1460-P: Type 2 Diabetes Polygenic Score in Addition to Clinical Factors for Prediction of Diabetes Incidence in an Indigenous American Population

Diabetes ◽  
2020 ◽  
Vol 69 (Supplement 1) ◽  
pp. 1460-P
Author(s):  
LAUREN E. WEDEKIND ◽  
SAYUKO KOBES ◽  
WEN-CHI HSUEH ◽  
LESLIE BAIER ◽  
WILLIAM C. KNOWLER ◽  
...  
Keyword(s):  
Type 2 Diabetes ◽  
Diabetes Incidence ◽  
American Population ◽  
Clinical Factors ◽  
Polygenic Score ◽  
Prediction Of Diabetes ◽  
P Type

scholarly journals Predicting the Development of Type 2 Diabetes in a Large Australian Cohort Using Machine-Learning Techniques: Longitudinal Survey Study (Preprint)

2019 ◽  
Author(s):  
Lei Zhang ◽  
Xianwen Shang ◽  
Subhashaan Sreedharan ◽  
Xixi Yan ◽  
Jianbin Liu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Type 2 Diabetes ◽  
Risk Prediction ◽  
Machine Learning Algorithms ◽  
Survey Study ◽  
Gradient Boosting ◽  
Diabetes Incidence ◽  
Diabetes Onset ◽  
Prediction Of Diabetes

BACKGROUND Previous conventional models for the prediction of diabetes could be updated by incorporating the increasing amount of health data available and new risk prediction methodology. OBJECTIVE We aimed to develop a substantially improved diabetes risk prediction model using sophisticated machine-learning algorithms based on a large retrospective population cohort of over 230,000 people who were enrolled in the study during 2006-2017. METHODS We collected demographic, medical, behavioral, and incidence data for type 2 diabetes mellitus (T2DM) in over 236,684 diabetes-free participants recruited from the 45 and Up Study. We predicted and compared the risk of diabetes onset in these participants at 3, 5, 7, and 10 years based on three machine-learning approaches and the conventional regression model. RESULTS Overall, 6.05% (14,313/236,684) of the participants developed T2DM during an average 8.8-year follow-up period. The 10-year diabetes incidence in men was 8.30% (8.08%-8.49%), which was significantly higher (odds ratio 1.37, 95% CI 1.32-1.41) than that in women at 6.20% (6.00%-6.40%). The incidence of T2DM was doubled in individuals with obesity (men: 17.78% [17.05%-18.43%]; women: 14.59% [13.99%-15.17%]) compared with that of nonobese individuals. The gradient boosting machine model showed the best performance among the four models (area under the curve of 79% in 3-year prediction and 75% in 10-year prediction). All machine-learning models predicted BMI as the most significant factor contributing to diabetes onset, which explained 12%-50% of the variance in the prediction of diabetes. The model predicted that if BMI in obese and overweight participants could be hypothetically reduced to a healthy range, the 10-year probability of diabetes onset would be significantly reduced from 8.3% to 2.8% (<i>P</i>&lt;.001). CONCLUSIONS A one-time self-reported survey can accurately predict the risk of diabetes using a machine-learning approach. Achieving a healthy BMI can significantly reduce the risk of developing T2DM.

scholarly journals Predicting the Development of Type 2 Diabetes in a Large Australian Cohort Using Machine-Learning Techniques: Longitudinal Survey Study

10.2196/16850 ◽  
2020 ◽  
Vol 8 (7) ◽  
pp. e16850 ◽  
Author(s):  
Lei Zhang ◽  
Xianwen Shang ◽  
Subhashaan Sreedharan ◽  
Xixi Yan ◽  
Jianbin Liu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Type 2 Diabetes ◽  
Risk Prediction ◽  
Machine Learning Algorithms ◽  
Survey Study ◽  
Gradient Boosting ◽  
Diabetes Incidence ◽  
Diabetes Onset ◽  
Prediction Of Diabetes

Background Previous conventional models for the prediction of diabetes could be updated by incorporating the increasing amount of health data available and new risk prediction methodology. Objective We aimed to develop a substantially improved diabetes risk prediction model using sophisticated machine-learning algorithms based on a large retrospective population cohort of over 230,000 people who were enrolled in the study during 2006-2017. Methods We collected demographic, medical, behavioral, and incidence data for type 2 diabetes mellitus (T2DM) in over 236,684 diabetes-free participants recruited from the 45 and Up Study. We predicted and compared the risk of diabetes onset in these participants at 3, 5, 7, and 10 years based on three machine-learning approaches and the conventional regression model. Results Overall, 6.05% (14,313/236,684) of the participants developed T2DM during an average 8.8-year follow-up period. The 10-year diabetes incidence in men was 8.30% (8.08%-8.49%), which was significantly higher (odds ratio 1.37, 95% CI 1.32-1.41) than that in women at 6.20% (6.00%-6.40%). The incidence of T2DM was doubled in individuals with obesity (men: 17.78% [17.05%-18.43%]; women: 14.59% [13.99%-15.17%]) compared with that of nonobese individuals. The gradient boosting machine model showed the best performance among the four models (area under the curve of 79% in 3-year prediction and 75% in 10-year prediction). All machine-learning models predicted BMI as the most significant factor contributing to diabetes onset, which explained 12%-50% of the variance in the prediction of diabetes. The model predicted that if BMI in obese and overweight participants could be hypothetically reduced to a healthy range, the 10-year probability of diabetes onset would be significantly reduced from 8.3% to 2.8% (P<.001). Conclusions A one-time self-reported survey can accurately predict the risk of diabetes using a machine-learning approach. Achieving a healthy BMI can significantly reduce the risk of developing T2DM.

scholarly journals Enjoyment of life predicts reduced type 2 diabetes incidence over 12 years of follow-up: findings from the English Longitudinal Study of Ageing

2020 ◽  
pp. jech-2020-214302
Author(s):  
Laura Panagi ◽  
Ruth A Hackett ◽  
Andrew Steptoe ◽  
Lydia Poole
Keyword(s):  
Type 2 Diabetes ◽  
Longitudinal Study ◽  
Purpose In Life ◽  
Well Being ◽  
Diabetes Incidence ◽  
Subjective Well Being ◽  
Clinical Factors ◽  
The Relationship ◽  
English Longitudinal Study

BackgroundSubjective well-being appears to be associated with reduced risk of type 2 diabetes (T2D). However, it is unknown whether this association is similar across different types of well-being. We examined the relationship between hedonic and eudaimonic well-being and incident T2D, and explored the role of sociodemographic, behavioural and clinical factors in these associations.MethodsWe used data from 4134 diabetes-free participants from the English Longitudinal Study of Ageing (mean age =64.97). Enjoyment of life and purpose in life were assessed using items from the CASP-19 to reflect hedonic and eudaimonic well-being, respectively. Participants reported T2D diagnosis over 12 years. We used Cox proportional hazards regression analyses and also explored the percentage of association explained by different covariates.ResultsResults revealed a protective role for enjoyment of life in T2D rate adjusting for sociodemographic (age, sex, wealth, ethnicity, marital status), behavioural (physical activity, smoking, alcohol consumption, body mass index) and clinical (hypertension, coronary heart disease and glycated haemoglobin) characteristics (HR =0.93, p=0.021, 95% CI (0.87, 0.99)). Sociodemographic, behavioural and clinical factors accounted for 27%, 27% and 18% of the association, respectively. The relationship between purpose in life and T2D was non-significant (adjusted HR =0.92, p=0.288, 95% CI (0.78, 1.08)).ConclusionThis study illustrates how the link between subjective well-being and T2D varies between well-being components. It also demonstrates that sociodemographic, behavioural and clinical factors partially explain this association. Intervention studies examining whether changes in enjoyment of life can help delay T2D onset are warranted.

1158-P: Type 2 Diabetes Patients Subtype Analysis: Unbiased Machine Learning for Future Personalized T2D Care

Diabetes ◽  
2019 ◽  
Vol 68 (Supplement 1) ◽  
pp. 1158-P
Author(s):  
LI CHEN ◽  
LINGGE FENG ◽  
CUI TANG ◽  
YI ZHANG
Keyword(s):  
Machine Learning ◽  
Type 2 Diabetes ◽  
P Type ◽  
Diabetes Patients

1758-P: Type 2 Diabetes–Associated Mood Disorders: Role of Insulin Resistance in Serotonergic Neurons

Diabetes ◽  
2020 ◽  
Vol 69 (Supplement 1) ◽  
pp. 1758-P
Author(s):  
HUGO MARTIN ◽  
SÉBASTIEN BULLICH ◽  
FABIEN DUCROCQ ◽  
MARION GRALAND ◽  
CLARA OLIVRY ◽  
...  
Keyword(s):  
Insulin Resistance ◽  
Type 2 Diabetes ◽  
Mood Disorders ◽  
Serotonergic Neurons ◽  
P Type

1249-P: Type 2 Diabetes in Prepubertal Children under 10 Years Old

Diabetes ◽  
2020 ◽  
Vol 69 (Supplement 1) ◽  
pp. 1249-P
Author(s):  
MARCELA ASTUDILLO ◽  
AHMAD K. REFAEY ◽  
MUSTAFA TOSUR ◽  
ALEJANDRO F. SILLER ◽  
SIRIPOOM MCKAY ◽  
...  
Keyword(s):  
Type 2 Diabetes ◽  
Prepubertal Children ◽  
P Type

1135-P: Type 2 Diabetes Modulates DNA Methylation in Human Sperm

Diabetes ◽  
2021 ◽  
Vol 70 (Supplement 1) ◽  
pp. 1135-P
Author(s):  
LEI SU ◽  
DANIELLE WOLFS ◽  
MARIE-FRANCE HIVERT ◽  
JAY PATEL ◽  
LAUREN RICHARDSON ◽  
...  
Keyword(s):  
Type 2 Diabetes ◽  
Dna Methylation ◽  
Human Sperm ◽  
P Type

381-P: Type 2 Diabetes Significantly Modulates the Power of Lipoprotein(a) to Predict Cardiovascular Events and Mortality in Young Coronary Artery Disease Patients

Diabetes ◽  
2021 ◽  
Vol 70 (Supplement 1) ◽  
pp. 381-P
Author(s):  
ARTHUR MADER ◽  
MAXIMILIAN MAECHLER ◽  
BARBARA LARCHER ◽  
LUKAS SPRENGER ◽  
BEATRIX MUTSCHLECHNER ◽  
...  
Keyword(s):  
Type 2 Diabetes ◽  
Coronary Artery Disease ◽  
Coronary Artery ◽  
Cardiovascular Events ◽  
Lipoprotein A ◽  
Artery Disease ◽  
P Type

scholarly journals The Active Role of Leguminous Plant Components in Type 2 Diabetes

2014 ◽  
Vol 2014 ◽  
pp. 1-12 ◽  
Author(s):  
Monika Gętek ◽  
Natalia Czech ◽  
Małgorzata Muc-Wierzgoń ◽  
Elżbieta Grochowska-Niedworok ◽  
Teresa Kokot ◽  
...  
Keyword(s):  
Type 2 Diabetes ◽  
Bioactive Compounds ◽  
International Diabetes Federation ◽  
Noncommunicable Diseases ◽  
Antidiabetic Activity ◽  
Leguminous Plant ◽  
Morbidity Rate ◽  
Diabetes Incidence ◽  
Leguminous Plants

Diabetes appears to be one of the most frequent noncommunicable diseases in the world. A permanent growth in the incidence of diabetes can be observed and according to the International Diabetes Federation (IDF) the year 2030 will mark the increase in the number of diabetics to 439 mln worldwide. Type 2 diabetes accounts for about 90% of all diabetes incidence. Nutrition model modification not only features the basic element in type 2 diabetes treatment but also constitutes the fundamental factor influencing a morbidity rate decrease. Leguminous plants are a key factor in the diabetic diet; plants such as pulses or soybeans are nutritious products valued highly in nutrition. These legumes are high in the content of wholesome protein and contain large amounts of soluble alimentary fiber fractions, polyunsaturated fatty acids, vitamins and minerals, and bioactive substances with antioxidant, anti-inflammatory, and anticancer activity. They are distinguished by the high amount of bioactive compounds that may interfere with the metabolism of glucose. The most significant bioactive compounds displaying antidiabetic activity in leguminous plants are as follows: genistein and daidzein, alpha-amylase inhibitors, and alpha-glucosidase inhibitors.In vitroresearch using leguminous plant extracts has confirmed their antidiabetic properties. Leguminous plants should be employed in the promotion of healthy lifestyles in terms of functional food.

scholarly journals Serum Selenium Status in Patients with Type 2 Diabetes and Control Group

2016 ◽  
Vol 9 (5) ◽  
pp. 234
Author(s):  
Zahra Heidari ◽  
Zahra Sepehri ◽  
Aleme Doostdar
Keyword(s):  
Type 2 Diabetes ◽  
Serum Level ◽  
Control Group ◽  
Diabetic Patients ◽  
Diabetes Incidence ◽  
Serum Selenium ◽  
Type 2 Diabetic Patients ◽  
Significant Difference ◽  
The Mean

<p>In addition to known risk factors, the role of different micronutrients such as selenium in diabetes incidence has been proposed. Some previous studies have shown an association of selenium deficiency and type 2 diabetes mellitus, while other studies have not confirmed such a relationship. The aim of this study was to evaluate serum level of selenium in patients with Type 2 diabetes compared with the control group. This cross-sectional study was carried out on patients with type 2 diabetes in Zahedan, southeastern Iran. One hundred newly diagnosed type 2 diabetic patients were evaluated for serum selenium level. One hundred subjects from the general population who had normal fasting blood sugar levels were selected as the control group. The control group subjects were matched in pairs with each of patients on the basis of sex, age (± one year), and body mass index (±1). Serum level of selenium was determined by spectrometry method. Results were compared using t-test. The mean serum level of selenium in patients was 94.47±18.07 µg/L whereas in control group was 142.79±23.67 µg/L. The mean serum level of selenium was significantly different between the two groups (P&lt;0.001). Serum levels of selenium in diabetic patients with significant difference statistically were lower than the control group. In order to evaluate serum level of selenium in patients with diabetes, studies with larger sample size are required. Likewise, prospective studies along with selenium supplementation and investigating its effect on incidence of diabetes are accordingly needed.</p>

Sign in / Sign up

Export Citation Format

Share Document