Conditional mutual information-based feature selection for congestive heart failure recognition using heart rate variability

Feature selection plays an important role in pattern recognition systems. In this study, we explored the problem of selecting effective heart rate variability (HRV) features for recognizing congestive heart failure (CHF) based on mutual information (MI). The MI-based greedy feature selection approach proposed by Battiti was adopted in the study. The mutual information conditioned by the first-selected feature was used as a criterion for feature selection. The uniform distribution assumption was used to reduce the computational load. And, a logarithmic exponent weighting was added to model the relative importance of the MI with respect to the number of the already-selected features. The CHF recognition system contained a feature extractor that generated four categories, totally 50, features from the input HRV sequences. The proposed feature selector, termed UCMIFS, proceeded to select the most effective features for the succeeding support vector machine (SVM) classifier. Prior to feature selection, the 50 features produced a high accuracy of 96.38%, which confirmed the representativeness of the original feature set. The performance of the UCMIFS selector was demonstrated to be superior to the other MI-based feature selectors including MIFS-U, CMIFS, and mRMR. When compared to the other outstanding selectors published in the literature, the proposed UCMIFS outperformed them with as high as 97.59% accuracy in recognizing CHF using only 15 features. The results demonstrated the advantage of using the recruited features in characterizing HRV sequences for CHF recognition. The UCMIFS selector further improved the efficiency of the recognition system with substantially lowered feature dimensions and elevated recognition rate.

[1]  T. Inouye,et al.  Quantification of EEG irregularity by use of the entropy of the power spectrum. , 1991, Electroencephalography and clinical neurophysiology.

[2]  Yalcin Isler,et al.  Combining classical HRV indices with wavelet entropy measures improves to performance in diagnosing congestive heart failure , 2007, Comput. Biol. Medicine.

[3]  Anil K. Jain,et al.  Statistical Pattern Recognition: A Review , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  C. M. Lim,et al.  Cardiac state diagnosis using higher order spectra of heart rate variability , 2008, Journal of medical engineering & technology.

[5]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[6]  Musa H. Asyali,et al.  Discrimination power of long-term heart rate variability measures , 2003, Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE Cat. No.03CH37439).

[7]  Ji-Wu Zhang,et al.  Bispectrum analysis of focal ischemic cerebral EEG signal using third-order recursion method , 2000, IEEE Transactions on Biomedical Engineering.

[8]  Roberto Battiti,et al.  Using mutual information for selecting features in supervised neural net learning , 1994, IEEE Trans. Neural Networks.

[9]  J. Shieh,et al.  Parameter Investigation of Detrended Fluctuation Analysis for Short-term Human Heart Rate Variability , 2010 .

[10]  G. Breithardt,et al.  Heart rate variability: standards of measurement, physiological interpretation and clinical use. Task Force of the European Society of Cardiology and the North American Society of Pacing and Electrophysiology. , 1996 .

[11]  A. Malliani,et al.  Heart rate variability. Standards of measurement, physiological interpretation, and clinical use , 1996 .

[12]  Ron Kohavi,et al.  Irrelevant Features and the Subset Selection Problem , 1994, ICML.

[13]  Bruce A. Draper,et al.  Feature selection from huge feature sets , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[14]  Chong-Ho Choi,et al.  Input feature selection for classification problems , 2002, IEEE Trans. Neural Networks.

[15]  Jacek M. Zurada,et al.  Normalized Mutual Information Feature Selection , 2009, IEEE Transactions on Neural Networks.

[16]  Niels Wessel,et al.  Potential of feature selection methods in heart rate variability analysis for the classification of different cardiovascular diseases , 2002, Statistics in medicine.

[17]  Paolo Melillo,et al.  Discrimination power of long-term heart rate variability measures for chronic heart failure detection , 2011, Medical & Biological Engineering & Computing.

[18]  Wei Liu,et al.  Conditional Mutual Information Based Feature Selection , 2008, 2008 International Symposium on Knowledge Acquisition and Modeling.

[19]  Sung-Nien Yu,et al.  Improving discriminality in heart rate variability analysis using simple artifact and trend removal preprocessors , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

[20]  Francisco Sepulveda,et al.  Classifying mental tasks based on features of higher-order statistics from EEG signals in brain-computer interface , 2008, Inf. Sci..

[21]  Huan Liu,et al.  Feature Selection for Classification , 1997, Intell. Data Anal..

[23]  Madalena Costa,et al.  Multiscale entropy analysis of biological signals. , 2005, Physical review. E, Statistical, nonlinear, and soft matter physics.

[24]  Xiaoming Xu,et al.  A Wrapper for Feature Selection Based on Mutual Information , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[25]  M. Mesbah,et al.  HRV feature selection based on discriminant and redundancy analysis for neonatal seizure detection , 2007, 2007 6th International Conference on Information, Communications & Signal Processing.

[26]  Fuhui Long,et al.  Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy , 2003, IEEE Transactions on Pattern Analysis and Machine Intelligence.