Feature Ranking in Predictive Models for Hospital-Acquired Acute Kidney Injury.
Feature Ranking in Predictive Models for Hospital-Acquired Acute Kidney Injury.
复制标题
医院获得性急性肾损伤预测模型中的特征排名
DOI：
10.1038/s41598-018-35487-0
复制
发表时间：
2018-11-23
影响因子：
4.6
通讯作者：
Liu M
中科院分区：
文献类型：
--
作者：
Wu L;Hu Y;Liu X;Zhang X;Chen W;Yu ASL;Kellum JA;Waitman LR;Liu M
急性肾损伤（AKI）是住院患者中常见的并发症，其成本、发病率和死亡率显著增加。早期预测AKI具有深远的临床意义，因为目前没有治疗AKI的方法。特征选择（FS）是建立准确和可解释的预测模型的必要过程，但据我们所知，还没有研究调查了这种选择过程对AKI的鲁棒性和适用性。在这项研究中，我们比较了使用9年电子病历（EMR）预测AKI的8种广泛应用的FS方法，并检查了这些方法产生的特征排名的异质性。比较了FS方法在数据采样变化、选择结果之间的相似性和AKI预测性能方面的稳定性。预测精度并不能从本质上保证特征排序的稳定性。在不同的FS方法中，预测性能变化不显著，但特征的重要性排序有较大差异。适宜FS方法的复杂度与样本量呈正相关。该研究提供了一些实际意义，包括认识到特征稳定性的重要性，因为它是模型可重复性的理想选择，确定重要的AKI危险因素以进行进一步研究，并促进AKI的早期预测。
Acute Kidney Injury (AKI) is a common complication encountered among hospitalized patients, imposing significantly increased cost, morbidity, and mortality. Early prediction of AKI has profound clinical implications because currently no treatment exists for AKI once it develops. Feature selection (FS) is an essential process for building accurate and interpretable prediction models, but to our best knowledge no study has investigated the robustness and applicability of such selection process for AKI. In this study, we compared eight widely-applied FS methods for AKI prediction using nine-years of electronic medical records (EMR) and examined heterogeneity in feature rankings produced by the methods. FS methods were compared in terms of stability with respect to data sampling variation, similarity between selection results, and AKI prediction performance. Prediction accuracy did not intrinsically guarantee the feature ranking stability. Across different FS methods, the prediction performance did not change significantly, while the importance rankings of features were quite different. A positive correlation was observed between the complexity of suitable FS method and sample size. This study provides several practical implications, including recognizing the importance of feature stability as it is desirable for model reproducibility, identifying important AKI risk factors for further investigation, and facilitating early prediction of AKI.
登录
查看更多内容
DOI：
10.1136/amiajnl-2014-002733
发表时间：
2014-11
期刊：
Journal of the American Medical Informatics Association : JAMIA
影响因子：
--
作者：
Huang SH;LePendu P;Iyer SV;Tai-Seale M;Carrell D;Shah NH
通讯作者：
Shah NH
影响因子：
38.9
作者：
Flechet, Marine;Guiza, Fabian;Meyfroidt, Geert
通讯作者：
Meyfroidt, Geert
影响因子：
8
作者：
Bradley, AP
通讯作者：
Bradley, AP
DOI：
10.1093/bioinformatics/btp191
发表时间：
2009-06-15
期刊：
Bioinformatics (Oxford, England)
影响因子：
--
作者：
Abeel T;Van de Peer Y;Saeys Y
通讯作者：
Saeys Y
影响因子：
4.6
作者：
Miotto R;Li L;Kidd BA;Dudley JT
通讯作者：
Dudley JT