Speciality Medical Dialogues
    • facebook
    • twitter
    Login Register
    • facebook
    • twitter
    Login Register
    • Medical Dialogues
    • Education Dialogues
    • Business Dialogues
    • Medical Jobs
    • Medical Matrimony
    • MD Brand Connect
    Speciality Medical Dialogues
    • Editorial
    • News
        • Anesthesiology
        • Cancer
        • Cardiac Sciences
        • Critical Care
        • Dentistry
        • Dermatology
        • Diabetes and Endo
        • Diagnostics
        • ENT
        • Featured Research
        • Gastroenterology
        • Geriatrics
        • Medicine
        • Nephrology
        • Neurosciences
        • Nursing
        • Obs and Gynae
        • Ophthalmology
        • Orthopaedics
        • Paediatrics
        • Parmedics
        • Pharmacy
        • Psychiatry
        • Pulmonology
        • Radiology
        • Surgery
        • Urology
    • Practice Guidelines
        • Anesthesiology Guidelines
        • Cancer Guidelines
        • Cardiac Sciences Guidelines
        • Critical Care Guidelines
        • Dentistry Guidelines
        • Dermatology Guidelines
        • Diabetes and Endo Guidelines
        • Diagnostics Guidelines
        • ENT Guidelines
        • Featured Practice Guidelines
        • Gastroenterology Guidelines
        • Geriatrics Guidelines
        • Medicine Guidelines
        • Nephrology Guidelines
        • Neurosciences Guidelines
        • Obs and Gynae Guidelines
        • Ophthalmology Guidelines
        • Orthopaedics Guidelines
        • Paediatrics Guidelines
        • Psychiatry Guidelines
        • Pulmonology Guidelines
        • Radiology Guidelines
        • Surgery Guidelines
        • Urology Guidelines
    LoginRegister
    Speciality Medical Dialogues
    LoginRegister
    • Home
    • Editorial
    • News
      • Anesthesiology
      • Cancer
      • Cardiac Sciences
      • Critical Care
      • Dentistry
      • Dermatology
      • Diabetes and Endo
      • Diagnostics
      • ENT
      • Featured Research
      • Gastroenterology
      • Geriatrics
      • Medicine
      • Nephrology
      • Neurosciences
      • Nursing
      • Obs and Gynae
      • Ophthalmology
      • Orthopaedics
      • Paediatrics
      • Parmedics
      • Pharmacy
      • Psychiatry
      • Pulmonology
      • Radiology
      • Surgery
      • Urology
    • Practice Guidelines
      • Anesthesiology Guidelines
      • Cancer Guidelines
      • Cardiac Sciences Guidelines
      • Critical Care Guidelines
      • Dentistry Guidelines
      • Dermatology Guidelines
      • Diabetes and Endo Guidelines
      • Diagnostics Guidelines
      • ENT Guidelines
      • Featured Practice Guidelines
      • Gastroenterology Guidelines
      • Geriatrics Guidelines
      • Medicine Guidelines
      • Nephrology Guidelines
      • Neurosciences Guidelines
      • Obs and Gynae Guidelines
      • Ophthalmology Guidelines
      • Orthopaedics Guidelines
      • Paediatrics Guidelines
      • Psychiatry Guidelines
      • Pulmonology Guidelines
      • Radiology Guidelines
      • Surgery Guidelines
      • Urology Guidelines
    • Home
    • News
    • Diabetes and Endo
    • GluNet: A deep...

    GluNet: A deep learning framework that can forecast blood sugar accurately

    Written by Dr. Kamal Kant Kohli Kohli Published On 2019-08-10T09:02:45+05:30  |  Updated On 10 Aug 2019 9:02 AM IST
    GluNet: A deep learning framework that can forecast  blood sugar accurately

    Researchers have developed GluNet: A deep learning framework for accurate blood sugar forecasting. Deep learning is the latest addition in healthcare and medical research to achieve state-of-the-art results in a range of tasks including disease diagnosis. The findings of the study regarding this development have been published in the IEEE Journal of Biomedical and Health Informatics.


    For people with Type 1 diabetes (T1D), forecasting of blood sugar can be used to effectively avoid hyperglycemia, hypoglycemia and associated complications. The latest continuous glucose monitoring (CGM) technology allows people to observe blood sugar in real-time. However, an accurate blood sugar forecast remains a challenge.


    Control of blood sugar is essential for diabetes management. Current digital therapeutic approaches for subjects with Type 1 diabetes mellitus (T1DM) such as the artificial pancreas and insulin bolus calculators leverage machine learning techniques for predicting subcutaneous glucose for improved control. Deep learning has recently been applied in healthcare and medical research to achieve state-of-the-art results in a range of tasks including disease diagnosis, and patient state prediction among others.


    Researchers have introduced GluNet, a framework that leverages on a personalized deep neural network to predict the probabilistic distribution of short-term (30-60 minutes) future CGM measurements for subjects with T1D based on their historical data including glucose measurements, meal information, insulin doses, and other factors. It adopts the latest deep learning techniques consisting of four components: data pre-processing, label transform/recover, multi-layers of dilated convolution neural network (CNN), and post-processing. The method is evaluated in-silico for both adult and adolescent subjects.


    The results show significant improvements over existing methods in the literature through a comprehensive comparison in terms of root mean square error (RMSE) (8.88 ± 0.77 mg/dL) with short time lag (0.83 ± 0.40 minutes) for prediction horizons (PH) = 30 mins (minutes), and RMSE (19.90 ± 3.17 mg/dL) with time lag (16.43 ± 4.07 mins) for PH = 60 mins for virtual adult subjects. In addition, GluNet is also tested on two clinical data sets. Results show that it achieves an RMSE (19.28 ± 2.76 mg/dL) with time lag (8.03 ± 4.07 mins) for PH = 30 mins and an RMSE (31.83 ± 3.49 mg/dL) with time lag (17.78 ± 8.00 mins) for PH = 60 mins.


    These are the best reported results for blood sugar forecasting when compared with other methods including the neural network for predicting glucose (NNPG), the support vector regression (SVR), the latent variable with exogenous input (LVX), and the autoregression with exogenous input (ARX) algorithm.


    For further reference log on to :

    DOI: 10.1109/JBHI.2019.2931842
    blood glucoseblood sugarblood sugar testCGM measurementscontinuous glucose monitoringdiabetes insipidusdiabetes managementDiabetes Mellitusdiabetes symptomsFasting blood sugargestational diabetesGluNetIEEE Journal of  Biomedical and  Health Informaticsindian medical newsinsulininsulin dosageinsulin injection sites diabetesmachine learningMedical newsmobile computingnormal blood sugarnormal blood sugar leveltype 1 diabetes symptomstype 2 diabetes symptomsType-1 diabetesType-2 diabe

    Disclaimer: This site is primarily intended for healthcare professionals. Any content/information on this website does not replace the advice of medical and/or health professionals and should not be construed as medical/diagnostic advice/endorsement or prescription. Use of this site is subject to our terms of use, privacy policy, advertisement policy. © 2020 Minerva Medical Treatment Pvt Ltd

    Dr. Kamal Kant Kohli Kohli
    Dr. Kamal Kant Kohli Kohli
      Show Full Article
      Next Story
      Similar Posts
      NO DATA FOUND

      • Email: info@medicaldialogues.in
      • Phone: 011 - 4372 0751

      Website Last Updated On : 12 Oct 2022 7:06 AM GMT
      Company
      • About Us
      • Contact Us
      • Our Team
      • Reach our Editor
      • Feedback
      • Submit Article
      Ads & Legal
      • Advertise
      • Advertise Policy
      • Terms and Conditions
      • Privacy Policy
      • Editorial Policy
      • Comments Policy
      • Disclamier
      Medical Dialogues is health news portal designed to update medical and healthcare professionals but does not limit/block other interested parties from accessing our general health content. The health content on Medical Dialogues and its subdomains is created and/or edited by our expert team, that includes doctors, healthcare researchers and scientific writers, who review all medical information to keep them in line with the latest evidence-based medical information and accepted health guidelines by established medical organisations of the world.

      Any content/information on this website does not replace the advice of medical and/or health professionals and should not be construed as medical/diagnostic advice/endorsement or prescription.Use of this site is subject to our terms of use, privacy policy, advertisement policy. You can check out disclaimers here. © 2025 Minerva Medical Treatment Pvt Ltd

      © 2025 - Medical Dialogues. All Rights Reserved.
      Powered By: Hocalwire
      X
      We use cookies for analytics, advertising and to improve our site. You agree to our use of cookies by continuing to use our site. To know more, see our Cookie Policy and Cookie Settings.Ok