Effective Decision Support Research Articles

Explainable Artificial Intelligence for Human Decision Support System in the Medical Domain

In this paper, we present the potential of Explainable Artificial Intelligence methods for decision support in medical image analysis scenarios. Using three types of explainable methods applied to the same medical image data set, we aimed to improve the comprehensibility of the decisions provided by the Convolutional Neural Network (CNN). In vivo gastral images obtained by a video capsule endoscopy (VCE) were the subject of visual explanations, with the goal of increasing health professionals’ trust in black-box predictions. We implemented two post hoc interpretable machine learning methods, called Local Interpretable Model-Agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP), and an alternative explanation approach, the Contextual Importance and Utility (CIU) method. The produced explanations were assessed by human evaluation. We conducted three user studies based on explanations provided by LIME, SHAP and CIU. Users from different non-medical backgrounds carried out a series of tests in a web-based survey setting and stated their experience and understanding of the given explanations. Three user groups (n = 20, 20, 20) with three distinct forms of explanations were quantitatively analyzed. We found that, as hypothesized, the CIU-explainable method performed better than both LIME and SHAP methods in terms of improving support for human decision-making and being more transparent and thus understandable to users. Additionally, CIU outperformed LIME and SHAP by generating explanations more rapidly. Our findings suggest that there are notable differences in human decision-making between various explanation support settings. In line with that, we present three potential explainable methods that, with future improvements in implementation, can be generalized to different medical data sets and can provide effective decision support to medical experts.

Formulating the dynamics of an online community and identifying the influential members using the animal flocking model

• The concept of animal flock movement is used to formulate the community’s dynamics. • We propose a ratio-based method to describe the movement trajectory of a community. • We propose a novel influencer identification procedure, RemovalTest. • The identified influencers have concrete impact on changes of discussion direction. To provide effective decision support for online community management, this study proposes new methods for formulating community dynamics and identifying influential members through the animal flocking model. We considered the online community as an animal flock, where members of the community are individual animals. The change in the direction of community discussions is analogous to the migration of an animal flock, although this occurs in virtual rather than physical space. To accurately formulate the community dynamics, we established a virtual space by using the ratios of articles in various categories as coordinates. In addition, the influence of members was defined according to their ability to change the direction of community discussions in the virtual space. On the basis of this concept, a novel algorithm was developed to identify the influential members. The evaluation results showed that the influential members identified using conventional measurements of influence often have no substantial impact on changes of the discussion direction. By contrast, the method proposed in this study clearly marked the influential members in the community. In addition, the results also demonstrated that the virtual space construction method can appropriately formulate community dynamics.

Flood Mapping in the Coastal Region of Bangladesh Using Sentinel-1 SAR Images: A Case Study of Super Cyclone Amphan

Floods are triggered by water overflow into drylands from several sources, including rivers, lakes, oceans, or heavy rainfall. Near real-time (NRT) flood mapping plays an important role in taking strategic measures to reduce flood damage after a flood event. There are many satellite imagery based remote sensing techniques that are widely used to generate flood maps. Synthetic aperture radar (SAR) images have proven to be more effective in flood mapping due to its high spatial resolution and cloud penetration capacity. This case study is focused on the super cyclone, commonly known as Amphan, stemming from the west Bengal-Bangladesh coast across the Sundarbans on 20 May 2020, with a wind speed between 155 -165 gusting up to 185 . The flooding extent is determined by analyzing the pre and post-event synthetic aperture radar images, using the change detection and thresholding (CDAT) method. The results showed an inundated landmass of 2146 on 22 May 2020, excluding Sundarban. However, the area became 1425 about a week after the event, precisely on 28 May 2020 . This persistency generated a more severe and intense flood, due to the broken embankments. Furthermore, 13 out of 19 coastal districts were affected by the flooding, while 8 were highly inundated, including Bagerhat, Pirojpur, Satkhira, Khulna, Barisal, Jhalokati, Patuakhali and Barguna. These findings were subsequently compared with an inundation map created with a validation survey immediately after the event and also with the disposed location using a machine learning-based image classification technique. Consequently, the comparison showed a close similarity between the inundation scenario and the flood reports from the secondary sources. This circumstance envisages the significant role of CDAT application in providing relevant information for an effective decision support system.

Early prediction of central line associated bloodstream infection using machine learning

Central line-associated bloodstream infections (CLABSIs) are associated with significant morbidity, mortality, and increased healthcare costs. Despite the high prevalence of CLABSIs in the U.S., there are currently no tools to stratify a patient's risk of developing an infection as the result of central line placement. To this end, we have developed and validated a machine learning algorithm (MLA) that can predict a patient's likelihood of developing CLABSI using only electronic health record data in order to provide clinical decision support. We created three machine learning models to retrospectively analyze electronic health record data from 27,619 patient encounters. The models were trained and validated using an 80:20 split for the train and test data. Patients designated as having a central line procedure based on International Statistical Classification of Diseases and Related Health Problems 10 codes were included. XGBoost was the highest performing MLA out of the three models, obtaining an AUROC of 0.762 for CLABSI risk prediction at 48 hours after the recorded time for central line placement. Our results demonstrate that MLAs may be effective clinical decision support tools for assessment of CLABSI risk and should be explored further for this purpose.

Forecasting of China's solar PV industry installed capacity and analyzing of employment effect: based on GRA-BiLSTM model.

With the acceleration of China's energy transformation process and the rapid increase of renewable energy market demand, the photovoltaic (PV) industry has created more jobs and effectively alleviated the employment pressure of the labor market under the normalization of the epidemic situation. First, to accurately predict China’s solar PV installed capacity, this paper proposes a multi-factor installed capacity prediction model based on bidirectional long short-term memory-grey relation analysis. The results show that, the MAPE value of the GRA-LSTM combined model established in this paper is 5.995, compared with the prediction results of other models, the prediction accuracy of the GRA-BiLSTM model is higher. Second, the BiLSTM model is used to forecast China’s installed solar PV capacity from 2020 to 2035. The forecast results show that China’s newly installed solar PV capacity will continue to grow and reach 2833GW in 2035. Third, the employment number in China’s solar PV industry during 2020–2035 is predicted by the employment factors (EF) method. The results show that the energy transition in China during 2020–2035 will have a positive impact on the future stability and growth of the labor market in the solar PV industry. Overall, an accurate forecast of solar PV installed capacity can provide effective decision support for planning electric power development strategy and formulating employment policy of solar PV industry.

A theory-based meta-regression of factors influencing clinical decision support adoption and implementation.

The purpose of the study was to explore the theoretical underpinnings of effective clinical decision support (CDS) factors using the comparative effectiveness results. We leveraged search results from a previous systematic literature review and updated the search to screen articles published from January 2017 to January 2020. We included randomized controlled trials and cluster randomized controlled trials that compared a CDS intervention with and without specific factors. We used random effects meta-regression procedures to analyze clinician behavior for the aggregate effects. The theoretical model was the Unified Theory of Acceptance and Use of Technology (UTAUT) model with motivational control. Thirty-four studies were included. The meta-regression models identified the importance of effort expectancy (estimated coefficient = -0.162; P = .0003); facilitating conditions (estimated coefficient = 0.094; P = .013); and performance expectancy with motivational control (estimated coefficient = 1.029; P = .022). Each of these factors created a significant impact on clinician behavior. The meta-regression model with the multivariate analysis explained a large amount of the heterogeneity across studies (R2=88.32%). Three positive factors were identified: low effort to use, low controllability, and providing more infrastructure and implementation strategies to support the CDS. The multivariate analysis suggests that passive CDS could be effective if users believe the CDS is useful and/or social expectations to use the CDS intervention exist. Overall, a modified UTAUT model that includes motivational control is an appropriate model to understand psychological factors associated with CDS effectiveness and to guide CDS design, implementation, and optimization.

An Early Palliative Care Telehealth Coaching Intervention to Enhance Advanced Cancer Family Caregivers’ Decision Support Skills: The CASCADE Pilot Factorial Trial

ContextPatients with advanced cancer often involve family caregivers in health-related decision-making from diagnosis to end-of-life; however, few interventions have been developed to enhance caregiver decision support skills. ObjectivesAssess the feasibility, acceptability, and potential efficacy of individual intervention components of CASCADE (CAre Supporters Coached to be Adept DEcision Partners), an early telehealth, palliative care coach-led decision support training intervention for caregivers. MethodsPilot factorial trial using the multiphase optimization strategy (October 2019-October 2020). Family caregivers and their care recipients with newly-diagnosed advanced cancer (n = 46 dyads) were randomized to1 of 8 experimental conditions that included a combination of one of the following three CASCADE components: 1) effective decision support psychoeducation; 2) decision support communication training; and 3) Ottawa Decision Guide training. Feasibility was assessed by completion of sessions and questionnaires (predefined as ≥80%). Acceptability was determined through postintervention interviews and participants’ ratings of their likelihood to recommend. Measures of effective decision support and caregiver and patient distress were collected at Twelve and Twenty four weeks. ResultsCaregiver participants completed 78% of intervention sessions and 81% of questionnaires; patients completed 80% of questionnaires. Across conditions, average caregiver ratings for recommending the program to others was 9.9 on a scale from 1-Not at all likely to 10-Extremely likely. Individual CASCADE components were observed to have potential benefit for effective decision support and caregiver distress. ConclusionWe successfully piloted a factorial trial design to examine components of a novel intervention to enhance the decision support skills of advanced cancer family caregivers. A fully-powered factorial trial is warranted. Key MessageWe pilot tested components of CASCADE, an early palliative care decision support training intervention for family caregivers of patients with advanced cancer. CASCADE components were acceptable and the trial design feasible, providing promising future directions for palliative care intervention development and testing. Pilot results will inform a fully-powered trial.

A patent portfolio-based approach for identifying technological threat from competitors

ABSTRACT Effectively identifying technological threats from competitors and assessing their possible impact directly affects the company’s interests and security. This study proposes an early identification approach for technological threats based on patent portfolio analysis. The approach measures and aggregates three dimensions of analysis – technological maturity, technological similarity, and the technological capability gap between a company and its competitors – in a range of technological fields. The novelty of this approach is that it uses patent portfolios to evaluate the level of technological threats faced by companies and to identify technological fields associated with high threat levels. The empirical research results show that this approach has the following advantages (1) it can address the shortcomings of previous studies that identified technological threats on the basis of a single dimension. (2) It is possible to evaluate the level of technological threats faced by the company in a variety of technological fields at the same time. (3) This approach is capable of determining the causes of technological threats faced by a company in each technological field and of providing effective decision-making support for companies that need to formulate reasonable response strategies to counter technological threats.

Review and Comparative Study of Decision Support Tools for the Mitigation of Urban Heat Stress

Over the last few decades, Urban Heat Stress (UHS) has become a crucial concern of scientists and policy-makers. Many projects have been implemented to mitigate Urban Heat Island (UHI) effects using nature-based solutions. However, decision-making and selecting an adequate framework are difficult because of complex interactions between natural, social, economic and built environments. This paper contributes to the UHI issue by: (i) identifying the most important key factors of a Decision Support Tool (DST) used for urban heat mitigation, (ii) presenting multi-criteria methods applied to urban heat resilience, (iii) reviewing existing spatial and non-spatial DSTs, (iv) and analyzing, classifying and ranking DSTs. It aims to help decision-makers through an overview of the pros and cons of existing DSTs and indicate which tool is providing maximum support for choosing and planning heat resilience measures from the designing phase to the heat mitigation phase. This review shows that Multi-Criteria Decision Analysis (MCDA) can be used for any pilot site and the criteria can be adapted to the given location accordingly. It also highlights that GIS-based spatial tools have an effective decision support system (DSS) because they offer a quick assessment of interventions and predict long-term effects of urban heat. Through a comparative study using specific chosen criteria, we conclude that the DSS tool is well suited and fulfils many prerequisites to support new policies and interventions to mitigate UHS.

A data value metric for quantifying information content and utility

Data-driven innovation is propelled by recent scientific advances, rapid technological progress, substantial reductions of manufacturing costs, and significant demands for effective decision support systems. This has led to efforts to collect massive amounts of heterogeneous and multisource data, however, not all data is of equal quality or equally informative. Previous methods to capture and quantify the utility of data include value of information (VoI), quality of information (QoI), and mutual information (MI). This manuscript introduces a new measure to quantify whether larger volumes of increasingly more complex data enhance, degrade, or alter their information content and utility with respect to specific tasks. We present a new information-theoretic measure, called Data Value Metric (DVM), that quantifies the useful information content (energy) of large and heterogeneous datasets. The DVM formulation is based on a regularized model balancing data analytical value (utility) and model complexity. DVM can be used to determine if appending, expanding, or augmenting a dataset may be beneficial in specific application domains. Subject to the choices of data analytic, inferential, or forecasting techniques employed to interrogate the data, DVM quantifies the information boost, or degradation, associated with increasing the data size or expanding the richness of its features. DVM is defined as a mixture of a fidelity and a regularization terms. The fidelity captures the usefulness of the sample data specifically in the context of the inferential task. The regularization term represents the computational complexity of the corresponding inferential method. Inspired by the concept of information bottleneck in deep learning, the fidelity term depends on the performance of the corresponding supervised or unsupervised model. We tested the DVM method for several alternative supervised and unsupervised regression, classification, clustering, and dimensionality reduction tasks. Both real and simulated datasets with weak and strong signal information are used in the experimental validation. Our findings suggest that DVM captures effectively the balance between analytical-value and algorithmic-complexity. Changes in the DVM expose the tradeoffs between algorithmic complexity and data analytical value in terms of the sample-size and the feature-richness of a dataset. DVM values may be used to determine the size and characteristics of the data to optimize the relative utility of various supervised or unsupervised algorithms.

Can efficiency evaluation be applied to power plant operation improvement? A combined method with modified weighted russell directional distance model and pattern matching

When there is no further potential to be gained from technological upgrading, it is crucial for coal-fired power plants to effectively utilize their input fuels to improve their operational efficiency and reduce emissions. This paper proposes a coal management model that combines modified weighted russell directional distance model and pattern matching to help coal-fired power plants improve their operation while finding more potential for energy saving and emission abatement. An operational strategy base is established by using efficiency evaluation results for unit daily operational data, and feasible coal blending schemes are accordingly located in the strategy base for different load conditions. The model measures the improvement potential from three perspectives: coal blending, coal input and load dispatching. The daily operational data of four units (two units with circulating fluidized bed (CFB) boilers and two sub-critical units) in a typical coal-fired power plant were collected for case study, and the results indicate that our model can provide effective decision support in plants’ operational management to achieve efficiency improvement.

ATA2021ATA2021 Annual Conference & Expo(Virtual*)Tuesdays and Thursdays in June 2021(ABSTRACTS)

ATA2021ATA2021 Annual Conference & Expo(Virtual*)Tuesdays and Thursdays in June 2021(ABSTRACTS)

RADAR-X: An Interactive Interface Pairing Contrastive Explanations with Revised Plan Suggestions

Automated Planning techniques can be leveraged to build effective decision support systems that assist the human-in-the-loop. Such systems must provide intuitive explanations when the suggestions made by these systems seem inexplicable to the human. In this regard, we consider scenarios where the user questions the system's suggestion by providing alternatives (referred to as foils). In response, we empower existing decision support technologies to engage in an interactive explanatory dialogue with the user and provide contrastive explanations based on user-specified foils to reach a consensus on proposed decisions. To provide contrastive explanations, we adapt existing techniques in Explainable AI Planning (XAIP). Furthermore, we use this dialog to elicit the user's latent preferences and propose three modes of interaction that use these preferences to provide revised plan suggestions. Finally, we showcase a decision support system that provides all these capabilities.

АВТОМАТИЗАЦІЯ ПРОТИАВАРІЙНОГО КЕРУВАННЯ ЕНЕРГОСИСТЕМОЮ НА ОСНОВІ ЛОГІКО-ІМОВІРНІСНОГО МОДЕЛЮВАННЯ НАДІЙНОСТІ ПРОДУКЦІЙНИМИ МЕРЕЖАМИ ПЕТРІ

The paper presents the results of research on methods for constructing knowledge bases of decision support systems for dispatch control of power supply systems in crisis situations. Models of products based on Petri nets are proposed for assessing the parameters of reliability of power supply systems. An algorithm for calculating the reliability parameters of the electrical network using analytical matrix equations of Petri nets has been implemented. The work is devoted to the topical problem of intellectualization of power supply systems and means of automation of control of large power systems. The relevance of research in the field of building intelligent power systems is grounded. The basic requirements for the reliability of modern power supply systems are formulated. The concept of intellectualization of power systems and management of their reliability is a stable trend in the development of large energy systems and automated dispatch control systems. The solution to the problem lies in the implementation of intelligent decision support systems. The main task of the work is to model the reliability of the power supply system in order to build an effective knowledge base about the parameters of the reliability of the power supply system. For this purpose, we use a probabilistic approach to assessing reliability. This approach is based on the concepts of the probability of failure-free operation and the probability of failure, which are expressed in terms of the failure rate. On the basis of the obtained models, the construction of intelligent software systems for dispatching can be carried out taking into account the reliability indicators of the components of power supply systems. As a mechanism for formalizing failure circuits in power supply circuits, the production approach of knowledge representation is applied, which implements conjunctive-disjunctive connections of statements associated with failures. The outlined approach is invariant in relation to subject areas, which makes it possible to build effective decision support systems in the field of operational emergency control of the energy system.

Spatially apportioning the source-oriented ecological risks of soil heavy metals using robust spatial receptor model with land-use data and robust residual kriging

Previous ecological risk assessments were mainly concentration-oriented rather than source-oriented. Moreover, land use is usually related to source emissions but was rarely used to improve the source apportionment accuracy. In this study, the land-use effects of heavy metals (HMs) in surface (0–20 cm) and subsurface (20–40 cm) soils were first explored using ANOVA in a suburb of Changzhou City, China; next, based on robust absolute principal component scores-robust geographically weighted regression (RAPCS/RGWR), this study proposed RAPCS/RGWR with land-use type (RAPCS/RGWR-LUT) and compared its source apportionment accuracy with those of basic RAPCS/RGWR and commonly-used absolute principal component scores/multiple linear regression (APCS/MLR); then, the source-oriented ecological risks were apportioned based on RAPCS/RGWR-LUT and Hakanson potential ecological risk index method; finally, this study proposed robust residual kriging with land-use type (RRK) for spatially predicting the source-oriented ecological risks, and compared its spatial prediction accuracy with those of robust ordinary kriging (ROK) and traditionally-used ordinary kriging (OK). Results showed that: (i) by incorporating land-use effects, RAPCS/RGWR-LUT obtained higher source apportionment accuracy than RAPCS/RGWR and APCS/MLR; (ii) the two most important external input sources of the ecological risks were 'atmospheric deposition' (PERIsurface = 47.11 and PERIsubsurface = 35.27) and 'agronomic measure' (PERIsurface = 28.93 and PERIsubsurface = 20.37); (iii) the biggest ecological risk factor was soil Cd (ERsurface = 57.14 and ERsubsurface = 47.62), which was mainly contributed by 'atmospheric deposition' (ERsurface=33.14 and ERsubsurface=25.71); (iv) RRK obtained higher spatial prediction accuracy than ROK and OK; (v) the high-risk areas derived from 'atmospheric deposition' were mainly located in the southwest of the study area, and the high-risk areas derived from 'agronomic measure' were scattered in the agricultural land in the north and south of the study area. The above information provided effective spatial decision support for reducing the source-oriented input of the ecological risks of soil HMs in a large-scale area.

Dynamic Process Models for the Evaluation of the Compliance Level Evolution: Evidence from Italy

Decision support systems are used in different contexts, including tax policies. In these pages a theoretical analysis is proposed, based on random utility maximization and dynamic process models, to forecast the evolution of the taxable income produced by the application of a rewarding-based compliance methodology recently introduced in Italy. We will briefly describe the econometric characteristics of the new fiscal methodology (SIR); then, we will focus on the theoretical aspects concerning the evolution of the taxable income, in case of both a stochastic and a deterministic process, the latter commonly used to estimate a limit condition of the process (usually a worst-case scenario). The results here obtained can be extended to different kind of tax compliance models and are supposed to be as a basic step to implement an effective IT decision support model. The theoretical connection between SIR and sector studies, the previous compliance methodology, will be discussed. Finally, a numerical example of a deterministic process model based on synthetic data will be provided.

Forging An Optimized Bayesian Network Model With Selected Parameters For Detection of The Coronavirus In Delta State of Nigeria

Machine learning algorithm have become veritable tools for effective decision support towards the construction of systems that assist experts (individuals) in their field of exploits and endeavor with regards to problematic tasks.. They are best suited for tasks where data is explored and exploited; and cases where the dataset contains noise, partial truth, ambiguities and in cases where there is shortage of datasets. For this study, we employ the Bayesian network to construct a model trained towards a target system that can help predict best parameters used for classification of the novel coronavirus (covid-19). Data was collected from Federal Medical Center Epidemiology laboratory (a centralized databank for all cases of the covid-19 in Delta State). Data was split into training and investigation (test) dataset for the target system. Results show high predictive capability.

Coupling sparse Cox models with clustering of longitudinal transcriptomics data for trauma prognosis

BackgroundLongitudinal gene expression analysis and survival modeling have been proved to add valuable biological and clinical knowledge. This study proposes a novel framework to discover gene signatures and patterns in a high-dimensional time series transcriptomics data and to assess their association with hospital length of stay.MethodsWe investigated a longitudinal and high-dimensional gene expression dataset from 168 blunt-force trauma patients followed during the first 28 days after injury. To model the length of stay, an initial dimensionality reduction step was performed by applying Cox regression with elastic net regularization using gene expression data from the first hospitalization days. Also, a novel methodology to impute missing values to the genes selected previously was proposed. We then applied multivariate time series (MTS) clustering to analyse gene expression over time and to stratify patients with similar trajectories. The validation of the patients’ partitions obtained by MTS clustering was performed using Kaplan-Meier curves and log-rank tests.ResultsWe were able to unravel 22 genes strongly associated with hospital’s discharge. Their expression values in the first days after trauma showed to be good predictors of the length of stay. The proposed mixed imputation method allowed to achieve a complete dataset of short time series with a minimum loss of information for the 28 days of follow-up. MTS clustering enabled to group patients with similar genes trajectories and, notably, with similar discharge days from the hospital. Patients within each cluster have comparable genes’ trajectories and may have an analogous response to injury.ConclusionThe proposed framework was able to tackle the joint analysis of time-to-event information with longitudinal multivariate high-dimensional data. The application to length of stay and transcriptomics data revealed a strong relationship between gene expression trajectory and patients’ recovery, which may improve trauma patient’s management by healthcare systems. The proposed methodology can be easily adapted to other medical data, towards more effective clinical decision support systems for health applications.

Site-Specific Nutrient Management

The editorial introduces to a Special Issue entitled ”Site-Specific Nutrient Management. The concept of the nitrogen gap (NG) is as a core challenge for an effective realization of the so called “twin objectives” in sustainable agriculture. This special issue stresses on some hot spots in crop production, being responsible in the yield gap development, that farmers have to take control. The yield gap cannot be ameliorated without the synchronization of the in-season requirements of the currently grown crop for N with its three-dimensional variability in a supply on a field (temporal, spatial and vertical). A recognition of soil fertility status in the rooted zone, which includes availability of both mineral N and nutrients decisive for its uptake, is the first step in the NG amelioration. The sustainability in soil fertility, as a prerequisite of N fertilizer application, requires a wise strategy of organic matter management, based on farmyard manure, and/or cultivation of legumes. The soil fertility status, irrespectively of the World region determines ways of the N rate optimization. The division of a particular field into homogenous productive units is the primary step in the NG cover. It can be delineated, using both data on soil physico-chemical properties of the soil rooted zone, and then validated by using satellite spectral images of the crop biomass in a well-defined stage of its growth, decisive for yield. The proposed set of diagnostic tools is a basis for elaboration an effective agronomic decision support system.

Factors associated with low-dose CT lung cancer screening participation in a high burden state: Results from the 2017-2018 BRFSS

IntroductionThe purpose of this study was to examine low-dose computed tomography (LDCT) for lung cancer screening (LCS) eligibility, utilization, and factors associated with self-reported participation among eligible individuals. MethodsData from the 2017 and 2018 Oklahoma Behavioral Risk Factor Surveillance System (BRFSS) were used and analysis was restricted to data from individuals eligible for screening based on the US Preventive Services Task Force (USPSTF) guidelines. Analyses using recursive partitioning and weighted logistic regression were conducted from November 2019 to March 2020. The final study sample consisted of 596 respondents. ResultsOnly 10.84 % of participants reported LCS participation. Differences in participation by sex were observed. Among males, those with COPD were more likely to report participating in screening. Among females, those who self-reported their health status as “fair or worse” were more likely to participate in LCS. ConclusionRates of utilization were higher in this study than in earlier estimates; however, utilization of LCS remains suboptimal. Although LCS participation rates were similar for males and females, differences were observed by sex. Opportunities exist to increase screening participation among eligible individuals, and findings from this study can be used for program planning such as patient engagement resources and effective clinical decision support. Policy statementThis study further demonstrates the complex nature of cancer screening participation, specifically LDCT LCS. Under the current USPSTF guidelines only a small proportion of the population is considered eligible thus to prevent lung cancer mortality, the eligibility criteria regarding smoking history and screening age may need to be reevaluated. Furthermore, this study adds to the evidence that strategies to increase screening participation among eligible individuals may need to differ by sex.