Analytical Study of Selected Classification Algorithms for Clinical Dataset

The objective of this paper is to analyze and identify the best classification solution for clinical decision making. Several classification algorithms Like Discriminant Analysis (LDA), Support Vector Machine (SVM), Artificial Neural Network (ANN), Naive Bayes (NB), and Decision Trees are compared to find the optimum diagnostic accuracy. The performance of classification algorithms are compared using benchmark dataset, breast cancer. The effects of normalization using z-score and min-max approaches are also investigated. The results are compared based on different performance parameters like accuracy, sensitivity, specificity and root node error value. Accuracy has been improved for all classifications methods after normalizing the data set. Z-score normalization performs better for all the measures when compared to min-max normalization. The proposed approach shows higher accuracy rate for Naive Bayes algorithm when compared with the other algorithms.

[1]  Kuldip K. Paliwal,et al.  Cancer classification by gradient LDA technique using microarray gene expression data , 2008, Data Knowl. Eng..

[2]  T. Velmurugan,et al.  A Comparative Analysis on the Evaluation of Classification Algorithms in the Prediction of Students Performance , 2015 .

[3]  Hao Jiang,et al.  Towards Prediction of Pancreatic Cancer Using SVM Study Model , 2014 .

[4]  Atul Kumar Pandey,et al.  A Heart Disease Prediction Model Using Decision Tree , 2013 .

[5]  C. P. Sumathi,et al.  A Novel Metaheuristic Data Mining Algorithm for the Detection and Classification of Parkinson Disease , 2015 .

[6]  R. Manjula,et al.  Data Mining: Building Social Network , 2015 .

[7]  K. Duraiswamy,et al.  EVALUATION OF NEURAL NETWORK BASED CLASSIFICATION SYSTEMS FOR CLINICAL CANCER DATA CLASSIFICATION , 2008 .

[8]  S. Karthika,et al.  A Naïve Bayesian Classifier for Educational Qualification , 2015 .

[9]  Sameh Ghwanmeh,et al.  Innovative Artificial Neural Networks-Based Decision Support System for Heart Diseases Diagnosis , 2013 .

[10]  Lawrence O. Hall,et al.  A Comparison of Decision Tree Ensemble Creation Techniques , 2007 .

[11]  Jerzy Krysiński,et al.  Artificial neural networks approach to early lung cancer detection , 2014 .

[12]  Seyyed Reza Khaze,et al.  A New Approach in Bloggers Classification with Hybrid of K-Nearest Neighbor and Artificial Neural Network Algorithms , 2015 .

[13]  K. Thenmozhi,et al.  Heart Disease Prediction Using Classification with Different Decision Tree Techniques , 2014 .

[14]  S. Charles Schulz,et al.  Classification of adolescent psychotic disorders using linear discriminant analysis , 2006, Schizophrenia Research.

[15]  Bekir Karlik,et al.  Personalized Cancer Treatment by Using Naive Bayes Classifier , 2012 .

[16]  K. Vaidehi,et al.  Breast Tissue Characterization Using Combined K-NN Classifier , 2015 .

[17]  Jason Weston,et al.  Gene Selection for Cancer Classification using Support Vector Machines , 2002, Machine Learning.

[18]  Amit Ganatra,et al.  A Comparative Study of Training Algorithms for Supervised Machine Learning , 2012 .

[19]  Thair Nu Phyu.  Survey of Classification Techniques in Data Mining , 2009 .

[20]  S. Archana,et al.  Survey of Classification Techniques in Data Mining , 2014 .

[21]  Wei-Chung Cheng,et al.  Gene selection for cancer identification: a decision tree model empowered by particle swarm optimization algorithm , 2014, BMC Bioinformatics.

[22]  Nello Cristianini,et al.  Support vector machine classification and validation of cancer tissue samples using microarray expression data , 2000, Bioinform..

[23]  Mei-Ling Huang,et al.  Fetal distress prediction using discriminant analysis, decision tree, and artificial neural network , 2012 .

[24]  B Theodoulidis,et al.  Using T3, an Improved Decision Tree Classifier, for Mining Stroke-related Medical Data , 2007, Methods of Information in Medicine.

[25]  Chun-Hsi Huang,et al.  Comparison of LDA and SPRT on Clinical Dataset Classifications , 2011, Biomedical informatics insights.