An expert system for diabetes prediction using auto tuned multi-layer perceptron

Medical Expert Systems is an active research area where data analysts and medical experts are continuously collaborating to make these systems more accurate and therefore, more useful in real life. Recent surveys by World Health Organization indicated a great increase in number of diabetic patients and the deaths that are attributed to diabetes each year. Therefore, early diagnosis of diabetes is a major concern among researchers and practitioners. The paper presents an application of automatic multilayer perceptron (AutoMLP) which is combined with an outlier detection method Enhanced Class Outlier Detection using distance based algorithm to create a novel prediction framework. AutoMLP is an auto-tunable and performs parameter optimization automatically on the run during training process, which otherwise requires human intervention. Our framework performs outlier detection during pre-processing of data. A series of experiments are performed publicly available dataset: UCI (Prima Indian) and system achieved an accuracy of 88.7% which bests the highest reported results.

[1]  Nabil M. Hewahi,et al.  A comparative Study of Outlier Mining and Class Outlier Mining , 2009 .

[2]  N. A. Nnamoko,et al.  Meta-classification model for diabetes onset forecast: A proof of concept , 2014, 2014 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[3]  Fevzullah Temurtas,et al.  A comparative study on diabetes disease diagnosis using neural networks , 2009, Expert Syst. Appl..

[4]  Xuehui Meng,et al.  Comparison of three data mining models for predicting diabetes or prediabetes by risk factors , 2013, The Kaohsiung journal of medical sciences.

[5]  Senlin Luo,et al.  Rule Extraction From Support Vector Machines Using Ensemble Learning Approach: An Application for Diagnosis of Diabetes , 2015, IEEE Journal of Biomedical and Health Informatics.

[6]  M Anbarasi,et al.  ENHANCED PREDICTION OF HEART DISEASE WITH FEATURE SUBSET SELECTION USING GENETIC ALGORITHM , 2010 .

[7]  Amir Akramin Shafie,et al.  A novel signal diagnosis technique using pseudo complex-valued autoregressive technique , 2011, Expert Syst. Appl..

[8]  Sungyoung Lee,et al.  Prediction of Diabetes Mellitus Based on Boosting Ensemble Modeling , 2014, UCAmI.

[9]  Dursun Delen,et al.  Predicting breast cancer survivability: a comparison of three data mining methods , 2005, Artif. Intell. Medicine.

[10]  A. A. Shafie,et al.  Application of modeling techniques to diabetes diagnosis , 2010, 2010 IEEE EMBS Conference on Biomedical Engineering and Sciences (IECBES).

[11]  Murali S. Shanker,et al.  Using Neural Networks To Predict the Onset of Diabetes Mellitus , 1996, J. Chem. Inf. Comput. Sci..

[12]  Usman Qamar,et al.  HMV: A medical decision support framework using multi-layer classifiers for disease prediction , 2016, J. Comput. Sci..

[13]  Nabil M. Hewahi,et al.  Class Outliers Mining: Distance-Based Approach , 2007 .

[14]  Bayu Adhi Tama,et al.  An Early Detection Method of Type-2 Diabetes Mellitus in Public Hospital , 2011 .

[15]  Somula Ramasubbareddy,et al.  Classification of Heart Disease Using Support Vector Machine , 2019, Journal of Computational and Theoretical Nanoscience.

[16]  Jin Park,et al.  A sequential neural network model for diabetes prediction , 2001, Artif. Intell. Medicine.

[17]  Illhoi Yoo,et al.  Data Mining in Healthcare and Biomedicine: A Survey of the Literature , 2012, Journal of Medical Systems.

[18]  Praveen Kumar,et al.  Improving the Prediction Rate of Diabetes Diagnosis Using Fuzzy, Neural Network, Case Based (FNC) Approach , 2012 .

[19]  Shweta Kharya,et al.  Using data mining techniques for diagnosis and prognosis of cancer disease , 2012, ArXiv.

[20]  M A Musen,et al.  Sequential versus standard neural networks for pattern recognition: An example using the domain of coronary heart disease , 1997, Comput. Biol. Medicine.

[21]  K Kasikumar,et al.  Applications of Data Mining Techniques in Healthcare and Prediction of Heart Attacks , 2018, International Journal of Data Mining Techniques and Applications.