Kidney Research Institute and Division of Nephrology, University of Washington, Seattle, Washington.
Department of Medicine, University of California, San Francisco, California.
Clin J Am Soc Nephrol. 2021 Jul;16(7):1015-1024. doi: 10.2215/CJN.01060121. Epub 2021 Jul 12.
Atrial fibrillation (AF) is common in CKD and associated with poor kidney and cardiovascular outcomes. Prediction models developed using novel methods may be useful to identify patients with CKD at highest risk of incident AF. We compared a previously published prediction model with models developed using machine learning methods in a CKD population.
DESIGN, SETTING, PARTICIPANTS, & MEASUREMENTS: We studied 2766 participants in the Chronic Renal Insufficiency Cohort study without prior AF with complete cardiac biomarker (N-terminal pro-B-type natriuretic peptide and high-sensitivity troponin T) and clinical data. We evaluated the utility of machine learning methods as well as a previously validated clinical prediction model (Cohorts for Heart and Aging Research in Genomic Epidemiology [CHARGE]-AF, which included 11 predictors, using original and re-estimated coefficients) to predict incident AF. Discriminatory ability of each model was assessed using the ten-fold cross-validated -index; calibration was evaluated graphically and with the Grønnesby and Borgan test.
Mean (SD) age of participants was 57 (11) years, 55% were men, 38% were Black, and mean (SD) eGFR was 45 (15) ml/min per 1.73 m; 259 incident AF events occurred during a median of 8 years of follow-up. The CHARGE-AF prediction equation using original and re-estimated coefficients had indices of 0.67 (95% confidence interval, 0.64 to 0.71) and 0.67 (95% confidence interval, 0.64 to 0.70), respectively. A likelihood-based boosting model using clinical variables only had a index of 0.67 (95% confidence interval, 0.64 to 0.70); adding N-terminal pro-B-type natriuretic peptide, high-sensitivity troponin T, or both biomarkers improved the index by 0.04, 0.01, and 0.04, respectively. In addition to N-terminal pro-B-type natriuretic peptide and high-sensitivity troponin T, the final model included age, non-Hispanic Black race/ethnicity, Hispanic race/ethnicity, cardiovascular disease, chronic obstructive pulmonary disease, myocardial infarction, peripheral vascular disease, use of angiotensin-converting enzyme inhibitor/angiotensin receptor blockers, calcium channel blockers, diuretics, height, and weight.
Using machine learning algorithms, a model that included 12 standard clinical variables and cardiac-specific biomarkers N-terminal pro-B-type natriuretic peptide and high-sensitivity troponin T had moderate discrimination for incident AF in a CKD population.
心房颤动（AF）在 CKD 中很常见，与肾脏和心血管不良结局相关。使用新方法开发的预测模型可能有助于识别发生 AF 风险最高的 CKD 患者。我们比较了一种先前发表的预测模型与使用机器学习方法在 CKD 人群中开发的模型。
设计、设置、参与者和测量：我们研究了 2766 名无先前 AF 的慢性肾功能不全队列研究参与者，他们具有完整的心脏生物标志物（N 末端脑利钠肽前体和高敏肌钙蛋白 T）和临床数据。我们评估了机器学习方法以及先前验证的临床预测模型（包含 11 个预测因素的心脏和衰老研究中的基因组流行病学队列[CHARGE]-AF，使用原始和重新估计的系数）预测 AF 事件的能力。使用十折交叉验证 - 指数评估每个模型的判别能力；通过图形和 Grønnesby 和 Borgan 检验评估校准。
参与者的平均（标准差）年龄为 57（11）岁，55%为男性，38%为黑人，平均（标准差）eGFR 为 45（15）ml/min/1.73m；中位随访 8 年期间发生 259 例 AF 事件。CHARGE-AF 预测方程使用原始和重新估计的系数的指数分别为 0.67（95%置信区间，0.64 至 0.71）和 0.67（95%置信区间，0.64 至 0.70）。仅使用临床变量的基于似然的提升模型的指数为 0.67（95%置信区间，0.64 至 0.70）；分别添加 N 末端脑利钠肽前体、高敏肌钙蛋白 T 或两者的生物标志物，指数分别提高了 0.04、0.01 和 0.04。除了 N 末端脑利钠肽前体和高敏肌钙蛋白 T 之外，最终模型还包括年龄、非西班牙裔黑人种族/民族、西班牙裔种族/民族、心血管疾病、慢性阻塞性肺疾病、心肌梗死、外周血管疾病、血管紧张素转换酶抑制剂/血管紧张素受体阻滞剂的使用、钙通道阻滞剂、利尿剂、身高和体重。
在 CKD 人群中，使用机器学习算法，包含 12 个标准临床变量和心脏特异性生物标志物 N 末端脑利钠肽前体和高敏肌钙蛋白 T 的模型对 AF 事件具有中等的判别能力。
