出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：A huge amount of medical data is generated every day, which presents a challenge in analysingthese data. The obvious solution to this challenge is to reduce the amount of data withoutinformation loss. Dimension reduction is considered the most popular approach for reducingdata size and also to reduce noise and redundancies in data. In this paper, we investigate theeffect of feature selection in improving the prediction of patient deterioration in ICUs. Weconsider lab tests as features. Thus, choosing a subset of features would mean choosing themost important lab tests to perform. If the number of tests can be reduced by identifying themost important tests, then we could also identify the redundant tests. By omitting the redundanttests, observation time could be reduced and early treatment could be provided to avoid the risk.Additionally, unnecessary monetary cost would be avoided. Our approach uses state-of-the-artfeature selection for predicting ICU patient deterioration using the medical lab results. Weapply our technique on the publicly available MIMIC-II database and show the effectiveness ofthe feature selection. We also provide a detailed analysis of the best features identified by ourapproach.
关键词：Big data analytics; data mining; ICU; lab test; feature selection; learning algorithm
