Value of baseline characteristics in the risk prediction of atrial fibrillation

Abstract

IntroductionAtrial fibrillation (AF) is prone to heart failure and stroke. Early management can effectively reduce the stroke rate and mortality. Current clinical guidelines screen high-risk individuals based solely on age, while this study aims to explore the possibility of other AF risk predictors.MethodsA total of 18,738 elderly people (aged over 60 years old) in Chinese communities were enrolled in this study. The baseline characteristics were mainly based on the diagnosis results of electrocardiogram (ECG) machine during follow up, accompanied by some auxiliary physical examination basic data. After the analysis of both independent and combined baseline characteristics, AF risk predictors were obtained and prioritized according to the results. Independent characteristics were studied from three aspects: Chi-square test, Mann–Whitney U test and Cox univariate regression analysis. Combined characteristics were studied from two aspects: machine learning models and Cox multivariate regression analysis, and the former was combined with recursive feature elimination method and voting decision.ResultsThe resulted optimal combination of risk predictors included age, atrial premature beats, atrial flutter, left ventricular hypertrophy, hypertension and heart disease.ConclusionPatients diagnosed by short-time ECG machines with the occurrence of the above events had a higher probability of AF episodes, who are suggested to be included in the focus of long-term ECG monitoring or increased screening density. The incidence of risk predictors in different age ranges of AF patients suggests differences in age-specific patient management. This can help improve the detection rate of AF, standardize the management of patients, and slow down the progression of AF.

Artificial intelligence for atrial fibrillation detection, prediction, and treatment: A systematic review of the last decade (2013–2023)

“…J. He et al (2023) incorporated baseline risk predictors like age, presence of atrial premature beats, atrial flutter, left ventricular hypertrophy, hypertension, and heart disease into their ML model to predict AF risk. Insights gained assisted personalized AF risk assessment and management.…”

Precise risk‐prediction model including arterial stiffness for new‐onset atrial fibrillation using machine learning techniques

“…Six models were developed using a large electronic medical records database, 36,39–43 while the diagnosis of AF during follow‐up was based on electrocardiogram in one previous study 38 and ours. Across all published ML model studies, the number of subjects in the derivation cohorts ranged from 3534 to 2 994 837, the number of outcomes ranged from 88 to 95 607, and the age at baseline ranged from 19 to 97 years; two studies only included data from individuals aged ≥60 years 36,38 . Duration of follow‐up ranged from 0.5 to 12 years.…”

“…Machine learning (ML) and data‐driven approaches are becoming very important in many areas 35 . Recently, prediction models for new‐onset AF that use ML algorithms have been developed 36–44 …”

“…35 Recently, prediction models for new-onset AF that use ML algorithms have been developed. [36][37][38][39][40][41][42][43][44] Arterial stiffness is known to precede development of hypertension, 45 and risk for AF. [7][8][9] However, to our knowledge, there are no ML models that included hypertension and cardio-ankle vascular index (CAVI).…”

Association between dietary selenium intake and severe abdominal aortic calcification in the United States: a cross-sectional study

“…14,15 Diabetes mellitus was defined as the use of hypoglycemic medications, physician-diagnosed diabetes, fasting plasma glucose ≥126 mg dL −1 , or glycated hemoglobin ≥6.5%. 16,17 Chronic kidney disease (CKD) was defined as an estimated glomerular filtration rate (eGFR) <0 mL min −1 /1.73 m 2 or ≥60 mL min −1 /1.73 m 2 with albuminuria. CKD groups were categorized as no CKD, CKD stages 1 and 2 (presence of albuminuria and eGFR ≥60 mL min −1 /1.73 m 2 ) and CKD stages 3–5 (eGFR <60 mL min −1 /1.73 m 2 ).…”