Skip Ribbon Commands
Skip to main content
Sign In

    A Noninvasive Monitor to Predict Hypoglycemia in Diabetes



    A Noninvasive Monitor to Predict Hypoglycemia in Diabetes Patients Using Artificial Intelligence

    Project-1 The identification of hypoglycemia is critical to reduce the morbidity and mortality among patients with type 1 or type 2 diabetes, especially in patients treated with insulin. This research proposal investigates the utility of non-invasive physiological sensor technologies and machine learning techniques to predict the development of hypoglycemia. The prediction of a hypoglycemic event through non-invasive monitoring would have a major impact on the ability of the patient and healthcare provider to achieve optimal glycemic control without increasing the risk of hypoglycemia. A non-invasive wearable sensor that predicts the development of hypoglycemia may prevent the significant morbidity and mortality associated with severe hypoglycemia.

    In this project, the team will develop a wearable device that applies sophisticated machine learning techniques on measures of skin temperature, tremor, whole body acceleration, heart rate, sweat rate and skin glucose to detect and predict hypoglycemia in patients with diabetes.





    Members

    Lead Principal Investigator (LPI):

    •  Dr. Rayaz Malik, Weill Cornell Medicine, Qatar (Email: ram2045@qatar-med.cornell.edu)

    Principal Investigators (PI):

    • Dr. John-John Cabibihan, Mechanical and Industrial Engineering Department, QU (Email: john.cabibihan@qu.edu.qa) 
    • Dr. Abdulaziz Al-Ali, KINDI Center for Computing Research, Qatar University (Email: a.alali@qu.edu.qa)
    • Dr. Kishor Kumar Sadasivuni, Center of Advanced Material, Qatar University (Email: kushorkumars@qu.edu.qa)

    Research Assistants (RA):

    • Ahmed Yaser Alhaddad, Mechanical and Industrial Engineering Dept, Qatar University (Email: a.yaser@qu.edu.qa)
    • Hoda Gad, Weill Cornell Medicine in Qatar (Email: hyg2002@qatar-med.cornell.edu)
    • Hussein Ahmed Aly, KINDI Center for Computing Research, Qatar University (Email: hussien.aly@qu.edu.qa)
    • Sreedevi Paramparambath, Center of Advanced Material, Qatar University (Email: sreedevi.p@qu.edu.qa)

    Publications

    • Elsafi A.M., Krishnasamy V., Kannan K., Cabibihan J.J., AlAli A.K., Malik R.A., Sadasivuni K.K., "Non-invasive Electrochemical Detection of Glucose using CuO-NiO/MXene Modified Electrode", Qatar University Annual Research Forum and Exhibition (QUARFE 2020), Doha, 2020, https://doi.org/10.29117/quarfe.2020.0096
    • Elsafi A.M., Krishnasamy V., Kannan K., Cabibihan J.J., AlAli A.K., Malik R.A., Sadasivuni K.K., "Construction of Modified CuO-Co3O4-ZnO Electrode for Acetone Detection in Breath", Qatar University Annual Research Forum and Exhibition (QUARFE 2020), Doha, 2020, https://doi.org/10.29117/quarfe.2020.0098
    • Shafath S., Krishnasamy V., Kannan K., Cabibihan J.J., AlAli A.K., Malik R.A., Sadasivuni K.K., "Detection of acetone in breath solution using nanocomposite CeO2-NiO-ZnO", Qatar University Annual Research Forum and Exhibition (QUARFE 2020), Doha, 2020, https://doi.org/10.29117/quarfe.2020.0100
    • Riyaz N.U.S., Kannan K., Krishnasamy V., Cabibihan J.J., AlAli A.K., Malik R.A., Sadasivuni K.K., "Biosensing studies on CuO-MgO nanocomposites for glucose detection", Qatar University Annual Research Forum and Exhibition (QUARFE 2020), Doha, 2020, https://doi.org/10.29117/quarfe.2020.0095
    • Shafath S., Krishnasamy V., Kannan K., Cabibihan J.J., AlAli A.K., Malik R.A., Sadasivuni K.K., "Synthesis, characterization and biosensor applications of CuO-NiO nanocomposite", Qatar University Annual Research Forum and Exhibition (QUARFE 2020), Doha, 2020, https://doi.org/10.29117/quarfe.2020.0101
    • Thatikayala, D.; Ponnamma, D.; Sadasivuni, K.K.; Cabibihan, J.-J.; Al-Ali, A.K.; Malik, R.A.; Min, B. Progress of Advanced Nanomaterials in the Non-Enzymatic Electrochemical Sensing of Glucose and H2O2. Biosensors 2020, 10, 151. https://doi.org/10.3390/bios10110151

    Media

    Figure-1

    Figure 1: The proposed prototype glove model showing a multisensory system approach to predict hypoglycemia. A cut-away view at the index finger shows the location of the primary sensors.

    Figure-2

    Figure 2: Electrospinning of polymer nanocomposite to fabricate nanofibers for Heart rate, and Sweat rate.

    Figure-3

    Figure 3: Clark error Grid evaluating the performance of the proposed AI model that can predict glucose level non-invasively from wearable sensors. The graph is divided into zones. Zone A represent accurate prediction, Zone B represents prediction error that did not result in wrong treatment (acceptable error), and zones C, D, E represents prediction error that resulted in wrong treatment (unacceptable error). 99% of the prediction points are in zone A, and 1% falls in zone B.

    Dates

    Started: June 1, 2019

    Ends: May 31, 2022

    Funding (if applicable)

    Funded By: QNRF – NATIONAL PRIORITY RESEARCH PROGRAM.

    Project Number: NPRP11S-0110-180247

    Collaborating Institutions (if applicable)

    • Weill Cornell Medicine in Qatar

    Industrial Collaborators (if applicable)

    • Hamad Medical Corporation