The diagnostics of diabetes mellitus based on ensemble modeling and hair/urine element level analysis

The aim of the present work focuses on exploring the feasibility of analyzing the relationship between diabetes mellitus and several element levels in hair/urine specimens by chemometrics. A dataset involving 211 specimens and eight element concentrations was used. The control group was divided into three age subsets in order to analyze the influence of age. It was found that the most obvious difference was the effect of age on the level of zinc and iron. The decline of iron concentration with age in hair was exactly consistent with the opposite trend in urine. Principal component analysis (PCA) was used as a tool for a preliminary evaluation of the data. Both ensemble and single support vector machine (SVM) algorithms were used as the classification tools. On average, the accuracy, sensitivity and specificity of ensemble SVM models were 99%, 100%, 99% and 97%, 89%, 99% for hair and urine samples, respectively. The findings indicate that hair samples are superior to urine samples. Even so, it can provide more valuable information for prevention, diagnostics, treatment and research of diabetes by simultaneously analyzing the hair and urine samples.

[1]  Chao Tan,et al.  The Prediction of Cardiovascular Disease Based on Trace Element Contents in Hair and a Classifier of Boosting Decision Stumps , 2008, Biological Trace Element Research.

[2]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[3]  Joshua C. Denny,et al.  Type 2 Diabetes Risk Forecasting from EMR Data using Machine Learning , 2012, AMIA.

[4]  J. Štupar,et al.  Longitudinal hair chromium profiles of elderly subjects with normal glucose tolerance and type 2 diabetes mellitus. , 2007, Metabolism: clinical and experimental.

[5]  S. Wild,et al.  Global prevalence of diabetes: estimates for the year 2000 and projections for 2030. , 2004, Diabetes care.

[6]  C. Keen,et al.  Copper, Zinc, Manganese, and Magnesium Status and Complications of Diabetes Mellitus , 1991, Diabetes Care.

[7]  Katherine H Thompson,et al.  Vanadium in diabetes: 100 years from Phase 0 to Phase I. , 2006, Journal of inorganic biochemistry.

[8]  S. K. Vashist.  Non-invasive glucose monitoring technology in diabetes management: a review. , 2012, Analytica chimica acta.

[9]  T. Kazi,et al.  Status of essential trace metals in biological samples of diabetic mother and their neonates , 2009, Archives of Gynecology and Obstetrics.

[10]  Chao Tan,et al.  Early prediction of lung cancer based on the combination of trace element analysis in urine and an Adaboost algorithm. , 2009, Journal of pharmaceutical and biomedical analysis.

[11]  Joshua R Edwards,et al.  Cadmium, diabetes and chronic kidney disease. , 2009, Toxicology and applied pharmacology.

[12]  J. McNeill,et al.  Effect of vanadium on insulin sensitivity and appetite. , 2001, Metabolism: clinical and experimental.

[13]  Tingting Zou,et al.  Support vector regression for determination of component of compound oxytetracycline powder on near-infrared spectroscopy. , 2006, Analytical biochemistry.

[14]  Meng-long Li,et al.  Comparison of chemometric methods for brand classification of cigarettes by near-infrared spectroscopy , 2009 .

[15]  Xueguang Shao,et al.  A consensus least squares support vector regression (LS-SVR) for analysis of near-infrared spectra of plant samples. , 2007, Talanta.

[16]  T. Kazi,et al.  Copper, Chromium, Manganese, Iron, Nickel, and Zinc Levels in Biological Samples of Diabetes Mellitus Patients , 2008, Biological Trace Element Research.

[17]  D. Spence,et al.  A perspective on the role of metals in diabetes: past findings and possible future directions , 2009 .

[18]  C. Erem,et al.  The Effects of Impaired Trace Element Status on Polymorphonuclear Leukocyte Activation in the Development of Vascular Complications in Type 2 Diabetes Mellitus , 2001, Clinical chemistry and laboratory medicine.

[19]  F. Petrucci,et al.  Recent Developments in Trace Element Analysis in the Prevention, Diagnosis, and Treatment of Diseases , 1998 .

[20]  Menglong Li,et al.  Determination of nicotine in tobacco samples by near-infrared spectroscopy and boosting partial least squares , 2010 .

[21]  T. Næs,et al.  Ensemble methods and partial least squares regression , 2004 .

[22]  Vinod Sharma,et al.  Comparative analysis of machine learning techniques in prognosis of type II diabetes , 2014, AI & SOCIETY.

[23]  C. Roberts,et al.  Oxidative stress and metabolic syndrome. , 2009, Life sciences.

[24]  S. Harris,et al.  Global complication rates of type 2 diabetes in Indigenous peoples: A comprehensive review. , 2008, Diabetes research and clinical practice.

[25]  L. Buydens,et al.  Comparing support vector machines to PLS for spectral regression applications , 2004 .

[26]  E. Marengo,et al.  Experimental design optimization for the ICP-AES determination of Li, Na, K, Al, Fe, Mn and Zn in human serum. , 2007, Journal of pharmaceutical and biomedical analysis.

[27]  J. Blomberg,et al.  Sequential trace element changes in serum and blood during a common viral infection in mice. , 2007, Journal of trace elements in medicine and biology : organ of the Society for Minerals and Trace Elements.

[28]  F. Nielsen.  Importance of making dietary recommendations for elements designated as nutritionally beneficial, pharmacologically beneficial, or conditioinally essential , 2000 .

[29]  Dorte Vistisen,et al.  Global healthcare expenditure on diabetes for 2010 and 2030. , 2010, Diabetes research and clinical practice.

[30]  Mykola Pechenizkiy,et al.  Diversity in search strategies for ensemble feature selection , 2005, Inf. Fusion.

[31]  Peter Tiño,et al.  Managing Diversity in Regression Ensembles , 2005, J. Mach. Learn. Res..

[32]  D. Templeton.  The importance of trace element speciation in biomedical science , 2003, Analytical and bioanalytical chemistry.

[33]  Chao Tan,et al.  Application of Boosting Classification and Regression to Modeling the Relationships Between Trace Elements and Diseases , 2009, Biological Trace Element Research.

[34]  Zhide Hu,et al.  Study on the relationship between intake of trace elements and breast cancer mortality with chemometric methods , 2003, Comput. Biol. Chem..

[35]  Thomas Tolxdorff,et al.  Classification Models for Early Detection of Prostate Cancer , 2008, Journal of biomedicine & biotechnology.

[36]  E. Lander,et al.  Reactive oxygen species have a causal role in multiple forms of insulin resistance , 2006, Nature.

[37]  L. Cai,et al.  The Role of Zinc, Copper and Iron in the Pathogenesis of Diabetes and Diabetic Complications: Therapeutic Effects by Chelators , 2008, Hemoglobin.

[38]  Z. Zhang,et al.  Diagnosis of lung cancer based on metal contents in serum and hair using multivariate statistical methods. , 1997, Talanta.

[39]  Nathan Intrator,et al.  Optimal ensemble averaging of neural networks , 1997 .