ICU Patient Deterioration prediction: a Data-Mining Approach

A huge amount of medical data is generated every day, which presents a challenge in analysing these data. The obvious solution to this challenge is to reduce the amount of data without information loss. Dimension reduction is considered the most popular approach for reducing data size and also to reduce noise and redundancies in data. In this paper, we investigate the effect of feature selection in improving the prediction of patient deterioration in ICUs. We consider lab tests as features. Thus, choosing a subset of features would mean choosing the most important lab tests to perform. If the number of tests can be reduced by identifying the most important tests, then we could also identify the redundant tests. By omitting the redundant tests, 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-ofthe- art feature selection for predicting ICU patient deterioration using the medical lab results. We apply our technique on the publicly available MIMIC-II database and show the effectiveness of the feature selection. We also provide a detailed analysis of the best features identified by our approach.

[1]  Yixin Chen,et al.  An integrated data mining approach to real-time clinical monitoring and deterioration warning , 2012, KDD.

[2]  Nazar Zaki,et al.  Ant Colony Optimization Algorithm for Interpretable Bayesian Classifiers Combination: Application to Medical Predictions , 2014, PloS one.

[3]  Mohammed Saeed,et al.  Latent topic discovery of clinical concepts from hospital discharge summaries of a heterogeneous patient cohort , 2014, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[4]  Qingzhong Liu,et al.  Mining the Big Data: The Critical Feature Dimension Problem , 2014, 2014 IIAI 3rd International Conference on Advanced Applied Informatics.

[5]  L. Celi,et al.  Customized Prediction of Short Length of Stay Following Elective Cardiac Surgery in Elderly Patients Using a Genetic Algorithm , 2013, World journal of cardiovascular surgery.

[6]  Kjell Johnson,et al.  An Introduction to Feature Selection , 2013 .

[7]  J. Platt Sequential Minimal Optimization : A Fast Algorithm for Training Support Vector Machines , 1998 .

[8]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[9]  Philip S. Yu,et al.  Top 10 algorithms in data mining , 2007, Knowledge and Information Systems.

[10]  Mohammed Saeed,et al.  Methods of Blood Pressure Measurement in the ICU* , 2013, Critical care medicine.

[11]  Chitra Nasa,et al.  Evaluation of Different Classification Techniques for WEB Data , 2012 .

[12]  João Miguel da Costa Sousa,et al.  Reducing unnecessary lab testing in the ICU with artificial intelligence , 2013, Int. J. Medical Informatics.

[13]  Viju Raghupathi,et al.  Big data analytics in healthcare: promise and potential , 2014, Health Information Science and Systems.

[14]  Pedro Larrañaga,et al.  A review of feature selection techniques in bioinformatics , 2007, Bioinform..

[15]  Marios D. Dikaiakos,et al.  Big Data in Healthcare: Intensive Care Units as a Case Study , 2014, ERCIM News.