current efforts directed towards the minimisation of NIHL within HCPs. The study highlighted that the current practices on recording noise risk assessment information remain incomplete, adversely diminishing the impact of the assessment as an important decision-making tool. The identified technical issues specifically, when addressed, will increase trust on the decisions derived from noise risk assessments.

The Predictive Power of Credit Scores: Examining Default Probability in Taiwanese Credit Card Clients

The concept of a scorecard originated from the need to establish a standardized and objective approach to evaluate credit applicants. Various techniques have been utilized to build scoring model. This research chooses Logistic regression to construct a scorecard using SPSS modeler. In this way, the study enhances the understanding of the relationship between credit scores and default behavior. By using a scorecard constructed through logistic regression, the study provides a comprehensive and interpretable model for evaluating creditworthiness. The study also employs linear probability models (LPM), logit, and probit models to assess the predictive power of credit scores on default probability. By utilizing these statistical techniques, the research presents robust empirical evidence on the significance of credit scores in predicting default behavior. Moreover, the research paper systematically analyzes prediction effects with and without control variables. By incorporating control variables such as demographic characteristics, the study adds depth to the understanding of scoring models. Overall, the findings provide valuable guidance for credit risk assessment practices and contribute to the ongoing development of effective credit evaluation frameworks.

Abstract 14601: Increased Risk of Major Adverse Cardiovascular Events Attributed to Lipoprotein(a) Across Current Atherosclerotic Cardiovascular Disease Risk Categories

Introduction: AHA guidelines recommend measurement of lipoprotein(a) [Lp(a); an inherited, causal risk factor for atherosclerotic cardiovascular disease (ASCVD)] in individuals with a family or personal history of premature ASCVD. Lp(a) measurement is also recommended for recalibrating the 10-year risk score for borderline or intermediate risk individuals. However, there is limited evidence on the risk of MACE attributed to elevated Lp(a) across ASCVD risk categories. Hypothesis: To assess the impact of elevated Lp(a) levels on MACE across ASCVD 10-year risk categories. Methods: This observational, retrospective study included a primary prevention cohort of Caucasian and Black ethnicities from the UK Biobank (2006-2020). Associations of Lp(a) level (categories of 105-150, 150-190, 190-215, and 215-260 nmol/L were compared to Lp(a) &lt;105 nmol/L) with time to first MACE and MI were assessed using Cox proportional hazard models adjusted for age, sex, and ethnicity, stratified by ASCVD 10-year risk score category. Results: The cohort (N=362,061) included 55.2% female, 94.3% Caucasian and 1.6% Black. MACE incidence rates (IR, per 100 person/years) increased with 10-year ASCVD risk score: low risk IR=0.14 (n=161,183), intermediate risk IR=0.72 (n=121,272) and high-risk IR=1.52 (n=27,733). Within and across these risk categories, elevated Lp(a) conferred a significant increase in risk of MACE and myocardial infarction (MI). In the low-risk category, HRs ranged from 1.15-1.55 (MACE) and 1.32-1.72 (MI), in the intermediate risk category HRs ranged from 1.19-1.51 (MACE) and 1.37-1.77 (MI), and in the high-risk category HRs ranged from 1.12-1.55 (MACE) and 1.14-1.76 (MI) (Figure 1). Conclusions: Our study demonstrates that elevated Lp(a) increases the risk of MACE independently of ASCVD risk score. Measuring and considering elevated Lp(a) levels as part of individual ASCVD risk assessment in routine clinical practice may help improve the risk predication.

Abstract 12307: Machine Learning Model Predicting Bleeding Risk in Patients With Coronary Artery Disease

Background: Bleeding complication during antiplatelet therapy for coronary artery disease (CAD) is an adverse issue due to high risk of subsequent death and cardiovascular events. Although many bleeding risk scores have been proposed, simple and personalized risk assessment in routine clinical practice is challenging because of the heterogeneous and multifactorial pathophysiological condition. We aimed to develop a machine learning-based risk prediction for bleeding events in CAD patients treated with antiplatelet therapy. Methods: This study was a retrospective, observational cohort study using the Japanese nationwide electronic medical record database. Data from 49,324 CAD patients who underwent revascularization and received antiplatelet therapy between July 2008 through July 2022 were randomly assigned to the model derivation and validation sets. Data balancing technique: synthetic minority over-sampling technique was used to process the imbalanced data. Risk prediction model was developed using random forest (RF) after feature selection by the Boruta algorithm. Outcome was defined as bleeding events requiring hospitalization. Results: Of all, 1,684 (3.4%) bleeding events were observed during study period. The area under the curves of receiver operator characteristics of RF (95% confidence intervals) for bleeding were 0.977 (0.976-0.978) in derivation and 0.975 (0.972-0.977) in validation set. The performance metrics of the model were well acceptable (accuracy, 0.939; precision, 0.990; recall, 0.887; F1-score 0.936, respectively) in validation set. The sigmoid calibrated RF models resulted in well approximating observed bleeding events in the calibration plot and the Brier score of 0.042. Conclusions: This machine learning model could predict bleeding risk for CAD patients treated with antiplatelet therapy in real-world setting.

Results of multi-actor collaboration in risk analysis: a simplified risk assessment toolkit for rapid detection of emerging risks.

The dynamic field of food safety faces continuous challenges, prompting stakeholders to develop collaborative actions for improved food safety systems. As part of these actions, the EU-FORA fellowship programme was dedicated to a multi-actor collaboration addressing risks of the unregulated mycotoxins T-2 and HT-2 toxins in oats. Critical gaps in risk assessment procedures were identified, leading to a joint effort to develop a strategy for rapid data collection and risk assessment, including the development of a risk assessment toolkit comprising of a training manual and two intuitive Microsoft® Excel files. The toolkit enables efficient data collection and processing, facilitating risk assessment calculations and rapid risk detection. Applying the toolkit to assess T-2 and HT-2 toxin risks in Belgian oats revealed minimal concerns, except for children aged 3-9 years, likely due to an overestimation. The toolkit is available on the FoodSafety4EU Platform and will be refined based on user feedback, promoting better risk assessment practices. This approach empowers stakeholders, from professionals to policymakers, fostering collaboration and enhancing food safety practices.