Shifting decision thresholds can undermine the probative value and legal utility of forensic pattern-matching evidence.

Forensic pattern analysis requires examiners to compare the patterns of items such as fingerprints or tool marks to assess whether they have a common source. This article uses signal detection theory to model examiners' reported conclusions (e.g., identification, inconclusive, or exclusion), focusing on the connection between the examiner's decision threshold and the probative value of the forensic evidence. It uses a Bayesian network model to explore how shifts in decision thresholds may affect rates and ratios of true and false convictions in a hypothetical legal system. It demonstrates that small shifts in decision thresholds, which may arise from contextual bias, can dramatically affect the value of forensic pattern-matching evidence and its utility in the legal system.

Bayesian network models identify cooperative GPCR:G protein interactions that contribute to G protein coupling.

Cooperative interactions in protein-protein interfaces demonstrate the interdependency or the linked network-like behavior and their effect on the coupling of proteins. Cooperative interactions also could cause ripple or allosteric effects at a distance in protein-protein interfaces. Although they are critically important in protein-protein interfaces, it is challenging to determine which amino acid pair interactions are cooperative. In this work, we have used Bayesian network modeling, an interpretable machine learning method, combined with molecular dynamics trajectories to identify the residue pairs that show high cooperativity and their allosteric effect in the interface of G protein-coupled receptor (GPCR) complexes with Gα subunits. Our results reveal six GPCR:Gα contacts that are common to the different Gα subtypes and show strong cooperativity in the formation of interface. Both the C terminus helix5 and the core of the G protein are codependent entities and play an important role in GPCR coupling. We show that a promiscuous GPCR coupling to different Gα subtypes, makes all the GPCR:Gα contacts that are specific to each Gα subtype (Gαs, Gαi, and Gαq). This work underscores the potential of data-driven Bayesian network modeling in elucidating the intricate dependencies and selectivity determinants in GPCR:G protein complexes, offering valuable insights into the dynamic nature of these essential cellular signaling components.

Multivariate analysis of a missense variant in CREBRF reveals associations with measures of adiposity in people of Polynesian ancestries.

The minor allele of rs373863828, a missense variant in CREB3 Regulatory Factor, is associated with several cardiometabolic phenotypes in Polynesian peoples. To better understand the variant, we tested the association of rs373863828 with a panel of correlated phenotypes (body mass index [BMI], weight, height, HDL cholesterol, triglycerides, and total cholesterol) using multivariate Bayesian association and network analyses in a Samoa cohort (n = 1632), Aotearoa New Zealand cohort (n = 1419), and combined cohort (n = 2976). An expanded set of phenotypes (adding estimated fat and fat-free mass, abdominal circumference, hip circumference, and abdominal-hip ratio) was tested in the Samoa cohort (n = 1496). In the Samoa cohort, we observed significant associations (log10 Bayes Factor [BF] ≥ 5.0) between rs373863828 and the overall phenotype panel (8.81), weight (8.30), and BMI (6.42). In the Aotearoa New Zealand cohort, we observed suggestive associations (1.5 < log10 BF < 5) between rs373863828 and the overall phenotype panel (4.60), weight (3.27), and BMI (1.80). In the combined cohort, we observed concordant signals with larger log10 BFs. In the Samoa-specific expanded phenotype analyses, we also observed significant associations between rs373863828 and fat mass (5.65), abdominal circumference (5.34), and hip circumference (5.09). Bayesian networks provided evidence for a direct association of rs373863828 with weight and indirect associations with height and BMI.

Clarifying directional dependence among measures of early auditory processing and cognition in schizophrenia: leveraging Gaussian graphical models and Bayesian networks.

BACKGROUND: Research using latent variable models demonstrates that pre-attentive measures of early auditory processing (EAP) and cognition may initiate a cascading effect on daily functioning in schizophrenia. However, such models fail to account for relationships among individual measures of cognition and EAP, thereby limiting their utility. Hence, EAP and cognition may function as complementary and interacting measures of brain function rather than independent stages of information processing. Here, we apply a data-driven approach to identifying directional relationships among neurophysiologic and cognitive variables. METHODS: Using data from the Consortium on the Genetics of Schizophrenia 2, we estimated Gaussian Graphical Models and Bayesian networks to examine undirected and directed connections between measures of EAP, including mismatch negativity and P3a, and cognition in 663 outpatients with schizophrenia and 630 control participants. RESULTS: Chain structures emerged among EAP and attention/vigilance measures in schizophrenia and control groups. Concerning differences between the groups, object memory was an influential variable in schizophrenia upon which other cognitive domains depended, and working memory was an influential variable in controls. CONCLUSIONS: Measures of EAP and attention/vigilance are conditionally independent of other cognitive domains that were used in this study. Findings also revealed additional causal assumptions among measures of cognition that could help guide statistical control and ultimately help identify early-stage targets or surrogate endpoints in schizophrenia.

Evaluation and comparison of efficacy and safety of tirzepatide and semaglutide in patients with type 2 diabetes mellitus: A Bayesian network meta-analysis.

BACKGROUND: As new antidiabetic drugs, tirzepatide (Tir) and semaglutide (Sem) are progressively applied in clinical practice. However, their efficacy and safety profiles have not been comprehensively assessed. Therefore, a Bayesian network meta-analysis was used to evaluate and compare the efficacy and safety of Tir and Sem in treating type 2 diabetes mellitus (T2DM). METHODS: PubMed, EMBASE, Web of Science, Cochrane Library and ClinicalTrials.gov were systematically searched from inception to April 3rd, 2023. Randomized clinical trials (RCTs) comparing the efficacy and safety of Tir and Sem with placebo or the other antidiabetic drugs in treating T2DM were included. The efficacy outcomes included changes in glycated hemoglobin (HbA1c), body weight (BW), body mass index (BMI), and the proportion of participants with HbA1c< 7 %. The safety outcome was the proportion of participants experiencing gastrointestinal adverse events (GIAEs). RESULTS: A total of 38 studies involving 34,166 participants were included. Compared to 1 mg of subcutaneous Sem (Sem SC), 5 mg, 10 mg and 15 mg of Tir demonstrated superior efficacy in reducing HbA1c (mean difference (MD), [95 % CI], -0.22 [-0.40, -0.03] %, -0.42 [-0.60, -0.24] % and -0.53 [-0.71, -0.35] %, respectively) and BW (MD [95 % CI], -1.48 [-2.53, -0.43] kg, -4.00 [-5.05, -2.95] kg and -5.71 [-6.73, -4.68] kg, respectively). Conversely, 7 mg and 14 mg of oral Sem (Sem PO) displayed inferior efficacy in reducing HbA1c (MD [95 % CI], 0.47 [0.26, 0.68] % and 0.35 [0.16, 0.54] %, respectively) and BW (MD [95 % CI], 2.36 [1.24, 3.48] kg and 1.11 [0.10, 2.13] kg). However, 20 mg and 40 mg of Sem PO were non-inferior in reducing HbA1c (MD [95 % CI], 0.13 [-0.29, 0.55] % and 0.01 [-0.38, 0.40] %, respectively) and BW (MD [95 % CI], -0.41 [-2.71, 1.90] kg and -1.32 [-3.58, 0.92] kg). In terms of safety, compared to 1 mg of Sem SC, 5 mg, 10 mg and 15 mg of Tir did not significantly increase the incidence of GIAEs (odd ratio (OR) [95 % CI], 0.70 [0.42, 1.10], 0.87 [0.52, 1.36] and 0.99 [0.60, 1.54], respectively), while 7 mg of Sem PO showed a lower incidence of GIAEs (OR [95 % CI], 0.48 [0.25, 0.83]). Compared to insulin, 0.5 mg of Sem SC, 1 mg of Sem SC, 5 mg of Tir, 10 mg of Tir and 15 mg of Tir displayed better efficacy in lowering HbA1c (MD [95 % CI], -0.40 [-0.63, -0.18] %, -0.69 [-0.90, -0.48] %, -0.91 [-1.10, -0.72] %, -1.11 [-1.30, -0.92] % and -1.22 [-1.41, -1.03] %, respectively) and BW (MD [95 % CI], -5.34[-6.60, -4.09] kg, -6.70 [-7.90,-5.51] kg, -8.18 [-9.27, -7.10] kg, -10.70 [-11.79, -9.61] kg and -12.41 [-13.49,-11.33] kg, respectively). According to the surface under the cumulative ranking curve (SUCRA) value, among all the included interventions, 15 mg of Tir exhibited the most potent effect in reducing HbA1c (99.81 %) and BW (99.98 %), followed by 10 mg of Tir (96.83 % and 95.72 %), 5 mg of Tir (92.88 % and 86.04 %), 1 mg of Sem SC (85.85 % and 74.97 %), 40 mg of Sem PO (83.66 % and 84.31 %), 20 mg of Sem PO (76.98 % and 77.12 %), 300 mg of Can (49.93 % and 60.89 %), insulin (36.38 % and 0.22 %) and 100 mg of Sit (12.28 % and 18.51 %) respectively. Meanwhile, 5 mg, 10 mg, and 15 mg of Tir (48.32 %, 30.96 %, and 21.07 %, respectively), 0.5 mg and 1 mg of Sem SC (33.54 % and 24.77 %, respectively) significantly increased the incidence of GIAEs. CONCLUSION: Both Tir and Sem demonstrated favorable antidiabetic effects and were particularly suitable for T2DM patients who were obese or overweight. Despite a high incidence of GIAEs, their safety profile was deemed acceptable. Tir was the best option among all the included interventions.

Time-varying dynamic Bayesian network learning for an fMRI study of emotion processing.

This article presents a novel method for learning time-varying dynamic Bayesian networks. The proposed method breaks down the dynamic Bayesian network learning problem into a sequence of regression inference problems and tackles each problem using the Markov neighborhood regression technique. Notably, the method demonstrates scalability concerning data dimensionality, accommodates time-varying network structure, and naturally handles multi-subject data. The proposed method exhibits consistency and offers superior performance compared to existing methods in terms of estimation accuracy and computational efficiency, as supported by extensive numerical experiments. To showcase its effectiveness, we apply the proposed method to an fMRI study investigating the effective connectivity among various regions of interest (ROIs) during an emotion-processing task. Our findings reveal the pivotal role of the subcortical-cerebellum in emotion processing.

Integrated regulatory and metabolic networks of the tumor microenvironment for therapeutic target prioritization.

Translation of genomic discovery, such as single-cell sequencing data, to clinical decisions remains a longstanding bottleneck in the field. Meanwhile, computational systems biological models, such as cellular metabolism models and cell signaling pathways, have emerged as powerful approaches to provide efficient predictions in metabolites and gene expression levels, respectively. However, there has been limited research on the integration between these two models. This work develops a methodology for integrating computational models of probabilistic gene regulatory networks with a constraint-based metabolism model. By using probabilistic reasoning with Bayesian Networks, we aim to predict cell-specific changes under different interventions, which are embedded into the constraint-based models of metabolism. Applications to single-cell sequencing data of glioblastoma brain tumors generate predictions about the effects of pharmaceutical interventions on the regulatory network and downstream metabolisms in different cell types from the tumor microenvironment. The model presents possible insights into treatments that could potentially suppress anaerobic metabolism in malignant cells with minimal impact on other cell types' metabolism. The proposed integrated model can guide therapeutic target prioritization, the formulation of combination therapies, and future drug discovery. This model integration framework is also generalizable to other applications, such as different cell types, organisms, and diseases.

Predicting lung cancer survival prognosis based on the conditional survival bayesian network.

Lung cancer is a leading cause of cancer deaths and imposes an enormous economic burden on patients. It is important to develop an accurate risk assessment model to determine the appropriate treatment for patients after an initial lung cancer diagnosis. The Cox proportional hazards model is mainly employed in survival analysis. However, real-world medical data are usually incomplete, posing a great challenge to the application of this model. Commonly used imputation methods cannot achieve sufficient accuracy when data are missing, so we investigated novel methods for the development of clinical prediction models. In this article, we present a novel model for survival prediction in missing scenarios. We collected data from 5,240 patients diagnosed with lung cancer at the Weihai Municipal Hospital, China. Then, we applied a joint model that combined a BN and a Cox model to predict mortality risk in individual patients with lung cancer. The established prognostic model achieved good predictive performance in discrimination and calibration. We showed that combining the BN with the Cox proportional hazards model is highly beneficial and provides a more efficient tool for risk prediction.

Using joint probability density to create most informative unidimensional indices: a new method using pain and psychiatric severity as examples.

BACKGROUND: Dimension reduction methods do not always reduce their underlying indicators to a single composite score. Furthermore, such methods are usually based on optimality criteria that require discarding some information. We suggest, under some conditions, to use the joint probability density function (joint pdf or JPD) of p-dimensional random variable (the p indicators), as an index or a composite score. It is proved that this index is more informative than any alternative composite score. In two examples, we compare the JPD index with some alternatives constructed from traditional methods. METHODS: We develop a probabilistic unsupervised dimension reduction method based on the probability density of multivariate data. We show that the conditional distribution of the variables given JPD is uniform, implying that the JPD is the most informative scalar summary under the most common notions of information. B. We show under some widely plausible conditions, JPD can be used as an index. To use JPD as an index, in addition to having a plausible interpretation, all the random variables should have approximately the same direction(unidirectionality) as the density values (codirectionality). We applied these ideas to two data sets: first, on the 7 Brief Pain Inventory Interference scale (BPI-I) items obtained from 8,889 US Veterans with chronic pain and, second, on a novel measure based on administrative data for 912 US Veterans. To estimate the JPD in both examples, among the available JPD estimation methods, we used its conditional specifications, identified a well-fitted parametric model for each factored conditional (regression) specification, and, by maximizing the corresponding likelihoods, estimated their parameters. Due to the non-uniqueness of conditional specification, the average of all estimated conditional specifications was used as the final estimate. Since a prevalent common use of indices is ranking, we used measures of monotone dependence [e.g., Spearman's rank correlation (rho)] to assess the strength of unidirectionality and co-directionality. Finally, we cross-validate the JPD score against variance-covariance-based scores (factor scores in unidimensional models), and the "person's parameter" estimates of (Generalized) Partial Credit and Graded Response IRT models. We used Pearson Divergence as a measure of information and Shannon's entropy to compare uncertainties (informativeness) in these alternative scores. RESULTS: An unsupervised dimension reduction was developed based on the joint probability density (JPD) of the multi-dimensional data. The JPD, under regularity conditions, may be used as an index. For the well-established Brief Pain Interference Inventory (BPI-I (the short form with 7 Items) and for a new mental health severity index (MoPSI) with 6 indicators, we estimated the JPD scoring. We compared, assuming unidimensionality, factor scores, Person's scores of the Partial Credit model, the Generalized Partial Credit model, and the Graded Response model with JPD scoring. As expected, all scores' rankings in both examples were monotonically dependent with various strengths. Shannon entropy was the smallest for JPD scores. Pearson Divergence of the estimated densities of different indices against uniform distribution was maximum for JPD scoring. CONCLUSIONS: An unsupervised probabilistic dimension reduction is possible. When appropriate, the joint probability density function can be used as the most informative index. Model specification and estimation and steps to implement the scoring were demonstrated. As expected, when the required assumption in factor analysis and IRT models are satisfied, JPD scoring agrees with these established scores. However, when these assumptions are violated, JPD scores preserve all the information in the indicators with minimal assumption.

Estimating and displaying population attributable fractions using the R package: graphPAF.

Here we introduce graphPAF, a comprehensive R package designed for estimation, inference and display of population attributable fractions (PAF) and impact fractions. In addition to allowing inference for standard population attributable fractions and impact fractions, graphPAF facilitates display of attributable fractions over multiple risk factors using fan-plots and nomograms, calculations of attributable fractions for continuous exposures, inference for attributable fractions appropriate for specific risk factor → mediator → outcome pathways (pathway-specific attributable fractions) and Bayesian network-based calculations and inference for joint, sequential and average population attributable fractions in multi-risk factor scenarios. This article can be used as both a guide to the theory of attributable fraction estimation and a tutorial regarding how to use graphPAF in practical examples.

Quantitative association between lead exposure and amyotrophic lateral sclerosis: a Bayesian network-based predictive study.

BACKGROUND: Environmental lead (Pb) exposure have been suggested as a causative factor for amyotrophic lateral sclerosis (ALS). However, the role of Pb content of human body in ALS outcomes has not been quantified clearly. The purpose of this study was to apply Bayesian networks to forecast the risk of Pb exposure on the disease occurrence. METHODS: We retrospectively collected medical records of ALS inpatients who underwent blood Pb testing, while matched controlled inpatients on age, gender, hospital ward and admission time according to the radio of 1:9. Tree Augmented Naïve Bayes (TAN), a semi-naïve Bayes classifier, was established to predict probability of ALS or controls with risk factors. RESULTS: A total of 140 inpatients were included in this study. The whole blood Pb levels of ALS patients (57.00 µg/L) were more than twice as high as the controls (27.71 µg/L). Using the blood Pb concentrations to calculate probability of ALS, TAN produced the total coincidence rate of 90.00%. The specificity, sensitivity of Pb for ALS prediction was 0.79, or 0.74, respectively. CONCLUSION: Therefore, these results provided quantitative evidence that Pb exposure may contribute to the development of ALS. Bayesian networks may be used to predict the ALS early onset with blood Pb levels.

Machine learning and Bayesian network analyses identifies associations with insomnia in a national sample of 31,285 treatment-seeking college students.

BACKGROUND: A better understanding of the relationships between insomnia and anxiety, mood, eating, and alcohol-use disorders is needed given its prevalence among young adults. Supervised machine learning provides the ability to evaluate which mental disorder is most associated with heightened insomnia among U.S. college students. Combined with Bayesian network analysis, probable directional relationships between insomnia and interacting symptoms may be illuminated. METHODS: The current exploratory analyses utilized a national sample of college students across 26 U.S. colleges and universities collected during population-level screening before entering a randomized controlled trial. We used a 4-step statistical approach: (1) at the disorder level, an elastic net regularization model examined the relative importance of the association between insomnia and 7 mental disorders (major depressive disorder, generalized anxiety disorder, social anxiety disorder, panic disorder, post-traumatic stress disorder, anorexia nervosa, and alcohol use disorder); (2) This model was evaluated within a hold-out sample. (3) at the symptom level, a completed partially directed acyclic graph (CPDAG) was computed via a Bayesian hill-climbing algorithm to estimate potential directionality among insomnia and its most associated disorder [based on SHAP (SHapley Additive exPlanations) values)]; (4) the CPDAG was then tested for generalizability by assessing (in)equality within a hold-out sample using structural hamming distance (SHD). RESULTS: Of 31,285 participants, 20,597 were women (65.8%); mean (standard deviation) age was 22.96 (4.52) years. The elastic net model demonstrated clinical significance in predicting insomnia severity in the training sample [R2 = .44 (.01); RMSE = 5.00 (0.08)], with comparable performance in the hold-out sample (R2 = .33; RMSE = 5.47). SHAP values indicated that the presence of any mental disorder was associated with higher insomnia scores, with major depressive disorder as the most important disorder associated with heightened insomnia (mean |SHAP|= 3.18). The training CPDAG and hold-out CPDAG (SHD = 7) suggested depression symptoms presupposed insomnia with depressed mood, fatigue, and self-esteem as key parent nodes. CONCLUSION: These findings provide insights into the associations between insomnia and mental disorders among college students and warrant further investigation into the potential direction of causality between insomnia and depression. TRIAL REGISTRATION: Trial was registered on the National Institute of Health RePORTER website (R01MH115128 || 23/08/2018).

Association between interpregnancy interval and risk of autism spectrum disorder: a systematic review and Bayesian network meta-analysis.

Although the risk of autism spectrum disorder (ASD) has been reported to be associated with interpregnancy intervals (IPIs), their association remains debatable due to inconsistent findings in existing studies. Therefore, the present study aimed to explore their association. PubMed, Embase, Web of Science, and the Cochrane Library were systematically retrieved up to May 25, 2022. An updated search was performed on May 25, 2023, to encompass recent studies. The quality of the included studies was assessed using the Newcastle-Ottawa Scale (NOS). Our primary outcome measures were expressed as adjusted odds ratios (ORs). Given various control measures for IPI and diverse IPI thresholds in the included studies, a Bayesian network meta-analysis was performed. Eight studies were included, involving 24,865 children with ASD and 2,890,289 children without ASD. Compared to an IPI of 24 to 35 months, various IPIs were significantly associated with a higher risk of ASD (IPIs < 6 months: OR = 1.63, 95% CI 1.53-1.74, n = 5; IPIs of 6-11 months: OR = 1.50, 95% CI 1.42-1.59, n = 4; IPIs of 12-23 months: OR = 1.19, 95% CI 1.12-1.23, n = 10; IPIs of 36-59 months: OR = 0.96, 95% CI 0.94-0.99, n = 2; IPIs of 60-119 months: OR = 1.15, 95% CI 1.10-1.20, n = 4; IPIs > 120 months: OR = 1.57, 95% CI 1.43-1.72, n = 4). After adjusting confounding variables, our analysis delineated a U-shaped restricted cubic spline curve, underscoring that both substantially short (< 24 months) and excessively long IPIs (> 72 months) are significantly correlated with an increased risk of ASD.  Conclusion: Our analysis indicates that both shorter and longer IPIs might predispose children to a higher risk of ASD. Optimal childbearing health and neurodevelopmental outcomes appear to be associated with a moderate IPI, specifically between 36 and 60 months. What is Known: • An association between autism spectrum disorder (ASD) and interpregnancy intervals (IPIs) has been speculated in some reports. • This association remains debatable due to inconsistent findings in available studies. What is New: • Our study delineated a U-shaped restricted cubic spline curve, suggesting that both shorter and longer IPIs predispose children to a higher risk of ASD. • Optimal childbearing health and neurodevelopmental outcomes appear to be associated with a moderate IPI, specifically between 36 and 60 months.

Enhancing understanding of healthy aging based on time-varying dependencies among multidimensional health, life satisfaction, and health behaviors of older adults aged 60 years and over.

BACKGROUND: Healthy aging is a process of not only achieving good health but also increasing the life satisfaction of older adults aged 60 years and over, in which health behaviors play an important role. There is a lack of research on the time-varying dependencies between health, life satisfaction, and health behaviors, impeding a deeper understanding of healthy aging. PURPOSE: To develop an integrated framework for modeling the interrelationships among the components of healthy aging between multiple time slices. METHODS: Based on the Chinese Longitudinal Healthy Living Survey (CLHLS) data in the three waves of 2011/2012, 2014, and 2017/2018, Bayesian network and dynamic Bayesian network are jointly employed to study the relationships among the components of healthy aging within one time slice, as well as to explore the time-varying dependencies among the components between time slices. RESULTS: The results of structure learning reveal the direction of effects between different dimensions of health, with mental health and social health affecting physical health and self-rated health affecting both physical and mental health. In addition, health behaviors are found to affect mental health and social health, while self-rated health can influence life satisfaction. The parameters learned from the data show the magnitude and direction of concurrent effects, one-period lagged effects and two-period lagged effects between the factors, which find that the time-varying dependencies vary but are generally positive, long-term, and accumulative over time. In addition, the results of autoregressive effects show the positive predictive effects of health and life satisfaction. CONCLUSIONS: It confirms the influence pathway from health behaviors to multidimensional health to life satisfaction, and the time-varying dependencies among the components of healthy aging, which facilitates a deeper understanding of healthy aging. Combining the results of autoregressive effects and descriptive statistics, it further indicates that healthy aging is a comprehensive result arising from interactions of multiple factors. Policymakers should guide older adults aged 60 years and over to adopt healthier behaviors and ensure the long-term sustainability and continuity of policies.

A data-driven approach to identify risk profiles and protective drugs in COVID-19.

As the COVID-19 pandemic is spreading around the world, increasing evidence highlights the role of cardiometabolic risk factors in determining the susceptibility to the disease. The fragmented data collected during the initial emergency limited the possibility of investigating the effect of highly correlated covariates and of modeling the interplay between risk factors and medication. The present study is based on comprehensive monitoring of 576 COVID-19 patients. Different statistical approaches were applied to gain a comprehensive insight in terms of both the identification of risk factors and the analysis of dependency structure among clinical and demographic characteristics. The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) virus enters host cells by binding to the angiotensin-converting enzyme 2 (ACE2), but whether or not renin-angiotensin-aldosterone system inhibitors (RAASi) would be beneficial to COVID-19 cases remains controversial. The survival tree approach was applied to define a multilayer risk stratification and better profile patient survival with respect to drug regimens, showing a significant protective effect of RAASi with a reduced risk of in-hospital death. Bayesian networks were estimated, to uncover complex interrelationships and confounding effects. The results confirmed the role of RAASi in reducing the risk of death in COVID-19 patients. De novo treatment with RAASi in patients hospitalized with COVID-19 should be prospectively investigated in a randomized controlled trial to ascertain the extent of risk reduction for in-hospital death in COVID-19.

A copula-based method of risk prediction for autonomous underwater gliders in dynamic environments.

Autonomous underwater gliders (AUGs) are effective platforms for oceanic research and environmental monitoring. However, complex underwater environments with uncertainties could pose the risk of vehicle loss during their missions. It is therefore essential to conduct risk prediction to assist decision making for safer operations. The main limitation of current studies for AUGs is the lack of a tailored method for risk analysis considering both dynamic environments and potential functional failures of the vehicle. Hence, this study proposed a copula-based approach for evaluating the risk of AUG loss in dynamic underwater environments. The developed copula Bayesian network (CBN) integrated copula functions into a traditional Bayesian belief network (BBN), aiming to handle nonlinear dependencies among environmental variables and inherent technical failures. Specifically, potential risk factors with causal effects were captured using the BBN. A Gaussian copula was then employed to measure correlated dependencies among identified risk factors. Furthermore, the dependence analysis and CBN inference were performed to assess the risk level of vehicle loss given various environmental observations. The effectiveness of the proposed method was demonstrated in a case study, which considered deploying a Slocum G1 Glider in a real water region. Risk mitigation measures were provided based on key findings. This study potentially contributes a tailored tool of risk prediction for AUGs in dynamic environments, which can enhance the safety performance of AUGs and assist in risk mitigation for decision makers.

Risk assessment of infectious disease epidemic based on fuzzy Bayesian network.

The prevention and control of infectious disease epidemic (IDE) is an important task for every country and region. Risk assessment is significant for the prevention and control of IDE. Fuzzy Bayesian networks (FBN) can capture complex causality and uncertainty. The study developed a novel FBN model, integrating grounded theory, interpretive structural model, and expert weight determination algorithm for the risk assessment of IDE. The algorithm is proposed by the authors for expert weighting in fuzzy environment. The proposed FBN model comprehensively takes into account the risk factors and the interaction among them, and quantifies the uncertainty of IDE risk assessment, so as to make the assessment results more reliable. Taking the epidemic situation of COVID-19 in Wuhan as a case, the application of the proposed model is illustrated. And sensitivity analysis is performed to identify the important risk factors of IDE. Moreover, the effectiveness of the model is checked by the three-criterion-based quantitative validation method including variation connection, consistent effect, and cumulative limitation. Results show that the probability of the outbreak of COVID-19 in Wuhan is as high as 82.26%, which is well-matched with the actual situation. "Information transfer mechanism," "coordination and cooperation among various personnel," "population flow," and "ability of quarantine" are key risk factors. The constructed model meets the above three criteria. The application potential and effectiveness of the developed FBN model are demonstrated. The study provides decision support for preventing and controlling IDE.

An international relations quantitative evaluation model (IRQEM) based on an integrated method.

International relations (IR) have great uncertainty and instability. Bad IR or conflicts will bring about heavy economic losses and widespread social unrest domestically and internationally. The accurate prediction for bilateral relations can support decision making for timely responses, which will be used to find ways to maintain development in the complex international situation. An international relations quantitative evaluation model (IRQEM) is proposed by integrating a variety of research models and methods like the interpretative structural modeling method (ISM), Bayesian network (BN) model, the Bayesian search (BS), and the expectation-maximization (EM) algorithm, which is novel for IR research. Factors from several different fields are identified as BN nodes. Each node is assigned different state values. The hierarchical structure of these BN nodes is obtained by ISM. The data collection of 192 cases is used to construct the BN model by GeNIe 4.0. The IRQEM can be used to evaluate the influence of emergencies on IR. The critical factors of IR also can be explored through our proposed model. Results show that the prediction of bilateral relations under emergencies can be realized by updating the indicator set when emergencies occur. The capability to anticipate threats of IR changes is advanced by optimizing the reporting information of IR forecasting through a combination of qualitative and quantitative methods, charts, and texts. Relevant analysis results can provide support for national security decision making.

How do navy escorts influence piracy risk in East Africa? A Bayesian network approach.

Navy escorts are considered crucial in countering illegal piracy attacks. In this paper, a novel approach is developed to investigate the effect of navy escorts on piracy incidents by models based on two enhanced Tree-Augmented Naïve (TAN) Bayesian networks. This approach offers a systematic investigation into the various factors that influence pirate activities, and helps to identify changes in piracy attack behaviors when confronted by navy escorts and assess the effectiveness of anti-piracy measures. An empirical study is conducted utilizing a unique data set compiled from multiple sources from 2000 to 2019. The empirical evidence shows that there was a gradual reduction in the incidence of piracy attacks in East Africa following the implementation of navy escorts in 2009, but with a surge in 2010 and 2011. The data set is, thus, divided into two time periods at the point of 2009 to facilitate a robust and comprehensive analysis, resulting in the development of two TAN models. Meanwhile, the geographical distribution of pirate attacks has shifted from international waters to port areas and territorial waters. We argue that the surge and geographical shift could be attributed to the calculating behavior of pirates when they encounter external pressures. Finally, a Shapely approach is introduced to evaluate the potential effectiveness of the implemented risk management strategies from a Game Theory perspective. This study offers new insights into the promotion of navy escorts and contributes to the development of a framework for assessing piracy risks in uncertain and dynamic anti-piracy environments.

Enhancing maritime transportation security: A data-driven Bayesian network analysis of terrorist attack risks.

Maritime terrorist accidents have a significant low-frequency-high-consequence feature and, thus, require new research to address the associated inherent uncertainty and the scarce literature in the field. This article aims to develop a novel method for maritime security risk analysis. It employs real accident data from maritime terrorist attacks over the past two decades to train a data-driven Bayesian network (DDBN) model. The findings help pinpoint key contributing factors, scrutinize their interdependencies, ascertain the probability of different terrorist scenarios, and describe their impact on different manifestations of maritime terrorism. The established DDBN model undergoes a thorough verification and validation process employing various techniques, such as sensitivity, metrics, and comparative analyses. Additionally, it is tested against recent real-world cases to demonstrate its effectiveness in both retrospective and prospective risk propagation, encompassing both diagnostic and predictive capabilities. These findings provide valuable insights for the various stakeholders, including companies and government bodies, fostering comprehension of maritime terrorism and potentially fortifying preventive measures and emergency management.