https://scholars.lib.ntu.edu.tw/handle/123456789/611804
標題: | Artificial neural networks applied to fetal monitoring in labour | 作者: | Georgieva A. Payne S.J. Moulden M. Redman C.W.G. STEPHEN JOHN PAYNE |
關鍵字: | Classification (of information);Feedforward neural networks;Fetal monitoring;Forecasting;Heart;Large dataset;Neonatal monitoring;Neural networks;Automated methods;Clinical parameters;Clinical practices;Diagnostic analysis;Feed-forward artificial neural networks;Fetal heart rate monitoring;Labour;Misclassification rates;Diagnosis | 公開日期: | 2013 | 卷: | 22 | 期: | 1 | 起(迄)頁: | 85-93 | 來源出版物: | Neural Computing and Applications | 摘要: | Birth asphyxia can result in death or permanent brain damage. To prevent it, the fetal heart rate (FHR) is recorded in labour on a paper strip. In clinical practice, the complicated FHR patterns are assessed by eye, which is error-prone, inconsistent and unreliable. Objective alternatives are needed and thus we investigated the applicability of feed-forward artificial neural networks (ANNs) for FHR analysis. Six FHR features were extracted and combined with six clinical parameters to form a feature space of 12 dimensions. The feature space was reduced to six dimensions by principal component analysis. Subsequently, a network committee of ten ANNs was trained with the data of 124 patients (a balanced set of 62 adverse, coded 1, and 62 normal outcomes, coded 0). The ANN committee was tested on another balanced set of 252 patients obtaining misclassification rate of 36%. Finally, the committee was tested on a large dataset of 7,568 patients (non-balanced). As the committee output continuously increased from 0 to 1, there was a consistent growth of the adverse outcome rate (from 0.26 to 5.3%) and the low umbilical pH rate (from 2.6 to 16.7%.) Based on this correlation between the committee output and the risk of compromise, we concluded that ANNs can be successfully applied to FHR monitoring in labour. However, extensive further work is necessary, for which we outline our plans. To our knowledge, this is the first time that an automated method for FHR diagnostic analysis has been tested on a database of this size. ? 2011 Springer-Verlag London Limited. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-84871955611&doi=10.1007%2fs00521-011-0743-y&partnerID=40&md5=d5bd60ed95c661f48c6c2c44e167eaea https://scholars.lib.ntu.edu.tw/handle/123456789/611804 |
DOI: | 10.1007/s00521-011-0743-y |
顯示於: | 應用力學研究所 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。