BiLSTM calibrated iGLU with demographic data: Non-invasive Glucose Measurement Device

Diabetes is regarded as a 21stcentury crisis, with new cases more than doubling in the last decade. Diabetes affects nearly 530 million people worldwide, with three out of every four adults living in low and middle-income countries. In general, one out of every two adults with diabetes is undiagnosed. The paper presents the calibration of noninvasive glucose measurement device (iGLU) using BiLSTM (Bidirectional Long Short Term Memory) model. The acquisition module of iGLU has been designed to collect the data from real subjects. The demographic data has been considered along with NIR sensor values for the calibration purpose for a test population under different blood glucose conditions. The validation of the proposed model is carried out using Clarke Error Grid Analysis (CEGA). The performance of the model has been calculated using the different parameters like: Mean Absolute Relative Difference (mARD), Average Error (AvgE), mean absolute deviation (MAD), and Root Mean Square Error (RMSE). The proposed model has 2.21% mARD, 2.32% AvgE, 1.05% MAD and 10.32% RMSE. It has outperformed all the previous models and it is precise as well as is useful for clinical testing as per the CEGA standard.

[1]  Prateek Jain,et al.  Machine learning models for non-invasive glucose measurement: towards diabetes management in smart healthcare , 2022, Health and Technology.

[2]  D. Klonoff,et al.  Products for Monitoring Glucose Levels in the Human Body With Noninvasive Optical, Noninvasive Fluid Sampling, or Minimally Invasive Technologies , 2021, Journal of diabetes science and technology.

[3]  Saraju P. Mohanty,et al.  Everything You Wanted to Know About Continuous Glucose Monitoring , 2021, IEEE Consumer Electronics Magazine.

[4]  Amit M. Joshi,et al.  DepHNN: A novel hybrid neural network for electroencephalogram (EEG)-based screening of depression , 2021, Biomed. Signal Process. Control..

[5]  Prateek Jain,et al.  Everything You Wanted to Know About Noninvasive Glucose Measurement and Control , 2021, 2101.08996.

[6]  Prateek Jain,et al.  iGLU 2.0: A New Wearable for Accurate Non-Invasive Continuous Serum Glucose Measurement in IoMT Framework , 2020, IEEE Transactions on Consumer Electronics.

[7]  Xiaoxia Song,et al.  Global, regional, and national burden and trend of diabetes in 195 countries and territories: an analysis from 1990 to 2025 , 2020, Scientific Reports.

[8]  Navneet Agrawal,et al.  iGLU 2.0: A New Wearable for Accurate Non-Invasive Continuous Serum Glucose Measurement in IoMT Framework , 2020, IEEE Transactions on Consumer Electronics.

[9]  Amit M. Joshi,et al.  iGLU: An Intelligent Device for Accurate Noninvasive Blood Glucose-Level Monitoring in Smart Healthcare , 2019, IEEE Consumer Electronics Magazine.

[10]  Niraj K. Jha,et al.  DiabDeep: Pervasive Diabetes Diagnosis Based on Wearable Medical Sensors and Efficient Neural Networks , 2019, IEEE Transactions on Emerging Topics in Computing.

[11]  Rongsheng Chen,et al.  Polypyrrole Supported With Copper Nanoparticles Modified Alkali Anodized Steel Electrode for Probing of Glucose in Real Samples , 2018, IEEE Sensors Journal.

[12]  S. Saydah,et al.  Prevalence of Diagnosed Diabetes in Adults by Diabetes Type — United States, 2016 , 2018, MMWR. Morbidity and mortality weekly report.

[13]  Gang Wang,et al.  Wearable Microsystem for Minimally Invasive, Pseudo-Continuous Blood Glucose Monitoring: The e-Mosquito , 2017, IEEE Transactions on Biomedical Circuits and Systems.

[14]  Faycal Bensaali,et al.  Novel Approach to Non-Invasive Blood Glucose Monitoring Based on Transmittance and Refraction of Visible Laser Light , 2017, IEEE Access.

[15]  S. Haxha,et al.  Optical Based Noninvasive Glucose Monitoring Sensor Prototype , 2016, IEEE Photonics Journal.

[16]  Abdelhak M. Zoubir,et al.  Measuring Blood Glucose Concentrations in Photometric Glucometers Requiring Very Small Sample Volumes , 2016, IEEE Transactions on Biomedical Engineering.

[17]  Hoi-Jun Yoo,et al.  An Impedance and Multi-Wavelength Near-Infrared Spectroscopy IC for Non-Invasive Blood Glucose Estimation , 2015, IEEE Journal of Solid-State Circuits.

[18]  Tao Dai,et al.  In Vivo Blood Characterization From Bioimpedance Spectroscopy of Blood Pooling , 2009, IEEE Transactions on Instrumentation and Measurement.

[19]  Richard D. Beach,et al.  Towards a miniature implantable in vivo telemetry monitoring system dynamically configurable as a potentiostat or galvanostat for two- and three-electrode biosensors , 2005, IEEE Transactions on Instrumentation and Measurement.

[20]  S. Hochreiter,et al.  Long Short-Term Memory , 1997, Neural Computation.

[21]  Kuldip K. Paliwal,et al.  Bidirectional recurrent neural networks , 1997, IEEE Trans. Signal Process..

[22]  A. Joshi,et al.  SzHNN: A Novel and Scalable Deep Convolution Hybrid Neural Network Framework for Schizophrenia Detection Using Multichannel EEG , 2022, IEEE Transactions on Instrumentation and Measurement.

[23]  Swapna Banerjee,et al.  Accuracy Enhancement for Noninvasive Glucose Estimation Using Dual-Wavelength Photoacoustic Measurements and Kernel-Based Calibration , 2018, IEEE Transactions on Instrumentation and Measurement.