scholarly journals Performance of the Finnish Diabetes Risk Score and a Simplified Finnish Diabetes Risk Score in a Community-Based, Cross-Sectional Programme for Screening of Undiagnosed Type 2 Diabetes Mellitus and Dysglycaemia in Madrid, Spain: The SPREDIA-2 Study

PLoS ONE ◽  
2016 ◽  
Vol 11 (7) ◽  
pp. e0158489 ◽  
Author(s):  
M. A. Salinero-Fort ◽  
C. Burgos-Lunar ◽  
C. Lahoz ◽  
J. M. Mostaza ◽  
J. C. Abánades-Herranz ◽  
...  
Keyword(s):  
Diabetes Mellitus ◽  
Type 2 Diabetes ◽  
Type 2 Diabetes Mellitus ◽  
Risk Score ◽  
Diabetes Risk ◽  
Community Based ◽  
Cross Sectional ◽  
Diabetes Risk Score

scholarly journals Indian Diabetes Risk Score Helps to Distinguish Type 2 from Non-Type 2 Diabetes Mellitus (GDRC-3)

2011 ◽  
Vol 5 (2) ◽  
pp. 419-425 ◽  
Author(s):  
Kunal M. Sharma ◽  
Harish Ranjani ◽  
Ha Nguyen ◽  
Shuba Shetty ◽  
Manjula Datta ◽  
...  
Keyword(s):  
Diabetes Mellitus ◽  
Type 2 Diabetes ◽  
Type 2 Diabetes Mellitus ◽  
Risk Score ◽  
Diabetes Risk ◽  
Diabetes Risk Score

scholarly journals Prediction of type 2 diabetes mellitus onset using simple logistic regression models

2020 ◽  
Author(s):  
Yochai Edlitz ◽  
Eran Segal
Keyword(s):  
Diabetes Mellitus ◽  
Type 2 Diabetes ◽  
Type 2 Diabetes Mellitus ◽  
Logistic Regression ◽  
Risk Score ◽  
Diabetes Risk ◽  
Blood Tests ◽  
Glutamyl Transferase ◽  
Diabetes Risk Score

Diabetes mellitus has a world death rate of 1.6 million (2016) of which Type 2 diabetes mellitus (T2DM) accounts for ~90% of all cases. Early detection of T2D high-risk patients can reduce the incidence of the disease through a change in lifestyle, diet, or medication. Since lower socio-demographics layers are more susceptible to T2D and might have limited resources for laboratory testing, there is a need for accurate prediction models based on non-laboratory parameters. Here, we analysed data of 44,879 non-diabetic, UK-Biobank participants at the ages 40-65 within a time frame of 7.3±2.3 years. We devise a non-laboratory prediction model for T2DM onset probability using sex, age, weight, height, waist, hips-circumferences, Waist-Hips Ratio (WHR) and Body-Mass Index (BMI). This model achieved an Area Under the Receiver Operating Curve (auROC) of 0.82 (0.79-0.84 95% CI) and an odds ratio (OR) between the top and lowest prevalence deciles of x42 (33-49). The logistic regression top predictive parameters are WHR with OR of 0.67 (0.49-0.88 95%CI) followed by BMI with OR of 0.53 (0.26-0.79). We further analyse the contribution of laboratory-based parameters and devise a blood-test model based on only five blood tests. In this model, we are using age, sex, Glycated Hemoglobin (HbA1c%), reticulocyte count, Gamma Glutamyl-Transferase, Triglycerides, and HDL cholesterol to predict T2D onset more accurately. This model achieves an auROC of 0.89 (0.87-0.92) and a deciles' OR of x59 (27-75). We also analysed a model that included genotyping data and other environmental factors and found that it did not provide further benefit over the five-blood-tests model. Our models outperform the current state of the art, non-laboratory, Finnish Diabetes Risk Score and the German Diabetes Risk Score, trained on our data, achieving auROC of 0.74 (0.7-0.77) and 0.63 (0.59-0.67), respectively.

Sign in / Sign up

Export Citation Format

Share Document