24-Hour Crisis Hotline: (877)SAFEGBC or (877)723-3422 Mental Health & Substance Abuse Issues

6502 Nursery Drive, Suite 100
Victoria, TX 77904
(361)575-0611
(800)421-8825

Diabetes
Resources
Basic InformationLatest News
Blame Diabetes: Rates of 2 Nerve Conditions on the RiseElectronic Messaging Intervention Cuts Cardiovascular Risk in T2DMHealth Tip: Preventing Diabetic Foot SoresEarly Menopause May Be Tied to Type 2 DiabetesMore Than 100 Million Americans Have Diabetes or Prediabetes: CDCNT-proBNP Improves Heart Failure Prediction in T2DMStem Cell Educator Therapy May Help Fight DiabetesResistance Training Improves Microvascular Blood Flow in T2DMNew Diabetes Treatment Teaches Rogue Immune Cells to BehaveIncreased Parental Anxiety With Increased Diabetes RiskIntensive Lifestyle Changes May Up Frailty Fracture Risk in DMExercising Safely With DiabetesHyperbaric Oxygen Therapy Increasingly Being UsedTherapeutic Inertia in 19 Percent With T2DM, HbA1c ≥8 PercentT1DM Patients With Active β-Cell Function Differ ImmunologicallyMany People With Type 1 Diabetes Still Make Some InsulinTryptophan May Be Marker for Diabetic NephropathyEstimated Prevalence of Diabetes 10.9 Percent in ChinaReview Spotlights Optimal Care of T2DM + OsteoporosissRAGE Linked to Risk of Incident Diabetic NephropathyDiabetic Ketoacidosis Poses Fetal Risk During/After EventFDA Warns Diabetics Against Use of Secondhand Test StripsRisk of Cardiovascular Events Similar With, Without DiabetesPCSK9 Increased in Females, Youth With Type 1 DiabetesText Messaging Intervention Can Up Glycemic Control in T2DMGood Results for Zone MPC-Based Artificial PancreasBroccoli Extract Shows Promise for Type 2 DiabetesSleep Apnea Linked to Diabetic Retinopathy in Type 2 DiabetesADA: Canagliflozin Tied to Lower Risk of Cardiovascular EventsKey Diabetes Test Gives Higher Blood Sugar Readings in Black PatientsFor Diabetics, Nasal Powder Fixed Severe Low Blood SugarADA: Glucose Self-Monitoring Often Lacks Benefit in T2DMCan Folks With Type 2 Diabetes Forgo the Finger Stick?Sitagliptin Stimulates Distal Tubular Natriuresis in T2DMStudy Confirms Link Between Diabetes Med and Rare But Dangerous ComplicationLower HbA1c Linked to Better Diabetes-Specific HRQoL in YouthHealth Tip: What's My Target Blood Glucose?Comorbid Celiac Disease Common Among Youth With T1DMDiabetic Foot Ulcers, Infections Significantly Up Burden of CareMapping IDs Geographic Access Barriers for Diabetic RetinopathyNormal Meal Tolerance Test Is Practical, Reliable in T2DMNo Link to Cognition in Diabetes Prevention Program StudySuicide by Insulin?Promising Start for National Diabetes Prevention ProgramDiabetes Drug Gets FDA Warning Due to Amputation RiskAngela Bassett Puts the Spotlight on Heart HealthAs Temps Rise, Risk of Pregnancy Complication May TooPharmacist-Involved Collaborative Care Benefits T2DMNever Breastfeeding Linked to Increased Risk of T1DMBioengineered Intraabdominal Endocrine Pancreas Feasible
Links
Related Topics

Medical Disorders

Algorithm Integrated Into App Forecasts Glucose Levels


HealthDay News
Updated: Apr 28th 2017

new article illustration

FRIDAY, April 28, 2017 (HealthDay News) -- A mechanistic model based on Gaussian process models and data assimilation can produce a personalized, nutrition-based glucose forecast for individuals with type 2 diabetes, according to a study published online April 27 in PLOS Computational Biology.

David J. Albers, Ph.D., from Columbia University in New York City, and colleagues used three forecasting machines to examine the glycemic impact of different meals: data assimilation, which uses Bayesian modeling to infuse data with human knowledge in a mechanistic model to generate real-time, personalized forecasts; model averaging of data assimilation output; and dynamic Gaussian process model regression.

The researchers found that the data assimilation machine estimated states and parameters using a modified dual unscented Kalman filter, thereby personalizing the mechanistic models. To make a personalized model selection for the individual and their measurement characteristics, model selection was used. The data assimilation forecasts were assessed against actual postprandial glucose measurements that individuals with type 2 diabetes captured and against predictions that were generated by diabetes educators based on reviewing nutritional records and glucose measurements for the same individual.

"Our algorithm, integrated into an easy-to-use app, predicts the consequences of eating a specific meal before the food is eaten, allowing individuals to make better nutritional choices during mealtime," Albers said in a statement. "Now our task is to make the data assimilation tool powering the app even better."

Abstract/Full Text