1 iGLU: An Intelligent Device for Accurate NonInvasive Blood Glucose-Level Monitoring in Smart Healthcare Prateek Jain Amit M. Joshi Malaviya National Institute of Technology Malaviya National Institute of Technology Saraju P. Mohanty University of North Texas Abstract—In case of diabetes, fingertip pricking for blood sample is inconvenient for glucose measurement. Invasive approaches like laboratory test and one touch glucometer enhance the risk of blood related infections. To mitigate this important issue, in the current paper, we propose a novel Internetof-Medical-Things (IoMT) enabled edge-device for precise, non-invasive blood glucose measurement. The novel device called “Intelligent Glucose Meter” (i.e. iGLU) is based on near-infrared (NIR) spectroscopy and machine learning (ML) model of high accuracy. iGLU has been validated in a hospital and blood glucose values are stored IoMT platform for remote monitoring by endocrinologist.  Non Invasive Measurement  Prescribed Medicine and Fasting and Postprandial Precautions for Instant Blood Glucose Values (mg/dl) Treatment Internet Connectivity Cloud Storage  Endocrinologist Internet Connectivity  Blood Glucose Readings of the Patient Nearest Hospital For Treatment  Connecting to the available Endocrinologist Fig. 1: Blood glucose diagnosis in smart healthcare. I. I NTRODUCTION Mart healthcare system comprises of ambient intelligence, quality of service and also offers continuous support of the critical diseases monitoring [1], [2]. This system is most demandable for remote monitoring of diabetic patients with low cost and rapid diagnosis [3]. Traditional blood glucose measurement is unable to serve everyone’s need at remote location. Despite having good diagnostic centers for clinical test facility in urban area, medical services are not approachable to everyone at remote location [4], [5]. It is necessary to monitor blood glucose of diabetic patients where diagnosis facility are not easily available. The instant diagnose of blood glucose and frequent monitoring are the recent challenges in smart healthcare. The process flow of blood glucose diagnosis in smart healthcare is depicted in Figure 1. S IoMT enabled handheld non-invasive glucose measurement end-device has strong potential for rapid monitoring as well as to facilitate the interact with endocrinologist to the remote located diabetic patients where diagnosis centers and hospitals are not easily available. According to this environment, patients measure their glucose without pricking blood and directly store to the cloud where nearby endocrinologist can monitor the glucose data of each patient. The prescription would also be provided by endocrinologist to the remote located patient for further treatment. The ubiquity of diabetic patients has become double from 2010 over the world. The estimated diabetes dissemination from 2009 is 290 million and is expected to affect 450 million people by 2030. Hence, it is essential 2 to develop the glucose measurement device for rapid diagnosis of diabetes. People will be more conscious for their glucose level with frequent monitoring. Invasive method for glucose measurement is not advisable in case of continuous monitoring. Therefore, it required to design the non-invasive device for clinical tests, which is beneficial for health care. In proposed work, optical detection is involved. Blood glucose is predicted by machine learning based computation model. II. S TATE - OF -A RT IN B LOOD G LUCOSE -L EVEL M EASUREMENT Blood glucose measurement is possible using invasive, minimally invasive and non-invasive methods (Figure 2). Frequent pricking, as needed in invasive methods, for glucose measurement causes trauma. Therefore, the semi-invasive approach has the advantage of continuous glucose monitoring without multiple times pricking. However, noninvasive methods can completely eliminate pricking which opens door to painless and continuous glucose monitoring (CGM). A. Invasive Methods A low-invasive amperometric glucose monitoring biosensor has been proposed using fine pointed glucose oxidase immobilized electrode which doesn’t require more than 1mm in length to be inserted in skin [6]. A fully implanted first-generation prototype sensor has been presented for long-term monitoring of subcutaneous tissue glucose [7]. This wearable sensor which is integrated as an implant is based on a membrane containing immobilized glucose oxidase and catalase coupled to oxygen electrodes, and a telemetry system. B. Minimally Invasive Methods Implantable biosensors have been deployed for continuous glucose monitoring [8]. Wearable minimally invasive microsystem has been explored for glucose monitoring [9]. A microsystem has been presented for glucose monitoring which consists of microfabricated biosensor flip-chip bonded to a transponder chip [10]. A method has been discussed to reduce the frequency of calibration of minimally invasive Dexcom sensor [11]. An artificial pancreas has been represented along with glucose sensor to control diabetes [12]. But, approaches based semi-invasive devices have not been tried for real time application. These wearable microsystems are neither painless nor cost effective solutions. C. Non-invasive Methods To make the painless system, photoacoustic spectroscopy has been introduced for non-invasive glucose measurement [13]. However, utilization of LASER makes the setup costly and bulky. An enzyme sensor has been explored for glucose measurement in saliva [14]. Glucose detection is possible using Intensity Modulated Photocurrent Spectroscopy (IMPS) spectroscopy that connects the electrodes to the skin which is affected by sweat [15]. High precision level is not possible through these methods as sweat and saliva properties vary for individuals. The blood glucose measurement has also been explored using Raman spectroscopy in laboratory [16]. The experimental setup for Raman spectroscopy required a large area and will not be portable. Glucose measurement has also been done from anterior chamber of the eye which limits it’s usage of continuous monitoring [17]. Blood glucose can been estimated using photoplethysmography (PPG) signal [18], [19]. PPG signal analysis is not based on principle of glucose molecule detection. Therefore, specific wavelengths are not required for glucose estimation. Hence, iGLU is more precise compared to PPG signal analysis based system for glucose measurement. In this way, long NIR wave for optical detection has been considered for glucose measurement which is not comparatively precise glucose measurement system as long wave has shallow penetration [20]. Therefore, small NIR wave is preferred for glucose detection (Figure 3). Prior works related to glucose monitoring have been discussed which represent wearable and nonwearable approaches. Raman spectroscopy, photoacoustic spectroscopy and invasive approach based systems are not wearable. Minimally invasive devices which have been discussed, are implantable. Other approaches based non-invasive device are wearable. Here, iGLU is non-invasive, optical detection based wearable device for continuous glucose monitoring with IoMT framework. 3 Blood Glucose Monitoring System Invasive Amperometric Bio-impedance Minimally Invasive Implanted Sensor Raman Spectroscopy Electrochemical Biosensor Polarimetry Implanted Micro System Photoplethysmography (PPG) Signal Non Invasive Glucose Control System Long Wave NearInfrared (NIR) Detection In-vivo Near-Infrared (NIR) Spectroscopy iGLU In-vitro Photoacoustic Fig. 2: An overview of various blood glucose-level measurement devices or systems. PPG Signal Analysis Specific Wavelengths are not required LED Detector Logged signal for pulse analysis and features extraction NIR Spectroscopy Specific LED Detector Wavelengths needed for glucose molecule detection Logged voltage values after absorption and reflectance of light from glucose molecule Fig. 3: PPG signal versus NIRS based glucose estimation D. Consumer Electronics for Glucose-Level Monitoring Several devices have been developed for noninvasive blood glucose measurement. Some products such as glucotrack, glutrac, glucowise, DiaMon Tech and device from CNOGA medical are not commercialized. Glutrac is multi-parameter health test device with smart healthcare. However, they have limitations in terms of precise measurement. The cost of product is also high which varies in the range of 300-400 USD. Therefore, the cost effective solution for non-invasive blood glucose measurement is needed. III. N OVEL D EVICE I GLU TO A DVANCE THE S TATE - OF -A RT IN W EARABLE FOR C ONTINUOUS B LOOD G LUCOSE M ONITORING Non-invasive measurement reduces the possibility of blood-related diseases. However, this approach have some limitations such as large setup, measuring object (ratina) and skin properties (including dielectric constant and sweat level). Therefore, portable non-invasive precise glucose measurement device for continuous monitoring is needed. An initial example is a non-invasive glucose measurement using NIR spectroscopy and Huber’s regression model [21]. There are several glucose monitoring systems which neither provide precise measurement nor cost effective solution. These systems are not enabled for smart healthcare. The following questions are resolved in iGLU for the advancement of smart healthcare: (1) How can we have a device that automatically performs all the tasks of blood-glucose monitoring at the user end without internet connectivity and stores the data in cloud for future use by the patient and healthcare providers? (2) Can we have a device that can perform automatically to avoid hassle and risky finger pricking all the time monitoring is needed? This article introduces an edge-device called “Intelligent Glucose Meter” (i.e. iGLU) for noninvasive, precise, painless, low-cost continuous glucose monitoring at the user-end and stores the data on cloud in an IoMT framework. A non-invasive device has been proposed with precise and low cost solution. The proposed device is also integrated with IoMT where the data is accessible to caretaker for point of care. The device will be portable after packaging to use everywhere. The device is fast operated and easy to use for smart healthcare. The flow of proposed iGLU is represented in Figure 4. The contributions this article to advance the stateof-art in smart healthcare include the following: 1) A novel accurate non-invasive glucometer (iGLU) by judiciously using short NIR waves 4 Vibrations (Stretching, Wagging, Bending) Start Power Supply ON for Emitters and Detectors of Three Channels and ADS 1115 Attenuated Infrared Detector Wave Connect the Arduino Uno Board to PC through USB Port Infrared Transmitted Wave Emitters (940nm, 1300nm) Infrared Detector Analog-toDigital Converter (ADS1115) Postprocessing Computation Model Estimated Blood Glucose Value Upload the Program of Data Processing through ADS 1115 using Arduino 1.8.5 Software Cloud Storage Fig. 4: A conceptual overview of iGLU. with absorption and reflectance of light using specific wavelengths (940 and 1300 nm) has been introduced. The wavelengths are judiciously selected after experimental analysis which has been done in material research center MNIT, Jaipur (India). 2) A novel accurate machine learning based method for glucose sensor calibration has been presented with calibrated and validated healthy, prediabetic and diabetic samples. 3) The proposed non-invasive blood glucose measurement device has been integrated in IoMT framework for data (blood glucose values) storage, patient monitoring and treatment on proper time with cloud access by both the patient and doctor. Uploading Failed Check Mode Program Uploaded Placing of objects (Fingers or Ear Lobes) in Clips for Glucose Measurement Re-connect the Arduino Uno Board to PC through USB Port Run the Tera Term Application on PC for Data Logging Sampling and Averaging of Collected Data from Three Channels for Calibration and Validation of Regression Models Stop Fig. 5: Process flow data acquisition for iGLU. alyzed that absorbance and reflectance are sharper and stronger in short wave NIR region [22]. The absorption peak of glucose spectra at 1314 nm has been analyzed [23]. The non-invasive blood glucose measurement using 850, 950 and 1300 nm has been implemented [15]. The 940 nm wavelength for detection of glucose molecule has been identified [24]. NIR spectra of sucrose, glucose and fructose are elaborated with CH2 , CH and OH stretching at 930, 960 and 984 nm, respectively [25]. B. Proposed Module for Data Acquisition IV. P ROPOSED N ON - INVASIVE B LOOD G LUCOSE M EASUREMENT D EVICE ( I GLU) The proposed device based on NIR spectroscopy with two short wavelengths is designed and implemented using three channels. Each channel is embedded with emitter and detector of specific wavelength for optical detection. The data is collected and serially processed by 16 bit ADC with sampling rate of 128 samples per second. The logged data is calibrated and validated thorough existing regression techniques to analyse the optimized model. The flow of data acquisition for proposed iGLU is presented in Figure 5. A. The Approach for Glucose Molecule Detection Glucose molecule vibrates according to its atomic structure at specific wavelengths. It is an- Proposed iGLU uses NIR spectroscopy to improve the accuracy. A 2-Layer PCB has been developed to embed infra-red emitters (MTE1300W -for 1300 nm, TSAL6200 -for 940 nm, TCRT1000 -for 940 nm) and detectors (MTPD1364D -for 1300 nm, 3004MID -for 940 nm, TCRT1000 -for 940 nm). The hardware is designed for data acquisition from emitters, detectors and ADC with 5V DC supply. According to the emitters and detectors, compatible passive components have been chosen. Architecture of glucose sensing is shown in Figure 6. Detectors with daylight blocking filters are packaged and not affected by sweat. ADS 1115 with 860 SPS, 16 bit, I 2 C compatible and single ended is controlled through microcontroller ATmega328P and used to convert the data (in Volts) from all channel in decimal form. The noise power and signal-to-noise 5 ratio (SNR) have also been found 0.08 and 25.2 dB, respectively, which show the minimum noise level. Arduino Supply Power Supply Arduino Uno Board Power Supply Node 100 Ω 100Ω Photo Diode LED GND 10k Ω 940 nm (Absorption) Channel 2 1300 nm Channel 1 O/P 3 LED O/P 2 O/P Voltage GND A D S Photo Diode Object GND 940 nm (Reflectance) Channel 3 GND 10k Ω TABLE I: Specification of iGLU prototype Data Output 1 1 1 5 GND O/P 3 O/P 2 O/P 1 Forward Voltage (Emitter) Forward Current (Emitter) Reverse Voltage (Detector) Output Current (Detector) Measurement range Specific Wavelength Spectroscopy Channel 1 Channel 2 Channel 3 Measured (Ideal) 4.95V 4.96V 4.95V (5V) (5V) (5V) 0.96V 1.42V 1.40V (1.1V) (1.5V) (1.5V) 53.4mA 52.8mA 52.9mA (100mA) (60mA) (60mA) 4.25V 4.16V 4.25V (5V) (5V) (5V) 0.45mA 0.5mA 0.52mA (1mA) (1mA) (1mA) 3.2-4.68V 0.8-4.7V 0.5-4.7V 1300nm 940nm 940nm Absorption Absorption Reflectance Fig. 6: Circuit topology of proposed device (iGLU). and sensors (emitters and detectors). Hence, the probability of a faulty measurement is minimized. C. A Specific Prototype of the iGLU Absorption and reflectance at 940 nm and absorption at 1300 nm are implemented for detection of the glucose molecules. The detector’s voltage depends on received light intensity. After placing the fingertip between emitter and detector, the voltage values are logged. Change in light intensity depends upon glucose molecule concentration. During experiments, blood glucose is measured through the invasive device standard diagnostics (SD) check glucometer for validation of the noninvasive results. The reading is taken as referenced blood glucose values (mg/dl). During the process, optical responses through detectors have been collected from 3 channels simultaneously. During measurement, the channels data is collected in the form of voltages from 3 detectors. These collected voltages correspond to referenced blood glucose concentration. These voltage values are converted into decimal form using 4-channel ADS 1115 (Texas Instruments) ADC [26]. Coherent averaging has been done after collection of responses. Specification of a iGLU prototype are presented in Table I. The prototype view of proposed iGLU is shown in Figure 7. The data is collected after fixing three fingers in free space of pads. The pads are designed in such a way that emitters and detectors are placed beneath the surfaces of pads. Because of this, there will be enough free spaces between the object Fig. 7: Prototype view of proposed device (iGLU). V. P ROPOSED M ACHINE -L EARNING (ML) BASED M ETHOD FOR I GLU C ALIBRATION Regression models are calibrated to analyze the optimized computation model for glucose estimation. The detector’s output from three channels are logged as input vectors for glucose prediction. The collected data from the samples is required to convert in the form of estimated glucose values. It is necessary to develop optimal model for precise measurement and hence analysis of M AD, mARD, AvgE and RM SE are performed to ensure accuracy. The estimated and reference blood glucose concentration are calculated as BGEst and BGRef , respectively. A total of 97 samples are taken for device calibration which include prediabetic, diabetic and healthy samples. The baseline 6 characteristics of samples for calibration is represented in Table II. The proposed process flow of calibration and validation is shown in Figure 8. TABLE II: Baseline characteristics of samples Calibration Validation and Testing Gender Wise Samples Male:- 53 Male:- 64 Female:- 44 Female:- 29 Prediabetic Male:- 18 Male:- 11 Female:- 13 Female:- 10 Diabetic Male:- 16 Male:- 17 Female:- 14 Female:- 11 Healthy Male:- 19 Male:- 36 Female:- 17 Female:- 08 Input Vectors (Voltage values from 3 Channels) Referenced Blood Concentration (mg/dl) Proposed Machine Learning based Regression Model Data Set (Input Voltage values with Referenced Blood Glucose) Channel 1 1 Channel 2 2 w w 1 10 Weight of the Glucose Value 1 bias w’ 2 2 3 3 10 10 w’ w’ Ʃ Predicted Blood Glucose (mg/dl) Input w Channel 3 w 3 Voltage Sigmoid Activation Function w’ 10 Hidden Layers Neural Network for Computation of Blood Glucose Output Layer Prediction of Blood Glucose Fig. 9: The Deep Neural Network (DNN) for proposed work The Pearson’s correlation coefficient (R) is 0.953. The error analysis of calibrated machine learning models is represented in Table III. Calibration through Machine Learning Technique Error Analysis from Predicted Glucose Concentration 1 TABLE III: Analysis of calibration and validation of proposed combination and ML model (DNN). Calibration (Validation) Prediction from Calibrated Machine Learning Model for Validation Referenced Blood Concentration (mg/dl) Weight of the Voltage Output Samples Basic Characteristics Age (Years) Male:- 22-77 Female:- 17-75 Age (Years) Male:- 22-65 Female:- 26-75 Age (Years) Male:- 30-68 Female:- 30-73 Age (Years) Male:- 22-65 Female:- 17-70 values are formed through the modeling of three channels voltage values. Weights of the voltage values correlate predicted glucose values to the channels data. The overall accuracy is improved using 10 hidden layers. MARD (%) AvgE (%) MAD (mg/dl) RMSE (mg/dl) Fig. 8: The process flow of calibration and validation of proposed device (iGLU). Deep Neural Network (DNN) based machine learning model has been applied for precise blood glucose prediction (Figure 9) [2]. Proposed DNN uses sigmoid activation functions and has been trained through Levenberg-Marquardt backpropagation algorithm [15]. In proposed model, 10 hidden neurons and 10 hidden layers are analyzed to estimate the precise blood glucose values. This model has been used to analyze the non-linear statistical data which is utilized to calibrate and validate the model for precise measurement. Here, the voltage values from three channels are used as inputs of proposed DNN model. The predicted blood glucose mARD (%) 6.65 7.32 AvgE (%) 7.30 7.03 M AD (mg/dl) 12.67 09.89 RM SE (mg/dl) 21.95 11.56 VI. VALIDATION OF THE P ROPOSED I GLU D EVICE To validate and test iGLU, 93 healthy, prediabetic and diabetic samples aged 17-75 are taken following medical protocols. A total of 64 males and 29 females are identified during collection of these 93 samples. All samples are taken in fasting, postprandial and random modes. The baseline characteristics and error analysis is represented in Table II and III, respectively. A 10-fold cross validation has been performed to validate iGLU. To test the device stability, an experiments have been performed from multiple measurements of same sample by couple of times. For this experimental work, a volunteer has been recruited to measure blood glucose through iGLU and invasive method with time intervals of 5 minutes. A value of 10 mg/dl deviation are considered in observations during 7 iterations of blood glucose 7 B lo o d G lu c o s e C o n c e n tr a tio n (m g /d l) 1 4 0 R e fe r e P r e d ic W ith d F r o m 1 3 8 1 3 6 1 3 4 n c e te d iffe e a r d B lo o d G lu c o s e C o n c e n tr a tio n (m g /d l) B lo o d G lu c o s e C o n c e n tr a tio n (m g /d l) r e n t fin g e r c o m b in a tio n lo b e 1 3 2 1 3 0 1 2 8 1 2 6 1 2 4 1 2 2 1 2 0 8 :0 0 A M 8 :0 5 A M 8 :1 0 A M 8 :1 5 A M 8 :2 0 A M 8 :2 5 A M 8 :3 0 A M B lo o d G lu c o s e C o n c e n tr a tio n (m g /d l) measurement. During analysis, 2-4 mg/dl deviation has been observed (Figure 10(a)). A different volunteer has also been taken for another experimental analysis to validate the accuracy of iGLU (Figure 10(b)). Measurement has been done with time interval of 60 minutes using 7 iterations. Variations (low to high) in reference blood glucose values between 8:00 AM-10:00 AM, 10:00 AM-2:00 PM and 2:00 PM-4:00 PM represent the glucose intakes in the form of food. During analysis, 5-10 mg/dl deviation represents the stability of iGLU. It was observed that the effect of fingers or earlobes changes is negligible. CEG analysis is used to analyze the accuracy of predicted glucose values from proposed device. CEG categorizes the devices in terms of precise measurement and elaborates the zones by the difference between referenced and predicted glucose values [27]. The predicted values are in the zone A and B; then the device will be desirable. During analysis, all predicted glucose values found in zone A and B (Figure 11). 2 1 0 2 0 0 1 9 0 1 8 0 1 7 0 1 6 0 1 5 0 1 4 0 1 3 0 1 2 0 1 1 0 1 0 0 R e fe r e P r e d ic W ith d F r o m 8 :0 0 A M n c e te d iffe e a r d B B lo r e n lo b 9 :0 0 A M lo o d G lu c o s e C o n c e n tr a tio n (m g /d l) o d G lu c o s e C o n c e n tr a tio n (m g /d l) t fin g e r c o m b in a tio n e 1 0 :0 0 A M T im e 2 :0 0 P M T im e 3 :0 0 P M 4 :0 0 P M 5 :0 0 P M (a) Time interval of 5 minutes (b) Time interval of 60 minutes Clarke's Error Grid Analysis 400 E C B A (90%) B (10%) 300 B 200 D D 100 0 A 0 C 100 200 E 300 400 Reference Concentration [mg/dl] (a) Validation Predicted Concentration [mg/dl] Predicted Concentration [mg/dl] Fig. 10: Predicted and reference blood glucose concentration for validation of iGLU on single sample. Clarke's Error Grid Analysis 500 E C B A (94%) B (06%) 400 300 B 200 D D 100 A 0 0 E C 100 200 300 400 500 Reference Concentration [mg/dl] (b) Testing Fig. 11: CEG analysis of predicted glucose values VII. C ONCLUSIONS AND F UTURE D IRECTIONS This article introduced a dual short-wave spectroscopy NIR technique based non-invasive glucose monitoring low cost (approximately 20-25 USD) device iGLU for real-life application. The error margins for iGLU are improved compared to other non-invasive approach based systems. After CEG analysis, 100% samples come in the zone A and B. During analysis of possible combinations with proposed ML model, iGLU is found more optimized compared to other measurement device. In the future research on iGLU, we will involve more features of IoMT. Glucose-level measurement from serum is a immediate next goal to further improve accuracy of iGLU. Integration of stress measurement along with blood-glucose level is also in pipeline. A closed feedback from healthcare providers-end to the end-user side for control of effects when needed to ensure remote healthcare when there may be shortage of healthcare providers can be more effective. ACKNOWLEDGMENT The authors would like to thank Dispensary MNIT Jaipur (India). We would also thank Dr. Navneet Agrawal (diabetologist) and his team for the support at Diabetes, Obesity and Thyroid Centre Gwalior (India). R EFERENCES [1] S. Ruan, “Intelligent systems for smart health care: Leveraging information for better well-being,” IEEE Consumer Electronics Magazine, vol. 8, no. 2, pp. 71–71, March 2019. [2] P. Sundaravadivel, K. Kesavan, L. Kesavan, S. P. Mohanty, and E. Kougianos, “Smart-Log: A Deep-Learning Based Automated Nutrition Monitoring System in the IoT,” IEEE Trans. Consum. Electron, vol. 64, no. 3, pp. 390–398, Aug 2018. [3] S. P. Mohanty and E. Kougianos, “Biosensors: A Tutorial Review,” IEEE Potentials, vol. 25, no. 2, pp. 35–40, March 2006. [4] S. P. Mohanty, U. Choppali, and E. Kougianos, “Everything you wanted to know about smart cities: The Internet of things is the backbone,” IEEE Consumer Electronics Magazine, vol. 5, no. 3, pp. 60–70, July 2016. [5] P. Sundaravadivel, E. Kougianos, S. P. Mohanty, and M. K. Ganapathiraju, “Everything You Wanted to Know about Smart Health Care: Evaluating the Different Technologies and Components of the Internet of Things for Better Health,” IEEE Consumer Electronics Magazine, vol. 7, no. 1, pp. 18–28, January 2018. 8 [6] J. Li, P. Koinkar, Y. Fuchiwaki, and M. Yasuzawa, “A fine pointed glucose oxidase immobilized electrode for lowinvasive amperometric glucose monitoring,” Biosensors and Bioelectronics, vol. 86, pp. 90–94, 2016. [7] J. Y. Lucisano, T. L. Routh, J. T. Lin, and D. A. Gough, “Glucose monitoring in individuals with diabetes using a long-term implanted sensor/telemetry system and model,” IEEE Transactions on Biomedical Engineering, vol. 64, no. 9, pp. 1982–1993, 2017. [8] A. Sun, A. G. Venkatesh, and D. A. Hall, “A multitechnique reconfigurable electrochemical biosensor: Enabling personal health monitoring in mobile devices,” IEEE Transactions on Biomedical Circuits and Systems, vol. 10, no. 5, pp. 945–954, Oct 2016. [9] G. Wang, M. D. Poscente, S. S. Park, C. N. Andrews, O. Yadid-Pecht, and M. P. Mintchev, “Wearable microsystem for minimally invasive, pseudo-continuous blood glucose monitoring: The e-mosquito,” IEEE Transactions on Biomedical Circuits and Systems, vol. 11, no. 5, pp. 979–987, Oct 2017. [10] M. M. Ahmadi and G. A. Jullien, “A wireless-implantable microsystem for continuous blood glucose monitoring,” IEEE Transactions on Biomedical Circuits and Systems, vol. 3, no. 3, pp. 169–180, June 2009. [11] G. Acciaroli, M. Vettoretti, A. Facchinetti, G. Sparacino, and C. Cobelli, “Reduction of blood glucose measurements to calibrate subcutaneous glucose sensors: A bayesian multiday framework,” IEEE Transactions on Biomedical Engineering, vol. 65, no. 3, pp. 587–595, 2018. [12] I. Pagkalos, P. Herrero, C. Toumazou, and P. Georgiou, “Bio-inspired glucose control in diabetes based on an analogue implementation of a β-cell model,” IEEE Transactions on Biomedical Circuits and Systems, vol. 8, no. 2, pp. 186–195, April 2014. [13] P. P. Pai, A. De, and S. Banerjee, “Accuracy enhancement for noninvasive glucose estimation using dual-wavelength photoacoustic measurements and kernel-based calibration,” IEEE Transactions on Instrumentation and Measurement, vol. 67, no. 1, pp. 126–136, 2018. [14] M. Yamaguchi, M. Mitsumori, and Y. Kano, “Noninvasively measuring blood glucose using saliva,” IEEE Engineering in Medicine and Biology Magazine, vol. 17, no. 3, pp. 59–63, May 1998. [15] K. Song, U. Ha, S. Park, J. Bae, and H. J. Yoo, “An impedance and multi-wavelength near-infrared spectroscopy ic for non-invasive blood glucose estimation,” IEEE Journal of Solid-State Circuits, vol. 50, no. 4, pp. 1025–1037, April 2015. [16] W.-C. Shih, K. L. Bechtel, and M. V. Rebec, “Noninvasive glucose sensing by transcutaneous raman spectroscopy,” Journal of biomedical optics, vol. 20, no. 5, p. 051036, 2015. [17] C. W. Pirnstill, B. H. Malik, V. C. Gresham, and G. L. Coté, “In vivo glucose monitoring using dual-wavelength polarimetry to overcome corneal birefringence in the presence of motion,” Diabetes technology & therapeutics, vol. 14, no. 9, pp. 819–827, 2012. [18] E. Monte-Moreno, “Non-invasive estimate of blood glucose and blood pressure from a photoplethysmograph by means of machine learning techniques,” Artificial intelligence in medicine, vol. 53, no. 2, pp. 127–138, 2011. [19] S. Habbu, M. Dale, and R. Ghongade, “Estimation of blood glucose by non-invasive method using photoplethysmography,” Sādhanā, vol. 44, no. 6, p. 135, 2019. [20] S. Sharma, M. Goodarzi, L. Wynants, H. Ramon, and W. Saeys, “Efficient use of pure component and interferent spectra in multivariate calibration,” Analytica chimica acta, vol. 778, pp. 15–23, 2013. [21] P. Jain, R. Maddila, and A. M. Joshi, “A precise noninvasive blood glucose measurement system using NIR spectroscopy and Hubers regression model,” Optical and Quantum Electronics, vol. 51, no. 2, p. 51, 2019. [22] Y. Uwadaira, A. Ikehata, A. Momose, and M. Miura, “Identification of informative bands in the shortwavelength nir region for non-invasive blood glucose measurement,” Biomedical Optics Express, vol. 7, no. 7, pp. 2729–2737, 2016. [23] W. Zhang, R. Liu, W. Zhang, H. Jia, and K. Xu, “Discussion on the validity of nir spectral data in non-invasive blood glucose sensing,” Biomedical optics express, vol. 4, no. 6, pp. 789–802, 2013. [24] S. Haxha and J. Jhoja, “Optical based noninvasive glucose monitoring sensor prototype,” IEEE Photonics Journal, vol. 8, no. 6, pp. 1–11, 2016. [25] M. Golic, K. Walsh, and P. Lawson, “Short-wavelength near-infrared spectra of sucrose, glucose, and fructose with respect to sugar concentration and temperature,” Applied spectroscopy, vol. 57, no. 2, pp. 139–145, 2003. [26] P. Jain and S. Akashe, “Analyzing the impact of bootstrapped adc with augmented nmos sleep transistors configuration on performance parameters,” Circuits, Systems, and Signal Processing, vol. 33, no. 7, pp. 2009–2025, 2014. [27] W. L. Clarke, “The original Clarke error grid analysis (EGA),” Diabetes technology & therapeutics, vol. 7, no. 5, pp. 776–779, 2005. A BOUT THE AUTHORS Prateek Jain is a Research Scholar in ECE department of MNIT, Jaipur, India. He can be contacted at: prtk.ieju@gmail.com. Amit M. Joshi is an Assistant Professor in Department of ECE, MNIT, Jaipur, India. He can be contacted at: amjoshi.ece@mnit.ac.in. Saraju P. Mohanty is the Editor in Chief of the IEEE Consumer Electronics Magazine and Professor in the Department of Computer Science and Engineering (CSE), University of North Texas (UNT), Denton, TX, USA. Contact him at Saraju.Mohanty@unt.edu. 99 Chapter 6 Diabetes Patients Monitoring by Cloud Computing Sepideh Poorejbari Pervasive and Cloud Computing Laboratory, Iran Hamed Vahdat-Nejad University of Birjand, Iran Wathiq Mansoor University in Dubai, UAE ABSTRACT The healthcare system is important due to the focus on human care and the interference with human lives. In recent years, we have witnessed a rapid rise in e-healthcare technologies such as Electronic Health Records (EHR) and the importance of emergency detection and response. Cloud computing is one of the new approaches in distributed systems that can handle some of the challenges of smart healthcare in terms of security, sharing, integration and management. In this study, an architecture design of a cloud-based pervasive healthcare system for diabetes treatment has been proposed. For this, three different components are defined as follows: (1) The home context manager which gathers necessary information from patients while simultaneously providing feedback, (2) a patient health record manager that is accessible by nurses or physicians at the hospital, and (3) a diabetes management system which is located with the cloud infra-structure for managing and accessing patient’s information. The performance of proposed architecture is demonstrated through a user scenario. DOI: 10.4018/978-1-5225-1002-4.ch006 Copyright ©2017, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited. Diabetes Patients Monitoring by Cloud Computing INTRODUCTION Information technology can play a vital role in healthcare services in terms of electronic health. Recent advances in e-health can be broadly defined as the application of information and communication technologies in healthcare systems (Varshney, 2009). Making use of the internet for storing, accessing and modifying healthcare information and digitizing many processes and tasks is a necessary step for realizing e-health. In this case, we have the advantages of e-health such as a rise in the quality of services in aging societies, reduction in cost and in medical errors and the ease by which data can be moved to the right place. However, digitizing paperbased records, collecting and storing medical information as well as lack of suitable technology for preventive care can become rather challenging. After the emergence of the pervasive computing paradigm, pervasive healthcare technology has been proposed to support a wide range of applications and services including patient monitoring and emergency response. However, they simultaneously introduce several challenges including data storage and management, interoperability, availability of resources and ubiquitous access issues (Ziefle & Rocker, 2010). Diabetes is one of the major chronic diseases in the world. Diabetes, often referred to by doctors as diabetes mellitus, describes a group of metabolic diseases in which the person has high blood glucose (blood sugar), either because insulin production is inadequate, or because the body’s cells do not respond properly to insulin, or both. Diabetes manifests itself in three types: Type 1: This type of diabetes is usually diagnosed in children and young adults, and was previously known as juvenile diabetes. Only 5% of people with diabetes have this form of the disease. In this type of diabetes, the body does not produce insulin. Type 2: Is a problem with your body that causes blood glucose (sugar) levels to rise higher than normal. This is also called hyperglycemia. Type 2 is the most common form of diabetes; About 90 percent of people with diabetes have type 2 diabetes. Type 3: Gestational Diabetes is a temporary condition that occurs during pregnancy. It affects approximately 2 to 4 percent of all pregnancies and involves an increased risk of developing diabetes for both the mother and child. All forms of diabetes increase a patient’s risk of emerging different health complications. Short-term complications such as hypoglycemia and hyperglycemia (very low and high blood glucose), and long-term complications such as eyes, heart, kidneys, nerves and feet failure are serious and life-threatening. The proper management of blood glucose levels reduces the risk of developing these complications. Factors 100 Diabetes Patients Monitoring by Cloud Computing such as the illness that patient suffers, treatment, physical and psychological stress, physical activity, drugs and diet (meal plan) can cause unpredictable and dangerous consequences such as hypoglycemia, hyperglycemia, and falling into a coma. The management of diabetes is becoming an increasingly important problem worldwide. In 2014, according to the International Diabetes Federation, at least 387 million people (or 8.3% world population) suffered from diabetes and it is expected that by 2035, the number of diabetes will increase to more than 590 million. Case Study: This scenario originates from the Imam Reza hospital, one of the leading and technical hospitals in Mashhad, Iran. Mr. Toosi, a 62 year old man has suffered from type 2 diabetes for more than 10 years. In this period of time, he has caught different health complications such as diabetes foot, eye problems, high blood pressure, and heart problems. His prescription includes 20 units of insulin per day, 12 units in the morning and 8 units at night. In addition he has to check his glucose level on a daily basis. On one early morning, Mr. Toosi woke up with shortness of breath and weakness in his body. Without special attention, he had his breakfast and injects his insulin. After two hours he feels more pain and weakness in his chest and body, but because he is alone at home he prefers to wait until one of the family members returns home, before heading out for a check-up. When Mr Toosi’s son arrives home, he immediately drives his father to the nearest hospital. At the hospital, the physicians and nurses run some treatments, however due to the lack of medical information and patient health records they are unable to make precise decisions and prefer to send the patient to the hospital where Mr. Toosi’s main physician is available. Unfortunately, after sending the patient to another hospital he falls into a diabetes coma and passes away after a second heart attack. The above scenario leads to a few issues that need to be addressed in pervasive diabetes health system. Here we focus on the following two problems: • • Monitoring patient remotely at home and detecting and managing different situations. Accessing patient health records and medical history at anytime and anywhere by legal persons. The concept of cloud-based pervasive healthcare system is a new paradigm for the healthcare sector that uses cloud computing to treat, manage and control patients pervasively. The systems are supported by different algorithms, cloud infrastructures, smart homes, devices, and sensors and create several service types according to their context and environment. This paper presents a Cloud-based pervasive healthcare 101 Diabetes Patients Monitoring by Cloud Computing system architecture for treating diabetes, in order to manage and control diabetic patients and reduce the hypoglycemia and hyperglycemia conditions and consequently their risks. The system, which we will refer to as DICPer-Health, is designed to control patients pervasively at their homes. Three environments including a home, hospital and cloud structure are considered as main parts of this system, by which each of these sections has its own components and acts separately. We have selected diabetes type 2 as the chronic condition cannot be cured and is the condition of 9/10 diabetes patients. In type 2 diabetes, the body cannot use insulin properly. This is called insulin resistance. Type 2 is treated with lifestyle changes, oral medications, and insulin injections. This type of diabetes usually gets worse over time, and in order for individuals with type 2 diabetes to control their blood glucose levels, they need to eat healthy, stay active, and use prescribed drugs appropriately. In this case we have considered three important factors in our framework; diet, activity, and insulin. These three factors control and manage the lifestyle of type 2 diabetes patients. The following sections of the paper are organized as follows; Section (2) presents the pervasive healthcare projects and related works. Section (3) presents architecture to support diabetes treatment. The architecture parts are described in subsections. Section (4) presents the evaluation of work according to real life patient scenario. Finally, section 5 will conclude the paper. RELATED WORKS Today, there is a great amount of research work in the field of pervasive healthcare to improve e-health services; however only a few number target the use of cloud infrastructure as a new IT paradigm and are surveyed as below. “The Integrated Cloud-based Healthcare Infrastructure” project, ICHI has been developed in Edinburgh Napier University of United Kingdom. ICHI presents a system that integrates a formal care system (DACAR) with an informal care system (Microsoft Health Vault) that enables not only sharing and access of health records right along the patient pathway, but also provides a high level of security and privacy within a cloud environment (Ekonomou, Fan, Buchanan, & Thuemmler, 2011). Another project in the University of Central Greece, “Bringing IoT and Cloud Computing towards Pervasive Healthcare”, IoTC, proposes a platform based on cloud computing for management of mobile and wearable healthcare sensors (Mu-Hsing Kuo, 2011). In another research project concluded at the University of Greece, namely “Managing Wearable Sensor Data through Cloud Computing” (MWSC), a wearable textile platform that collects motion and heartbeat data and stores them wirelessly 102 Diabetes Patients Monitoring by Cloud Computing on an open cloud infrastructure for monitoring and further processing was studied (Wan, Zou, Ullah, Lai, Zhou & Wang, 2013). “Cloud-Enabled Wireless Body Area Networks for Pervasive Healthcare (CWBAN)” is another article in the same context that focuses on a cloud-enabled WBAN architecture and its applications are within pervasive healthcare systems. CWBAN develops WBANs with MCC (Mobile Cloud Computing) capability, a Cloud-Enabled WBAN (Woon Ahn, Cheng, Baek, Jo & Chen, 2013). This project has also been developed in different universities including South China University of Technology, King Saud University, and the University of British Columbia. Another article namely “An Auto-Scaling Mechanism for Virtual Resources to Support Mobile, Pervasive, and Real-Time Healthcare Applications in Cloud Computing” (RTHA) proposes a novel server-side auto-scaling mechanism. The model is based on cloud computing with virtualization technologies in collaboration with the University of Houston and Korea University (Corredor, Tarrio, Bernardos, & Casar, 2013). As mentioned above, the number of pervasive healthcare projects related to cloud computing for diabetes are few. Moving forward, we have scrutinized just two articles that introduce a personal health system (PHS) to manage diabetic patients. One of these projects at the University of London, is “COMMODITY12: A Smart e-Health Environment for Diabetes Management” that emphasizes on designing the PHS to address major problems of both diabetic patients and doctors who treat diabetes (Kafah et al., 2013). COMMODITY12 consists of ambient, wearable and portable devices, which acquire, monitor and communicate physiological parameters and other health factors and vital body signals of a patient. In this system, there are intelligent agents that use expert biomedical knowledge to interpret data and then present a feedback from a patient’s health status directly to the patient from the device (Kafah et al., 2013). University of Murcia, Spain, has developed another healthcare project for diabetes, “An Internet of Things-based Personal device for Diabetes Therapy Management in Ambient Assisted Living (AAL)”, that presents a personal diabetes management device based on the Internet of Things. The target is to support a patient’s insulin therapy to decrease hyperglycemia and hypoglycemia counts and the risks involved (Jara, Zamora, & Skarmeta, 2011). This project focuses more on insulin dosage based on mobile assistance services. The project considers different factors such as the illness that patients suffer, drugs, treatments, stress, physical activity and meal (diet) for insulin therapy. One related survey is “An Introduction to Cloud-Based Pervasive Healthcare Systems”, that reviews different projects in healthcare sector with the focus on cloud computing (Poorejbari & Vahdat-nejad, 2014). 103 Diabetes Patients Monitoring by Cloud Computing THE PROPOSED FRAMEWORK Overview To introduce DICPer-Health, our first initiative is to present the general architecture of the system in order to briefly describe the main components. We will then concentrate on the description of three key components: Home Context Manager, Hospital Environment and Cloud Infrastructure. Figure 1 depicts our proposed architecture for a smart healthcare environment. The figure consists of three main components which are connected via Internet: (i) The home context manager which gathers necessary information from patients while simultaneously providing feedback, (ii) a patient health record form that is accessible by nurses or physicians at the hospital, and (iii) a diabetes management system which is located with the cloud infrastructure for managing and accessing patient’s information. In our proposed architecture, the home context manager plays a major role in collecting, storing and processing data. Once the initial procedures are complete, Figure 1. General Architecture of DICPer-Health 104 Diabetes Patients Monitoring by Cloud Computing the system presents alerts, suitable treatments, and advices to the patient. The function of the home context manager and its components will be described in a later section. Home Context Manager The main role of the home context manager is collecting different information such as blood glucose level, blood pressure, and heart rates from patients through various sensors at specific times. After gathering patient health parameters, all the required information is stored in a context database. The inference engine then infers two different important conditions; High risk and emergency situations. According to the conditions and patient health history, suitable advices and alarms will be communicated to the patient’s smart device or in an application connected to nurses or experts. The home context manager consists of the following components. Wireless Sensors Sensors are essential components in smart environments which sense and collect physical parameters. We utilize three types of wireless sensors in our framework, which gather fundamental physiological information from diabetes. The sensors are depicted in Table 1 and described below with the objective of sensing our requirements. • • • Glucose monitoring by finger prick (GlucoTel Sensor). Blood pressure monitoring (PressureTel Sensor) Heart rate monitoring (Pulse Sensor) None of the above sensors are expected to be considered obtrusive by the patients. Patients without any special knowledge can use them with ease. Table 1. Schema of context table Parameter Date Time 8 A.M. 10 A.M. 3 P.M. 10 P.M. Blood Glucose Blood Pressure Heart Rate 105 Diabetes Patients Monitoring by Cloud Computing Context Collector After sensing raw data by sensors, the context collector collects the data and delivers the information to the context database. 6LoWPAN is a technology for transferring sensed data to smart devices. This technology connects wireless clinical devices like glucometer to the smart environments or gateways. We proposed 6LoWPAN technology for sending data from the sensors to the context collectors and then by using SQL statements, context collector inserts data into the context database. Context Database This database consists of one table, namely the context table by which physiological parameters are the defined fields (Table 1). The parameter field is designed to evaluate a patients important physiological factors such as blood glucose, blood pressure, and heart rate levels. The date and time fields reveal patient check-up timings. For diabetic patients monitoring and managing blood glucose is an essential task as blood glucose levels should remain within normal ranges. There are two types of blood glucose measures that are very important in a diabetic treatment; FBS1 and the THG2 level check-up. In this case we have proposed four specific times in order to measure these parameters. It begins early morning at 8 A.M. for an initial measuring FBS, 10 A.M. for measuring the 2 hours glucose level after breakfast meal, 3 P.M. for evaluating the 2 hours glucose level after lunch time, and 10 P.M. for evaluating the 2 hours glucose level after dinner. In addition the patient’s blood pressure and heart rate levels will be checked simultaneously. After monitoring all the parameters via wireless sensors, the sensed data will be stored in a context table, by which the inference engine can use them for inferring suitable outcomes. Inference Engine The inference engine determines two principal situations; high risk and emergency based upon specified rules and algorithms. The inputs of the inference engine are the context table data and, the outputs of this function in high risk condition, is a patient form that shows alarms and useful advices such as practical diet, activity and correct insulin dosage, and in emergency situation, is a nurse or physician form that presents an alarm and dangerous factors to the nurse or experts. In our proposed framework, the data interpretation is based on the specific rules and defaults. Moving forward, we will describe the basic definitions and default rules. 106 Diabetes Patients Monitoring by Cloud Computing Table 2. Glucose different ranges Glucose Level Very Low Low Normal High Very High
Purchase answer to see full attachment