Using Bayesian network model with MMHC algorithm to detect risk factors for stroke

Abstract

<abstract> <p>Stroke is a major chronic non-communicable disease with high incidence, high mortality, and high recurrence. To comprehensively digest its risk factors and take some relevant measures to lower its prevalence is of great significance. This study aimed to employ Bayesian Network (BN) model with Max-Min Hill-Climbing (MMHC) algorithm to explore the risk factors for stroke. From April 2019 to November 2019, Shanxi Provincial People's Hospital conducted opportunistic screening for stroke in ten rural areas in Shanxi Province. First, we employed propensity score matching (PSM) for class balancing for stroke. Afterwards, we used Chi-square testing and Logistic regression model to conduct a preliminary analysis of risk factors for stroke. Statistically significant variables were incorporated into BN model construction. BN structure learning was achieved using MMHC algorithm, and its parameter learning was achieved with Maximum Likelihood Estimation. After PSM, 748 non-stroke cases and 748 stroke cases were included in this study. BN was built with 10 nodes and 12 directed edges. The results suggested that age, fasting plasma glucose, systolic blood pressure, and family history of stroke constitute direct risk factors for stroke, whereas sex, educational levels, high density lipoprotein cholesterol, diastolic blood pressure, and urinary albumin-to-creatinine ratio represent indirect risk factors for stroke. BN model with MMHC algorithm not only allows for a complicated network relationship between risk factors and stroke, but also could achieve stroke risk prediction through Bayesian reasoning, outshining traditional Logistic regression model. This study suggests that BN model boasts great prospects in risk factor detection for stroke.</p> </abstract>

Exploring factors related to heart attack complicated with hypertension using a Bayesian network model: a study based on the China Health and Retirement Longitudinal Study

“…When investigating risk factors for HAH, previous studies often relied on logistic regression, which uses probabilities to indicate the strength of the association. However, it cannot provide a comprehensive overview of the overall association between risk factors ( 15 ), nor can it detect direct or indirect risk factors. In contrast, BNs offer several advantages over logistic regression in establishing risk factor models ( 23 ).…”

“…Tabu-Search, a global optimization algorithm introduced by Glover ( 14 ), allows for good structure learning for BNs, overcoming the limitations of traditional logistic regression. Now, BNs has been applied to explore risk factors for stroke ( 15 ), hyperlipidemia ( 16 ), hyperhomocysteinemia ( 17 ). To the best of our knowledge, no scholars have yet sought to employ BNs for related factor exploration in HAH.…”

Peeling back the many layers of competitive exclusion

“…Several different network models were used, including the score-based learning algorithm—Hill-Climbing (HC) ( Friedman et al, 2013 ); constraint-based structure learning algorithms—Max–Min Parents and Children (MMPC) ( Lagani and Tsamardinos, 2010 ); hybrid structure learning algorithms—Max–Min Hill-Climbing (MMHC) ( Song et al, 2022 ), Hybrid Parents and Children (H2PC) ( Anonymous, 2021 ), and General 2-Phase Restricted Maximization (RSMAX2) ( Yu et al, 2019 ) to identify a common network structure for the various enzymes or categories described. Among all these implemented algorithms, HC performed best and produced the highest number of connections with various data sets.…”

Using Bayesian networks with Tabu-search algorithm to explore risk factors for hyperhomocysteinemia

“…Another important concept in Bayesian networks is that each child node has a conditional probability distribution that measures the effects of its predictor variables (parents). This is given by P (Xi| pa (Xi)), where P is the conditional probability, Xi represents each node and pa (Xi) represents the parents of node Xi 45 . Learning from Bayesian networks includes structural learning and parametric learning.…”