Bayesian Network Analysis Research Articles

Commentary: Efficacy and safety of the innovative monoclonal antibodies in adults with generalized myasthenia gravis: a Bayesian network analysis.

Commentary: Efficacy and safety of the innovative monoclonal antibodies in adults with generalized myasthenia gravis: a Bayesian network analysis.

Examining Factors Contributing to Motorcycle Collisions with Left-Turning Vehicles at Urban Intersection Locations

Motorcycle crashes account for a significant proportion of traffic-related fatalities on U.S. roadways. Compared with motor vehicles, motorcycles traveling straight ahead are more susceptible to collisions with left-turning vehicles at intersections (note – in a system where traffic travels on the right-hand side of the road). The limited knowledge of the causes and influences of this specific type of crash deters efforts to improve motorcycle safety and is partly influenced by two issues. First, significant variables are unknown; second, motorcycles comprise a small proportion of vehicles in the traffic stream. This study sought to understand the factors that may contribute to the disproportionate crash risk left-turning vehicles pose for motorcyclists while accounting for the imbalance of vehicle proportions. Data containing motorcycle-motor vehicle and motor vehicle-motor vehicle crashes involving left-turning motor vehicles at intersections in South Florida were collected from 2015 to 2017. The study applied logistic regression on a balanced dataset generated using the random oversampling technique. The proposed model improved the predictive accuracy and enabled the identification of factors contributing to motorcycle crashes with left-turning vehicles. A Bayesian network analysis was also applied to the balanced data to analyze the interrelationship of factors associated with motorcycle crashes with left-turning vehicles. Results indicated that the type of intersection and traffic control, time of day, age of drivers, sex of the motorcyclist, roadway type, and weather were significantly associated with motorcyclists’ susceptibility to collisions with left-turning vehicles. Recognizing these attributes could help devise engineering measures and policies for promoting motorcycle safety.

Sustainable water–ecosystem management using the Bayesian network and variable relationship analysis

ABSTRACT Under the pressures of global climate change and human activities, the carrying capacity of water and soil resources in agricultural lands has decreased, and the traditional models of agricultural development are no longer sustainable. Land degradation, groundwater quality reduction and ecosystem instability are the consequences of agricultural development without considering sustainability indicators. This article aims to investigate the use of variable relationship analysis and Bayesian network methods to analyze and investigate the relationship between irrigation in agriculture and the sustainability of the groundwater ecosystem. Descriptive statistics of agriculture including cultivation pattern, time, precipitation, irrigation, and land slope were analyzed and combined with the simulated characteristics of groundwater including specific yield, hydraulic conductivity and hydrodynamic diffusion coefficients. Five crops of wheat, barley, paddy, alfalfa, and potato were studied to evaluate the effect of plants on the pattern of nitrate release due to irrigation and fertilization in agriculture. The results showed that managing the amount of fertilizer and the volume of irrigation can positively affect the nitrate distribution pattern in the groundwater even in a short period of time.

Utility of Single Items within the Suicidal Behaviors Questionnaire-Revised (SBQ-R): A Bayesian Network Approach and Relative Importance Analysis.

The Suicidal Behaviors Questionnaire-Revised (SBQ-R) comprises four content-specific items widely used to assess the history of suicide-related thoughts, plans or attempts, frequency of suicidal ideation, communication of intent to die by suicide and self-reported likelihood of a suicide attempt. Each item focuses on a specific parameter of the suicide-related thoughts and behaviors construct. Past research has primarily focused on the total score. This study used Bayesian network modeling and relative importance analyses on SBQ-R data from 1160 U.S. and 1141 Chinese undergraduate students. The Bayesian network analysis results showed that Item 1 is suitable for identifying other parameters of the suicide-related thoughts and behaviors construct. The results of the relative importance analysis further highlighted the relevancy of each SBQ-R item score when examining evidence for suicide-related thoughts and behaviors. These findings provided empirical support for using the SBQ-R item scores to understand the performances of different suicide-related behavior parameters. Further, they demonstrated the potential value of examining individual item-level responses to offer clinically meaningful insights. To conclude, the SBQ-R allows for the evaluation of each critical suicide-related thought and behavior parameter and the overall suicide risk.

Fuzzy Bayesian network analysis for quantifying risk reduction rate of hierarchy of controls

In industries dealing with chemical substances, accidents can pose threats not only the workplace but also to neighboring communities. Therefore, it is crucial to assess and manage these risks. In South Korea, conducting risk assessments is mandatory as a preventive measure to avert accidents. However, determining the acceptability of risk levels and estimating the effectiveness of risk-reducing measures can be challenging during these assessments, despite prioritizing existing measures. This study focuses on evaluating the risk reduction rate of the Hierarchy of Controls. To address the challenges associated with estimating the risk reduction rate, especially in the face of unpredictability and uncertainties, we utilized the Fuzzy Bayesian Network (FBN). FBN combines Fuzzy set theory with the Bayesian Network, providing a more reliable approach to risk assessment. Specifically, our study examines quantifying the risk reduction rate of Controls concerning fire and explosion risks, considering the severity of potential accidents. The findings from this research have the potential to enhance the efficiency of decision-making processes in risk assessments, contributing to improved safety measures.

Analysis of the Associations of Measurements of Body Composition and Inflammatory Factors with Cardiovascular Disease and Its Comorbidities in a Community-Based Study.

The associations of cardiovascular disease (CVD) with comorbidities and biochemical and body composition measurements are repeatedly described but have not been studied simultaneously. In the present cross-sectional study, information on CVD and comorbidities [type 2 diabetes mellitus (T2DM), hypertension (HTN), and hyperlipidemia (HDL)], body composition, levels of soluble markers, and other measures were collected from 1079 individuals. When we examined the association of each comorbidity and CVD, controlling for other comorbidities, we observed a clear pattern of the comorbidity-related specific associations with tested covariates. For example, T2DM was significantly associated with GDF-15 levels and the leptin/adiponectin (L/A) ratio independently of two other comorbidities; HTN, similarly, was independently associated with extracellular water (ECW) levels, L/A ratio, and age; and HDL was independently related to age only. CVD showed very strong independent associations with each of the comorbidities, being associated most strongly with HTN (OR = 10.89, 6.46-18.38) but also with HDL (2.49, 1.43-4.33) and T2DM (1.93, 1.12-3.33). An additive Bayesian network analysis suggests that all three comorbidities, particularly HTN, GDF-15 levels, and ECW content, likely have a main role in the risk of CVD development. Other factors, L/A ratio, lymphocyte count, and the systemic inflammation response index, are likely indirectly related to CVD, acting through the comorbidities and ECW.

Bayesian Network Analysis of Industrial Accident Risk for Fishers on Fishing Vessels Less Than 12 m in Length

The Marine Stewardship Council estimates that approximately 38 million people worldwide work in fisheries, and more than one-third of the global population is dependent on aquatic products for protein, highlighting the importance of sustainable fisheries. The FISH Safety Foundation reports that 300 fishers die every day. To achieve sustainable fisheries as a primary industry, the safety of human resources is of the utmost importance. The International Maritime Organization (IMO) and the International Labor Organization (ILO) have made efforts towards this goal, including the issuance of agreements and guidelines to reduce industrial accidents among fishing vessel workers. The criterion for applying these guidelines is usually a total ship length ≥12 m or ≥24 m. However, a vast majority of registered fishing vessels are <12 m long, and the fishers of these vessels suffer substantially more industrial accidents. Thus, we conducted a quantitative analysis of 1093 industrial accidents affecting fishers on fishing vessels <12 m in length, analyzed risk using a Bayesian network analysis (a method proposed by the Formal Safety Assessment of the IMO), and administered a questionnaire survey to a panel of experts in order to ascertain the risk for different types of industrial accidents and propose specific measures to reduce this risk.

Bayesian network analysis of factors influencing type 2 diabetes, coronary heart disease, and their comorbidities

ObjectiveBayesian network (BN) models were developed to explore the specific relationships between influencing factors and type 2 diabetes mellitus (T2DM), coronary heart disease (CAD), and their comorbidities. The aim was to predict disease occurrence and diagnose etiology using these models, thereby informing the development of effective prevention and control strategies for T2DM, CAD, and their comorbidities.MethodEmploying a case-control design, the study compared individuals with T2DM, CAD, and their comorbidities (case group) with healthy counterparts (control group). Univariate and multivariate Logistic regression analyses were conducted to identify disease-influencing factors. The BN structure was learned using the Tabu search algorithm, with parameter estimation achieved through maximum likelihood estimation. The predictive performance of the BN model was assessed using the confusion matrix, and Netica software was utilized for visual prediction and diagnosis.ResultThe study involved 3,824 participants, including 1,175 controls, 1,163 T2DM cases, 982 CAD cases, and 504 comorbidity cases. The BN model unveiled factors directly and indirectly impacting T2DM, such as age, region, education level, and family history (FH). Variables like exercise, LDL-C, TC, fruit, and sweet food intake exhibited direct effects, while smoking, alcohol consumption, occupation, heart rate, HDL-C, meat, and staple food intake had indirect effects. Similarly, for CAD, factors with direct and indirect effects included age, smoking, SBP, exercise, meat, and fruit intake, while sleeping time and heart rate showed direct effects. Regarding T2DM and CAD comorbidities, age, FBG, SBP, fruit, and sweet intake demonstrated both direct and indirect effects, whereas exercise and HDL-C exhibited direct effects, and region, education level, DBP, and TC showed indirect effects.ConclusionThe BN model constructed using the Tabu search algorithm showcased robust predictive performance, reliability, and applicability in forecasting disease probabilities for T2DM, CAD, and their comorbidities. These findings offer valuable insights for enhancing prevention and control strategies and exploring the application of BN in predicting and diagnosing chronic diseases.

Exploring the Link Between Sensory Processing and Psychopathology in a Community Sample of Young Adults: Bayesian Network Analyses

AbstractSensory processing is a fundamental aspect of human experience, and varies significantly between individuals, potentially affecting individual functioning, behaviour, and mental health. This study investigated the associations between sensory processing and psychopathology in a sample of the general population. Participants responded to a general psychiatric screening tool (DSM-5 Self-Rated Level 1 Cross-Cutting Symptom Measure-Adult) and to the Adolescent/Adult Sensory Profile (AASP) questionnaire. The sample comprised 1108 young adults (77.25% females, mean age 22.6). Data were analysed using item response theory and Bayesian network analyses, revealing specific associations between sensory profiles and psychopathological dimensions. Specifically, we detected associations between the low registration sensory profile and the dimensions of psychosis, substance use, and mania. Sensation seeking was associated with mania. Sensory sensitivity was related to depression and mania, while sensation avoiding was inversely correlated with mania. These findings suggest that reduced external sensory awareness may be linked to a predisposition to psychosis, while a multifaceted sensory processing pattern may indicate vulnerability to mood disorders. Assessing sensory processing could yield crucial insights into individual susceptibilities to mental disorders and help identify targeted preventive and therapeutic strategies

Bayesian analysis suggests independent development of sensitization to different fungal allergens

BackgroundFungi are known for their ability to cause allergies, but data on individual sensitization to them are insufficient. The purpose of the study was to carry out a comprehensive analysis of the fungal allergens’ sensitization profile in the Ukrainian population and to determine both population and individual sensitivity to these allergens. MethodsWe utilized a set of ALEX allergy test data from 20,033 inhabitants of 17 regions of Ukraine from 1 to 89 years conducted in 2020–2022. A complex of programs in the Python language was developed and Bayesian network analysis was applied to determine the sensitivity combinations in individual patients to various fungal components. ResultsSensitivity to Alt a 1 dominated and was observed in 79.39% of patients, and 62.17% of them were sensitive solely to Alt a 1. Exclusive sensitivity to Mala s 6 was second in individual patient profiles with a frequency of 4.06%. Combined sensitivity to Alt a 1 – Asp f 3 was third with a share of 3.28%. Pen ch and Cla h extracts stimulated the production of the lowest median sIgE levels. The highest median sIgE levels were for Alt a 1, Mala s 11 and Asp f 6, respectively. Median sIgE levels increased in adults compared to children for all components of Aspergillus fumigatus, as well as for Mala s 5 and Mala s 11. In the rest of the cases, they decreased in adults compared to children. The sensitization rates to fungi in general and specifically to Alternaria were lower in the western parts of Ukraine, especially in the Carpathian region, situated within the Broad-leaved Forest zone. The results of Bayesian modeling revealed that in the case of Alt a 1, the simultaneous absence of sensitivity to Cla h 8, Mala s 11, Mala s 5 and Mala s 6 molecules could condition the presence of sensitization to the major Alternaria allergen with a probability of 92.42%. In all other cases, there was a high probability of absence of sensitivity to particular allergen against the background of absence of sensitivity to other ones, which may indicate the independent development of sensitization to different fungal allergens. ConclusionsSensitivity to Alt a 1 dominated in the studied population with a lower rate in the western regions. The highest median sIgE levels were induced by Alt a 1, Mala s 11 and Asp f 6. Bayesian Analysis suggest a high probability of the independent development of sensitization to different fungal allergens. The idea that sensitization to one allergen may be protective against sensitization to another one(s) requires further clinical study.

The application of Bayesian network analysis in demystifying construction project subcontracting complexities for developing countries

PurposeThis study aimed to address a gap in subcontractor management by focusing on previously unexplored complexities surrounding subcontractor management in developing countries. While past studies concentrated on selection and relationships, this study delved into how effective subcontractor management impacts project success.Design/methodology/approachThis study used the Bayesian Network analysis approach, through a meticulously developed questionnaire survey refined through a piloting stage involving experienced industry professionals. The survey was ultimately distributed among participants based in Accra, Ghana, resulting in a response rate of approximately 63%.FindingsThe research identified diverse components contributing to subcontractor disruptions, highlighted the necessity of a clear regulatory framework, emphasized the impact of financial and leadership assessments on performance, and underscored the crucial role of main contractors in Integrated Project and Labour Cost Management with Subcontractor Oversight and Coordination.Originality/valuePrevious studies have not considered the challenges subcontractors face in projects. This investigation bridges this gap from multiple perspectives, using Bayesian network analysis to enhance subcontractor management, thereby contributing to the successful completion of construction projects.

New insights into the interactions between the gut microbiota and the inflammatory response to ulcerative colitisin a mouse model of dextran sodium sulfate and possible mechanisms of action for treatment with PE&AFWE.

Inflammatory bowel disease (IBD), comprising Crohn's disease (CD) and ulcerative colitis (UC), is a heterogeneous state of chronic intestinal inflammation. Intestinal innate immunity, including innate immune cells, defends against pathogens and excessive entry of gut microbiota, while preserving immune tolerance to resident intestinal microbiota, and may be characterized by its capacity to produce a rapid and nonspecific reaction. The association between microbiota dysbiosis and the pathogenesis of IBD is complex and dynamic. When the intestinal ecosystem is in dysbiosis, the reduced abundance and diversity of intestinal gut microbiota make the host more vulnerable to the attack of exogenous and endogenous pathogenic gut microbiota. The aim of our study was to comprehensively assess the relationship between microbial populations within UC, the signaling pathways of pathogenic gut microbe therein and the inflammatory response, as well as to understand the effects of using PE&AFWE (poppy extract [Papaver nudicaule L.] and Artemisia frigida Willd. extract) on UC modulation. A UC mouse model was established by inducing SPF-grade C57BL/6 mice using dextrose sodium sulfate (DSS). Based on metagenomic sequencing to characterize the gut microbiome, the relationship between gut microbiota dysbiosis and gut microbiota was further studied using random forest and Bayesian network analysis methods, as well as histopathological analysis. (1) We found that the 5 gut microbiota with the highest relative abundance of inflammatory bowel disease UC model gut microbiota were consistent with the top 5 ranked natural bacteria. There were three types of abundance changes in the model groups: increases (Chlamydiae/Proteobacteria and Deferribacteres), decreases (Firmicutes), and no significant changes (Bacteroidetes). The UC model group was significantly different from the control group, with 1308 differentially expressed species with abundance changes greater than or equal to 2-fold. (2) The proportion of the fecal flora in the UC group decreased by 37.5% in the Firmicutes and increased by 14.29% in the proportion of Proteobacteria compared to the control group before treatment. (3) The significantly enriched and increased signaling pathways screened were the 'arachidonic acid metabolic pathway' and the 'phagosomal pathway', which both showed a decreasing trend after drug administration. (4) Based on the causal relationship between different OTUs and the UC model/PE&AFWE administration, screening for directly relevant OTU networks, the UC group was found to directly affect OTU69, followed by a cascade of effects on OTU12, OTU121, OTU93, and OTU7, which may be the pathway of action that initiated the pathological changes in normal mice. (5) We identified a causal relationship between common differentially expressed OTUs and PE&AFWE and UC in the pre- and post-PE&AFWE-treated groups. Thereby, we learned that PE&AFWE can directly affect OTU90, after which it inhibits UC, inhibiting the activity of arachidonic acid metabolic pathway by affecting OTU118, which in turn inhibits the colonization of gut microbiota by OTU93 and OTU7. (6) Histopathological observation and scoring (HS) of the colon showed that there was a significant difference between the model group and the control group (p < 0.001), and that there was a significant recovery in both the sulfasalazine (SASP)and the PE&AFWE groups after the administration of the drug (p < 0.0001). We demonstrated causal effects and inflammatory metabolic pathways in gut microbiota dysbiosis and IBD, with five opportunistic pathogens directly contributing to IBD. PE&AFWE reduced the abundance of proteobacteria in the gut microbiota, and histopathology showed significant improvement.

Predictive model of positive surgical margins after radical prostatectomy based on Bayesian network analysis.

This study aimed to analyze the independent risk factors for marginal positivity after radical prostatectomy and to evaluate the clinical value of the predictive model based on Bayesian network analysis. We retrospectively analyzed the clinical data from 238 patients who had undergone radical prostatectomy, between June 2018 and May 2022. The general clinical data, prostate specific antigen (PSA)-derived indicators, puncture factors, and magnetic resonance imaging (MRI) characteristics were included as predictive variables, and univariate and multivariate analyses were conducted. We established a nomogram model based on the independent predictors and adopted BayesiaLab software to generate tree-augmented naive (TAN) and naive Bayesian models based on 15 predictor variables. Of the 238 patients included in the study, 103 exhibited positive surgical margins. Univariate analysis revealed that PSA density (PSAD) (P = 0.02), Gleason scores for biopsied tissue (P = 0.002) and the ratio of positive biopsy cores (P < 0.001), preoperative T staging (P < 0.001), and location of abnormal signals (P = 0.002) and the side of the abnormal signal (P = 0.009) were all statistically significant. The area under curve (AUC) of the established nomogram model based on independent predictors was 73.80%, the AUC of the naive Bayesian model based on 15 predictors was 82.71%, and the AUC of the TAN Bayesian model was 80.80%. The predictive model of positive resection margin after radical prostatectomy based on Bayesian network demonstrated high accuracy and usefulness.

Strength of spatial correlation between gray matter connectivity and patterns of proto-oncogene and neural network construction gene expression is associated with diffuse glioma survival.

Like other forms of neuropathology, gliomas appear to spread along neural pathways. Accordingly, our group and others have previously shown that brain network connectivity is highly predictive of glioma survival. In this study, we aimed to examine the molecular mechanisms of this relationship via imaging transcriptomics. We retrospectively obtained presurgical, T1-weighted MRI datasets from 669 adult patients, newly diagnosed with diffuse glioma. We measured brain connectivity using gray matter networks and coregistered these data with a transcriptomic brain atlas to determine the spatial co-localization between brain connectivity and expression patterns for 14 proto-oncogenes and 3 neural network construction genes. We found that all 17 genes were significantly co-localized with brain connectivity (p < 0.03, corrected). The strength of co-localization was highly predictive of overall survival in a cross-validated Cox Proportional Hazards model (mean area under the curve, AUC = 0.68 +/- 0.01) and significantly (p < 0.001) more so for a random forest survival model (mean AUC = 0.97 +/- 0.06). Bayesian network analysis demonstrated direct and indirect causal relationships among gene-brain co-localizations and survival. Gene ontology analysis showed that metabolic processes were overexpressed when spatial co-localization between brain connectivity and gene transcription was highest (p < 0.001). Drug-gene interaction analysis identified 84 potential candidate therapies based on our findings. Our findings provide novel insights regarding how gene-brain connectivity interactions may affect glioma survival.

Research on constructing a safety assessment model for the “Environment-Psychology” space in urban villages based on CPTED theory

ABSTRACT This study aimed to develop an “environment-psychological” safety assessment model for urban villages. The objective was to create a comprehensive safety evaluation and identify key influencing factors. To start, establish a spatial environmental safety assessment system for urban villages, drawing on the six principles of Crime Prevention Through Environmental Design (CPTED) theory. Use Analytic Hierarchy Process and Bayesian network analysis for determining weights and scores. The research findings reveal that: 1) The safety of the spatial environment in urban villages is directly induced by factors such as “natural surveillance” and “image maintenance” while being indirectly impacted by factors like “territoriality” and “access control.” Notably, the effects of activity support and target hardening on spatial environmental safety are found to be insubstantial. 2) Z urban village in Xuzhou city has a level IV spatial environmental safety rating. Factors include line-of-sight transparency, environmental hygiene, and road layout. The proposed optimization measures include improving space layout, enhancing surveillance levels, and maintaining a favorable environment for crime prevention. This study aids decision-makers in establishing priority sequences for spatial planning during urban village renewal. The “Environment-Psychology” model enhances the explanatory power of environmental factors on psychological elements and can aid in spatial optimization strategies.

A Bayesian network analysis to examine the effects of HIV stigma processes on self-concept and depressive symptoms among persons living with HIV.

This study examines the relationships between HIV stigma dimensions, self-related mechanisms, and depressive symptoms among persons living with HIV. HIV stigma hinders the well-being of individuals living with HIV, which is linked to depressive symptoms and increased risk of poor clinical outcomes. However, the mechanisms underlying stigma's impact on depression are poorly understood. Psychosocial theories propose that experiencing HIV stigma leads to internalized stigma, impacting self-concept and mental health. Using Bayesian network analysis, we explored associations among HIV stigma processes (experienced, anticipated, internalized, perceived community stigma, and HIV status disclosure) and self-related mechanisms (self-esteem, fear of negative evaluation [FNE], self-blame coping, and social exclusion), and depressive symptoms. Our diverse sample of 204 individuals, primarily men, gay/bisexual, Black, and lower-middle SES, who experienced stigma showed increased anticipated, internalized, and perceived community stigma, FNE, and depressive symptoms. Internalized stigma contributed to self-blame coping and higher depressive symptoms. Anticipated and perceived community stigma and FNE correlated with increased social exclusion. This study investigates potential mechanisms through which HIV stigma may impact depression. Identifying these mechanisms establishes a foundation for future research to inform targeted interventions, enhancing mental health and HIV outcomes among individuals living with HIV, especially from minority backgrounds. Insights gained guide evidence-based interventions to mitigate HIV stigma's detrimental effects, ultimately improving overall well-being and health-related outcomes for people with HIV.

One Month Prediction of Pressure Ulcers in Nursing Home Residents with Bayesian Networks

ObjectivesPressure ulcers (PUs) are a common and avoidable condition among residents of nursing homes, and their consequences are severe. Reliable and simple identification of high-risk residents is a major challenge for prevention. Available tools like the Braden and Norton scale have imperfect predictive performance. The objective is to predict the occurrence of PUs in nursing home residents from electronic health record (EHR) data. DesignLongitudinal retrospective nested case-control study. Setting and ParticipantsEHR database of French nursing homes from 2013 to 2022. MethodsResidents who suffered from PUs were cases and those who did not were controls. For cases, we analyzed the data available in their EHR 1 month before the occurrence of the first PU. For controls, we used available data 1 month before an index date adjusted on the delays of PU onset. We conducted a Bayesian network (BN) analysis, an explainable machine learning method, using 136 input variables of potential medical interest determined with experts. To validate the model, we used scores, features selection, and explainability tools such as Shapley values. ResultsAmong 58,368 residents analyzed, 29% suffered from PUs during their stay. The obtained BN model predicts the occurrence of a PU at a 1-month horizon with a sensitivity of 0.94 (±0.01), a precision of 0.32 (±0.01) and an area under the curve of 0.69 (±0.02). It selects 3 variables: length of stay, delay since last hospitalization, and dependence for transfer. This BN model is suitable and simpler than models provided by other machine learning methods. Conclusions and ImplicationsOne-month prediction for incident PU is possible in nursing home residents from their EHR data. The study paves the way for the development of a predictive tool fueled by routinely collected data that do not require additional work from health care professionals, thereby opening a new preventive strategy for PUs.

Proof of concept for quantitative adverse outcome pathway modeling of chronic toxicity in repeated exposure

Adverse Outcome Pathway (AOP) is a useful tool to glean mode of action (MOE) of a chemical. However, in order to use it for the purpose of risk assessment, an AOP needs to be quantified using in vitro or in vivo data. Majority of quantitative AOPs developed so far, were for single exposure to progressively higher doses. Limited attempts were made to include time in the modeling. Here as a proof-of concept, we developed a hypothetical AOP, and quantified it using a virtual dataset for six repeated exposures using a Bayesian Network Analysis (BN) framework. The virtual data was generated using realistic assumptions. Effects of each exposure were analyzed separately using a static BN model and analyzed in combination using a dynamic BN (DBN) model. Our work shows that the DBN model can be used to calculate the probability of adverse outcome when other upstream KEs were observed earlier. These probabilities can help in identification of early indicators of AO. In addition, we also developed a data driven AOP pruning technique using a lasso-based subset selection, and show that the causal structure of AOP is itself dynamic and changes over time. This proof-of-concept study revealed the possibility for expanding the applicability of the AOP framework to incorporate biological dynamism in toxicity appearance by repeated insults.

An artificial intelligence approach for investigating multifactorial pain-related features of endometriosis.

Endometriosis is a debilitating, chronic disease that is estimated to affect 11% of reproductive-age women. Diagnosis of endometriosis is difficult with diagnostic delays of up to 12 years reported. These delays can negatively impact health and quality of life. Vague, nonspecific symptoms, like pain, with multiple differential diagnoses contribute to the difficulty of diagnosis. By investigating previously imprecise symptoms of pain, we sought to clarify distinct pain symptoms indicative of endometriosis, using an artificial intelligence-based approach. We used data from 473 women undergoing laparoscopy or laparotomy for a variety of surgical indications. Multiple anatomical pain locations were clustered based on the associations across samples to increase the power in the probability calculations. A Bayesian network was developed using pain-related features, subfertility, and diagnoses. Univariable and multivariable analyses were performed by querying the network for the relative risk of a postoperative diagnosis, given the presence of different symptoms. Performance and sensitivity analyses demonstrated the advantages of Bayesian network analysis over traditional statistical techniques. Clustering grouped the 155 anatomical sites of pain into 15 pain locations. After pruning, the final Bayesian network included 18 nodes. The presence of any pain-related feature increased the relative risk of endometriosis (p-value < 0.001). The constellation of chronic pelvic pain, subfertility, and dyspareunia resulted in the greatest increase in the relative risk of endometriosis. The performance and sensitivity analyses demonstrated that the Bayesian network could identify and analyze more significant associations with endometriosis than traditional statistical techniques. Pelvic pain, frequently associated with endometriosis, is a common and vague symptom. Our Bayesian network for the study of pain-related features of endometriosis revealed specific pain locations and pain types that potentially forecast the diagnosis of endometriosis.

Investigating the network structure and causal relationships among bridge symptoms of comorbid depression and anxiety: A Bayesian network analysis.

The network analysis method emphasizes the interaction between individual symptoms to identify shared or bridging symptoms between depression and anxiety to understand comorbidity. However, the network analysis and community detection approach have limitations in identifying causal relationships among symptoms. This study aims to address this gap by applying Bayesian network (BN) analysis to investigate potential causal relationships. Data were collected from a sample of newly enrolled college students. The network structure of depression and anxiety was estimated using the Patient Health Questionnaire-9 (PHQ-9) and the Generalized Anxiety Disorder (GAD-7) Scale measures, respectively. Shared symptoms between depression and anxiety were identified through network analysis and clique percolation (CP) method. The causal relationships among symptoms were estimated using BN. The strongest bridge symptoms, as indicated by bridge strength, include sad mood (PHQ2), motor (PHQ8), suicide (PHQ9), restlessness (GAD5), and irritability (GAD6). These bridge symptoms formed a distinct community using the CP algorithm. Sad mood (PHQ2) played an activating role, influencing other symptoms. Meanwhile, restlessness (GAD5) played a mediating role with reciprocal influences on both anxiety and depression symptoms. Motor (PHQ8), suicide (PHQ9), and irritability (GAD6) assumed recipient positions. BN analysis presents a valuable approach for investigating the complex interplay between symptoms in the context of comorbid depression and anxiety. It identifies two activating symptoms (i.e., sadness and worry), which serve to underscore the fundamental differences between these two disorders. Additionally, psychomotor symptoms and suicidal ideations are recognized as recipient roles, being influenced by other symptoms within the network.