Automatic Detection of Excessive Glycemic Variability as long as Diabetes ManagementMat

Automatic Detection of Excessive Glycemic Variability as long as Diabetes ManagementMat www.phwiki.com

Automatic Detection of Excessive Glycemic Variability as long as Diabetes ManagementMat

Cleveland, Delane, General Assignment Reporter has reference to this Academic Journal, PHwiki organized this Journal Automatic Detection of Excessive Glycemic Variability as long as Diabetes ManagementMatthew Wiley, Razvan Bunescu, Cindy Marling,Jay Shubrook in addition to Frank SchwartzSchool of Electrical Engineering in addition to Computer ScienceAppalachian Rural Health Institute Diabetes in addition to Endocrine CenterAthens, Ohio, USAAutomatic Detection of Excessive Glycemic Variability as long as Diabetes Management Wiley et al.1DiabetesBody fails to effectively produce in addition to /or use insulinTreated in addition to managed with blood glucose controlAutomatic Detection of Excessive Glycemic Variability as long as Diabetes Management Wiley et al.2DiabetesBody fails to effectively produce in addition to /or use insulinTreated in addition to managed with blood glucose control346 million people world wideTwo major types:Type IType IIAutomatic Detection of Excessive Glycemic Variability as long as Diabetes Management Wiley et al.3

Art Academy of Cincinnati US www.phwiki.com

This Particular University is Related to this Particular Journal

Poor Control Increases Risk of ComplicationsAutomatic Detection of Excessive Glycemic Variability as long as Diabetes Management Wiley et al.4CONTROL Foot Ulcers Angina Heart Attack Coronary Bypass Surgery Stroke Blindness Amputation Dialysis Kidney Transplant Microalbuminuria Mild Retinopathy Mild Neuropathy Albuminuria Macular Edema Proliferative Retinopathy Periodontal Disease Impotence Gastroparesis DepressionRISKGoodPoorAdministering InsulinType I patients must administer insulinInjectionInsulin PumpAutomatic Detection of Excessive Glycemic Variability as long as Diabetes Management Wiley et al.5Continuous Glucose MonitoringTwo approaches to monitoring:FingersticksContinuous Glucose Monitoring (CGM) sensorsAutomatic Detection of Excessive Glycemic Variability as long as Diabetes Management Wiley et al.6

Data OverloadAutomatic Detection of Excessive Glycemic Variability as long as Diabetes Management Wiley et al.7CGM sensors record values every 5 or 10 minutesExcessive Glycemic VariabilityCharacterized by fluctuations in blood glucosePatients are not yet routinely screenedAutomatic Detection of Excessive Glycemic Variability as long as Diabetes Management Wiley et al.8Acceptable Glycemic VariabilityExcessive Glycemic VariabilityBackgroundPreliminary work:Two physicians individually classified 400 plotsNaïve Bayes classifier: 85% accuracyAutomatic Detection of Excessive Glycemic Variability as long as Diabetes Management Wiley et al.9

BackgroundPreliminary work:Two physicians individually classified 400 plotsNaïve Bayes classifier: 85% accuracyThree orthogonal directions:Smoothing of blood glucose dataFeature engineeringEvaluation of other classifiersAutomatic Detection of Excessive Glycemic Variability as long as Diabetes Management Wiley et al.10Smoothing Blood Glucose DataSensors record at ±20% accuracyPhysicians implicitly smooth noiseAutomatic Detection of Excessive Glycemic Variability as long as Diabetes Management Wiley et al.11Smoothing Blood Glucose DataSeveral smoothing methods were investigated:Moving averagesPolynomial regressionDiscrete Fourier trans as long as m filterCubic spline interpolationCubic spline identified as the best matchAutomatic Detection of Excessive Glycemic Variability as long as Diabetes Management Wiley et al.12

Cubic Spline InterpolationTwo reasons:Smooth curves Significant pointsDoctorSplineAutomatic Detection of Excessive Glycemic Variability as long as Diabetes Management Wiley et al.13Feature EngineeringSeveral features were investigated in this work:Automatic Detection of Excessive Glycemic Variability as long as Diabetes Management Wiley et al.14Feature SelectionTwo methods are reported:t-Test filterGreedy backward eliminationBoth raw in addition to smooth dataAutomatic Detection of Excessive Glycemic Variability as long as Diabetes Management Wiley et al.15

Feature SelectionTwo methods are reported:t-Test filterGreedy backward eliminationBoth raw in addition to smooth dataOut of the four feature sets selected:No feature appeared in all four setsEccentricity in addition to bending energy were never selectedAutomatic Detection of Excessive Glycemic Variability as long as Diabetes Management Wiley et al.16Experimental EvaluationThree classifiers compared:Naïve Bayes (NB)Support Vector Machines (SVM)Multilayer Perceptron (MP)Automatic Detection of Excessive Glycemic Variability as long as Diabetes Management Wiley et al.17Experimental EvaluationThree classifiers compared:Naïve Bayes (NB)Support Vector Machines (SVM)Multilayer Perceptron (MP)Evaluated with 10-fold cross validationTuned with development datasetFeatures from feature selectionBoth raw in addition to smooth dataAutomatic Detection of Excessive Glycemic Variability as long as Diabetes Management Wiley et al.18

Visual Overview of EvaluationAutomatic Detection of Excessive Glycemic Variability as long as Diabetes Management Wiley et al.19ResultsNB with raw data: 87.1%Same settings as preliminary work – the baselinet-test filter:SVM with smoothed data: 92.8%Greedy backward elimination:MP with smoothed data: 93.8%Automatic Detection of Excessive Glycemic Variability as long as Diabetes Management Wiley et al.20ResultsNB with raw data: 87.1%Same settings as preliminary work – the baselinet-test filter:SVM with smoothed data: 92.8%Greedy backward elimination:MP with smoothed data: 93.8%Overall:Additional features helpedSmoothed data helpedAutomatic Detection of Excessive Glycemic Variability as long as Diabetes Management Wiley et al.21

Comparison of ROC Curves as long as Best ClassifiersAutomatic Detection of Excessive Glycemic Variability as long as Diabetes Management Wiley et al.22Future Work This experiment was constrained by the dataset sizePotentially suboptimal parameters in addition to featuresCollecting more data is a high priorityAutomatic Detection of Excessive Glycemic Variability as long as Diabetes Management Wiley et al.23Future Work This experiment was constrained by the dataset sizePotentially suboptimal parameters in addition to featuresCollecting more data is a high priorityPlans as long as a “5-star” ordinal schemeAlleviate disagreements between annotatorsOpportunity to further improve accuracy Automatic Detection of Excessive Glycemic Variability as long as Diabetes Management Wiley et al.24

Cleveland, Delane KMSB-TV General Assignment Reporter www.phwiki.com

From Bench to BedsideIntegration with current CGM management systemsGlucose sensors are in common use as a diagnostic toolSome patients use glucose sensors year roundManufacturers already provide reportingAutomatic Detection of Excessive Glycemic Variability as long as Diabetes Management Wiley et al.25From Bench to BedsideIntegration with current CGM management systemsGlucose sensors are in common use as a diagnostic toolSome patients use glucose sensors year roundManufacturers already provide reportingDevelopment of a screen as long as routine clinical useIdentify at risk patients in the clinical settingCompletion of the intended applicationAutomatic Detection of Excessive Glycemic Variability as long as Diabetes Management Wiley et al.26AcknowledgementsNational Science FoundationMedtronicOhio UniversityOur Dedicated Research NursesMy Fellow Graduate Research AssistantsOver 50 Anonymous Patients with Type 1 Diabetes on Insulin Pump TherapyAutomatic Detection of Excessive Glycemic Variability as long as Diabetes Management Wiley et al.27

Thanks!QuestionsAutomatic Detection of Excessive Glycemic Variability as long as Diabetes Management Wiley et al.28

Cleveland, Delane General Assignment Reporter

Cleveland, Delane is from United States and they belong to KMSB-TV and they are from  Tucson, United States got related to this Particular Journal. and Cleveland, Delane deal with the subjects like Local News

Journal Ratings by Art Academy of Cincinnati

This Particular Journal got reviewed and rated by Art Academy of Cincinnati and short form of this particular Institution is US and gave this Journal an Excellent Rating.