心房顫動風(fēng)險(xiǎn)預(yù)測模型的評估（來自動脈粥樣硬化多種族研究[MESA]）
BACKGROUND
Atrial fibrillation (AF) is prevalent and strongly associated with higher cardiovascular disease (CVD) risk. Machine learning is increasingly used to identify novel predictors of CVD risk, but prediction improvements beyond established risk scores are uncertain.
房顫（AF）普遍存在，并與較高的心血管疾病（CVD）風(fēng)險(xiǎn)密切相關(guān)。機(jī)器學(xué)習(xí)算法已越來越被用于識別CVD風(fēng)險(xiǎn)因素，但未確定既定風(fēng)險(xiǎn)評分之外的預(yù)測改進(jìn)方法。
METHODS
We evaluated improvements in predicting 5-year AF risk when adding novel candidate variables identified by machine learning to the CHARGE-AF Enriched score, which includes age, race/ethnicity, height, weight, systolic and diastolic blood pressure, current smoking, use of antihypertensive medication, diabetes, and NT-proBNP. We included 3,534 participants (mean age, 61.3 years，52.0% female) with complete data from the prospective Multi-Ethnic Study of Atherosclerosis. Incident AF was defined based on study electrocardiograms and hospital discharge diagnosis ICD-9 codes. Prediction performance was evaluated using Cox regression and a parsimonious model was selected using LASSO.
我們通過機(jī)器學(xué)習(xí)識別，在CHARGE-AF Enriched分?jǐn)?shù)中添加了的新候選變量時(shí)，評估了預(yù)測5年房顫風(fēng)險(xiǎn)改善情況，該變量包括年齡、種族/族裔、身高、體重、收縮壓和舒張壓、當(dāng)前吸煙情況、抗高血壓藥物使用、糖尿病和腦鈉肽數(shù)量。我們招募了3,534名參與者（平均年齡61.3歲，女性占52.0％），并有前瞻性動脈粥樣硬化多種族研究的完整數(shù)據(jù)。我們通過機(jī)器學(xué)習(xí)識別，在CHARGE-AF Enriched分?jǐn)?shù)中添加了的新候選變量時(shí)，評估了預(yù)測5年房顫風(fēng)險(xiǎn)改善情況，該變量包括年齡、種族/族裔、身高、體重、收縮壓和舒張壓、當(dāng)前吸煙情況、抗高血壓藥物使用、糖尿病和腦鈉肽數(shù)量。我們招募了3,534名參與者（平均年齡61.3歲，女性占52.0％），并有前瞻性動脈粥樣硬化多種族研究的完整數(shù)據(jù)。
RESULTS
Within 5 years of baseline, 124 participants had incident AF. Compared with the CHARGE-AF Enriched model (c-statistic, 0.804), variables identified by machine learning, including biomarkers, cardiac magnetic resonance imaging variables, electrocardiogram variables, and subclinical CVD variables, did not significantly improve prediction. A 23-item score derived by machine learning achieved a c-statistic of 0.806, whereas a parsimonious model including the clinical risk factors age, weight, current smoking, NT-proBNP, coronary artery calcium score, and cardiac troponin-T achieved a c-statistic of 0.802. This analysis confirms that the CHARGE-AF Enriched model and a parsimonious 6-item model performed similarly to a more extensive model derived by machine learning.
在基線的5年內(nèi)，有124位參與者發(fā)生了房顫。和CHARGE-AF Enriched模型（c-統(tǒng)計(jì)量，0.804）相比，通過機(jī)器學(xué)習(xí)識別，包括生物標(biāo)志物、心臟磁共振成像變量、心電圖變量和亞臨床CVD變量在內(nèi)的變量未明顯改善預(yù)測。機(jī)器學(xué)習(xí)得出的23個項(xiàng)目評分的c-統(tǒng)計(jì)量為0.806，而包括臨床風(fēng)險(xiǎn)因素、年齡、體重、當(dāng)前吸煙、腦鈉肽、冠狀動脈鈣化評分和心肌肌鈣蛋白T的簡化模型達(dá)到了0.802c-統(tǒng)計(jì)量。該分析證實(shí)，CHARGE-AF Enriched模型及簡約6項(xiàng)模型和機(jī)器學(xué)習(xí)得到更廣泛的模型作用相似。
CONCLUSIONS
In conclusion, these simple models remain the gold standard for risk prediction of AF, although addition of the coronary artery calcium score should be considered.
總之，盡管應(yīng)考慮增加冠狀動脈鈣評分，這些簡易模型仍是預(yù)測房顫風(fēng)險(xiǎn)的金標(biāo)準(zhǔn)。
