心血管疾病幸存者死亡率的风险分层：生存条件推理树分析。

Risk stratification for mortality in cardiovascular disease survivors: A survival conditional inference tree analysis.

机构信息

Department of Cardiology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China.

Department of Cardiology, Kailuan Hospital, Tangshan, China.

出版信息

Nutr Metab Cardiovasc Dis. 2021 Feb 8;31(2):420-428. doi: 10.1016/j.numecd.2020.09.029. Epub 2020 Oct 3.

DOI:10.1016/j.numecd.2020.09.029

PMID:33223407

Abstract

BACKGROUND AND AIMS

Efficient analysis strategies for complex network with cardiovascular disease (CVD) risk stratification remain lacking. We sought to identify an optimized model to study CVD prognosis using survival conditional inference tree (SCTREE), a machine-learning method.

METHODS AND RESULTS

We identified 5379 new onset CVD from 2006 (baseline) to May, 2017 in the Kailuan I study including 101,510 participants (the training dataset). The second cohort composing 1,287 CVD survivors was used to validate the algorithm (the Kailuan II study, n = 57,511). All variables (e.g., age, sex, family history of CVD, metabolic risk factors, renal function indexes, heart rate, atrial fibrillation, and high sensitivity C-reactive protein) were measured at baseline and biennially during the follow-up period. Up to December 2017, we documented 1,104 deaths after CVD in the Kailuan I study and 170 deaths in the Kailuan II study. Older age, hyperglycemia and proteinuria were identified by the SCTREE as main predictors of post-CVD mortality. CVD survivors in the high risk group (presence of 2-3 of these top risk factors), had higher mortality risk in the training dataset (hazard ratio (HR): 5.41; 95% confidence Interval (CI): 4.49-6.52) and in the validation dataset (HR: 6.04; 95%CI: 3.59-10.2), than those in the lowest risk group (presence of 0-1 of these factors).

CONCLUSION

Older age, hyperglycemia and proteinuria were the main predictors of post-CVD mortality.

TRIAL REGISTRATION

ChiCTR-TNRC-11001489.

摘要

背景和目的

对于心血管疾病（CVD）风险分层的复杂网络，仍缺乏有效的分析策略。我们试图通过机器学习方法 - 生存条件推理树（SCTREE），来确定一种优化的模型以研究 CVD 预后。

方法和结果

我们从 2006 年（基线）至 2017 年 5 月的开滦研究中识别出 5379 例新发 CVD，包括 101510 名参与者（训练数据集）。第二队列由 1287 例 CVD 幸存者组成，用于验证该算法（开滦 II 研究，n=57511）。所有变量（如年龄、性别、CVD 家族史、代谢危险因素、肾功能指标、心率、房颤和高敏 C 反应蛋白）均在基线和随访期间每两年测量一次。截至 2017 年 12 月，我们记录了开滦 I 研究中 1104 例 CVD 后死亡和开滦 II 研究中 170 例死亡。SCTREE 将年龄较大、高血糖和蛋白尿鉴定为 CVD 后死亡的主要预测因素。高风险组（存在 2-3 个这些主要危险因素）的 CVD 幸存者在训练数据集（风险比（HR）：5.41；95%置信区间（CI）：4.49-6.52）和验证数据集（HR：6.04；95%CI：3.59-10.2）中的死亡率风险更高，而最低风险组（存在 0-1 个这些因素）则更低。