A noninvasive intelligent approach for predicting the risk in dengue patients

The scope of the difficulties that has been addressed in dengue disease includes the definition of the risk criteria in dengue disease and the prediction of the risk in dengue patients. It is critical to precisely and efficiently predict the level of risk in dengue disease for clinical care, surveillance and lifesaving. Even though some studies showed significant results in this area, a complete, systematic approach for predicting the risk in dengue disease has never been attained yet. Therefore, this study was carried out to develop a noninvasive intelligent technique for predicting the risk in dengue patients. A combination of the self-organizing map (SOM) and multilayer feed-forward neural networks (MFNN) was employed for this task. Clinical manifestations and bioelectrical impedance analysis (BIA) parameters belonging to the dengue patients were considered for this aim. The SOM was used to define the significant risk predictors, whereas the MFNN was employed for constructing the prediction model. Seven significant risk predictors as defined by SOM were employed for the dengue patient risk classification. The MFNN prediction model defined by 10 hidden neurons, momentum of 0.99, learning rate of 0.1 and iteration rate of 20,000 achieved a 70% predicative accuracy with 0.121 sum squared error.

[1]  Mohd Nasir Taib,et al.  Analysis of significant factors for dengue infection prognosis using the self organizing map , 2008, 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[2]  Xinxing Wu,et al.  Constructing of the risk classification model of cervical cancer by artificial neural network , 2007, Expert Syst. Appl..

[3]  David Gil Méndez,et al.  Application of artificial neural networks in the diagnosis of urological dysfunctions , 2009, Expert Syst. Appl..

[4]  S. Hales,et al.  Potential effect of population and climate changes on global distribution of dengue fever: an empirical model , 2002, The Lancet.

[5]  Tom Solomon,et al.  Clinical diagnosis and assessment of severity of confirmed dengue infections in Vietnamese children: is the world health organization classification system helpful? , 2004, The American journal of tropical medicine and hygiene.

[6]  F. Ibrahim,et al.  Prognosis of Dengue Fever and Dengue Haemorrhagic Fever using Bioelectrical Impedance , 2005 .

[7]  A. Kroeger,et al.  Classifying dengue: a review of the difficulties in using the WHO case classification for dengue haemorrhagic fever , 2006, Tropical medicine & international health : TM & IH.

[8]  Mehmet Engin,et al.  The classification of human tremor signals using artificial neural network , 2007, Expert Syst. Appl..

[9]  Fatimah Ibrahim,et al.  A novel dengue fever (DF) and dengue haemorrhagic fever (DHF) analysis using artificial neural network (ANN) , 2005, Comput. Methods Programs Biomed..

[10]  M Narayanan,et al.  Dengue Fever - Clinical and Laboratory Parameters Associated with Complications , 2003 .

[11]  P. W. Chan,et al.  Risk factors for hemorrhage in severe dengue infections. , 2002, The Journal of pediatrics.

[12]  Fatimah Binti Ibrahim.  Fatimah Ibrahim, 2005, Prognosis of dengue fever and dengue haemorrhagic fever using bioelectric impedance, Department of Biomedical Engineering, Faculty of Engineering, University of Malaya, Kuala Lumpur , 2005 .

[13]  Sadik Kara,et al.  Comparison of multilayer perceptron training algorithms for portal venous doppler signals in the cirrhosis disease , 2006, Expert Syst. Appl..

[14]  G. Crane.  Dengue haemorrhagic fever: diagnosis, treatment, prevention and control , 1999 .

[15]  M. Datta,et al.  Predictors of spontaneous bleeding in Dengue , 2004, Indian journal of pediatrics.

[16]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[17]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[18]  D. Gubler.  Epidemic dengue/dengue hemorrhagic fever as a public health, social and economic problem in the 21st century. , 2002, Trends in microbiology.

[19]  Taweewong Tantracheewathorn,et al.  Risk factors of dengue shock syndrome in children. , 2007, Journal of the Medical Association of Thailand = Chotmaihet thangphaet.

[20]  Esa Alhoniemi,et al.  Self-Organizing Map for Data Mining in MATLAB: The SOM Toolbox , 1999 .

[21]  A. Nisalak,et al.  Early clinical and laboratory indicators of acute dengue illness. , 1997, The Journal of infectious diseases.

[22]  Faisal T Ibrahim F. Taib M.N.  Proposition of new risk classification criteriafor dengue patients , 2008 .

[23]  Juha Vesanto,et al.  Hunting for Correlations in Data Using the Self-Organizing Map , 1999 .

[24]  T. Monath,et al.  Dengue: the risk to developed and developing countries. , 1994, Proceedings of the National Academy of Sciences of the United States of America.

[25]  Fatimah Ibrahim,et al.  A novel approach to classify risk in dengue hemorrhagic fever (DHF) using bioelectrical impedance analysis (BIA) , 2005, IEEE Transactions on Instrumentation and Measurement.

[26]  D. Gubler,et al.  Dengue and Dengue Hemorrhagic Fever , 1998, Clinical Microbiology Reviews.

[27]  Francesco Corona,et al.  MEASURES OF TOPOLOGICAL RELEVANCE FOR SOFT SENSING PRODUCT PROPERTIES , 2007 .

[28]  Teuvo Kohonen,et al.  The self-organizing map , 1990 .