A Critical Comparative Study of Liver Patients from USA and INDIA: An Exploratory Analysis

Recent research studies on liver diagnosis indicated difference in classification accuracy of various classifiers with different data sets. K-Nearest Neighbor classifier is observed to be giving best results with India liver patients’ data set with all feature set combinations. Performance is better for the India Liver dataset compared to UCLA liver dataset with all the selected algorithms [1]. In order to envisage the reason for this difference, we propose to analyze the liver patients’ populations of both USA and India. We have carried out extensive ANOVA, MANOVA analysis on these data sets to observe any significant difference among the groups. It has observed that liver patients of both the countries are having significant difference which is the reason for difference in classifiers performance. Results of this study are very important for the development of automatic medical diagnosis system and the need for its localization settings based

[1]  D. J. Newman,et al.  UCI Repository of Machine Learning Database , 1998 .

[2]  Zahra Moussavi,et al.  Application of fractal dimension on vestibular response signals for diagnosis of Parkinson's disease , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[3]  Catherine Blake,et al.  UCI Repository of machine learning databases , 1998 .

[4]  A Villers Ruiz,et al.  Statistical package for the social sciences (spss) , 1981 .

[5]  Ajai S. Gaur,et al.  Statistical Methods for Practice and Research: A Guide to Data Analysis Using SPSS , 2006 .

[6]  William A. Sandham,et al.  Assessment of the effect of time in the repeatability of the stabilometric parameters in diabetic and non-diabetic subjects during bipedal standing using the LorAn pressure distribution measurement system , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[7]  S. Dimitrova.  Investigations of some human physiological parameters in relation to geomagnetic variations of solar origin and meteorological factors , 2005, Proceedings of 2nd International Conference on Recent Advances in Space Technologies, 2005. RAST 2005..

[8]  A. Vadivel,et al.  Classifying Digital Mammogram Masses Using Univariate ANOVA Discriminant Analysis , 2009, 2009 International Conference on Advances in Recent Technologies in Communication and Computing.

[9]  Timothy A. Thomas,et al.  OFDM channel estimation in the presence of interference , 2004, IEEE Transactions on Signal Processing.

[10]  D. Moitre,et al.  Multivariate Analysis of Variance Applied to Competitive Electricity Markets: The Fixed Effects Model , 2007, 2007 IEEE Power Engineering Society General Meeting.

[11]  A. Infantosi,et al.  Multivariate analysis of neonatal EEG in different sleep stages: methods and preliminary results , 1995, Proceedings of 17th International Conference of the Engineering in Medicine and Biology Society.

[13]  Neven Cukrov,et al.  Anthropogenic and natural influences on the Krka River (Croatia) evaluated by multivariate statistical analysis , 2009, Proceedings of the ITI 2009 31st International Conference on Information Technology Interfaces.

[14]  Junning Li,et al.  A Framework for Group Analysis of fMRI Data using Dynamic Bayesian Networks , 2007, 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[15]  Z. Haddi,et al.  Application of a portable electronic nose device to discriminate and identify cheeses with known percentages of cow's and goat's milk , 2010, 2010 IEEE Sensors.

[16]  B. F. Merembeck,et al.  Directed Canonical Analysis And the Performance of Classifiers under Its Associated Linear Transformation , 1980, IEEE Transactions on Geoscience and Remote Sensing.