Electronic Health Records are providing high amount of genetic data and clinical information through the exceptional advances in biotechnology and health sciences. The application of machine learning and data mining methods in biosciences is crucial, more than that very important to transform cleverly all available information into precious knowledge. Diabetes mellitus is defined as a collection of metabolic disorders exerting major pressure on human health worldwide. Large amounts of data generated due to the widespread researches in all areas of diabetes. This study is to present a systematic approach of the applications of machine learning algorithm along with data mining techniques and tools in the field of diabetes research especially in Health Care Resource Utilization (HCRU). There were so many machine learning algorithms used here. Supervised machine learning algorithm, unsupervised machine learning algorithm and Semi-supervised Machine Learning Algorithm (SMLA).This research shows that SMLA such that Transductive Support Vector Machine (TSVM) fits the best for the research in healthcare resource utilization by considering the type of diabetes patient’s medical datasets.

Diabetes mellitus, Machine Learning, Healthcare resource utilization, Support Vector Machine

[1] Agrawal R, Imielinski T, Swami A. Mining association rules between sets of items in large databases. Proceedings of the ACM SIGMOD conference on management of data; 1993. p. 207–16.
[2] Agrawal R, Srikant R. Fast algorithms for mining association rules in large data-bases. Proceedings of the 20th International Conference on Very Large Databases; 1994. p. 478–99.
[3] Kavakiotis I, Tzanis G, Vlahavas I. Mining frequent patterns and association rules from biological data. In: Elloumi M, Zomaya AY, editors. Biological knowledge discovery handbook: preprocessing, mining and post processing of biological data. Wiley Book series on bioinformatics: computational techniques and engineering, New Jersey, USA: Wiley-Blackwell, John Wiley & Sons Ltd.; 2014
[4] Han J, Kamber M, Pei J. Data mining: concepts and techniques. The Morgan Kaufmann series in data management systems; 2011.
[5] Alpaydin E. Introduction to machine learning. Cambridge Massachusetts London England: The MIT Press; 2004.
[6] Guyon I, Elisseeff A. An introduction to variable and feature selection. J Mach Learn Res 2003; 3:1157–82.
[7] Witten IH, Frank E, Hall MA. Data mining: practical machine learning tools and techniques. 3rd ed. Burlington, MA: Morgan Kaufmann; 2011.
[8] American Diabetes Association. Diagnosis and classification of diabetes mellitus. Diabetes Care 2009; 32 (Suppl. 1):S62–7.
[9] Cox EM, Elelman D. Test for screening and diagnosis of type 2 diabetes. Clinical Diabetes 2009;4(27):132–8.
[10] Krentz AJ, Bailey CJ. Oral ant diabetic agents: current role in type 2 diabetes mellitus. Drugs 2005;65(3):385–411.
[11] Tsave O,et al. Structure-specific adipogenic capacity of novel, well-defined ternary Zn(II)-Schiff base materials. Biomolecular correlations in zinc-induced differentiation of 3T3-L1 pre-adipocytes to adipocytes. J Inorg Biochem Nov 2015; 152:123–37.
[12] Halevas E, et al. Design, synthesis and characterization of novel binary V (V)-Schiff base materials linked with insulin-mimetic vanadium-induced differentiation of 3T3-L1 fibro-blasts to adipocytes. Structure–function correlations at the molecular level. J Inorg Biochem Jun 2015; 147:99–115.
[13] Tsave O, et al. The adipogenic potential of Cr (III). A molecular approach exemplifying metal-induced enhancement of insulin mimesis in diabetes mellitus II. J Inorg Biochem Oct 2016; 163:323–31.
[14] “Records in DBLP”. Statistics. DBLP. Retrieved 2016–07-16; 2016.
[15] Agarwal V et al. Learning statistical models of phenotypes using noisy labeled training data. J Am Med Inform
[16] Hoyt R, Linnville S, Thaler S, Moore J. Digital family history data mining with neural networks: a pilot study. Perspect Health Information Management Jan 1 2016.
[17] Anderson JP et al. Reverse engineering and evaluation of prediction models for progression to type 2 diabetes: an application of machine learning using electronic health records. J Diabetes SciTechnology Dec 20 2015; 10(1):6–18.
[18] Anderson AE et al. Electronic health record phenotyping improves detection and screening of type 2 diabetes in the general United States population: a cross-sectional, unselected, retrospective study. J Biomed Inform Apr 2016; 60:162–8.
[19] Bashir S, Qamar U, Khan FH. IntelliHealth: a medical decision support application using a novel weighted multi-layer classifier ensemble framework. J Biomed In-form Feb 2016; 59:185–200.
[20] Multilevel Weighted Support Vector Machine for Classification on Healthcare Data with Missing Values.Talayeh Razzaghi, Oleg Roderick, Ilya Safro, and Nicholas Marko Published: May 19, 2016.
[21] J. H. Friedman. Multivariate adaptive regression splines. Annals of Statistics, 19(1):1–67, 1991.[9] A. Gawande. The hot spotters. New Yorker, January 2011.
[22] A. K. Jain and Richard C. Dubes. Algorithms for Clustering Data. Prentice-Hall, Upper Saddle River, NJ, USA, 1988.
[23] ChaitraliDangare, S. and Sulaba Apte,S.Improved study of disease prediction using data mining classification techmiques. Int.J.Comp.Appl. 2012, 47(10):75-88.