Retrospective Risk Assessment Research Articles

A conceptual framework for landscape-based environmental risk assessment (ERA) of pesticides

While pesticide use is subject to strict regulatory oversight worldwide, it remains a main concern for environmental protection, including biodiversity conservation. This is partly due to the current regulatory approach that relies on separate assessments for each single pesticide, crop use, and non-target organism group at local scales. Such assessments tend to overlook the combined effects of overall pesticide usage at larger spatial scales. Integrative landscape-based approaches are emerging, enabling the consideration of agricultural management, the environmental characteristics, and the combined effects of pesticides applied in a same or in different crops within an area. These developments offer the opportunity to deliver informative risk predictions relevant for different decision contexts including their connection to larger spatial scales and to combine environmental risks of pesticides, with those from other environmental stressors. We discuss the needs, challenges, opportunities and available tools for implementing landscape-based approaches for prospective and retrospective pesticide Environmental Risk Assessments (ERA). A set of “building blocks” that emerged from the discussions have been integrated into a conceptual framework. The framework includes elements to facilitate its implementation, in particular: flexibility to address the needs of relevant users and stakeholders; means to address the inherent complexity of environmental systems; connections to make use of and integrate data derived from monitoring programs; and options for validation and approaches to facilitate future use in a regulatory context. The conceptual model can be applied to existing ERA methodologies, facilitating its comparability, and highlighting interoperability drivers at landscape level. The benefits of landscape-based pesticide ERA extend beyond regulation. Linking and validating risk predictions with relevant environmental impacts under a solid science-based approach will support the setting of protection goals and the formulation of sustainable agricultural strategies. Moreover, landscape ERA offers a communication tool on realistic pesticide impacts in a multistressors environment for stakeholders and citizens.

Distribution characteristics and investigation evaluation of ammonia nitrogen in the soil and groundwater of a chemical plant

ABSTRACT In this study, we analyzed the distribution characteristics of ammonia nitrogen, and evaluated the pollution status of the soil and groundwater in this legacy site. The results revealed that the concentration of ammonia nitrogen in the soil ranged from 2.36 to 32.7 mg/kg, and the areas with higher ammonia nitrogen concentration were the compression workshop, conversion workshop, sewage treatment area, and slag yard, the concentration of ammonia nitrogen in these areas ranged from 10.1 to 32.7 mg/kg. The groundwater ammonia nitrogen concentration ranged from 0.04 to 1.47 mg/L, the average value was 0.526 mg/L. Soil and groundwater ammonia nitrogen pollution in the plant area was mainly attributed to the node leakage of waste water pipes, and the investigation and evaluation results revealed that the soil test results of this site are consistent with the corresponding screening values. As the groundwater in this site is not used for drinking and other purposes, its risk to human health is considered acceptable. The detection indicators of groundwater in some plots exceed the Class III or IV standards, so long-term monitoring and retrospective risk assessment are the focus of future risk management and control of the plots.

Using emerging science to inform risk characterizations for wildlife within current regulatory frameworks.

Many jurisdictions have regulatory frameworks that seek to reduce the effects of environmental exposures of anthropogenic chemicals on terrestrial wildlife (i.e., mammals, birds, reptiles, and amphibians). The frameworks apply for new and existing chemicals, including pesticides (prospective assessments), and to environmental contamination from releases (retrospective risk assessments). Relatively recently, there have been many scientific advances that could improve risk estimates for wildlife. Here, we briefly describe current regulations from North America (United States and Canada) and from Europe that include risk assessments for wildlife to ascertain whether they are conducive to the use of emerging science and new methods. We also provide examples where new and emerging science may be used to improve wildlife risk characterization and identify areas in need of future research. Integr Environ Assess Manag 2024;20:765-779. © 2024 His Majesty the King in Right of Canada and The Authors. Integrated Environmental Assessment and Management © 2024 Society of Environmental Toxicology & Chemistry (SETAC). Reproduced with the permission of the Minister of Environment and Climate Change Canada. This article has been contributed to by U.S. Government employees and their work is in the public domain in the USA.

Retrospective Risk Assessment of Injuries and Fatalities in the Forestry and Logging Workforce in the United States, 2003-2019.

The objectives of this study on the forestry and logging workforce are to: 1) Analyze causes of injuries/fatalities to inform future intervention studies focused on risk mitigation, 2) determine whether there are any trends or associations between work-related risk factors and workplace injuries/fatalities over a 16-year period (2003-2019), and 3) identify knowledge gaps related to injuries and fatalities for future studies to address. Data on fatalities, injuries, and illnesses of the forestry and logging workforce from the United States Bureau of Labor Statistics were analyzed. Correlation analysis (p < .05) was conducted to assess the relationship between causes of forestry and logging workforce fatalities by cause of fatality in the United States. Injury and fatality rates were calculated for each year (fatalities: 2003-2018; injuries: 2005-2019) and time span-specific incidence rates were calculated by cause. Contact with objects and equipment was the primary cause of injuries and fatalities in the forestry and logging workforce during the study period. Transportation-related incidents ranked second as the cause of fatalities, while the category of falls, slips, and trips was the second leading cause of injuries. Gaps in occupational health and safety identified by this study should be collaboratively addressed by researchers and the forestry industry.

Is there any added value of the second generation in the Extended One-Generation Reproductive Toxicity Study (EOGRTS)? A retrospective analysis of 24 EOGRTS

The Extended One-Generation Reproductive Toxicity Study (EOGRTS) is a standard information requirement under Registration, Evaluation, Authorization and restriction of Chemicals (REACH) in Europe. Inclusion of an F2 generation is considered useful if this impacts hazard identification or when it provides additional information altering the reproductive or developmental No Observed Adverse Effect Level (NOAEL) and subsequent risk assessment. In this retrospective analysis the added value of the F2 generation in 24 EOGRTS was evaluated. Our retrospective analysis showed an added value of the second generation in 1/24 EOGRTS only, where extending with the F2 generation lowered both the reproductive and developmental NOAEL. For this substance, extension with the F2 generation led to classification for effects on fertility. Hazard identification for developmental effects was not impacted based on clear developmental toxic effects already observed in the F1 generation and in previous studies with this substance. Risk assessment may be impacted if the developmental toxic effects are the most critical effects observed for this substance. For 23/24 studies included in this retrospective analysis, hazard and risk assessment were unaffected by inclusion of the F2 generation. Moreover, for 13/13 studies with external triggers for inclusion of the F2 generation hazard and risk assessment were unaffected. By decreasing the number of EOGRTS that are extended with an F2 generation, the number of animals used in regulatory developmental and reproductive toxicity studies may be significantly reduced in the future without negatively affecting the ability to identify potentially harmful chemicals.

Standard regulatory action for retrospective cumulative risk assessment of pesticides in MCRA

Standard regulatory action for retrospective cumulative risk assessment of pesticides in MCRA

Retrospective Post-Hospitalisation COVID-19 Mortality Risk Assessment of Patients in South Africa.

Background: This study explores the determinants impacting the mortality risk of COVID-19 patients following hospitalisation within South Africa's Limpopo province. Methods: Utilising a dataset comprising 388 patients, the investigation employs a frailty regression model to evaluate the influence of diverse characteristics on mortality outcomes, contrasting its performance against other parametric models based on loglikelihood measures. Results: The findings underscore diabetes and hypertension as notable contributors to heightened mortality rates, underscoring the urgency of effectively managing these comorbidities to optimise patient well-being. Additionally, regional discrepancies come to the fore, with the Capricorn district demonstrating elevated mortality risks, thereby accentuating the necessity for precisely targeted interventions. Medical interventions, particularly ventilation, emerge as pivotal factors in mitigating mortality risk. Gender-based distinctions in mortality patterns also underscore the need for bespoke patient care strategies. Conclusions: Collectively, these outcomes supply practical insights with implications for healthcare interventions, policy formulation, and clinical strategies aimed at ameliorating COVID-19 mortality risk among individuals discharged from hospitals within South Africa's Limpopo province.

Sink Drains in a Neonatal Intensive Care Unit: A Retrospective Risk Assessment and Evaluation.

Water systems in health care facilities can form reservoirs for Gram-negative bacteria. While planning a new neonatal intensive care unit (NICU), we performed a retrospective evaluation of potential risks from water-diverting systems on the existing NICU of our tertiary care University Hospital. During 2017 to 2023, we recorded nine nosocomial cluster events with bacterial pathogens in our NICU. Of these, three clusters of Gram-negative bacteria were potentially related to sink drains: A Klebsiella oxytoca, a Pseudomonas aeruginosa, and an Enterobacter hormaechei cluster were uncovered by clinical routine screening of patients and breastmilk samples. They were confirmed using whole-genome sequencing and a subsequent core genome multilocus sequence typing (cgMLST) algorithm. Our observations highlight that the implementation of sink drains in a NICU may have negative effects on patients' safety. Construction planning should concentrate on the avoidance of washbasins in patient rooms when redesigning sensitive areas such as NICUs.

Long-term exposure and health risk assessment from air pollution: impact of regional scale mobility

BackgroundThe negative effect of air pollution on human health is widely reported in recent literature. It typically involves urbanized areas where the population is concentrated and where most primary air pollutants are produced. A comprehensive health risk assessment is therefore of strategic importance for health authorities.MethodsIn this study we propose a methodology to perform an indirect and retrospective health risk assessment of all-cause mortality associated with long-term exposure to particulate matter less than 2.5 microns (PM2.5), nitrogen dioxide (NO2) and ozone (O3) in a typical Monday to Friday working week. A combination of satellite-based settlement data, model-based air pollution data, land use, demographics and regional scale mobility, allowed to examine the effect of population mobility and pollutants daily variations on the health risk. A Health Risk Increase (HRI) metric was derived on the basis of three components: hazard, exposure and vulnerability, utilizing the relative risk values from the World Health Organization. An additional metric, the Health Burden (HB) was formulated, which accounts for the total number of people exposed to a certain risk level.ResultsThe effect of regional mobility patterns on the HRI metric was assessed, resulting in an increased HRI associated with all three stressors when considering a dynamic population compared to a static one. The effect of diurnal variation of pollutants was only observed for NO2 and O3. For both, the HRI metric resulted in significantly higher values during night. Concerning the HB parameter, we identified the commuting flows of the population as the main driver in the resulting metric.ConclusionsThis indirect exposure assessment methodology provides tools to support policy makers and health authorities in planning intervention and mitigation measures. The study was carried out in Lombardy, Italy, one of the most polluted regions in Europe, but the incorporation of satellite data makes our approach valuable for studying global health.

Priorities and Challenges in Methodology for Human Health Risk Assessment from Combined Exposure to Multiple Chemicals.

This paper reviews key elements in the assessment of human health effects from combined exposure to multiple chemicals taking into consideration current knowledge and challenges to identify areas where scientific advancement is mostly needed and proposes a decision-making scheme on the basis of existing methods and tools. The assumption of dose addition and estimation of the hazard index (HI) is considered as a starting point in component-based risk assessments. When, based on the generic HI approach, an unacceptable risk is identified, more specific risk assessment options may be implemented sequentially or in parallel depending on problem formulation, characteristics of the chemical group under assessment, exposure levels, data availability and resources. For prospective risk assessments, the reference point index/margin of exposure (RPI/MOET) (Option 1) or modified RPI/normalized MOET (mRPI/nMOET) (Option 2) approaches may be implemented focusing on the specific mixture effect. Relative potency factors (RPFs) may also be used in the RPI approach since a common uncertainty factor for each mixture component is introduced in the assessment. Increased specificity in the risk assessment may also be achieved when exposure of selected population groups is considered (Option 3/exposure). For retrospective risk assessments, human biomonitoring data available for vulnerable population groups (Option 3/susceptibility) may present more focused scenarios for consideration in human health risk management decisions. In data-poor situations, the option of using the mixture assessment factor (MAF) is proposed (Option 4), where an additional uncertainty factor is applied on each mixture component prior to estimating the HI. The magnitude of the MAF may be determined by the number of mixture components, their individual potencies and their proportions in the mixture, as previously reported. It is acknowledged that implementation of currently available methods and tools for human health risk assessment from combined exposure to multiple chemicals by risk assessors will be enhanced by ongoing scientific developments on new approach methodologies (NAMs), integrated approaches to testing and assessment (IATA), uncertainty analysis tools, data sharing platforms, risk assessment software as well as guideline development to meet legislative requirements.

Retrospective quantitative risk assessment of skin sensitization caused by an antimicrobial agent used in a consumer product: 2,3,5,6-Tetrachloro-4-(methylsulfonyl) pyridine.

Serious cases of allergic contact dermatitis (ACD) caused by exposure to 3,5,6-tetrachloro-4-(methylsulfonyl)pyridine (TCMSP; CAS no. 13108-52-6) used as an antimicrobial agent for desk mats have been reported in Japan. A quantitative risk assessment (QRA) of TCMSP contained in desk mats was performed retrospectively. A local lymph node assay (LLNA): BrdU-ELISA was conducted to determine a reliable EC1.6 value for TCMSP. The acceptable exposure level (AEL) for TCMSP was derived from the EC1.6 value by applying sensitization assessment factors (SAFs). The exposure level was estimated based on the assumption referring to the use conditions of thiabendazole in the same purpose. Then, the estimated exposure level was compared with the AEL to evaluate the skin sensitization risk. The AEL was calculated as 0.00458 μg/cm2 based on the EC1.6 value (0.011%, 2.75 μg/cm2 ) by applying a composite SAF of 600. The estimated TCMSP exposure level from the desk mat was 500 times greater than the AEL, indicating a serious skin sensitization risk. Assessments of skin sensitization potencies of chemicals to be used in consumer products are strongly recommended, and QRAs should be performed at the pre-marketing stage to avoid the skin sensitization risk in consumers.

An alternative risk assessment framework for tropical soil multi-metal contamination using arbuscular mycorrhizal fungi

Arbuscular mycorrhizal fungi (AMF) are a key group of soil organisms involved in several ecosystem services, but they had not been explored in retrospective ecological risk assessment (ERA) schemes, partially due to a lack of experimental protocols. We aimed to perform a site-specific test to assess the effects of multiple metal contaminated soil (Zn, Cu, Cd, and Pb) on several ecotypes of AMF and evaluate the conceptual fitness of the performed AMF test to include in the TRIAD approach of ERA schemes. The results demonstrated that increasing metal contaminated soil proportions that inhibited 50 % (IC50) of spore germination varied from 28 to >80. Ecotypes such as Claroideoglomus etunicatum (IC50 > 80) and Racocetra gregaria (IC50 > 80) experienced 50 % reduction in spore germination at metals concentrations of 10,776.3 for Zn, 1015.2 Cu, 65.5 Cd, 140.2 mg dm−3 Pb, that are 3 times higher than those for Acaulospora mellea CMM101 (IC50 28 [16.2–39.8]) (3441.7 Zn, 333.9 Cu, 17.8 Cd, 56.5 mg dm−3 Pb). In the evaluation of the suitability of the AMF ecotoxicological test to ERA, both spore germination and germinative tube growth were best evaluated and thus suitable in the following descending order: Tier III, Tier II, and Tier I. Variable effects of multiple-metal contamination on the ecotypes indicates how AMF community is affected in its pre-symbiotic structures. The ecotoxicological test allowed the selection of two species with the greatest sensitivity (Ambispora appendicula and Rhizophagus clarus CMM103) to the metal matrix, with the potential to best fit ERA objectives. The site-specific ecotoxicological test with AMF ex-situ proved adequate as an alternative test for Tiers II and III of TRIAD ERA schemes for metal contaminated areas. Data generated through test results, such as the inhibition concentrations (ICs), could be incorporated into ERAs risk indexes, increasing its ecological relevance, and reducing overall uncertainties.

Validating a tailored drought risk assessment methodology: drought risk assessment in local Papua New Guinea regions

Abstract. Climate change is increasing the frequency and intensity of natural hazards, causing disastrous impacts on vulnerable communities. Pacific Small Island Developing States (SIDS) are of particular concern, requiring resilient disaster risk management consisting of two key elements: proactivity and suitability. Drought risk knowledge can inform resilient risk management, but it is currently underexplored in Pacific SIDS, particularly in the highly vulnerable nation of Papua New Guinea (PNG). A tailored, meaning highly specific to the area under investigation, drought risk assessment methodology is key for expanding risk knowledge in vulnerable communities. A semi-dynamic and tailored drought risk assessment methodology to be utilised in PNG was developed in this research. Representative hazard, vulnerability, and exposure indicators were selected, and integrated geographic information system (GIS) processes were used to produce hazard, vulnerability, exposure, and risk indices and maps. The validity of the risk assessment was investigated with a retrospective risk assessment of drought in PNG (from 2014–2020) paired with a literature assessment (as a ground-truth source), and a sensitivity analysis. The preliminary drought risk assessment methodology demonstrated in this study was overall deemed valid and robust, with supplementary improvements proposed for consideration in future investigation. The developed methodology makes strides in addressing methodological knowledge gaps in drought risk assessment, for global assessments and those specific for PNG, and demonstrates the potential for risk assessment to inform resilient drought management practices in at-risk areas. Overall, the results of this study directly contribute to enhancing provincial drought risk knowledge in PNG.

Retrospective cumulative dietary risk assessment of craniofacial alterations by residues of pesticides.

EFSA established cumulative assessment groups and conducted retrospective cumulative risk assessments for two types of craniofacial alterations (alterations due to abnormal skeletal development, head soft tissue alterations and brain neural tube defects) for 14 European populations of women in childbearing age. Cumulative acute exposure calculations were performed by probabilistic modelling using monitoring data collected by Member States in 2017, 2018 and 2019. A rigorous uncertainty analysis was performed using expert knowledge elicitation. Considering all sources of uncertainty, their dependencies and differences between populations, it was concluded with varying degrees of certainty that the MOET resulting from cumulative exposure is above 100 for the two types of craniofacial alterations. The threshold for regulatory consideration established by risk managers is therefore not exceeded. Considering the severity of the effects under consideration, it was also assessed whether the MOET is above 500. This was the case with varying levels of certainty for the head soft tissue alterations and brain neural tube defects. However, for the alterations due to abnormal skeletal development, it was found about as likely as not that the MOET is above 500 in most populations. For two populations, it was even found more likely that the MOET is below 500. These results were discussed in the light of the conservatism of the methodological approach.

Could the magnitude of the 3/11 disaster have been reduced by ecological planning? A retrospective multi-hazard risk assessment through map overlay

On March 11, 2011, the Great East Japan Earthquake triggered a series of catastrophes in Japan. The sheer magnitude of this compound disaster—known as the 3/11 disaster—raises a question whether it was simply unavoidable. However, this study demonstrates that the 3/11 disaster could have been significantly reduced by strategic ecological planning, if not avoided altogether. Using an environmental inventory developed by the Japan National Land Agency (JNLA) in 1980, we conducted a retrospective multi-hazard risk assessment for Tohoku through map overlay. We found that 89 % of the damaged highways, 88.2 % of the damaged buildings, and 81 % of the wrecked Fukushima nuclear power plants and associated facilities in the 3/11 disaster are subject to high risks of one or more hazards identified in the 1980 environmental inventory. This implies that the historic data has “predicted” the major damages in the 3/11 disaster occurred 31 years later. A similar assessment using the 2019 risk data by Japan’s Ministry of Land, Infrastructure, Transport and Tourism (MLIT) shows that this current risk mapping, nevertheless, largely fails to indicate the aforementioned damages. Our study suggests that even simple “map overlay” can be instrumental to multi-hazard risk assessment; however, for map overlay to be effective, a high-quality environmental inventory map with integrated and comprehensive risk information is necessary, and thus risk mapping quality matters. To reduce compound disasters, the political will is most important to ensure that the results of multi-hazard risk assessment is taken into account in spatial planning.

Could the magnitude of the 3/11 disaster have been reduced by ecological planning? A retrospective multi-hazard risk assessment through map overlay

Could the magnitude of the 3/11 disaster have been reduced by ecological planning? A retrospective multi-hazard risk assessment through map overlay

Epinephrine Auto-Injector Prescription and Use: A Retrospective Analysis and Clinical Risk Assessment of Adult Patients Sensitised to Lipid Transfer Protein

Epinephrine Auto-Injector Prescription and Use: A Retrospective Analysis and Clinical Risk Assessment of Adult Patients Sensitised to Lipid Transfer Protein

Epinephrine Auto-Injector Prescription and Use: A Retrospective Analysis and Clinical Risk Assessment of Adult Patients Sensitised to Lipid Transfer Protein

Epinephrine Auto-Injector Prescription and Use: A Retrospective Analysis and Clinical Risk Assessment of Adult Patients Sensitised to Lipid Transfer Protein

Epinephrine Auto-Injector Prescription and Use: A Retrospective Analysis and Clinical Risk Assessment of Adult Patients Sensitized to Lipid Transfer Protein.

Lipid transfer proteins (LTPs) are widely widespread plant food allergens which represents the main cause of food allergy in adults living in the Mediterranean basin. The purpose of this study was to investigate in LTP patients the actual use of prescribed epinephrine auto-injector and appropriateness of its prescription. In addition, we investigated in these patients: (1) occurrence of new food reaction in the following three years after to diagnosis; (2) need and number of access to emergency services; (3) presence of possible predictive factors to further food reactions. One-hundred sixty-five adult patients sensitized to LTPs have been included. During follow-up, we recorded 68 further reactions, most of them (77.9%) characterized by local symptoms; rarely the patients required an emergency-department visits (16.1%) and only one patient (1.7%) used the epinephrine auto-injector. The patients with a previous history of anaphylaxis at baseline turned back to access to emergency services also during the follow-up (p = 0.006). The majority of patients with recorded systemic reactions (p = 0.004) and treated in an emergency room (p = 0.028) did not have any co-factor-enhanced at diagnosis. We noted an association between platanus pollen sensitization and severity of further reactions during the follow-up (p = 0.026). Epinephrine auto-injector were prescribed to 108/165 patients (65.5%) with an over-prescription rate of 25%. The unforeseeable clinical presentation of LTP allergic reactions and the eventual role played by the cofactor make necessary schedule a follow-up to monitor the patients over time and to assess the actual use of epinephrine auto injectors prescribed.

Abstract 1929: Deep-learning-enabled volumetric breast density estimation with digital breast tomosynthesis

Abstract Background: It has been widely established that breast density is an independent breast cancer risk factor. With the increasing utilization of digital breast tomosynthesis (DBT) in breast cancer screening, there is an opportunity to estimate volumetric breast density (VBD) routinely. However, current available methods extrapolate VBD from 2D images acquired with DBT and/or depend on the existence of raw DBT data which is rarely archived by clinical centers due to cost and storage constraints. This study aims to harness deep learning to develop a computational tool for VBD assessment based solely on 3D reconstructed, “for presentation” DBT images. Methods: We retrospectively analyzed 1,080 negative DBT screening exams (09/20/2011 - 11/25/2016) from the Hospital of the University of Pennsylvania (mean age ± SD, 57 ± 11 years; mean BMI ± SD, 28.7 ± 7.1 kg/m2; racial makeup, 41.2% White, 54.2% Black, 4.6% Other), for which both 3D reconstructed and 2D raw DBT images (Selenia Dimensions, Hologic Inc) were available. All available standard views (left and right mediolateral-oblique and cranio-caudal views) were included for each exam, leading to 7,850 DBT views. Corresponding 3D reference-standard tissue segmentations were generated from a previously validated software that uses both 3D reconstructed slices and raw 2D DBT data to provide VBD metrics, shown to be strongly correlated with VBD measures from MRI image volumes. We based our deep learning algorithm on the U-Net architecture within the open-source Generally Nuanced Deep Learning Framework (GaNDLF) and created a 3-label image segmentation task (background, dense tissue, and fatty tissue). Our dataset was randomly split into training (70%), validation (15%) and test (15%) sets, while ensuring that all views of the same DBT exam were assigned to the same set. The performance of our deep learning algorithm against the corresponding reference-standard segmentations was measured in terms of Dice scores (DSC), with 0 signifying no overlap and 1 signifying perfect overlap, overall, as well as separately for each label. Results: After training was complete, our deep learning algorithm achieved a DSC of 0.78 on the validation, as well as on the test set. Our method accurately segmented background from breast tissue (DSC = 0.94) and demonstrated moderate to high performance in segmenting dense and fatty tissue, respectively (DSC = 0.49 and 0.89). Conclusion: Our preliminary analysis suggests that deep learning shows promise in the estimation of VBD using 3D DBT reconstructed, “for presentation” images. Future work involving transfer learning based on ground truth masks by clinical radiologists could further enhance this method’s performance. In view of rapid clinical conversion to DBT screening, such a tool has the potential to enable large retrospective epidemiologic and personalized risk assessment studies of breast density with DBT. Citation Format: Vinayak S. Ahluwalia, Walter Mankowski, Sarthak Pati, Spyridon Bakas, Ari Brooks, Celine M. Vachon, Emily F. Conant, Aimilia Gastounioti, Despina Kontos. Deep-learning-enabled volumetric breast density estimation with digital breast tomosynthesis [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 1929.