Feature Selection Techniques for a Machine Learning Model to Detect Autonomic Dysreflexia.
Feature Selection Techniques for a Machine Learning Model to Detect Autonomic Dysreflexia.
复制标题
DOI：
10.3389/fninf.2022.901428
复制
发表时间：
2022
影响因子：
3.5
通讯作者：
Duerstock, Bradley S.
中科院分区：
文献类型：
--
作者：
Suresh, Shruthi;Newton, David T.;Everett, Thomas H.;Lin, Guang;Duerstock, Bradley S.
特征选择在机器学习算法的开发中起着至关重要的作用。了解特征对模型的影响及其生理相关性可以提高性能。这在需要用相对少量的数据来识别疾病状态的医疗保健领域中特别有帮助。自主神经反射障碍（AD）就是这样一个例子，其中这种神经系统疾病的管理不当可能导致脊髓损伤患者的严重后果。我们探索了不同的特征选择方法，以提高机器学习模型在检测AD发作时的性能。我们提出了不同的技术，以及使用从心电图，皮肤神经活动，血压和温度中提取的36个特征的数据集的理想指标。表现最好的算法是具有五个相关特征的五层神经网络，其在AD检测中的准确率为93.4%。本文中的技术可以应用于无数的医疗数据集，从而可以进行更深入的探索和改进机器学习模型的开发。通过关键特征选择，可以设计更好的机器学习算法，用于使用较小的数据集检测小生境疾病状态。
Feature selection plays a crucial role in the development of machine learning algorithms. Understanding the impact of the features on a model, and their physiological relevance can improve the performance. This is particularly helpful in the healthcare domain wherein disease states need to be identified with relatively small quantities of data. Autonomic Dysreflexia (AD) is one such example, wherein mismanagement of this neurological condition could lead to severe consequences for individuals with spinal cord injuries. We explore different methods of feature selection needed to improve the performance of a machine learning model in the detection of the onset of AD. We present different techniques used as well as the ideal metrics using a dataset of thirty-six features extracted from electrocardiograms, skin nerve activity, blood pressure and temperature. The best performing algorithm was a 5-layer neural network with five relevant features, which resulted in 93.4% accuracy in the detection of AD. The techniques in this paper can be applied to a myriad of healthcare datasets allowing forays into deeper exploration and improved machine learning model development. Through critical feature selection, it is possible to design better machine learning algorithms for detection of niche disease states using smaller datasets.
登录
查看更多内容
影响因子：
6.8
作者：
Rumshisky A;Ghassemi M;Naumann T;Szolovits P;Castro VM;McCoy TH;Perlis RH
通讯作者：
Perlis RH
影响因子：
--
作者：
Lenis G;Pilia N;Loewe A;Schulze WH;Dössel O
通讯作者：
Dössel O
DOI：
10.3791/1291
发表时间：
2009-05-15
期刊：
Journal of visualized experiments : JoVE
影响因子：
--
作者：
Daugherty, Alan;Rateri, Debra;Balakrishnan, Anju
通讯作者：
Balakrishnan, Anju
影响因子：
64.8
作者：
Esteva A;Kuprel B;Novoa RA;Ko J;Swetter SM;Blau HM;Thrun S
通讯作者：
Thrun S
影响因子：
3.1
作者：
Alfaras, Miquel;Soriano, Miguel C.;Ortin, Silvia
通讯作者：
Ortin, Silvia