Learning stochastic finite-state transducer to predict individual patient outcomes

详细信息    查看全文

• 作者：Patricia Ordoñez ; Nelson Schwarz ; Adnel Figueroa-Jiménez…
• 关键词：Prediction of patient outcomes ; Machine learning ; Classification and visualization of physiological data
• 刊名：Health and Technology
• 出版年：2016
• 出版时间：November 2016
• 年：2016
• 卷：6
• 期：3
• 页码：239-245
• 全文大小：558KB
• 刊物主题：Biomedical Engineering; Computational Biology/Bioinformatics; Medicine/Public Health, general; Biomedicine, general; R & D/Technology Policy; Biological and Medical Physics, Biophysics;
• 出版者：Springer Berlin Heidelberg
• ISSN：2190-7196
• 卷排序：6

文摘

The high frequency data in intensive care unit is flashed on a screen for a few seconds and never used again. However, this data can be used by machine learning and data mining techniques to predict patient outcomes. Learning finite-state transducers (FSTs) have been widely used in problems where sequences need to be manipulated and insertions, deletions and substitutions need to be modeled. In this paper, we learned the edit distance costs of a symbolic univariate time series representation through a stochastic finite-state transducer to predict patient outcomes in intensive care units. The Nearest-Neighbor method with these learned costs was used to classify the patient status within an hour after 10 h of data. Several experiments were developed to estimate the parameters that better fit the model regarding the prediction metrics. Our best results are compared with published works, where most of the metrics (i.e., Accuracy, Precision and F-measure) were improved.