Random forests for automatic differential diagnosis of erythemato-squamous diseases

Erythemato–squamous diseases (ESD) are frequent skin diseases that share some clinical features of erythema and scaling. Their automatic diagnosis was tackled using several approaches that achieved high performance accuracy. However, they generally remained unattractive for dermatologists because of the lack of direct readability of their output models. Decision trees are easy to understand, but their performance and structure are very sensitive to data changes. Ensembles of decision trees were introduced to reduce the effect of these problems, but on the expense of interpretability. In this paper, we present the results of our investigation of random forests and boosting as ensemble methods for the differential diagnosis of ESD. Experiments on clinical and histopathological data showed that the random forest outperformed the other ensemble classifiers in terms of accuracy, sensitivity and specificity. Its diagnosis accuracy, attaining more than 98%, was also better than those of classifiers based on genetic programming, genetic algorithms and k–means clustering.

[1]  Arif Gülten,et al.  A Robust Multi-Class Feature Selection Strategy Based on Rotation Forest Ensemble Algorithm for Diagnosis of Erythemato-Squamous Diseases , 2012, Journal of Medical Systems.

[2]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[3]  M. Cevdet Ince,et al.  A new feature selection method based on association rules for diagnosis of erythemato-squamous diseases , 2009, Expert Syst. Appl..

[4]  Elif Derya íbeyli.  Multiclass support vector machines for diagnosis of erythemato-squamous diseases , 2008 .

[5]  Mark Craven,et al.  Extracting comprehensible models from trained neural networks , 1996 .

[6]  Agnar Aamodt,et al.  Architectures Integrating Case-Based Reasoning and Bayesian Networks for Clinical Decision Support , 2010, Intelligent Information Processing.

[7]  Yali Amit,et al.  Shape Quantization and Recognition with Randomized Trees , 1997, Neural Computation.

[8]  Kemal Polat,et al.  A novel hybrid intelligent method based on C4.5 decision tree classifier and one-against-all approach for multi-class classification problems , 2009, Expert Syst. Appl..

[9]  Anupam Shukla,et al.  Clinical Decision Support System for Fetal Delivery Using Artificial Neural Network , 2009, 2009 International Conference on New Trends in Information and Service Science.

[10]  Byoung-Tak Zhang,et al.  AptaCDSS-E: A classifier ensemble-based clinical decision support system for cardiovascular disease level prediction , 2008, Expert Syst. Appl..

[11]  Ludmil Mikhailov,et al.  Evolving fuzzy medical diagnosis of Pima Indians diabetes and of dermatological diseases , 2010, Artif. Intell. Medicine.

[12]  Vijay Kumar Mago,et al.  Clinical decision support system for dental treatment , 2012, J. Comput. Sci..

[13]  Elpiniki I. Papageorgiou,et al.  Fuzzy cognitive map ensemble learning paradigm to solve classification problems: Application to autism identification , 2012, Appl. Soft Comput..

[14]  Ayhan Demiriz,et al.  Linear Programming Boosting via Column Generation , 2002, Machine Learning.

[15]  Eric Bauer,et al.  An Empirical Comparison of Voting Classification Algorithms: Bagging, Boosting, and Variants , 1999, Machine Learning.

[16]  P. K. Anooj,et al.  Clinical decision support system: Risk level prediction of heart disease using weighted fuzzy rules , 2012, J. King Saud Univ. Comput. Inf. Sci..

[17]  Thomas Richardson,et al.  Interpretable Boosted Naïve Bayes Classification , 1998, KDD.

[18]  Muhammad Zubair Shafiq,et al.  Guidelines to Select Machine Learning Scheme for Classification of Biomedical Datasets , 2009, EvoBIO.

[19]  Mirza Mansoor Baig,et al.  Fuzzy logic based smart Anaesthesia monitoring system in the operation theatre , 2012 .

[20]  Ian H. Witten,et al.  The WEKA data mining software: an update , 2009, SKDD.

[21]  H. Altay Güvenir,et al.  Learning differential diagnosis of erythemato-squamous diseases using voting feature intervals , 1998, Artif. Intell. Medicine.

[22]  David Gil Méndez,et al.  Decision Support System for the Diagnosis of Urological Dysfunctions Based on Fuzzy Logic , 2010, DCAI.

[23]  Arif Gülten,et al.  Classifier ensemble construction with rotation forest to improve medical diagnosis performance of machine learning algorithms , 2011, Comput. Methods Programs Biomed..

[24]  Alex Alves Freitas,et al.  A constrained-syntax genetic programming system for discovering classification rules: application to medical data sets , 2004, Artif. Intell. Medicine.

[25]  Pedro M. Domingos.  Knowledge Discovery Via Multiple Models , 1998, Intell. Data Anal..

[26]  L. Breiman.  OUT-OF-BAG ESTIMATION , 1996 .

[27]  Latha Parthiban,et al.  An intelligent agent for detection of erythemato- squamous diseases using Co-active Neuro-Fuzzy Inference System and genetic algorithm , 2009, 2009 International Conference on Intelligent Agent & Multi-Agent Systems.

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

[29]  Hendrik Blockeel,et al.  Seeing the Forest Through the Trees: Learning a Comprehensible Model from an Ensemble , 2007, ECML.

[30]  Elif Derya Übeyli,et al.  Automatic detection of erythemato-squamous diseases using adaptive neuro-fuzzy inference systems , 2004, Comput. Biol. Medicine.

[31]  Jacek M. Zurada,et al.  Training neural network classifiers for medical decision making: The effects of imbalanced datasets on classification performance , 2008, Neural Networks.

[32]  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..

[33]  Elif Derya Übeyli,et al.  Automatic Detection of Erythemato-Squamous Diseases Using k-Means Clustering , 2010, Journal of Medical Systems.

[34]  Elif Derya íbeyli.  Combined neural networks for diagnosis of erythemato-squamous diseases , 2009 .

[35]  Loris Nanni,et al.  An ensemble of classifiers for the diagnosis of erythemato-squamous diseases , 2006, Neurocomputing.

[36]  Novruz Allahverdi,et al.  Design of a fuzzy expert system for determination of coronary heart disease risk , 2007, CompSysTech '07.

[37]  Sim Heng Ong,et al.  Ensemble-based regression analysis of multimodal medical data for osteopenia diagnosis , 2013, Expert Syst. Appl..

[38]  Yoav Freund,et al.  Experiments with a New Boosting Algorithm , 1996, ICML.

[39]  H. A Güvenir,et al.  An expert system for the differential diagnosis of erythemato-squamous diseases , 2000 .

[40]  Alex A. Freitas,et al.  Discovering comprehensible classification rules with a genetic algorithm , 2000, Proceedings of the 2000 Congress on Evolutionary Computation. CEC00 (Cat. No.00TH8512).

[41]  José Hernández-Orallo,et al.  From Ensemble Methods to Comprehensible Models , 2002, Discovery Science.

[42]  Davar Giveki,et al.  Automatic detection of erythemato-squamous diseases using PSO-SVM based on association rules , 2013, Eng. Appl. Artif. Intell..

[43]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.