Relation of Hemoglobin A1C Levels to Risk of Ischemic Stroke and Mortality in Patients With Diabetes Mellitus and Atrial Fibrillation

Prediction of atrial fibrillation and stroke using machine learning models in UK Biobank

Objective

Atrial fibrillation (AF) is the most common cardiac arrythmia, and it is associated with increased risk for ischemic stroke, which is underestimated, as AF can be asymptomatic. The aim of this study was to develop optimal ML models for prediction of AF in the population, and secondly for ischemic stroke in AF patients.

Methods

To develop ML models for prediction of 1) AF in the general population and 2) ischemic stroke in patients with AF we constructed XGBoost, LightGBM, Random Forest, Deep Neural Network, Support Vector Machine and Lasso penalised logistic regression models using UK-Biobank's extensive real-world clinical data, questionnaires, as well as biochemical and genetic data, and their predictive performances were compared. Ranking and contribution of the different features was assessed by SHapley Additive exPlanations (SHAP) analysis. The clinical tool CHA2DS2-VASc for prediction of ischemic stroke among AF patients, was used for comparison to the best performing ML model.

Findings

The best performing model for AF prediction was LightGBM, with an area-under-the-roc-curve (AUROC) of 0.729 (95% confidence intervals (CI): 0.719, 0.738). The best performing model for ischemic stroke prediction in AF patients was XGBoost with AUROC of 0.631 (95% CI: 0.604, 0.657). The improved AUROC in the XGBoost model compared to CHA2DS2-VASc was statistically significant based on DeLong's test (p-value = 2.20E-06). In addition, the SHAP analysis showed that several peripheral blood biomarkers (e.g. creatinine, glycated haemoglobin, monocytes) were associated with ischemic stroke, which are not considered by CHA2DS2-VASc.

Implications

The best performing ML models presented have the potential for clinical use, but further validation in independent studies is required. Our results endorse the incorporation of some routinely measured blood biomarkers for ischemic stroke prediction in AF patients.

Role of cerebral microbleeds in acute ischemic stroke and atrial fibrillation

Cerebral microbleeds (CMBs) are commonly detected in the brains of patients with acute ischemic stroke (AIS). With the development of neuroimaging, clinicians are paying more attention to the presence of CMBs. CMBs were found to significantly increase the risk of intracranial hemorrhagic transformation and hemorrhage in patients with AIS, especially in patients with concurrent atrial fibrillation (AF). Additionally, the presence of CMBs is thought to be a symbol of a high risk of recurrent ischemic stroke (IS). A few researchers have found that the presence of CMBs has no significant effect on the prognosis of patients with AIS. Therefore, the current views on the role of CMBs in the prognoses of patients with IS are controversial. The use of anticoagulants and other drugs has also become a dilemma due to the special influence of CMBs on the prognosis of these patients. Due to the large number of patients with AF and CMBs, many studies have been conducted on the effects of CMBs on these patients and subsequent pharmacological treatments. However, at present, there are no relevant guidelines to guide the secondary preventive treatment of patients with stroke, CMBs, and AF. In this paper, we summarized the role of CMBs in AIS combined with AF and relevant preventive measures against the recurrence of stroke and the occurrence of intracerebral hemorrhage to help clarify the specifics of drug therapies for this group of patients.