782-P: Personalized, Machine Learning-Based Nutrition Reduces Diabetes Markers in Type 2 Diabetic Patients

Diabetes ◽  
2019 ◽  
Vol 68 (Supplement 1) ◽  
pp. 782-P
Author(s):  
YATIR BEN SHLOMO ◽  
SHAHAR AZULAY ◽  
TALI RAVEH-SADKA ◽  
YOSSI COHEN ◽  
ARIEL HANEMANN
Keyword(s):  
Machine Learning ◽  
Diabetic Patients ◽  
Type 2 Diabetic Patients ◽  
Type 2 Diabetic

scholarly journals Machine Learning for Screening Microvascular Complications in Type-2 Diabetic Patients using Demographic, Clinical, and Laboratory Profiles

2021 ◽  
Author(s):  
Mamunur Rashid ◽  
Mohanad Alkhodari ◽  
Abdul Mukit ◽  
Khawza Iftekhar Uddin Ahmed ◽  
Raqibul Mostafa ◽  
...  
Keyword(s):  
Machine Learning ◽  
Hemoglobin A1c ◽  
Microvascular Complications ◽  
Smoking History ◽  
Diabetic Patients ◽  
Type 2 Diabetic Patients ◽  
Albumin Creatinine Ratio ◽  
Machine Learning Approach ◽  
Type 2 Diabetic

Microvascular complications are one of the key causes of mortality among type-2 diabetic patients. This study was sought to investigate the use of a novel machine learning approach for predicting these complications from patient demographic, clinical, and laboratory profiles only. A total of 96 Bangladeshi participants having type-2 diabetes were recruited during their routine hospital visits. All patient profiles were assessed by using a Chi-squared (2) test to statistically determine the most important markers in predicting four microvascular complications; namely cardiac autonomic neuropathy (CAN), diabetic peripheral neuropathy (DPN), diabetic nephropathy (NEP), and diabetic retinopathy (RET). A machine learning approach based on random forest (RF) and support vector machine (SVM) was then developed to ensure automated clinical testing for microvascular complication in diabetic patients. The highest prediction accuracies were obtained by RF using diastolic blood pressure, Albumin-Creatinine ratio, and gender for CAN testing (98.67%), Microalbuminuria, smoking history, and hemoglobin A1C for DPN testing (67.78%), Albumin-Creatinine ratio for NEP testing (100%), and hemoglobin A1C, Microalbuminuria, and smoking history for RET testing (84.38%). This study suggests machine learning as a promising automated tool for predicting microvascular complications in diabetic patients using their profiles, which could help prvent those patients from further microvascular complications leading to early death.

944-P: Blood Glucose Prediction for Type 2 Diabetic Patients Using Machine Learning

Diabetes ◽  
2019 ◽  
Vol 68 (Supplement 1) ◽  
pp. 944-P
Author(s):  
DAEYEON KIM ◽  
HAN-BEOM LEE ◽  
YEOJOO KIM ◽  
SANG JIN KIM ◽  
SANG-JEONG LEE ◽  
...  
Keyword(s):  
Machine Learning ◽  
Blood Glucose ◽  
Diabetic Patients ◽  
Type 2 Diabetic Patients ◽  
Glucose Prediction ◽  
Type 2 Diabetic

Vitamin D3 supplementation improves glycemic control in type 2 diabetic patients: Results from an Italian clinical trial

2020 ◽  
pp. 1-10
Author(s):  
Giuseppe Derosa ◽  
Angela D’Angelo ◽  
Chiara Martinotti ◽  
Maria Chiara Valentino ◽  
Sergio Di Matteo ◽  
...  
Keyword(s):  
Vitamin D ◽  
Vitamin D Deficiency ◽  
Metabolic Control ◽  
Vitamin D3 ◽  
Therapy Group ◽  
Hypoglycemic Agents ◽  
Diabetic Patients ◽  
Type 2 Diabetic Patients ◽  
Type 2 Diabetic

Abstract. Background: to evaluate the effects of Vitamin D3 on glyco-metabolic control in type 2 diabetic patients with Vitamin D deficiency. Methods: one hundred and seventeen patients were randomized to placebo and 122 patients to Vitamin D3. We evaluated anthropometric parameters, glyco-metabolic control, and parathormone (PTH) value at baseline, after 3, and 6 months. Results: a significant reduction of fasting, and post-prandial glucose was recorded in Vitamin D3 group after 6 months. A significant HbA1c decrease was observed in Vitamin D3 (from 7.6% or 60 mmol/mol to 7.1% or 54 mmol) at 6 months compared to baseline, and to placebo (p < 0.05 for both). At the end of the study period, we noticed a change in the amount in doses of oral or subcutaneous hypoglycemic agents and insulin, respectively. The use of metformin, acarbose, and pioglitazone was significantly lower (p = 0.037, p = 0.048, and p = 0.042, respectively) than at the beginning of the study in the Vitamin D3 therapy group. The units of Lispro, Aspart, and Glargine insulin were lower in the Vitamin D3 group at the end of the study (p = 0.031, p = 0.037, and p = 0.035, respectively) than in the placebo group. Conclusions: in type 2 diabetic patients with Vitamin D deficiency, the restoration of value in the Vitamin D standard has led not only to an improvement in the glyco-metabolic compensation, but also to a reduced posology of some oral hypoglycemic agents and some types of insulin used.

Evaluation of aortic arch calcification in type 2 diabetic patients

VASA ◽  
2005 ◽  
Vol 34 (2) ◽  
pp. 113-117 ◽  
Author(s):  
Papanas ◽  
Symeonidis ◽  
Maltezos ◽  
Giannakis ◽  
Mavridis ◽  
...  
Keyword(s):  
Coronary Artery Disease ◽  
Coronary Artery ◽  
Aortic Arch ◽  
Diabetic Patients ◽  
Type 2 Diabetic Patients ◽  
Insulin Dependence ◽  
Artery Disease ◽  
Type 2 Diabetic ◽  
Aortic Arch Calcification

Background: The purpose of this study is to evaluate the severity of aortic arch calcification among type 2 diabetic patients in association with diabetes duration, diabetic complications, coronary artery disease and presence of cardiovascular risk factors. Patients and methods: This study included 207 type 2 diabetic patients (101 men) with a mean age of 61.5 ± 8.1 years and a mean diabetes duration of 13.9 ± 6.4 years. Aortic arch calcification was assessed by means of posteroanterior chest X-rays. Severity of calcification was graded as follows: grade 0 (no visible calcification), grade 1 (small spots of calcification or single thin calcification of the aortic knob), grade 2 (one or more areas of thick calcification), grade 3 (circular calcification of the aortic knob). Results: Severity of calcification was grade 0 in 84 patients (40.58%), grade 1 in 64 patients (30.92%), grade 2 in 43 patients (20.77%) and grade 3 in 16 patients (7.73%). In simple regression analysis severity of aortic arch calcification was associated with age (p = 0.032), duration of diabetes (p = 0.026), insulin dependence (p = 0.042) and presence of coronary artery disease (p = 0.039), hypertension (p = 0.019), dyslipidaemia (p = 0.029), retinopathy (p = 0.012) and microalbuminuria (p = 0.01). In multiple regression analysis severity of aortic arch calcification was associated with age (p = 0.04), duration of diabetes (p = 0.032) and presence of hypertension (p = 0.024), dyslipidaemia (p = 0.031) and coronary artery disease (p = 0.04), while the association with retinopathy, microalbuminuria and insulin dependence was no longer significant. Conclusions: Severity of aortic arch calcification is associated with age, diabetes duration, diabetic complications (retinopathy, microalbuminuria), coronary artery disease, insulin dependence, and presence of hypertension and dyslipidaemia.

Sign in / Sign up

Export Citation Format

Share Document