Risk factors assessment and a Bayesian network model for predicting ischemic stroke in patients with cardiac myxoma

Lin Ma; Bin Cai; Man-Li Qiao; Ze-Xin Fan; Li-Bo Fang; Chao-Bin Wang; Guang-Zhi Liu

doi:10.3389/fcvm.2023.1128022

Risk factors assessment and a Bayesian network model for predicting ischemic stroke in patients with cardiac myxoma

Front Cardiovasc Med. 2023 Mar 24:10:1128022. doi: 10.3389/fcvm.2023.1128022. eCollection 2023.

Authors

Lin Ma¹, Bin Cai¹, Man-Li Qiao², Ze-Xin Fan¹, Li-Bo Fang³, Chao-Bin Wang⁴, Guang-Zhi Liu¹

Affiliations

¹ Department of Neurology, Beijing Anzhen Hospital, Capital Medical University, Beijing, China.
² Department of General Practice Medicine, Beijing Anzhen Hospital, Capital Medical University, Beijing, China.
³ Department of Neurology, Beijing Fangshan District Liangxiang Hospital, Beijing, China.
⁴ Department of Neurology, Beijing Fuxing Hospital, Capital Medical University, Beijing, China.

Abstract

Objective: This study aims to identify relevant risk factors, assess the interactions between variables, and establish a predictive model for ischemic stroke (IS) in patients with cardiac myxoma (CM) using the Bayesian network (BN) approach.

Methods: Data of patients with CM were collected from three tertiary comprehensive hospitals in Beijing from January 2002 to January 2022. Age, sex, medical history, and information related to CM were extracted from the electronic medical record system. The BN model was constructed using the tabu search algorithm, and the conditional probability of each node was calculated using the maximum likelihood estimation method. The probability of each node of the network and the interrelationship between IS and its related factors were qualitatively and quantitatively analyzed. A receiver operating characteristic (ROC) curve was also plotted. Sensitivity, specificity, and area under the curve (AUC) values were calculated and compared between the BN and logistic regression models to evaluate the efficiency of the predictive model.

Results: A total of 416 patients with CM were enrolled in this study, including 61 with and 355 without IS. The BN model found that cardiac symptoms, systemic embolic symptoms, platelet counts, and tumor with high mobility were directly associated with the occurrence of IS in patients with CM. The BN model for predicting CM-IS achieved higher scores on AUC {0.706 [95% confidence interval (CI), 0.639-0.773]} vs. [0.697 (95% CI, 0.629-0.766)] and sensitivity (99.44% vs. 98.87%), but lower scores on accuracies (85.82% vs. 86.06%) and specificity (6.56% vs. 11.48%) than the logistic regression model.

Conclusion: Cardiac symptoms, systemic embolic symptoms, platelet counts, and tumor with high mobility are candidate predictors of IS in patients with CM. The BN model was superior or at least non-inferior to the traditional logistic regression model, and hence is potentially useful for early IS detection, diagnosis, and prevention in clinical practice.

Keywords: Bayesian network; cardiac myxoma; ischemic stroke; prediction model; risk factor.

Grants and funding

This work was supported by supported by China National Natural Science Foundation (82071342).