A Survey on Predictive Data mining Approaches for Medical Informatics

Among various data mining techniques, classification analysis is widely adopted for supporting medical diagnostic decisions. Medical diagnosis is considered as a classification problem: a record represents a given patient's case, predictor features are all patients' data and the class label is the diagnosis. Subsequently, the built classification model is essential and used to predict appropriate classes for novel and uncategorized cases. Medical data often contain irrelevant features and noise. Feature selection is frequently adopted to identify and remove the irrelevant and redundant information as much as possible. The selection of appropriate subset of the available features can yield a compact and easily interpretable representation of the target concept, model the target task adequately, and improve the classification accuracy especially in medical region .The Medical diagnosis is a complex and dynamic system with noisy, non stationary and chaotic data series. The aim of this paper is to explain the potential day by day research contributions of data mining to solve the complex problem of Medical diagnosis prediction. This study paper synthesizes five significant works and explains how data mining is gaining popularity in medical field.

[1]  Pasi Luukka,et al.  Similarity classifier in diagnosis of bladder cancer , 2008, Comput. Methods Programs Biomed..

[2]  Matthew A. Kupinski,et al.  Feature selection and classifiers for the computerized detection of mass lesions in digital mammography , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[3]  Juanying Xie,et al.  Using support vector machines with a novel hybrid feature selection method for diagnosis of erythemato-squamous diseases , 2011, Expert Syst. Appl..

[4]  Pat Langley,et al.  Selection of Relevant Features and Examples in Machine Learning , 1997, Artif. Intell..

[5]  Paul Scheunders,et al.  Genetic feature selection combined with composite fuzzy nearest neighbor classifiers for high-dimensional remote sensing data , 2000, Smc 2000 conference proceedings. 2000 ieee international conference on systems, man and cybernetics. 'cybernetics evolving to systems, humans, organizations, and their complex interactions' (cat. no.0.

[6]  J. Victor Marcos,et al.  Feature selection from nocturnal oximetry using genetic algorithms to assist in obstructive sleep apnoea diagnosis. , 2012, Medical engineering & physics.

[7]  C.W. Anderson,et al.  Comparison of linear, nonlinear, and feature selection methods for EEG signal classification , 2003, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[8]  A.J. Hoffman,et al.  Seismic buffer recognition using mutual information for selecting wavelet based features , 1998, IEEE International Symposium on Industrial Electronics. Proceedings. ISIE'98 (Cat. No.98TH8357).

[9]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[10]  Sam Kwong,et al.  Genetic algorithms and their applications , 1996, IEEE Signal Process. Mag..

[11]  Padraig Cunningham,et al.  Diversity versus Quality in Classification Ensembles Based on Feature Selection , 2000, ECML.

[12]  Mostefa Mesbah,et al.  An optimal feature set for seizure detection systems for newborn EEG signals , 2003, Proceedings of the 2003 International Symposium on Circuits and Systems, 2003. ISCAS '03..

[13]  Yanqing Zhang,et al.  Support vector machines with genetic fuzzy feature transformation for biomedical data classification , 2007, Inf. Sci..

[14]  H. K. Huang,et al.  Feature selection in the pattern classification problem of digital chest radiograph segmentation , 1995, IEEE Trans. Medical Imaging.

[15]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

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

[17]  T. Warren Liao.  Diagnosis of bladder cancers with small sample size via feature selection , 2011, Expert Syst. Appl..

[18]  Dayou Liu,et al.  A support vector machine classifier with rough set-based feature selection for breast cancer diagnosis , 2011, Expert Syst. Appl..