Wolfson Institute of Population Health, Queen Mary, University of London, UK.
Leeds Institute of Data Analytics, University of Leeds, UK; Leeds Institute for Cardiovascular and Metabolic Medicine, University of Leeds, UK; Department of Cardiology, Leeds Teaching Hospitals NHS Trust, Leeds, UK.
Am Heart J. 2024 Jun;272:1-10. doi: 10.1016/j.ahj.2024.03.001. Epub 2024 Mar 6.
The increasing burden of atrial fibrillation (AF) emphasizes the need to identify high-risk individuals for enrolment in clinical trials of AF screening and primary prevention. We aimed to develop prediction models to identify individuals at high-risk of AF across prediction horizons from 6-months to 10-years.
We used secondary-care linked primary care electronic health record data from individuals aged ≥30 years without known AF in the UK Clinical Practice Research Datalink-GOLD dataset between January 2, 1998 and November 30, 2018; randomly divided into derivation (80%) and validation (20%) datasets. Models were derived using logistic regression from known AF risk factors for incident AF in prediction periods of 6 months, 1-year, 2-years, 5-years, and 10-years. Performance was evaluated using in the validation dataset with bootstrap validation with 200 samples, and compared against the CHADS-VASc and CHEST scores.
Of 2,081,139 individuals in the cohort (1,664,911 in the development dataset, 416,228 in the validation dataset), the mean age was 49.9 (SD 15.4), 50.7% were women, and 86.7% were white. New cases of AF were 7,386 (0.4%) within 6 months, 15,349 (0.7%) in 1 year, 38,487 (1.8%) in 5 years, and 79,997 (3.8%) by 10 years. Valvular heart disease and heart failure were the strongest predictors, and association of hypertension with AF increased at longer prediction horizons. The optimal risk models incorporated age, sex, ethnicity, and 8 comorbidities. The models demonstrated good-to-excellent discrimination and strong calibration across prediction horizons (AUROC, 95%CI, calibration slope: 6-months, 0.803, 0.789-0.821, 0.952; 1-year, 0.807, 0.794-0.819, 0.962; 2-years, 0.815, 0.807-0.823, 0.973; 5-years, 0.807, 0.803-0.812, 1.000; 10-years 0.780, 0.777-0.784, 1.010), and superior to the CHADS-VASc and CHEST scores. The models are available as a web-based FIND-AF calculator.
The FIND-AF models demonstrate high discrimination and calibration across short- and long-term prediction horizons in 2 million individuals. Their utility to inform trial enrolment and clinical decisions for AF screening and primary prevention requires further study.
心房颤动（AF）负担不断增加，这强调了需要确定参加 AF 筛查和一级预防临床试验的高危个体。我们的目的是开发预测模型，以确定 6 个月至 10 年预测期内 AF 风险较高的个体。
我们使用来自英国临床实践研究数据链接-GOLD 数据集的二级保健相关初级保健电子健康记录数据，该数据来自 1998 年 1 月 2 日至 2018 年 11 月 30 日期间年龄≥30 岁且无已知 AF 的个体；随机分为推导（80%）和验证（20%）数据集。在 6 个月、1 年、2 年、5 年和 10 年的预测期内，使用 logistic 回归从已知的 AF 风险因素中推导模型来预测 AF 发病。在验证数据集中使用 bootstrap 验证（200 个样本）进行性能评估，并与 CHADS-VASc 和 CHEST 评分进行比较。
在队列中的 2081139 名个体中（开发数据集 1664911 名，验证数据集 416228 名），平均年龄为 49.9（SD 15.4），50.7%为女性，86.7%为白人。在 6 个月内新发生 AF 的病例为 7386（0.4%），1 年内为 15349（0.7%），5 年内为 38487（1.8%），10 年内为 79997（3.8%）。瓣膜性心脏病和心力衰竭是最强的预测因素，高血压与 AF 的关联在较长的预测期内增加。最佳风险模型纳入了年龄、性别、种族和 8 种合并症。该模型在各预测期均表现出良好到极好的区分度和强校准度（AUROC，95%CI，校准斜率：6 个月，0.803，0.789-0.821，0.952；1 年，0.807，0.794-0.819，0.962；2 年，0.815，0.807-0.823，0.973；5 年，0.807，0.803-0.812，1.000；10 年，0.780，0.777-0.784，1.010），优于 CHADS-VASc 和 CHEST 评分。这些模型可作为基于网络的 FIND-AF 计算器使用。
FIND-AF 模型在 200 万个体中显示出在短期和长期预测期内具有较高的区分度和校准度。它们在告知 AF 筛查和一级预防临床试验的入组和临床决策方面的效用需要进一步研究。
