A machine learning perspective: To analyze diabetes

Abstract This exploration work was directed on the plan and execution of a diabetes forecast framework, a contextual investigation of Pima Indian Diabetes. This exploration will help in robotizing expectation of diabetes even before clinicians showed up. In this analysis, diabetes is foreseen using basic credits, and the correlation of the changing characteristics is moreover depicted. The current cycle of conveying this action is physically which tends not to breaking down information adaptable for the specialists, and transmission of data isn't straightforward. Different algorithms had been used for better accuracy and the calculations are done on the basis of GINI coefficient. The neural network technique gave the best accuracy of 87.88% that can be useful for the doctors to treat this disease at an early stage.

[1]  S. Lavanya,et al.  Predictive Methodology for Diabetic Data Analysis in Big Data , 2015 .

[2]  Karim Keshavjee,et al.  Performance Analysis of Data Mining Classification Techniques to Predict Diabetes , 2016 .

[3]  Karim M. Orabi,et al.  Early Predictive System for Diabetes Mellitus Disease , 2016, ICDM.

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

[5]  Paul Varghese,et al.  Robust Optimized Artificial Neural Network Based PEM Fuelcell Voltage Tracking , 2015, IBICA.

[6]  K. Rajesh,et al.  Application of Data Mining Methods and Techniques for Diabetes Diagnosis , 2012 .

[7]  Malka N. Halgamuge,et al.  Impact of Different Data Types on Classifier Performance of Random Forest, Naïve Bayes, and K-Nearest Neighbors Algorithms , 2017 .

[8]  Mohammed Abdul Khaleel,et al.  A Survey of Data Mining Techniques on Medical Data for Finding Locally Frequent Diseases , 2013 .

[9]  Boon-Tiang Lau,et al.  Impact of Pharmacist-Led Diabetes Program on Glycated Hemoglobin and Diabetes-Related Hospitalizations in a District-Level Hospital: A Pilot Retrospective Cohort Study , 2018 .

[10]  N. Sambasiva Rao,et al.  Survey on clinical prediction models for diabetes prediction , 2017, Journal of Big Data.

[11]  T. M. Ahmed,et al.  DEVELOPING A PREDICTED MODEL FOR DIABETES TYPE 2 TREATMENT PLANS BY USING DATA MINING , 2016 .

[12]  S. Jeyalatha,et al.  Diagnosis of diabetes using classification mining techniques , 2015, ArXiv.

[13]  Rajani K. Mudi,et al.  Particle Swarm Optimization Based Adaptive PID Controller for pH-Neutralization Process , 2014, FICTA.