Predicting the Blood Sugar using Machine Learning Approach
Keywords:Diabetes, Statistical Classifiers, Decision Tree Classifier, Support Vector Machine, Classification and Regression Tree, NaÃ¯ve Bayes Classifier, K-Nearest Neighbour, C4.5, C5.
Background/Objective: This study is performed for predicting the blood sugar level by machine learning classifier techniques and identifies the best techniques among the techniques. Diabetes mellitus known as Diabetes caused due to increase in the blood glucose level. This will be impacting the pancreas and will be affecting the body beta cells. The beta cells play the major role in converting the glucose into energy. If the blood glucose remain undiagnosed for longer tenure, can cause various health complications like cardiovascular diseases neuropathy, nephropathy, organ failures and Eye disease. Diagnosing the sugar level in the earlier stage can help to prevent and control the health issues and save our life. Methods/Statistical Analysis: There are many classifiers already available in the computerized system. This analysis is to compare and identify the best classification technique between the classifier techniques like NaÃ¯ve Bayes (NB), Decision Tree (DT), Support Vector Machine (SVM), Classification and Regression Tree (CART), K â€“ Nearest Neighbour (K-NN) and C5. Findings: In 2017 the International Diabetes Federation had anticipated that 50% of the people in the world with the age group of 20 to 79 are not worried about their Diabetes and not aware that they may be impacted by Diabetes in near future. It also explained that 76.5% of Diabetic patients are from very low-income countries. These are not yet diagnosed if you really speaking that they donâ€™t know that they have Diabetes. So, there is a need to diagnose and monitor the diabetes to support and help them to cure it. Keeping that in mind there are various classification techniques used to predict the diabetes. The main objective of this study is to make a comparative study and identify the best classifier which is consistent among the various datasets. The datasets used for this comparative study is University of California, Irvine machine learning repository (UCI) and PIMA Indian Diabetes Dataset. Application/ Improvements: In this study, the R-Studio application tool is used for developing and comparing the classifiers.
 Veena Vijayan V, Anjali C â€œDecision Support Systems for Predicting Diabetes Mellitus â€“ A Reviewâ€ IEEE proceedings of 2015 Global Conference on Communication Technologies (GCCT 2015)
 R Bellazzi and B. Zupan â€œPredictive Data Mining in clinical Medicine:Current Issues and Guidelinesâ€, International Journal of Medical Informatics, Vol 77, pp 81-97, 2008
 Ning Wang, Guixia Kang, â€œMonitoring System for type 2 diabetes mellitusâ€, IEEE conference on e-Health Networking, pp 62-67, 2012
 Sonu Kumari, Archana Singh, â€œA data mining approach for the diagnosis of diabetes mellitusâ€, IEE conference on Intelligent systems and control, pp-373-375, 2013
 Rakesh Motka, Viral Parmar, â€œDiabetes Mellitus Forecast Using Different Data Mining Techniquesâ€, IEEE International Conference on Communication and Computer Technology (ICCCT), 2013
 Abid sarvwar, Vinod Sharma, â€œIntelligent NaÃ¯ve Bayes approach to Diagnose Diabetes Type 2â€ Special issue of International Journal of Computer Applications on Issues and Challenges in Networking, Intelligence and Computing Technologies, November 2012
 Veena Vijayan V, Aswathy Ravikumar, â€œStudy of Data Mining Algorithms for Prediction and Diagnosis of Diabetes Mellitusâ€ International Journal of Computer Applications, Vol 94 pp 12-16, June-2014
 C. Kalaiselvi, G.M Nasira, â€œA New Approach of Diagnosis of Diabetes and Prediction of Cancer using ANFISâ€, IEE Computing and Communicating Technologies, pp-188-190, 2014
 Nirmala Devi M, Appavu alias Balamurugan S, Swathi U.V, â€œAn Amalgam KNN to predict Diabetes Mellitusâ€, IEEE International Conference on Emerging Trends in Computing, Communication and Nano technology (ICECCN), pp 691-695, 2013
 Velu C.M, K.R Kashwan, â€œVisual Data Mining Technologies for Classification of Diabetic Patientsâ€, IEEE International Advance Computing Conference (IACC), pp 1070-1075, 2013
 Asma A, AlJarullah, â€œDecision Discovery for the Diagnosis of Type II Diabetesâ€, IEEE Conference on Innovations on Information Technology, pp 303-307, 2011
 Xiaoran Zhang, Ruoyu Ding, â€œPredicting Patients with Diabetes Type II from HER dataâ€ Computer Science Engineering.
 I. Kononenko, â€œMachine Learning for Medical Diagnosis: History State of the Art and Perspectiveâ€, Artificial Intelligence in Medicine, Vol 23, No 1, pp 89-109, 2001
 Pang-Ning Tan, Michael Steinbach, Vipin Kumar, â€œIntroduction to Data Miningâ€ Pearson Education, Inc 2006
 Vinod Chandra S.S, Anand Hareendran S, â€œArtificial Intelligence and Machine Learningâ€ PHI Learning Private Limited, Delhi 110092, 2014
 Nahla H. Barakat, Andrew P. Bradley, Mohamed Nabil H. Barakat, â€œIntelligible Support Vector Machine for Diagnosis of Diabetes Mellitusâ€, IEEE Transactions on Information Technology in Biomedicine, Vol 14, No 4, July 2010
 Krzysztof J. Cios, J William Moore, â€œUniqueness of Medical Data Miningâ€ Artificial Intelligence in Medicne Journal pp 1-19, 2002
 DeFronzo RA, Ferrannini E, Zimmet P, et al. International Text Book of Diabetes Mellitus 2 Volume Set, 4th Edition, Wiley Blackwell, 2015, IDF - DIABETES ATLAS Eighth edition 2017, pp 16-17, 2017
 Bum Ju Lee, Jong Yeol Kim, â€œIdentification of Type II Diabetes Risk Factor Using Phenotypes Consisting of Anthropometry and Triglycerides Based on Machine Learningâ€ IEE Journal of Biomedical and Health Informatics pp 4-7
 Paul Teetor, â€œR Cookbookâ€, Sixth Indian Reprint, pp 195-311, August 2014
 Nina Zumel, John Mount, â€œPractical Data Science With Râ€ Edition 2014, pp 175-251. 2016, Reprint Edition 2016.
View Full Article:
How to Cite
LicenseAuthors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under aÂ Creative Commons Attribution Licensethat allows others to share the work with an acknowledgement of the work''s authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal''s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (SeeÂ The Effect of Open Access).