Directed Acyclic Graph Research Articles

Network analysis of internet gaming disorder, problematic social media use, problematic smartphone use, psychological distress, and meaning in life among adolescents

Background Few studies have examined the connections between psychological distress, meaning in life, internet gaming disorder (IGD), problematic smartphone use (PSU), and problematic social media use (PSMU). Methods The central and bridging nodes of IGD, PSMU, and PSU symptoms were investigated using network analysis in China among 742 adolescents ( Mage = 15.39, SD = 1.68, range = 12–19; 53.23% female). The relationships between IGD, PSMU, and PSU and associated factors were investigated using a Directed Acyclic Graphs method. Results The results suggested that the central symptoms were withdrawal in IGD, mood modification in PSU, and tolerance in PSMU. Mood modification in IGD, mood modification in PSU, withdrawal in PSMU, and functional impairment in PSMU were the bridge symptoms. Males were more likely to experience symptoms of IGD than females, while females were more likely to need meaning than males. Stress is the root factor, while depression, meaning confusion, meaning anxiety, and meaning avoidance were closely associated with IGD, PSMU, and PSU. Conclusions The current research improved the understanding of IGD, PSMU, and PSU symptoms in teenagers and demonstrated the potential of dynamic systems perspectives on problematic use behaviors and stress/meaning-focused interventions.

Distributed Authentication in a Multi-Zone Direct Acyclic Graph Blockchain for IoT Environment

This research paper presents an indepth examination of the security aspects of the Multiple Zone Direct Acyclic Graph Blockchain (MZ-DAG Blockchain) framework. The MZ-DAG Blockchain features a security layer that implements a non-clonable physical function-based validation mechanism for the authentication of multiple certificates within the blockchain. To enhance the security of this layer, this study proposes the integration of a lightweight intrusion detection system specifically designed for the MZ-DAG Blockchain. This work is a contribution to the ongoing efforts to secure and streamline the implementation of blockchain networks in resourceconstrained environments.

Computational Graphs for Matrix Functions

Many numerical methods for evaluating matrix functions can be naturally viewed as computational graphs. Rephrasing these methods as directed acyclic graphs (DAGs) is a particularly effective approach to study existing techniques, improve them, and eventually derive new ones. The accuracy of these matrix techniques can be characterized by the accuracy of their scalar counterparts, thus designing algorithms for matrix functions can be regarded as a scalar-valued optimization problem. The derivatives needed during the optimization can be calculated automatically by exploiting the structure of the DAG in a fashion analogous to backpropagation. This article describes GraphMatFun.jl , a Julia package that offers the means to generate and manipulate computational graphs, optimize their coefficients, and generate Julia, MATLAB, and C code to evaluate them efficiently at a matrix argument. The software also provides tools to estimate the accuracy of a graph-based algorithm and thus obtain numerically reliable methods. For the exponential, for example, using a particular form (degree-optimal) of polynomials produces implementations that in many cases are cheaper, in terms of computational cost, than the Padé-based techniques typically used in mathematical software. The optimized graphs and the corresponding generated code are available online.

Factors associated with successful reintegration for male offenders: a systematic narrative review with implicit causal model

ObjectivesThis systematic review explored factors associated with successful reintegration into the community for male offenders and investigated which factors may be causally related to reintegration.MethodsDatabase searches were conducted in November 2021; a narrative synthesis and associated causal model with directed acyclic graph (DAG) was used to analyse the factors of reintegration.ResultsThirty-four studies met the inclusion criteria. Risk-Need-Responsivity–based interventions had the strongest evidence for reducing post-release offending. Fourteen good-quality studies met the inclusion criteria. The DAG shows six exposure variables (prison visits, witnessing victimisation, recovery perception, risk assessment, in-prison treatment, and pre-prison health) which link to several post-release outcomes (criminal justice outcomes, drug use, mental health, housing, and reintegration barriers) and confounding variables (demographics, offending history, prior reintegration barriers, substance misuse and attitudes).ConclusionsThe review identified factors that may be causally related to reintegration for male offenders and warrant further empirical investigation.

Deep neural networks with knockoff features identify nonlinear causal relations and estimate effect sizes in complex biological systems.

Learning the causal structure helps identify risk factors, disease mechanisms, and candidate therapeutics for complex diseases. However, although complex biological systems are characterized by nonlinear associations, existing bioinformatic methods of causal inference cannot identify the nonlinear relationships and estimate their effect size. To overcome these limitations, we developed the first computational method that explicitly learns nonlinear causal relations and estimates the effect size using a deep neural network approach coupled with the knockoff framework, named causal directed acyclic graphs using deep learning variable selection (DAG-deepVASE). Using simulation data of diverse scenarios and identifying known and novel causal relations in molecular and clinical data of various diseases, we demonstrated that DAG-deepVASE consistently outperforms existing methods in identifying true and known causal relations. In the analyses, we also illustrate how identifying nonlinear causal relations and estimating their effect size help understand the complex disease pathobiology, which is not possible using other methods. With these advantages, the application of DAG-deepVASE can help identify driver genes and therapeutic agents in biomedical studies and clinical trials.

Blockchain for achieving accountable outsourcing computations in edge computing

Edge Computing as a paradigm, provides services of outsourcing computations to a large number of end users. Since edge nodes are trustless, the integration of sampling-based replication calculation and the blockchain is used to verify the correctness of computation results in a trustless environment. However, the blockchain with the nature of decentralization, is confronted with some problems of high resource consumption, such that the verification with computational overhead cannot be directly deployed on the blockchain. Thus, we propose an accountable verification scheme based on an off-chain block. The off-chain block meets some requirements of Edge Computing, i.e., reduced latency of services, and edge nodes with heterogeneous resources. The off-chain block tries to address two challenges for reliable outsourcing computations: (i) how to generate the block efficiently and securely, and (ii) how to achieve accountable verification. In detail, the block is based on a Directed Acyclic Graph, in which the transactions of computation results and verification reports are updated in full decentralization. The hash of the block is recorded on the blockchain. Moreover, the integration of off-chain verification and on-chain arbitration provides reliable verification. A trust evaluation model achieves accountability for edge nodes. Besides, we conducted the security analysis based on some performance properties. Finally, the Raspberry Pis are leveraged to simulate lightweight edge nodes to prove the scalability of our outsourcing computations. A consortium blockchain with groups is also implemented to reveal the efficiency of blockchain updates of the proposed scheme.

DRL-Based Dependent Task Offloading Strategies with Multi-Server Collaboration in Multi-Access Edge Computing

Many applications in Multi-access Edge Computing (MEC) consist of interdependent tasks where the output of some tasks is the input of others. Most of the existing research on computational offloading does not consider the dependency of the task and uses convex relaxation or heuristic algorithms to solve the offloading problem, which lacks adaptability and is not suitable for computational offloading in the dynamic environment of fast fading channels. Therefore, in this paper, the optimization problem is modeled as a Markov Decision Process (MDP) in multi-user and multi-server MEC environments, and the dependent tasks are represented by Directed Acyclic Graph (DAG). Combined with the Soft Actor–Critic (SAC) algorithm in Deep Reinforcement Learning (DRL) theory, an intelligent task offloading scheme is proposed. Under the condition of resource constraint, each task can be offloaded to the corresponding MEC server through centralized control, which greatly reduces the service delay and terminal energy consumption. The experimental results show that the algorithm converges quickly and stably, and its optimization effect is better than existing methods, which verifies the effectiveness of the algorithm.

Investigating confounding in network-based test-negative design influenza vaccine effectiveness studies-Experience from the DRIVE project.

Establishing a large study network to conduct influenza vaccine effectiveness (IVE) studies while collecting appropriate variables to account for potential bias is important; the most relevant variables should be prioritized. We explored the impact of potential confounders on IVE in the DRIVE multi-country network of sites conducting test-negative design (TND) studies. We constructed a directed acyclic graph (DAG) to map the relationship between influenza vaccination, medically attended influenza infection, confounders, and other variables. Additionally, we used the Development of Robust and Innovative Vaccines Effectiveness (DRIVE) data from the 2018/2019 and 2019/2020 seasons to explore the effect of covariate adjustment on IVE estimates. The reference model was adjusted for age, sex, calendar time, and season. The covariates studied were presence of at least one, two, or three chronic diseases; presence of six specific chronic diseases; and prior healthcare use. Analyses were conducted by site and subsequently pooled. The following variables were included in the DAG: age, sex, time within influenza season and year, health status and comorbidities, study site, health-care-seeking behavior, contact patterns and social precautionary behavior, socioeconomic status, and pre-existing immunity. Across all age groups and settings, only adjustment for lung disease in older adults in the primary care setting resulted in a relative change of the IVE point estimate >10%. Our study supports a parsimonious approach to confounder adjustment in TND studies, limited to adjusting for age, sex, and calendar time. Practical implications are that necessitating fewer variables lowers the threshold for enrollment of sites in IVE studies and simplifies the pooling of data from different IVE studies or study networks.

Chain graph reduction into power chain graphs

Reduction of graphs is a class of procedures used to decrease the dimensionality of a given graph in which the properties of the reduced graph are to be induced from the properties of the larger original graph. This paper introduces both a new method for reducing chain graphs to simpler directed acyclic graphs (DAGs), that we call power chain graphs (PCG), as well as a procedure for structure learning of this new type of graph from correlational data of a Gaussian graphical model. A definition for PCGs is given, directly followed by the reduction method. The structure learning procedure is a two-step approach: first, the correlation matrix is used to cluster the variables; and then, the averaged correlation matrix is used to discover the DAGs using the PC-stable algorithm. The results of simulations are provided to illustrate the theoretical proposal, which demonstrate initial evidence for the validity of our procedure to recover the structure of power chain graphs. The paper ends with a discussion regarding suggestions for future studies as well as some practical implications.

On the upward book thickness problem: Combinatorial and complexity results

Among the vast literature concerning graph drawing and graph theory, linear layouts of graphs have been the subject of intense research over the years, both from a combinatorial and from an algorithmic perspective. In particular, upward book embeddings of directed acyclic graphs (DAGs) form a popular class of linear layouts with notable applications, and the upward book thickness of a DAG is the minimum number of pages required by any of its upward book embeddings.A long-standing conjecture by Heath, Pemmaraju, and Trenk (1999) states that the upward book thickness of outerplanar DAGs is bounded above by a constant. In this paper, we show that the conjecture holds for subfamilies of upward outerplanar graphs, namely those whose underlying graph is an internally-triangulated outerpath or a cactus, and those whose biconnected components are st-outerplanar graphs.On the complexity side, it is known that deciding whether a graph has upward book thickness k is NP-hard for any fixed k≥3. We show that the problem, for any k≥5, remains NP-hard for graphs whose domination number is O(k), but it is fixed-parameter tractable (FPT) in the vertex cover number.

DIFFERENTIAL ROLES OF COVID-19-RELATED STRESSORS IN MENTAL HEALTH PROBLEMS: A NETWORK APPROACH

Abstract COVID-19-related stress is heterogeneous and associated with increased mental health conditions in older adults. This study is to investigate relationships between different stressors and how different stressors may increase risks for mental health conditions through a network approach. A telephone survey was conducted among 4,921 older adults (age≥60) from April to June 2022 during the biggest community outbreak of COVID-19 in Hong Kong. The validated 8-item COVID-19-Related Stress Scale (CSS-old) (Cronbach’s α: 0.91) was used to investigate the different stressor for older people in Hong Hong. Respondents were screened for depression using the Patient Health Questionnaire-2 (PHQ-2), anxiety using the Generalized Anxiety Disorder 2-item (GAD-2), and stressors with the CSS-old, 4708 responded to all questions. A regularized partial correlation network via graphical LASSO procedure was computed to analyze the relationship between 8 stressors; a directed acyclic graph (DAG) via a Bayesian hill-climbing algorithm was generated from CSS-old and comorbidity network with PHQ-2 and GAD-2 items. Network analyses identified CSS-old item 6 (families or friends infected), item 3 (daily life interrupted), item 5 (fear of infection affecting the family), and item 8 (worry for community’s health) as the core stressors. DAG analysis found a key triggering role for item 1 (suspension of community services), and the activation of the mental health problems occurred through item 1, which bridged the COVID-19-related stress and mental health problems. These findings suggested that providing support for families with COVID-19 patients and alternative services during community service suspension may reduce mental health problems risks.

Multiple Objective Fairness Scheduling Optimization Algorithms Based on Multiple DAGs in Heterogeneous Edge Computing

The rapid development of edge computing has promoted the growing demand of applications. Quality of service (QoS) must be improved because this index involves issues such as unfairness and short Directed Acyclic Graph (DAG) schedule length. We propose a new algorithm named Multiple DAGs Depth Fairness Task Scheduling (MDDF) in this study to solve the multi-DAG task unfairness problem effectively, the algorithm on the basis of the measured depth of the task in the DAG, improves the fairness of multiple DAG, enhance the user QoS and obtain a fast response. The proposed algorithm is then compared with four common heuristic scheduling methods to verify its effectiveness. We propose another algorithm called Fast Multi-DAG Depth Fairness Task Scheduling (FMDDF) with high average slowdown to reduce the schedule length of short DAG and accelerate the response time. Experimental results show that FMDDF can improve scheduling and shorten the schedule length of short DAG by about 5% and MDDF can enhance fairness by about 2% while reducing the short DAG schedule length compared with other algorithms.

Adaptive Distributed Parallel Training Method for a Deep Learning Model Based on Dynamic Critical Paths of DAG

AI provides a new method for massive simulated data calculations in molecular dynamics, materials, and other scientific computing fields. However, the complex structures and large-scale parameters of neural network models make them difficult to develop and train. The automatic parallel technology based on graph algorithms is one of the most promising methods to solve this problem, despite the low efficiency in the design, implementation, and execution of distributed parallel policies for large-scale neural network models. In this paper, we propose an adaptive distributed parallel training method based on the dynamic generation of critical DAG (directed acyclic graph) paths, called FD-DPS, to solve this efficiency problem. Firstly, the proposed model splits operators with the dimension of the tensor, which can expand the space available for model parallelism. Secondly, a dynamic critical path generation method is employed to determine node priority changes in the DAG of the neural network models. Finally, the model implements the optimal scheduling of critical paths based on the priority of the nodes, thereby improving the performance of parallel strategies. Our experiments show that FD-DPS can achieve 12.76% and 11.78% faster training on PnasNet_mobile and ResNet_200 models, respectively, compared with the MP-DPS and Fast methods.

The Covering Threshold of a Directed Acyclic Graph by Directed Acyclic Subgraphs

Let $H$ be a directed acyclic graph (dag) that is not a rooted star. It is known that there are constants $c=c(H)$ and $C=C(H)$ such that the following holds for $D_n$, the complete directed graph on $n$ vertices. There is a set of at most $C\log n$ directed acyclic subgraphs of $D_n$ that covers every $H$-copy of $D_n$, while every set of at most $c\log n$ directed acyclic subgraphs of $D_n$ does not cover all $H$-copies. Here this dichotomy is considerably strengthened.
 Let ${\vec G}(n,p)$ denote the probability space of all directed graphs with $n$ vertices and with edge probability $p$. The fractional arboricity of $H$ is $a(H) = max \{\frac{|E(H')|}{|V(H')|-1}\}$, where the maximum is over all non-singleton subgraphs of $H$. If $a(H) = \frac{|E(H)|}{|V(H)|-1}$ then $H$ is totally balanced. Complete graphs, complete multipartite graphs, cycles, trees, and, in fact, almost all graphs, are totally balanced. It is proven that:
 
 Let $H$ be a dag with $h$ vertices and $m$ edges which is not a rooted star. For every $a^* > a(H)$ there exists $c^* = c^*(a^*,H) > 0$ such a.a.s. $G \sim {\vec G}(n,n^{-1/a^*})$ has the property that every set $X$ of at most $c^*\log n$ directed acyclic subgraphs of $G$ does not cover all $H$-copies of $G$. Moreover, there exists $s(H) = m/2 + O(m^{4/5}h^{1/5})$ such that the following stronger assertion holds for any such $X$: there is an $H$-copy in $G$ that has no more than $s(H)$ of its edges covered by each element of $X$.
 If $H$ is totally balanced then for every $0 < a^* < a(H)$, a.a.s. $G \sim {\vec G}(n,n^{-1/a^*})$ has a single directed acyclic subgraph that covers all its $H$-copies.
 
 As for the first result, note that if $h=o(m)$ then $s(H)=(1+o_m(1))m/2$ is about half of the edges of $H$. In fact, for infinitely many $H$ it holds that $s(H)=m/2$, optimally. As for the second result, the requirement that $H$ is totally balanced cannot, generally, be relaxed.

Causal Inference and Bias in Learning Analytics

As a research field geared toward understanding and improving learning, Learning Analytics (LA) must be able to provide empirical support for causal claims. However, as a highly applied field, tightly controlled randomized experiments are not always feasible nor desirable. Instead, researchers often rely on observational data, based on which they may be reluctant to draw causal inferences. The past decades have seen much progress concerning causal inference in the absence of experimental data. This paper introduces directed acyclic graphs (DAGs), an increasingly popular tool to visually determine the validity of causal claims. Based on this, three basic pitfalls are outlined: confounding bias, overcontrol bias, and collider bias. Further, the paper shows how these pitfalls may be present in the published LA literature alongside possible remedies. Finally, this approach is discussed in light of practical constraints and the need for theoretical development.

1194: THE MORTALITY CAUSAL EFFECT OF POSITIVE FLUID BALANCES SEPSIS SUBTYPES

Introduction: Millions of deaths occur each year due to sepsis and many questions regarding best practices remain. Volume of fluid resuscitation is one of these questions. It is thought that certain sepsis subtypes may actually fare worse with positive fluid balances, however, the current recommendation for an initial resuscitation of 30cc/kg of crystalloid fluids remains. Randomized controlled trials are the gold standard for determining causal effect, but are time and cost-intensive. Causal inference using inverse probability of treatment weighting (IPTW) provides a cost-effective alternative. Through causal inference, we will evaluate the mortality effect of positive fluid balances on sepsis subtypes with the hypothesis that pulmonary sepsis would have a worse outcome. Methods: An anonymous, publicly available database was analyzed using preexisting IRB approval. The eICU Collaborative Research Database contains data on over 200000 intensive care unit admissions. The analysis used 138986 patients with 30 initial features. We dropped features with more than 50% missing values. Imputation with Sklearn Iterative Imputator. Data scaled with Sklearn Standard Scaler. Selecting features sequentially with 6 final features was performed using MLxtend. The primary outcome was ICU mortality. Aim was to establish Average Treatment Effect for positive fluid balances in pulmonary sepsis compared with urosepsis. Pulmonary sepsis had 6754 patients compared to 4152 in urosepsis. Using domain knowledge, we built a Directed Acyclic Graph (DAG). We selected Apache IV as the confounder covariate based on our DAG. As effect modifiers, we selected creatinine and age. In both groups, IPTW was performed using IBM DoWhy. Results: Mortality analysis of the pulmonary sepsis group demonstrated an ATE of 0.13 (95% CI [0.08,0.19]). The urosepsis group showed an ATE of 0.06 (95% CI [0.054 -0.067]). Positive fluid balances had an increased causal effect on mortality for the pulmonary sepsis group. Conclusions: Positive fluid balance may be more harmful in certain sepsis subtypes. Pulmonary sepsis has a higher fluid balance-related effect on mortality than urosepsis, as determined by causal inference techniques. We hope that this analysis will lead to a further evaluation of fluids’ varying effects on sepsis subtypes.

291: DEVELOPING DELPHI EXPERT CONSENSUS RULES FOR A DIGITAL TWIN MODEL OF THE NEURO CRITICAL CARE UNIT

Introduction: In the past 20 years, the concept of the digital twin has been utilized in other fields to track the operations of wind turbines, monitor the status of spacecraft, and even create a model of the Earth for climate research While artificial intelligence holds much promise for the neurocritical care unit, these models should be clearly based on an understanding of underlying physiological variables rather than be opaque “black box” models. Our group has previously created such a digital twin model to predict acute response to treatment of sepsis. This project expands on our previous work by developing a similar model for the critical care of acute ischemic stroke. Methods: A panel of 18 experts in the field of critical care reviewed the clinical practice and pathophysiological statements related to neurology critical care. The core group of investigators developed statements based on a Directed Acyclic Graph (DAG) describing pathophysiology surrounding acute neurological issues encountered in the practice of Neurocritical Care (NCC). A modified Delphi method (3 rounds) was used to gauge agreement on 20 statements (120 sub statements) using a 7-point Likert scale. Agreement was defined a-priori by >80% selection of a 6 (“agree”) or 7 (“strongly agree”). Results: Consensus was achieved on 58 (48.3%) expert statements after completion of 2 rounds. After completion of 3rd round, the level of consensus increased to 93 (77.5%) expert statements. Some statements garnered 100% consensus in the first round of DELPHI such as “Reperfusion of ischemic stroke can lead to improvement of stroke.” Other statements required revision to capture the nuances of clinical practice before gaining consensus. For example, when the severity of infection was incorporated into the statement “Infection can lead to low blood pressure.” consensus increased from 56% to 100%. Conclusions: Our study demonstrated the feasibility of application of the DELPHI process to generate consensus among experts for use in development of a “digital twin” artificial intelligence model for use in the Neuro ICU. Compared to other models which rely on “black-box” associative artificial intelligence, our proposed causal AI model is based on a solid foundation of expert rules and casual mechanisms.

HILL CLIMBING ALGORITHM ON BAYESIAN NETWORK TO DETERMINE PROBABILITY VALUE OF SYMPTOMS AND EYE DISEASE

One of the five human senses referred to as photoreceptors is the eye because the eye is very sensitive to light stimuli. Refractive abnormalities in the eyes are often experienced, which are abnormalities that occur when the eyes cannot see clearly in the open or blurred vision. An unhealthy lifestyle is a trigger for an increase in individuals who experience complaints of eye diseases. In diagnosing a disease, doctors need patient information in the form of symptoms experienced so that patients can be treated immediately. Information in the form of symptoms and types of eye diseases can be used to make conjectures about eye diseases through the structure of BN. The symptom information and type of the disease are represented through nodes, while the relationships are represented through the edge. BN is one of the Probabilistic Graphical Models (PGM) consisting of nodes and edges. BN is also known as a direct acyclic graph (DAG), which is a directed graph that does not have a cycle. The approach method used is scored based on the evaluation process with the bic scoring function. The algorithm used in this study is the HC algorithm. The research data used consisted of 52 symptoms and 15 eye diseases. The results of the study were obtained by the final structure of BN formed by the HC algorithm produced 93 edges and 65 connected nodes, and the probability value of the disease and the symptoms of the disease in the eye.

A Bayesian Hierarchical Model for Extracting Individuals’ Theory-Based Causal Knowledge

Abstract Extracting an individual’s scientific knowledge is essential for improving educational assessment and understanding cognitive tasks in engineering activities such as reasoning and decision-making. However, knowledge extraction is an almost impossible endeavor if the domain of knowledge and the available observational data are unrestricted. The objective of this paper is to quantify individuals’ theory-based causal knowledge from their responses to given questions. Our approach uses directed-acyclic graphs (DAGs) to represent causal knowledge for a given theory and a graph-based logistic model that maps individuals’ question-specific subgraphs to question responses. We follow a hierarchical Bayesian approach to estimate individuals’ DAGs from observations. The method is illustrated using 205 engineering students’ responses to questions on fatigue analysis in mechanical parts. In our results, we demonstrate how the developed methodology provides estimates of population-level DAG and DAGs for individual students. This dual representation is essential for remediation since it allows us to identify parts of a theory that a population or individual struggles with and parts they have already mastered. An addendum of the method is that it enables predictions about individuals’ responses to new questions based on the inferred individual-specific DAGs. The latter has implications for the descriptive modeling of human problem-solving, a critical ingredient in sociotechnical systems modeling.

Bayesian Network Approach in Education: A Bibliometric Review Using R-Tool and Future Research Directions

The development and multiple variations in technology and science have endured the education. Nevertheless, education is one of the primary components that uphold the development of a country. In the meantime, diverse technologies have been introduced to blend in education. For example, Bayesian Networks is a probability-based data modelling approach that illustrates a set of variables and their conditional dependencies through a Directed Acyclic Graph (DAG). Each node formed inside the graph has a Conditional Probability Table (CPT). Therefore, the endurance of this bibliometric review is to identify peer-reviewed literature on the Bayesian network approach in education. Scopus citation databases are used in the data-gathering phase. In addition, PICOS Framework and PRISMA approach were obtained and analysed for keyword search on the research topic. This bibliographic data of articles published in the journals over ten years were extracted. R-tool and VOS viewer were used to analyse the data contained in all journals and articles. This bibliometric review shows the usage of the Bayesian network approach in education, especially in educational application development. The findings from 87 articles extracted show that teaching and learning activity delivery and educational management have improved. The findings show an increasing trend in published studies related to the Bayesian network in education. Next, the United Kingdom and the United States became highly productive countries in the publication of studies within the scope of the Bayesian network. Next, interdisciplinary became the primary choice in the publication of studies in the field of Bayesian networks. The level of predictive accuracy generated through the Bayesian network approach improves the quality of educational application development. However, the findings of previous studies indicate that there is a need to extend the Bayesian network approach in education.