The use of machine learning for the identification of peripheral artery disease and future mortality risk.
The use of machine learning for the identification of peripheral artery disease and future mortality risk.
复制标题
使用机器学习来鉴定外周动脉疾病和未来死亡率风险。
DOI：
10.1016/j.jvs.2016.04.026
复制
发表时间：
2016-11
影响因子：
4.3
通讯作者：
Leeper, Nicholas J.
中科院分区：
文献类型：
--
作者：
Ross, Elsie Gyang;Shah, Nigam H.;Dalman, Ronald L.;Nead, Kevin T.;Cooke, John P.;Leeper, Nicholas J.
精准医疗工作的一个关键方面是开发信息学工具，这些工具可以以自动化和自适应的方式分析和解释“大数据”集，同时提供准确和可操作的临床信息。本研究的目的是开发用于疾病识别和死亡风险预测的机器学习算法，并确定这些模型的性能是否优于经典统计分析。以外周动脉疾病（PAD）为重点，患者数据来自一项前瞻性观察性研究，该研究纳入了1，755例接受择期冠状动脉造影术的患者。我们采用了多种监督机器学习算法，并以无假设的方式利用各种临床，人口统计学，成像和基因组信息来构建可以识别PAD患者并预测未来死亡率的模型。与标准逐步线性回归模型进行比较。我们的机器学习模型在识别PAD患者（AUC分别为0.87和0.76，P=0.03）和预测未来死亡率（AUC分别为0.76和0.65，P=0.10）方面优于逐步逻辑回归模型。这两种机器学习模型的校准明显优于逐步逻辑回归模型，从而提供了更准确的疾病和死亡风险估计。机器学习方法可以产生更准确的疾病分类和预测模型。这些工具可能被证明在临床上有用的高度病态疾病患者的自动识别积极的风险因素管理可以改善结果。
A key aspect of the precision medicine effort is the development of informatics tools that can analyze and interpret ‘big data’ sets in an automated and adaptive fashion, while providing accurate and actionable clinical information. The aims of this study were to develop machine learning algorithms for the identification of disease and the prognostication of mortality risk, and to determine whether such models perform better than classical statistical analyses. Focusing on peripheral artery disease (PAD), patient data were derived from a prospective, observational study of 1,755 patients who presented for elective coronary angiography. We employed multiple supervised machine learning algorithms and utilized diverse clinical, demographic, imaging and genomic information in a hypothesis-free manner to build models that could identify patients with PAD and predict future mortality. Comparison was made to standard stepwise linear regression models. Our machine-learned models outperformed stepwise logistic regression models both for the identification of patients with PAD (AUC 0.87 versus 0.76, respectively, P=0.03), and predicting future mortality (AUC 0.76 versus 0.65, respectively, P=0.10). Both machine-learned models were markedly better calibrated than the stepwise logistic regression models, thus providing more accurate disease and mortality risk estimates. Machine learning approaches can produce more accurate disease classification and prediction models. These tools may prove clinically useful for the automated identification of patients with highly morbid diseases for which aggressive risk factor management can improve outcomes.
登录
查看更多内容
影响因子：
4.5
作者：
Jung K;Shah NH
通讯作者：
Shah NH
影响因子：
2.6
作者：
Finlay, G. Duncan;Rothman, Michael J.;Smith, Robert A.
通讯作者：
Smith, Robert A.
影响因子：
--
作者：
Celi LA;Tang RJ;Villarroel MC;Davidzon GA;Lester WT;Chueh HC
通讯作者：
Chueh HC
影响因子：
17.1
作者：
Henry, Katharine E.;Hager, David N.;Saria, Suchi
通讯作者：
Saria, Suchi
影响因子：
168.9
作者：
Fowkes, F. Gerald R.;Rudan, Diana;Criqui, Michael H.
通讯作者：
Criqui, Michael H.