Iot Based Glucose Monitoring System

By Author: Copperpod Intellectual Property
Total Articles: 2
Comment this article

IoT devices are using Artificial Intelligence (AI) and Machine Learning (ML) to bring intelligence and autonomy to systems and processes, such as autonomous driving, industrial smart manufacturing, medical equipment, and home automation.

Leading IoT companies offer devices and applications that track and manage medical equipment, staff, and patients within all types of medical environments. IoT applications typically have location sensors that are attached to various assets of the medical facility from the patient, to a staff member or a piece of medical equipment. Each asset is given a unique ID and the system tracks these tags. Such healthcare applications enable tracking in hospital units, rooms, beds, and even shelf-level tracking for true workflow automation. Internet of Things (IoT)-enabled devices have unleashed the potential to keep patients safe and healthy, and empower physicians to deliver superlative care.

4-Step Process for IoT based Healthcare System
Step 1: The first step consists of the deployment of interconnected devices including sensors, actuators, monitors, detectors, camera systems, ...
... etc. These devices collect the data.
Step 2: Usually, data received from sensors and other devices are in analog form, which needs to be aggregated and converted to the digital form for further data processing.
Step 3: Once the data is digitized and aggregated, this is pre-processed, standardized and moved to the data center or cloud.
Step 4: Final data is managed and analyzed at the required level. Advanced Analytics, applied to this data, brings actionable business insights for effective decision-making.

The usage of IoT tracking in medical surroundings is also referred to as “indoor GPS”. IoT majorly uses the technology of RFID tags (Radio-Frequency Identification) to track and monitor healthcare assets.
In this article, we will discuss the feasibility of invasive and continuous glucose monitoring (CGM) systems utilizing IoT based approaches. The CGM system is an IoT-based system design from a sensor device to a back-end system for presenting real-time glucose, body temperature and contextual data in human-readable forms to end-users such as patients and doctors. In addition, nRF communication protocol is customized for suiting the glucose monitoring system and achieving a high level of energy efficiency. Finally, the work provides many advanced services at a gateway level such as a push notification service for notifying patients and doctors in case of abnormal situations.

6 Types of Continuous Glucose Monitoring System

The CGM system is located near the critical cardiac patients in the intensive care unit. The system is built by a disposable subcutaneous glucose sensor, a glucose client, and a server. The system collects glucose data 4 times per day and stores it in a hospital information system. Doctors can use the bedside monitor to track the glucose data.
Bluetooth low energy (BLE) implantable glucose monitoring system - Glucose data collected from the system is transmitted through BLE to a PDA (smart-phone or iPad) which represents the received data in text forms for visualization. The system shows some achievements in reducing power consumption of an external power unit and an implantable unit.
Glucose monitoring in individuals with diabetes using long-term implanted sensor systems and models. Glucose data is sent every two minutes to external receivers. In addition, the system proves that implanted sensors can be placed inside a human body for a long period of time (180 days) for managing diabetes and other diseases.

A non-invasive blood glucose monitoring system using near-infrared (NIR) - Glucose in the blood is predicted based on the analysis of the variation in the received signal intensity obtained from a NIR sensor. The predicted glucose data is sent wirelessly to a remote computer for visualization.

A blood glucose level monitoring system based on wireless body area networks for detecting diabetes. The system is built by using a glucometer sensor, Arduino Uno, and a Zigbee module. Doctors and caregivers can access a web-page to monitor the glucose levels of a patient remotely.

A monitoring system for type 2 diabetes mellitus - The system is able to make decisions on the status of diabetes control and predict future glucose levels of an individual. Obtained glucose data can be monitored remotely by medical staff through wide area networks.

How does Continuous Glucose Monitoring (CGM) System Work?

1. Sensor Device Structure
The sensor device structure consists of primary component blocks such as sensors, a microcontroller, a wireless communication block, energy harvesting and management components. The micro-controller performs primary tasks of the device such as data acquisition and transmission, therefore consuming a large part of the device’s total power consumption. In the device, the micro-controller receives glucose data from an implantable glucose sensor via a wireless inductive link receiver while it collects environmental and body temperature via data link wires such as UART, SPI or I2C. The nRF wireless communication block is responsible for transmitting data from the microcontroller to the gateway equipped with an nRF transceiver. The block includes a RF transceiver IC for the 2.4GHz ISM band and an embedded antenna. Due to 2Mbps support, nRF completely fulfills the requirements of transmission data rates in a CGM system. Transmission data rates of nRF can be configured for achieving some levels of energy efficiency.

To evaluate the feasibility of the CGM system using IoT, the entire system is executed. Initially, the interaction of the biological tissue under investigation is studied. Since the glucose sensor will be subcutaneous, the electrical characteristics of the biological tissue i.e. skin will be evaluated from which the amount of power loss and absorption due to propagation through the biological tissue will be estimated. It is imperative to make sure that subjecting the human body to these continuous signals is within the safe specified measures. The guidelines for Electromagnetic Field Exposure (EMF) is in terms of Specific Absorption Rate (SAR) and the equivalent plane wave power density (SW/m2). SAR is a measure of the rate of energy absorption per unit mass due to exposure to an RF source. SAR is defined as:

SAR = (effErms2)/(W/Kg)

Where eff is the effective conductivity of the biological material such as skin and is proportional to the frequency of the applied field, is the mass density which is approximately 1000 kg/m3 for most biological tissues, and Erms is the root-mean-square value of the electric field E at the measurement point. As specified in the operating frequency of 2.4 GHz, the maximum E and S are 61 V/m and 10 W/m2 respectively which are well below the targeted operation power of the wireless sensor node.

2. Energy Harvesting Unit
Energy harvesting refers to harnessing energy from the environment or other energy sources (body heat, foot strike, finger strokes) and converting it to electrical energy. If the harvested energy source is large and periodically or continuously available, a sensor node can be powered perpetually. Energy sources can be broadly classified into the following two categories:

(i) Ambient Energy Sources: Sources of energy from the surrounding environment, e.g., solar energy, wind energy and RF energy, and
(ii) Human Power: Energy harvested from body movements of humans. Passive human power sources are those which are not user controllable like blood pressure, body heat and breath.

Active human power sources are those that are under user control, and the user exerts a specific force to generate the energy for harvesting, e.g., finger motion, paddling and walking. To power the glucose sensor node a combination of ambient and human powered sources is selected. Due to its present availability, RF energy is an adequate source for this application. Also, since the sensor is mounted on the human body it makes sense to exploit this medium as a source of energy. Through the use of a Thermoelectric Generator (TEG), thermal energy can be converted into electrical energy.

3. Gateway and Back-End Structure
The gateway collects data from wireless sensor devices and transmits the data to Cloud servers. The gateway performs its tasks by using an nRF transceiver and a wireless IP-based transceiver (i.e. Wifi, GPRS or 3G). The nRF transceiver, which is a plug-able component, is compatible with all types of smart devices (i.e. Android, iPhone, tablet). The nRF transceiver consists of a micro-controller and a low power RF transceiver IC, and an FTDI component. The micro-controller and the nRF components are the same as the ones used in the sensor device. The FTDI chip is used for converting from a UART connection to a USB connection. In addition to mentioned tasks, the gateway provides advanced services such as data processing, local database, local host with user interface and push notification. Due to a small amount of collected data (4-8 samples per 10 minutes), local databases can store the data for a long period of time. By supplying a local host with a user interface, real-time data can be monitored directly from the gateway without requiring Cloud servers. This helps to eliminate an unnecessary latency of transmitting and receiving data to and from the Cloud, respectively. In the gateway, decision making and push notification services work together to provide real-time notifications to doctors or caregivers. For example, when a monitored glucose level is higher and lower than an acceptable level, the decision-making service triggers the push notification to send messages for notifying a doctor in real-time. The back-end part comprises Cloud and a user access terminal. Doctors can access real-time data in the Cloud remotely via a web browser or a mobile application.

An Android app is built in the gateway for receiving data from the nRF component and performing other services. When data is available at one end of the USB port, the app automatically reads the data and performs the data processing service. In addition, the app is capable of representing the processed data in text and graphical forms and triggering a push notification service.

The push notification service is implemented by a push notification API. When the mobile app detects abnormal situations (i.e., too low or too high glucose level), the push notification service in the gateway is triggered for sending notification messages to Cloud which then notifies doctors and an end-user wearing the sensor device.

Future Insights
There is no doubt that the future of IoT in healthcare is bright and it has a lot of caliber to revolutionize healthcare services. From leading hospitals to small clinics, all are availing the benefits of IoT in healthcare. The future of IoT in healthcare with being a game-changer and the new IoT innovations will mobilize business patterns and automate the data monitoring process.

The future of CGM depends not only on advances in hardware technology but also on the way the stream of data is processed algorithmically. This will ultimately result in increased accuracy, biocompatibility, and wearability, consequently leading to improved user compliance, health, and quality of life.

There are still no officially accepted guidelines as to how to apply diabetes management decisions using CGM trend information and thus leading to a lot of challenges. IoT-enabled connected devices capture huge amounts of data, including sensitive information, giving rise to concerns about data security, so the implementation of apt security measures becomes crucial. IoT explores new dimensions of patient care through real-time health monitoring and access to patients’ health data. This data is a goldmine for healthcare stakeholders to improve patient’s health and experiences while making revenue opportunities and improving healthcare operations. Being prepared to harness this digital power would prove to be the classist in the increasingly connected globalized world.