Weight, height, weight change, and risk of incident atrial fibrillation in middle-aged men and women

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.

Diabetes, prediabetes, and atrial fibrillation-A population-based cohort study based on national and regional registers

BACKGROUND

Previous studies have shown an increased risk for atrial fibrillation and atrial flutter (AF) in people with type 2 diabetes and prediabetes. It is unclear whether this increase in AF risk is independent of other risk factors for AF.

OBJECTIVE

To investigate the association between diabetes and different prediabetic states, as independent risk factors for the onset of AF.

METHODS

We performed a population-based cohort study in Northern Sweden, including data on fasting plasma glucose, oral glucose tolerance test, major cardiovascular risk factors, medical history, and lifestyle factors. Participants were divided into six groups depending on glycemic status and followed through national registers for AF diagnosis. Cox proportional hazard model was used to assess the association between glycemic status and AF, using normoglycemia as reference.

RESULTS

The cohort consisted of 88,889 participants who underwent a total of 139,661 health examinations. In the model adjusted for age and sex, there was a significant association between glycemic status and development of AF in all groups except the impaired glucose tolerance group, with the strongest association for the group with known diabetes (p-value <0.001). In a model adjusted for sex, age, systolic blood pressure, body mass index, antihypertensive drugs, cholesterol, alcohol, smoking, education level, marital status, and physical activity, there was no significant association between glycemic status and AF.

CONCLUSIONS/INTERPRETATION

The association between glycemic status and AF disappears upon adjustment for potential confounders. Diabetes and prediabetes do not appear to be independent risk factors for AF.

Obesity and atrial fibrillation: a narrative review from arrhythmogenic mechanisms to clinical significance

The prevalence of obesity and atrial fibrillation (AF), which are inextricably linked, is rapidly increasing worldwide. Obesity rates are higher among patients with AF than healthy individuals. Some epidemiological data indicated that obese patients were more likely to develop AF, but others reported no significant correlation. Obesity-related hypertension, diabetes, and obstructive sleep apnea are all associated with AF. Additionally, increased epicardial fat, systemic inflammation, and oxidative stress caused by obesity can induce atrial enlargement, inflammatory activation, local myocardial fibrosis, and electrical conduction abnormalities, all of which led to AF and promoted its persistence. Weight loss reduced the risk and reversed natural progression of AF, which may be due to its anti-fibrosis and inflammation effect. However, fluctuations in weight offset the benefits of weight loss. Therefore, the importance of steady weight loss urges clinicians to incorporate weight management interventions in the treatment of patients with AF. In this review, we discuss the epidemiology of obesity and AF, summarize the mechanisms by which obesity triggers AF, and explain how weight loss improves the prognosis of AF.