Risk-Guided Atrial Fibrillation Screening With Artificial Intelligence-Enabled Electrocardiogram Models: A VITAL-AF Trial Analysis.

Current AF screening approaches using a guideline age-based threshold of ≥65 years have shown limited yield.

目前使用指南建议的年龄阈值≥65岁的AF筛查方法显示出有限的成效。

In an AF screening trial, we assessed whether the screening effect was larger among individuals at elevated AF risk using validated clinical and electrocardiogram (ECG)-based artificial intelligence (AI) risk models.

在一项房颤筛查试验中，我们评估了使用经过验证的临床和心电图（ECG）基础的人工智能（AI）风险模型，筛查效果是否在高房颤风险个体中更大。

Methods

VITAL-AF was a cluster-randomized trial of patients aged ≥65 years treated at 1 of 16 primary care practices affiliated with Massachusetts General Hospital. Patients randomized to a screening practice were screened using a single-lead ECG.

VITAL-AF 是一项针对年龄≥65岁，在马萨诸塞州总医院附属的16个初级保健诊所之一接受治疗的患者进行的群组随机试验。被随机分配到筛查实践的患者使用单导联心电图进行了筛查。

Among VITAL-AF participants without prevalent AF with at least one 12-lead ECG within 3 years before enrollment, we estimated AF risk using 3 validated models derived outside of VITAL-AF: the Cohorts of Heart and Aging Research in Genomic Epidemiology-AF (CHARGE-AF) clinical score, an AI-based model using a 12-lead ECG alone (ECG-AI), and a model combining ECG-AI and CHARGE-AF (CH-AI).

在没有既往房颤病史的VITAL-AF参与者中，我们使用了三个在VITAL-AF之外验证的模型来估计房颤风险：基于人群的遗传学和流行病学研究联盟-房颤(CHARGE-AF)临床评分、仅使用12导联心电图的AI基础模型（ECG-AI），以及结合ECG-AI和CHARGE-AF的模型（CH-AI）。

Two-year incident AF discrimination was assessed by the time-dependent area under the receiver-operating characteristic curve (AUROC) and average precision.

通过时间依赖的接收者操作特征曲线下的面积（AUROC）和平均精度来评估两年内新发房颤的鉴别能力。

AF screening effect was defined as the difference in 2-year incident AF diagnosis rate (per 100 person-years) in screening vs control across AF risk deciles.

AF筛查效果被定义为在AF风险十分位数中，筛查组与对照组2年新发AF诊断率（每100人年）的差异。

Results

Of 30,630 VITAL-AF participants without prevalent AF, 16,937 had pretrial ECG and clinical data.

在30,630名没有既往AF的VITAL-AF参与者中，有16,937人拥有试验前的ECG和临床数据。

Each score discriminated 2-year AF risk according to AUROC (CHARGE-AF: 0.711 [95% CI: 0.671-0.749]; ECG-AI: 0.784 [95% CI: 0.743-0.819]; CH-AI: 0.788 [95% CI: 0.754-0.824]) and average precision (0.0952 [95% CI: 0.0836-0.112]; 0.132 [95% CI: 0.113-0.157]; 0.133 [95% CI: 0.117-0.159]).

每个评分根据AUROC（CHARGE-AF: 0.711 [95% 置信区间: 0.671-0.749]; ECG-AI: 0.784 [95% 置信区间: 0.743-0.819]; CH-AI: 0.788 [95% 置信区间: 0.754-0.824]）和平均精确度（0.0952 [95% 置信区间: 0.0836-0.112]; 0.132 [95% 置信区间: 0.113-0.157]; 0.133 [95% 置信区间: 0.117-0.159]）区分了2年房颤风险。

An AF screening effect was observed in the top decile of CH-AI (AF diagnosis rate in screening 10.07/100 person-years [95% 8.28-11.87] vs 7.76 [95% 6.30-9.21] in control, P < 0.05), corresponding to a difference in AF diagnosis rate of 2.32/100 person-years (95% CI: 0.01-4.63) and number-needed-to-screen of 43 per year.

在CH-AI的前十分位数中观察到了房颤筛查效果（筛查中的房颤诊断率为每100人年10.07 [95% 置信区间: 8.28-11.87]，对照组为7.76 [95% 置信区间: 6.30-9.21]，P < 0.05），相当于房颤诊断率的差异为每100人年2.32（95% 置信区间: 0.01-4.63），每年需要筛查的人数为43。

Conclusions

Use of ECG-based AI and clinical factors identified individuals at particularly high risk for AF who may benefit from screening.

利用基于心电图的人工智能和临床因素，可以识别出特别高风险的房颤患者，这些患者可能从筛查中受益。

Findings suggest a trade-off between increasing AF screening efficiency and decreasing population coverage (ie, restriction of the screening pool).

研究结果表明，提高房颤筛查效率与减少人群覆盖范围之间存在权衡（即筛查池的限制）。

Future studies are needed to determine whether a risk-based approach is optimal or whether consideration of additional clinical- and systems-level factors (eg, access, health care system engagement) can further refine AF screening strategies.

需要进一步的研究来确定基于风险的方法是否最优，或者考虑额外的临床和系统级因素（例如，获取途径、卫生保健系统参与度）是否可以进一步完善房颤筛查策略。

(Screening for Atrial Fibrillation Among Older Patients in Primary Care Clinics [VITAL-AF]; NCT03515057).

（在初级保健诊所中对老年患者进行房颤筛查 [VITAL-AF]; NCT03515057）。