Development of a Predictive Model for Type 2 Diabetes Mellitus Using Genetic and Clinical Data

Lee, Juyoung; Keam, Bhumsuk; Jang, Eun Jung; Park, Mi Sun; Lee, Ji Young; Kim, Dan Bi; Lee, Chang-Hoon; Kim, Tak; Oh, Bermseok; Park, Heon Jin; Kwack, Kyu-Bum; Chu, Chaeshin; Kim, Hyung-Lae
September 2011
Osong Public Health & Research Perspectives;Sep2011, Vol. 2 Issue 2, p75
Academic Journal
Abstract: Objectives: Recent genetic association studies have provided convincing evidence that several novel loci and single nucleotide polymorphisms (SNPs) are associated with the risk of developing type 2 diabetes mellitus (T2DM). The aims of this study were: 1) to develop a predictive model of T2DM using genetic and clinical data; and 2) to compare misclassification rates of different models. Methods: We selected 212 individuals with newly diagnosed T2DM and 472 controls aged in their 60s from the Korean Genome and Epidemiology Study. A total of 499 known SNPs from 87 T2DM-related genes were genotyped using germline DNA. SNPs were analyzed for significant association with T2DM using various classification algorithms including Quest (Quick, Unbiased, Efficient, Statistical tree), Support Vector Machine, C4.5, logistic regression, and K-nearest neighbor. Results: We tested these models using the complete Korean Genome and Epidemiology Study cohort (n = 10,038) and computed the T2DM misclassification rates for each model. Average misclassification rates ranged at 28.2–52.7%. The misclassification rates for the logistic and machine-learning algorithms were lower than the statistical tree algorithms. Using 1-to-1 matched data, the misclassification rate of the statistical tree QUEST algorithm using body mass index and SNP variables was the lowest, but overall the logistic regression performed best. Conclusions: The K-nearest neighbor method exhibited more robust results than other algorithms. For clinical and genetic data, our “multistage adjustment” model outperformed other models in yielding lower rates of misclassification. To improve the performance of these models, further studies using warranted, strategies to estimate better classifiers for the quantification of SNPs need to be developed.


Related Articles

  • Relationship of Abdominal Visceral and Subcutaneous Adipose Tissue With Lipoprotein Particle Number and Size in Type 2 Diabetes. Sam, Susan; Haffner, Steven; Davidson, Michael H.; D'Agostino Sr., Ralph B.; Feinstein, Steven; Kondos, George; Perez, Alfonso; Mazzone, Theodore // Diabetes;Aug2008, Vol. 57 Issue 8, p2022 

    OBJECTIVE--Insulin resistance and type 2 diabetes are associated with an atherogenic lipoprotein profile. We examined the role of visceral and subcutaneous fat depots, independent of BMI, on the dyslipidemia associated with type 2 diabetes. RESEARCH DESIGN AND METHODS -- A total of 382 subjects...

  • Determinants of erectile dysfunction in type 2 diabetes. Giugliano, F.; Maiorino, M.; Bellastella, G.; Gicchino, M.; Giugliano, D.; Esposito, K. // International Journal of Impotence Research;May/Jun2010, Vol. 22 Issue 3, p204 

    This study was designed to evaluate the prevalence and correlates of ED in a population of diabetic men. Consecutive patients with type 2 diabetes were recruited among outpatients regularly attending Diabetes Clinics. Inclusion criteria for the initial selection of patients were a diagnosis of...

  • Screening for diabetes in dental settings. Walley, Siân // Dental Nursing;Jun2014, Vol. 10 Issue 6, p346 

    The article presents a study on screening for type 2 diabetes in dental care settings. Topics covered include the role played by dentists, dental therapists, hygienists and dental nurses in providing lifestyle advice to patients as part of their preventive care. Also mentioned are the low number...

  • Prediction of Type 2 Diabetes Using Alternate Anthropometric Measures in a Multi-Ethnic Cohort. Mackay, Meredith F.; Haffner, Steven M.; Wagenknecht, Lynne E.; D'Agostino Jr., Ralph B.; Hanley, Anthony J.G. // Diabetes Care;May2009, Vol. 32 Issue 5, p956 

    OBJECTIVE -- To compare different anthropometric measures in terms of their ability to predict type 2 diabetes and to determine whether predictive ability was modified by ethnicity. RESEARCH DESIGN AND METHODS -- Anthropometry was measured at baseline for 1,073 non-Hispanic white (nHW), African...

  • Association of Physical Activity with Risk of Type 2 Diabetes. Ghaderpanahi, M.; Fakhrzadeh, H.; Sharifi, F.; Badamchizade, Z.; Mirarefin, M.; Ebrahim, Rasool Pour; Ghotbi, S.; Nouri, M .; Larijani, B. // Iranian Journal of Public Health;2011, Vol. 40 Issue 1, p86 

    Background: Physical activity has shown to prevent type diabetes 2. However, the type, intensity and amount of effective physical activity as well as individuals' needs according to level of their risk for type 2 diabetes have not been clarified comprehensively. This study investigated a...

  • An in-depth analysis of glycosylated haemoglobin level, body mass index and left ventricular diastolic dysfunction in patients with type 2 diabetes. Zuo, Xin; Liu, Xueting; Chen, Runtian; Ou, Huiting; Lai, Jiabao; Zhang, Youming; Yan, Dewen // BMC Endocrine Disorders;8/27/2019, Vol. 19 Issue 1, pN.PAG 

    Background: Glycosylated hemoglobin (HbA1c) has a detrimental impact on the myocardium with left ventricular (LV) diastolic dysfunction. Obesity is a risk factor of type 2 diabetes. To understand the relationships between HbA1c, body mass index (BMI) and LV diastolic dysfunction, we performed...

  • 276G>T Polymorphism of the ADIPOQ Gene Influences Plasma Adiponectin in Type 2 Diabetes Patients but Is Not Predictive for Presence of Type 2 Diabetes in a Caucasian Cohort from Romania. KACSO, Ina Maria; FARCAS, Marius Florin; POP, Ioan Victor; BONDOR, Cosmina Ioana; POTRA, Alina Ramona; MOLDOVAN, Diana; RUSU, Crina; NITA, Cristina; GHERMAN, Caprioara Mirela; HANCU, Nicolae Dumitru // Romanian Journal of Medical Practice;2012, Vol. 7 Issue 4, p271 

    Background: Previous reports associated ADIPOQ 276G>T polymorphism with plasma adiponectin levels and diabetes. Our objective was to study this polymorphism in type 2 diabetes (T2D) Romanian patients and to assess its influence on plasma adiponectin levels; possible link to prevalence of T2D was...

  • Association between the NF-E2 Related Factor 2 Gene Polymorphism and Oxidative Stress, Anti-Oxidative Status, and Newly-Diagnosed Type 2 Diabetes Mellitus in a Chinese Population. Xia Wang; Hongxia Chen; Jun Liu; Yingying Ouyang; Di Wang; Wei Bao; Liegang Liu // International Journal of Molecular Sciences;Jul2015, Vol. 16 Issue 7, p16483 

    Oxidative stress is a major risk factor in the onset and progression of type 2 diabetes mellitus (T2DM). NF-E2 related factor 2 (NRF2) is a pivotal transcription factor in oxidative stress related illnesses. This study included 2174 subjects with 879 cases of newly-diagnosed T2DM and 1295...

  • Factors Associated with Consumption of Diabetic Diet among Type 2 Diabetic Subjects from Ahmedabad, Western India. Patel, Mayur; Patel, Ina M.; Patel, Yash M.; Rathi, Suresh K. // Journal of Health, Population & Nutrition;Dec2012, Vol. 30 Issue 4, p447 

    This cross-sectional study assessed the current situation of and factors associated with consumption of diabetic diet among 399 type 2 diabetes mellitus (T2DM) subjects from Ahmedabad, Western India. The study was performed with diagnosed (at least one year old) diabetic subjects who attended...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics