EAGA-MLP—An Enhanced and Adaptive Hybrid Classification Model for Diabetes Diagnosis

Disease diagnosis is a critical task which needs to be done with extreme precision. In recent times, medical data mining is gaining popularity in complex healthcare problems based disease datasets. Unstructured healthcare data constitutes irrelevant information which can affect the prediction ability of classifiers. Therefore, an effective attribute optimization technique must be used to eliminate the less relevant data and optimize the dataset for enhanced accuracy. Type 2 Diabetes, also called Pima Indian Diabetes, affects millions of people around the world. Optimization techniques can be applied to generate a reliable dataset constituting of symptoms that can be useful for more accurate diagnosis of diabetes. This study presents the implementation of a new hybrid attribute optimization algorithm called Enhanced and Adaptive Genetic Algorithm (EAGA) to get an optimized symptoms dataset. Based on readings of symptoms in the optimized dataset obtained, a possible occurrence of diabetes is forecasted. EAGA model is further used with Multilayer Perceptron (MLP) to determine the presence or absence of type 2 diabetes in patients based on the symptoms detected. The proposed classification approach was named as Enhanced and Adaptive-Genetic Algorithm-Multilayer Perceptron (EAGA-MLP). It is also implemented on seven different disease datasets to assess its impact and effectiveness. Performance of the proposed model was validated against some vital performance metrics. The results show a maximum accuracy rate of 97.76% and 1.12 s of execution time. Furthermore, the proposed model presents an F-Score value of 86.8% and a precision of 80.2%. The method is compared with many existing studies and it was observed that the classification accuracy of the proposed Enhanced and Adaptive-Genetic Algorithm-Multilayer Perceptron (EAGA-MLP) model clearly outperformed all other previous classification models. Its performance was also tested with seven other disease datasets. The mean accuracy, precision, recall and f-score obtained was 94.7%, 91%, 89.8% and 90.4%, respectively. Thus, the proposed model can assist medical experts in accurately determining risk factors of type 2 diabetes and thereby help in accurately classifying the presence of type 2 diabetes in patients. Consequently, it can be used to support healthcare experts in the diagnosis of patients affected by diabetes.

[1]  Maria-Teresa Martinez-Ingles,et al.  A Comparison of Different Models of Glycemia Dynamics for Improved Type 1 Diabetes Mellitus Management with Advanced Intelligent Analysis in an Internet of Things Context , 2020, Applied Sciences.

[2]  A. Tamilarasi,et al.  Implementation of Genetic Algorithm in Predicting Diabetes , 2012 .

[3]  Yuan Ren,et al.  Determination of Optimal SVM Parameters by Using GA/PSO , 2010, J. Comput..

[4]  V. Veena Vijayan,et al.  Prediction and diagnosis of diabetes mellitus — A machine learning approach , 2015, 2015 IEEE Recent Advances in Intelligent Computational Systems (RAICS).

[5]  Harleen Kaur,et al.  Predictive modelling and analytics for diabetes using a machine learning approach , 2020, Applied Computing and Informatics.

[6]  R. M. Chandrasekaran,et al.  Data Mining Techniques for Performance Evaluation of Diagnosis in Gestational Diabetes , 2002 .

[7]  Amine Chikh,et al.  Design of fuzzy classifier for diabetes disease using Modified Artificial Bee Colony algorithm , 2013, Comput. Methods Programs Biomed..

[8]  Sushruta Mishra,et al.  An Improved and Adaptive Attribute Selection Technique to Optimize Dengue Fever Prediction , 2018 .

[9]  Ying Li,et al.  Early Prediction of Diabetes Complications from Electronic Health Records: A Multi-Task Survival Analysis Approach , 2018, AAAI.

[10]  Yue Liu.  Artificial Intelligence–Based Neural Network for the Diagnosis of Diabetes: Model Development , 2020, JMIR medical informatics.

[11]  David Windridge,et al.  Patient level analytics using self-organising maps: A case study on Type-1 Diabetes self-care survey responses , 2014, 2014 IEEE Symposium on Computational Intelligence and Data Mining (CIDM).

[12]  A. Santhakumaran,et al.  A Novel Classification Method for Diagnosis of Diabetes Mellitus Using Artificial Neural Networks , 2010, 2010 International Conference on Data Storage and Data Engineering.

[13]  Md. Kamrul Hasan,et al.  Prediction of Disease Level Using Multilayer Perceptron of Artificial Neural Network for Patient Monitoring , 2015 .

[14]  Dinggang Shen,et al.  Multi-Layer Multi-View Classification for Alzheimer's Disease Diagnosis , 2018, AAAI.

[15]  Ricardo Femat,et al.  Fuzzy-Based Controller for Glucose Regulation in Type-1 Diabetic Patients by Subcutaneous Route , 2006, IEEE Transactions on Biomedical Engineering.

[16]  Thangavel Alphonse Thanaraj,et al.  Predictive models to assess risk of type 2 diabetes, hypertension and comorbidity: machine-learning algorithms and validation using national health data from Kuwait—a cohort study , 2013, BMJ Open.

[17]  Asma A. Al Jarullah.  Decision tree discovery for the diagnosis of type II diabetes , 2011, 2011 International Conference on Innovations in Information Technology.

[18]  Novruz Allahverdi,et al.  Design of a hybrid system for the diabetes and heart diseases , 2008, Expert Syst. Appl..

[19]  T. Pramananda Perumal,et al.  A Predictive Approach for Diabetes Mellitus Disease through Data Mining Technologies , 2014, 2014 World Congress on Computing and Communication Technologies.

[20]  Mahmood Alborzi,et al.  The Use of Genetic Algorithm, Clustering and Feature Selection Techniques in Construction of Decision Tree Models for Credit Scoring , 2013 .

[21]  Supriya Raheja,et al.  Improving the Prediction Rate of Diabetes using Fuzzy Expert System , 2015 .

[22]  Diego Andina,et al.  A Prediction Model to Diabetes Using Artificial Metaplasticity , 2011, IWINAC.

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

[24]  Aida Mustapha,et al.  Comparison between Neural Networks against Decision Tree in Improving Prediction Accuracy for Diabetes Mellitus , 2011, ICDIPC.

[25]  Ping Zhong,et al.  A new one-class SVM based on hidden information , 2014, Knowl. Based Syst..

[26]  Mei-Hui Wang,et al.  A Fuzzy Expert System for Diabetes Decision Support Application , 2011, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[27]  Ravinder Agarwal,et al.  Machine learning techniques for medical diagnosis of diabetes using iris images , 2018, Comput. Methods Programs Biomed..

[28]  A. V. Senthil Kumar,et al.  Communications in Computer and Information Science: Diagnosis of Diabetes Using Intensified Fuzzy Verdict Mechanism , 2011 .

[29]  Omar Bonerge Pineda Lezama,et al.  Diabetes Diagnostic Prediction Using Vector Support Machines , 2020, ANT/EDI40.

[30]  S Anto,et al.  A Medical Expert System based on Genetic Algorithm and Extreme Learning Machine for Diabetes Disease Diagnosis , 2014 .

[31]  Dr. R. Balasubramanian,et al.  Predicting Diabetes Mellitus using Data Mining Techniques , 2018 .

[32]  Ledisi G. Kabari,et al.  Diagnosing Diabetes Using Artificial Neural Networks , 2020 .

[33]  M.M.B.R. Vellasco,et al.  Inverted hierarchical neuro-fuzzy BSP system: a novel neuro-fuzzy model for pattern classification and rule extraction in databases , 2006, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[34]  Ashok Kumar Dwivedi.  Analysis of computational intelligence techniques for diabetes mellitus prediction , 2017, Neural Computing and Applications.

[35]  Kay Chen Tan,et al.  A hybrid evolutionary algorithm for attribute selection in data mining , 2009, Expert Syst. Appl..

[36]  Davar Giveki,et al.  Automatic Detection of Diabetes Diagnosis using Feature Weighted Support Vector Machines based on Mutual Information and Modified Cuckoo Search , 2012, ArXiv.

[37]  Kemal Polat,et al.  A cascade learning system for classification of diabetes disease: Generalized Discriminant Analysis and Least Square Support Vector Machine , 2008, Expert Syst. Appl..

[38]  E. P. Ephzibah,et al.  Cost effective approach on feature selection using genetic algorithms and fuzzy logic for diabetes diagnosis , 2011, ArXiv.

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

[40]  Riccardo Bellazzi,et al.  A stochastic model to assess the variability of blood glucose time series in diabetic patients self-monitoring , 2006, IEEE Transactions on Biomedical Engineering.

[41]  Durga Toshniwal,et al.  Hybrid prediction model for Type-2 diabetic patients , 2010, Expert Syst. Appl..

[42]  Yuan Yan Tang,et al.  An improved noninvasive method to detect Diabetes Mellitus using the Probabilistic Collaborative Representation based Classifier , 2018, Inf. Sci..

[43]  Shruti Garg,et al.  Prediction of Type 2 Diabetes using Machine Learning Classification Methods , 2020 .