McCarthy Cian P, Ibrahim Nasrien E, van Kimmenade Roland R J, Gaggin Hanna K, Simon Mandy L, Gandhi Parul, Kelly Noreen, Motiwala Shweta R, Mukai Renata, Magaret Craig A, Barnes Grady, Rhyne Rhonda F, Garasic Joseph M, Januzzi James L
Department of Medicine, Massachusetts General Hospital, Boston.
Division of Cardiology, Massachusetts General Hospital, Boston.
Clin Cardiol. 2018 Jul;41(7):903-909. doi: 10.1002/clc.22939. Epub 2018 Jun 14.
Peripheral arterial disease (PAD) is a global health problem that is frequently underdiagnosed and undertreated. Noninvasive tools to predict the presence and severity of PAD have limitations including inaccuracy, cost, or need for intravenous contrast and ionizing radiation.
A clinical/biomarker score may offer an attractive alternative diagnostic method for PAD.
In a prospective cohort of 354 patients referred for diagnostic peripheral and/or coronary angiography, predictors of ≥50% stenosis in ≥1 peripheral vessel (carotid/subclavian, renal, or lower extremity arteries) were identified from >50 clinical variables and 109 biomarkers. Machine learning identified variables predictive of obstructive PAD; a score derived from the final model was developed.
The score consisted of 1 clinical variable (history of hypertension) and 6 biomarkers (midkine, kidney injury molecule-1, interleukin-23, follicle-stimulating hormone, angiopoietin-1, and eotaxin-1). The model had an in-sample area under the receiver operating characteristic curve of 0.85 for obstructive PAD and a cross-validated area under the curve of 0.84; higher scores were associated with greater severity of angiographic stenosis. At optimal cutoff, the score had 65% sensitivity, 88% specificity, 76% positive predictive value (PPV), and 81% negative predictive value (NPV) for obstructive PAD and performed consistently across vascular territories. Partitioning the score into 5 levels resulted in a PPV of 86% and NPV of 98% in the highest and lowest levels, respectively. Elevated score was associated with shorter time to revascularization during 4.3 years of follow-up.
A clinical/biomarker score demonstrates high accuracy for predicting the presence of PAD.
外周动脉疾病（PAD）是一个全球性的健康问题，常常诊断不足且治疗不充分。用于预测PAD的存在和严重程度的非侵入性工具存在局限性，包括不准确、成本高或需要静脉注射造影剂和电离辐射。
临床/生物标志物评分可能为PAD提供一种有吸引力的替代诊断方法。
在一个前瞻性队列中，对354例因诊断性外周和/或冠状动脉造影而转诊的患者，从50多个临床变量和109种生物标志物中确定≥1条外周血管（颈动脉/锁骨下动脉、肾动脉或下肢动脉）中≥50%狭窄的预测因素。机器学习确定了阻塞性PAD的预测变量；并开发了一个从最终模型得出的评分。
该评分由1个临床变量（高血压病史）和6种生物标志物（中期因子、肾损伤分子-1、白细胞介素-23、促卵泡激素、血管生成素-1和嗜酸性粒细胞趋化因子-1）组成。该模型对于阻塞性PAD的受试者工作特征曲线下的样本内面积为0.85，交叉验证曲线下面积为0.84；评分越高，血管造影狭窄的严重程度越高。在最佳截断值时，该评分对于阻塞性PAD的敏感性为65%，特异性为88%，阳性预测值（PPV）为76%，阴性预测值（NPV）为81%，并且在各个血管区域表现一致。将评分分为5个等级，最高和最低等级的PPV分别为86%和NPV为98%。在4.3年的随访期间，评分升高与血管重建时间缩短相关。
临床/生物标志物评分在预测PAD的存在方面具有很高的准确性。
