Incorrect Decisions Research Articles

How Explainable Artificial Intelligence Can Increase or Decrease Clinicians' Trust in AI Applications in Health Care: Systematic Review.

Artificial intelligence (AI) has significant potential in clinical practice. However, its "black box" nature can lead clinicians to question its value. The challenge is to create sufficient trust for clinicians to feel comfortable using AI, but not so much that they defer to it even when it produces results that conflict with their clinical judgment in ways that lead to incorrect decisions. Explainable AI (XAI) aims to address this by providing explanations of how AI algorithms reach their conclusions. However, it remains unclear whether such explanations foster an appropriate degree of trust to ensure the optimal use of AI in clinical practice. This study aims to systematically review and synthesize empirical evidence on the impact of XAI on clinicians' trust in AI-driven clinical decision-making. A systematic review was conducted in accordance with PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, searching PubMed and Web of Science databases. Studies were included if they empirically measured the impact of XAI on clinicians' trust using cognition- or affect-based measures. Out of 778 articles screened, 10 met the inclusion criteria. We assessed the risk of bias using standard tools appropriate to the methodology of each paper. The risk of bias in all papers was moderate or moderate to high. All included studies operationalized trust primarily through cognitive-based definitions, with 2 also incorporating affect-based measures. Out of these, 5 studies reported that XAI increased clinicians' trust compared with standard AI, particularly when the explanations were clear, concise, and relevant to clinical practice. In addition, 3 studies found no significant effect of XAI on trust, and the presence of explanations does not automatically improve trust. Notably, 2 studies highlighted that XAI could either enhance or diminish trust, depending on the complexity and coherence of the provided explanations. The majority of studies suggest that XAI has the potential to enhance clinicians' trust in recommendations generated by AI. However, complex or contradictory explanations can undermine this trust. More critically, trust in AI is not inherently beneficial, as AI recommendations are not infallible. These findings underscore the nuanced role of explanation quality and suggest that trust can be modulated through the careful design of XAI systems. Excessive trust in incorrect advice generated by AI can adversely impact clinical accuracy, just as can happen when correct advice is distrusted. Future research should focus on refining both cognitive and affect-based measures of trust and on developing strategies to achieve an appropriate balance in terms of trust, preventing both blind trust and undue skepticism. Optimizing trust in AI systems is essential for their effective integration into clinical practice.

Healthcare with Wearable Devices and Machine Learning

As health management continues to grow in importance globally, driven by the quest for improved health outcomes, longevity, and personalized care, machine learning (ML) has become a popular technique for detecting and analyzing health indicators, playing an essential role in multiple areas of health detection, such as continuous heart and blood pressure monitoring, blood sugar tracking for diabetics, sleep analysis to improve sleep quality, and even disease prediction. With wearable devices, a particular scale of health detection data has been accumulated at this stage. With this data, machine learning can be predictive analytics to assess real-time health conditions, enabling early intervention and personalized treatment plans. However, data quality remains the most critical issue for machine learning-based health detection systems, as inaccuracies in sensor readings can lead to misdiagnoses or incorrect treatment decisions. In addition, privacy concerns are significant, as the sensitive health information collected by these devices requires strong security measures to protect users’ data. Moreover, the interpretability of machine learning algorithms, especially those involving deep learning, can be limited, hindering clinicians’ understanding and trust. This paper addresses these challenges by providing a comprehensive overview of relevant data sets used in health monitoring and examining the latest machine learning algorithms tailored for wearables-based health detection. It further delves into the current limitations and challenges facing this emerging field, providing insights into potential solutions and future directions for research and development.

Intervention Accuracy and Perception of Fatigue in State-Level Australian Football Umpires

This investigation examined intervention accuracy and perception of fatigue associated with umpiring state-level Australian Rules football (AF). 39 field umpires (Age: 25.2 ± 6.8 y, Body Mass: 74.6 ± 7.9 kg, Height: 178.9 ± 7.4 cm) employed by the Western Australian Football Commission, were recruited. Intervention accuracy (whether given free kicks were correct) was analysed post-event by the lead investigator using footage of the matches, with two umpire coaches being used for reliability. Perception of fatigue was assessed pre- and post-match using a questionnaire. Data was collected in 22 Western Australian Football League matches in the 2023 season. 384 free kicks were recorded, with 343 correct and 41 incorrect decisions. Each umpire awarded 9.8 ± 3.8 free-kicks, with a distribution of correct-to-incorrect being 8.8 ± 3.2 to 1.1 ± 1.1 free-kicks per match. Intervention accuracy was 89.3 ± 10.4% correct. Significant decline in intervention accuracy between first and second half (W = .931, p = .021) was found. No significant declines in intervention accuracy between quarters were observed. Perception of fatigue was unchanged across matches ( p = .074). Our results demonstrate that umpires are generally accurate when adjudicating free kicks but said accuracy declines across a match. The results of this study, provide important insight on free-kick accuracy and perception of fatigue in state-level AF umpires, and may help regulatory bodies designing strategies to improve umpiring outcomes.

The power of artificial intelligence for managing pandemics: A primer for public health professionals.

Artificial intelligence (AI) applications are complex and rapidly evolving, and thus often poorly understood, but have potentially profound implications for public health. We offer a primer for public health professionals that explains some of the key concepts involved and examines how these applications might be used in the response to a future pandemic. They include early outbreak detection, predictive modelling, healthcare management, risk communication, and health surveillance. Artificial intelligence applications, especially predictive algorithms, have the ability to anticipate outbreaks by integrating diverse datasets such as social media, meteorological data, and mobile phone movement data. Artificial intelligence-powered tools can also optimise healthcare delivery by managing the allocation of resources and reducing healthcare workers' exposure to risks. In resource distribution, they can anticipate demand and optimise logistics, while AI-driven robots can minimise physical contact in healthcare settings. Artificial intelligence also shows promise in supporting public health decision-making by simulating the social and economic impacts of different policy interventions. These simulations help policymakers evaluate complex scenarios such as lockdowns and resource allocation. Additionally, it can enhance public health messaging, with AI-generated health communications shown to be more effective than human-generated messages in some cases. However, there are risks, such as privacy concerns, biases in models, and the potential for 'false confirmations', where AI reinforces incorrect decisions. Despite these challenges, we argue that AI will become increasingly important in public health crises, but only if integrated thoughtfully into existing systems and processes.

Machine Learning Clustering Techniques to Support Structural Monitoring of the Valgadena Bridge Viaduct (Italy)

The lack of precise and comprehensive information about the health of bridges, and in particular long span ones, can lead to incorrect decisions regarding maintenance, repair, modernization, and reinforcement of the structure itself. While the consequences of inadequate interventions are quite apparent, incorrect decisions can also result in unnecessary or misdirected actions. For example, an inadequate assessment of the structural health can lead to the modernization and replacement of some components that are still sound. Structural Health Monitoring (SHM) involves the use of time series derived from periodic measurements of the structure’s behavior, considered in its operational and load environment. The goal is to determine its response to various solicitations and, in particular, to highlight any critical issue in the structure’s behavior that may affect its reliability and safety due to anomalies and deterioration. This paper proposes an SHM method applied to the Valgadena bridge, one of the tallest viaducts in Italy and Europe (maximum height 160 m), located on the Altopiano dei Sette Comuni in the Province of Vicenza. Despite the fact that the viaduct itself had already been monitored during its construction using classical geometric leveling techniques, the methodology proposed here is based instead on the use of affordable dual-frequency GNSS (Global Navigation Satellite System) receivers to determine static and dynamic components of the bridge movements. Specifically, an effective combination of time series analysis methods and machine learning techniques is proposed in order to determine the vibration modes of the monitored viaduct. Monitoring is performed in regular operation conditions of the bridge (operational modal analysis (OMA)), and the use of certain machine learning methods aims at supporting the development of an effective automatic OMA procedure. To be more specific, the random decrements technique is used in order to make the vibration characteristics of the collected signals more apparent. Time-domain-based subspace identification is applied in order to determine a proper model of the collected measurements. Then, clustering methods, namely DBSCAN (Density-Based Spatial Clustering of Applications with Noise) and GMMs (Gaussian Mixture Models), are used in order to reliably estimate the system poles, and hence the corresponding vibration characteristics. The performance of the considered methods is compared on the Valgadena bridge case study, showing that the use of GMM clustering reduces, with respect to DBSCAN, the impact of the choice of certain parameter values in the considered case.

Aneurism of the left portal vein branch in a teenager - a rare clinical case

The authors presented their own clinical observation of an aneurysm of the left portal vein branch in a teenager with a long-term asymptomatic course. Reduced serum concentrations of ceruloplasmin and α-1-antitrpsin made diagnostic search difficult, which could lead to incorrect therapeutic decisions. However, the results of imaging methods allowed us to establish the root cause of liver damage and its cirrhotic transformation. Vascular aneurysms of the portal vein system are a very rare pathology, and it should be taken into account in the differential diagnostic algorithm while excluding other, more obvious causes of liver pathology.

Kako se izogniti potvorjeni znanosti?

Purpose: The falsification of research data and ideas is not a new phenomenon in scientific communication, nor is it specifically related to open science, rather to the issue of web resources in general. Access to scientific publications has become even faster, cheaper and more accessible for the user. Unfortunately, misleading publishers, and sometimes the researchers themselves, are becoming increasingly inventive. Cooperation with such entities affects (non)evaluation of publications and creates a broader social problem. Not only are publications questionable but the use or misuse of such untrusted sources is also objectionable. Such practices adversely affect the development of society as a whole. Non-experts portray themselves as experts and refer to unverified, misleading scientific publications to justify their attitudes towards current social issues. In communication, including academic writing, we are witnessing a growing lack of knowledge and inability to think critically and an increasingly aggressive justification of the personal aspect as the only acceptable approach. One consequence is also the growing general mistrust in science and, in extreme cases, even deaths due to incorrect decisions by individuals, based on unverified claims and sources that appear to be scientific. Methodology: We have identified tools, platforms, and procedures that help identify and evaluate these practices, and are helpful to researchers and authors in selecting sources and publications in which to publish their findings. Results: The University of Maribor informs students and employees about this issue at lectures, and we have also prepared some research guides in which we try to raise awareness of the user, encourage them to think critically, and at the same time introduce them to the ways and tools that help them detect misleading practices

Moral reasoning in a digital age: blaming artificial intelligence for incorrect high-risk decisions

AbstractThe increasing involvement of Artificial Intelligence (AI) in moral decision situations raises the possibility of users attributing blame to AI-based systems for negative outcomes. In two experimental studies with a total of $$N = 911$$ participants, we explored the attribution of blame and underlying moral reasoning. Participants had to classify mushrooms in pictures as edible or poisonous with support of an AI-based app. Afterwards, participants read a fictitious scenario in which a misclassification due to an erroneous AI recommendation led to the poisoning of a person. In the first study, increased system transparency through explainable AI techniques reduced blaming of AI. A follow-up study showed that attribution of blame to each actor in the scenario depends on their perceived obligation and capacity to prevent such an event. Thus, blaming AI is indirectly associated with mind attribution and blaming oneself is associated with the capability to recognize a wrong classification. We discuss implications for future research on moral cognition in the context of human–AI interaction.

Application of SHAP and Multi-Agent Approach for Short-Term Forecast of Power Consumption of Gas Industry Enterprises

Currently, machine learning methods are widely applied in the power industry to solve various tasks, including short-term power consumption forecasting. However, the lack of interpretability of machine learning methods can lead to their incorrect use, potentially resulting in electrical system instability or equipment failures. This article addresses the task of short-term power consumption forecasting, one of the tasks of enhancing the energy efficiency of gas industry enterprises. In order to reduce the risks of making incorrect decisions based on the results of short-term power consumption forecasts made by machine learning methods, the SHapley Additive exPlanations method was proposed. Additionally, the application of a multi-agent approach for the decomposition of production processes using self-generation agents, energy storage agents, and consumption agents was demonstrated. It can enable the safe operation of critical infrastructure, for instance, adjusting the operation modes of self-generation units and energy-storage systems, optimizing the power consumption schedule, and reducing electricity and power costs. A comparative analysis of various algorithms for constructing decision tree ensembles was conducted to forecast power consumption by gas industry enterprises with different numbers of categorical features. The experiments demonstrated that using the developed method and production process factors reduced the MAE from 105.00 kWh (MAPE of 16.81%), obtained through expert forecasting, to 15.52 kWh (3.44%). Examples were provided of how the use of SHapley Additive exPlanation can increase the safety of the electrical system management of gas industry enterprises by improving experts’ confidence in the results of the information system.

How reliable is your diagnosis?

The effectiveness and justification of every therapy and other clinical decisions is based on a correct diagnosis. However, many types of test results can contain uncertainties that may lead to clinically incorrect decisions. The same applies to the reliability of expert opinions for legal disputes. Adequate communication of diagnostic and expert uncertainties in the examination report or expert opinion is therefore crucial for avoiding incorrect decisions. The liability of the person providing the service is also affected. However, uncertain or even erroneous findings can have various causes, only some of which are known to the examining or commissioning person. This article provides an overview of 3 different types of susceptibility to errors using the example of pathological biopsy and cytology examinations, which can also be transferred to other veterinary disciplines in a similar way. A solid understanding of the possible sources of error as well as adequate communication and discussion of case-specific, limited probabilities in investigation reports and expert opinions make a significant contribution to avoiding incorrect decisions. However, commonly used terms such as "highly probable", "suspected" or "cannot be ruled out" are sometimes interpreted in unclear or divergent ways, which are explained here with recommendations for uniform use. This is intended to enable the person making the decision, if necessary, to initiate further diagnostic tests or gather further evidence in the context of all other available data in order to reduce the risk of error as far as possible.

Preventing Miscarriage of Justice Using Artificial Intelligence in Pakistan

A miscarriage of justice is considered a situation when an incorrect decision has been made in a trial, and a guilty person is sentenced and punished. This is a very common problem in the criminal justice system of Pakistan, which has not been rectified for a very long time. In spite of measures being taken in the quest to eliminate such occurrences, miscarriages of justice are apparent for various causes, including wrong eyewitness identification, tainted confessions and inadequate counsel. The failure of justice is a denial of rights as well as the offenders to justice compartments the system's credibility. In recent years, with the aid of stiff progress in artificial intelligence (AI), it seems probable that miscarriages of justice can be reduced by accurately and efficiently facilitating criminal justice. Hence, this research adopts a doctrinal method to analyze the factual position of the miscarriage of justice system in Pakistan. This work will be very useful in dealing with the problem of miscarriage of justice in Pakistan. Therefore, it can be claimed that by defining the causal factors of wrongful convictions and providing specific recommendations, this study may help build a more efficient and just criminal justice system in Pakistan.

Estimation and modeling of pedestrian dilemma zone at uncontrolled intersections under mixed traffic conditions

Objectives Pedestrian gap acceptance (PGA) theory is the basic concept for pedestrian dilemma zone (PDZ) analysis and modeling and their gap acceptance behavior depends on dilemma behavior also. Uncontrolled intersections are one of the major locations where pedestrians have more dilemma and there is a possibility of an interaction between the pedestrian and vehicle due to the incorrect decision taken by the pedestrian when the vehicle lies within the limits of PDZ. Elimination and modeling of spatial boundaries of pedestrian dilemma stage improve the PGA. Methods The present study is intended to quantify and model the pedestrian dilemma zone (PDZ) boundaries at uncontrolled X-intersections under mixed traffic conditions. Video data were collected from four four-legged uncontrolled intersections in India. Pedestrian and vehicle information was extracted using DataFromSky software and manually from video. The Cumulative Gap Distribution (GCD) and Support Vector Machine (SVM) methods were used to estimate the boundaries of PDZ and developed a binary logistic regression model to estimate the PDZ boundary limits. Results The lower boundary limits of PDZ using GCD and SVM methods are 9.0 m and 6.0, respectively, and the upper boundary limits of PDZ using GCD and SVM methods are 16.5 and 18.5 m, respectively. The GCD method overestimated the lower limit and underestimated the upper limit compared with the SVM method. The binary logistic regression model results confirmed that pedestrian age, gender and crossing speed have a negative correlation and location of pedestrian crossing, vehicle type, and approaching speed have a positive correlation with the boundary limits of PDZ. Conclusions From the present study, it is concluded that SVM better estimated the PDZ boundary limits with the largest margin compared to the GCD method. It is concluded that the boundary limits shift away from the intersection in the case of female and old-age pedestrians compared to male and young-age pedestrians, respectively. The size benefit in the case of 2Ws is the reason for shifting the PDZ boundary limits close to the crosswalk. The lower approaching speeds of the vehicles at uncontrolled intersections are the reason for pedestrians accept the gap at shorter distances.

Auditor Independence and Experience in Fraud Detection: the Crucial Role of Professional Skepticism

This study aims to examine the effect of auditor independence and experience on fraud detection, with professional skepticism as a moderating variable. In today's business world, many companies strive to achieve maximum profits. In pursuit of this goal, some companies engage in fraudulent practices, which have become common among businesspeople and are well-known to the general public. These fraudulent practices occur not only in the private sector but are also frequently found in the government sector, harming many parties due to inaccurate and irrelevant information. Investors are the most affected, as they often make incorrect investment decisions based on misleading information. Agency theory suggests that more independent auditors tend to be more effective in detecting fraud because they are more likely to act in the interest of the capital owners than less independent auditors. This study involves 108 auditors from 19 audit firms in Bali. The structural equation modeling analysis method was employed to measure the strength of the relationship between the dependent and independent variables using Smart PLS. The results show that auditor independence and experience have a positive impact on fraud detection, and professional skepticism strengthens the effect of independence and auditor experience on fraud detection.

Bootstrapped Edge Count Tests for Nonparametric Two-Sample Inference Under Heterogeneity

Nonparametric two-sample testing is a classical problem in inferential statistics. While modern two-sample tests, such as the edge count test and its variants, can handle multivariate and non-Euclidean data, contemporary gargantuan datasets often exhibit heterogeneity due to the presence of latent subpopulations. Direct application of these tests, without regulating for such heterogeneity, may lead to incorrect statistical decisions. We develop a new nonparametric testing procedure that accurately detects differences between the two samples in the presence of unknown heterogeneity in the data generation process. Our framework handles this latent heterogeneity through a composite null that entertains the possibility that the two samples arise from a mixture distribution with identical component distributions but with possibly different mixing weights. In this regime, we study the asymptotic behavior of weighted edge count test statistic and show that it can be effectively recalibrated to detect arbitrary deviations from the composite null. For practical implementation we propose a Bootstrapped Weighted Edge Count test which involves a bootstrap-based calibration procedure that can be easily implemented across a wide range of heterogeneous regimes. A comprehensive simulation study and an application to detecting aberrant user behaviors in online games demonstrates the excellent non-asymptotic performance of the proposed test. Supplementary materials for this article are available online.

Deep contextual reinforcement learning algorithm for scalable power scheduling

This article introduces a deep contextual reinforcement learning (DCRL) optimization algorithm to tackle the NP-hard power scheduling problem. The algorithm is based on a multi-agent simulation environment that decomposes the power scheduling problem into sequential Markov decision processes (MDPs). The simulation environment inherently corrects incorrect decisions and adjusts supply capacities so that the MDPs adhere to the optimization constraints. A deep reinforcement learning (DRL) model is trained on these MDPs to provide optimal solutions. Demonstrating its applicability and effectiveness, the proposed method is evaluated on various test systems with different unit numbers, constraints, and production cost functions. The experimental results show that the proposed method has better performance relative to alternative methods, such as binary alternative moth-flame optimization (BAMFO), binary particle swarm optimization (BPSO), teaching learning-based optimization (TLBO), new binary particle swarm optimization (NBPSO), binary learning particle swarm optimization (BLPSO), quasi-oppositional teaching learning-based algorithm (QOTLBO), binary-real-coded genetic algorithm (BRCGA), hybrid genetic-imperialist competitive algorithm (HGICA), three-stage priority list (TSPL), and hybridized evolutionary algorithm and sequential quadratic programming (HEPSQP). The novelties of the proposed method lie in its adaptability to longer planning horizons and linear dimensionality complexity, rendering it suitable for large-scale power systems.

Let us talk about mistakes.

Unfortunately, errors and mistakes are part of life. Errors and mistakes can harm patients and incur unplanned costs. Errors may arise from various sources, which may be classified as systematic, latent, or active. Intrinsic and extrinsic factors also contribute to incorrect decisions. In addition to cognitive biases, our personality, socialization, personal chronobiology, and way of thinking (heuristic versus analytical) are influencing factors. Factors such as overload from private situations, long commuting times, and the complex environment of information technology must also be considered. The objective of this paper is to define and classify errors and mistakes in radiology, to discuss the influencing factors, and to present strategies for prevention. Hierarchical responsibilities and team "well-being" are also discussed.

Sequential investment decisions for mining projects using compound multiple volatility real options approach

Managers evaluating investment decisions in mining projects have reported using the net present value approach (NPV). However, NPV has the drawback of collapsing variations from uncertainties in future project cash flows into a fixed expected project value today. Ignoring future uncertainties and contingencies can lead managers to make incorrect up-front binary decisions, such as investing in or abandoning the project now. The real options analysis approach (ROA) instead captures variations from uncertainties as volatilities in project value and allows flexibility in investment decisions to be contingent on information as it is revealed. Managers we consulted agreed that ROA is superior to NPV in principle, but too complex to apply in practice. The advanced mathematics and restrictive assumptions required by analytical ROAs make them especially impractical for real-world projects exposed to multiple uncertainties. Furthermore, real-world projects are often multistage and involve valuing a compound option, which is an option on an underlying option, for sequential investment decisions. Extant numerical compound ROAs have been applied to such projects but suffer from various drawbacks. Amongst other issues, they combine variations from multiple uncertainties into a consolidated volatility of project value. This conceals the impact of each source of uncertainty, resulting in inaccurate project valuation and incorrect investment decisions. We present an innovative compound multiple volatility real options approach (C-MVR) to value a multistage project while accommodating separate volatilities of project value arising from multiple uncertainties for making sequential investment decisions. The resultant value is termed the compound enhanced net present value. Implementing C-MVR for a real coal mining project demonstrates how other ROAs can be seen as inaccurate simplifications that produce erroneous investment decisions. C-MVR provides a rigorous and versatile approach that can be applied to many investment decisions across various industries.

AI and XAI second opinion: the danger of false confirmation in human–AI collaboration

Can AI substitute a human physician’s second opinion? Recently the Journal of Medical Ethics published two contrasting views: Kempt and Nagel advocate for using artificial intelligence (AI) for a second...

Unraveling Dental Myths: A Comprehensive Study on Prevalence and Awareness among General Populations

Background: Dental myths are the misconceptions or false beliefs pertaining to oral health, dental care, and dental procedures. These myths can lead to incorrect practices or decisions regarding dental hygiene and treatment. Addressing dental myths proves essential for spreading accurate oral health information and assisting people in making informed decisions regarding their dental care.  Aims and Objectives: The Aim of this study was to assess the general public's understanding of dental myths and so promote awareness among them.  Study Design and Setting: The study was designed to assess the prevalence of dental myths among the general public through set of questionnaire that were converted into Google forms and shared to the participants via social network.  Materials and Methods: A questionnaire with demographic information and myths about dental health was delivered using Google forms. The online survey link was delivered via social media, and participants were asked to share it with their friends and family.  Results and Conclusion: The findings of this study suggest that people generally endorse numerous dental myths, which leads to poor oral health. This could be due to a lack of understanding and awareness of dental health and its importance. Thus Members of this population must be educated to understand the truths and take action to educate them about dental care.

A Virtual Reality Simulation to Examine the Relationship Between Post-Traumatic Stress Symptoms and Decision-Making in First Responders

ABSTRACT First responders (FRs) are continuously exposed to critical incidents, considered traumatic events (TEs). This cumulative exposure increases the risk for post-traumatic stress disorder (PTSD). However, there is no evidence about the relationship between PTSD symptoms and emergency decision-making (EDM). The objective of this study was to examine the EDM of FRs during a virtual reality through the simulation of two emergency scenarios to collect data on the reaction time and the number of incorrect decisions. We also assessed PTSD symptoms, TE, and sociodemographics. The sample included 368 Portuguese FRs, were 295 (80.20%) males and 73 (19.80%) females, with a mean age of 33.96 (SD = 9.38). Considering the probable PTSD diagnosis according to the DSM-5, 85 (23.10%) of the FRs met the criteria. These individuals who meet the criteria exhibited higher EDM scores (M = 19.60, SD = 5.99) compared to those without probable PTSD (M = 17.87, SD = .5.66) (F(1, 360) = 5.32, p = .02, partial η 2 = .015). We found that TEs had a direct effect on EDM, β = −.16, Z = −3.74, p < .001), and the pathway of trauma-PTSD symptoms-decision-making an indirect effect, β = .02, Z = 3.10, p = .002). Individuals exposed to more TEs demonstrated faster and more accurate decision-making in the context of EDM. However, when these individuals developed PTSD symptoms, their decision-making became slower and less accurate. The inclusion of a trauma-informed approach for FRs to prevent individual and job-related consequences is discussed.