IOT-BASED PORTABLE ECG MONITORING SYSTEM FOR SMART

HEALTHCARE
Pranay Niokse1,Mukul Somkuwar2,Faizan Shaikh3, , 5, 6
12345
UG Student, 6Professor
Department Of Electrical Engineering
Anjuman College of Engineering & Technology, Nagpur, Maharashtra, India

ABSTRACT
Sudden and unexpected death due to heart failure is a major cause of mortality among middle aged and elderly
people. An efficient heart monitoring system can find out the malformation of heart conditions and that can also be
helpful in diagnose at critical ambience. Sometimes the distance between patients and doctors is the main barrier
that people do not have access to quality health services and thus having trouble for their regular health examine.
IoT-based healthcare monitoring system is one of the manifested application areas in medical science. As a
significant access in diagnose heart disease ECG observing system is widely used. In this paper, a progressive
method for ECG monitoring system based on Internet of Things (IoT) has been proposed. In this study, a system is
designed to frequently monitor the Electrocardiogram (ECG) signal collected from patient’s body using wearable
sensors and the data is stored into the database which can be accessed by authorized personnel only. When any
malformation is found an automatic email is sent to the users and doctors for analyzing about the critical conditions
of the patients and provides emergency health assistances. In order to verify the authenticity of this system tests have
been implemented on several patients and the report shows that, this system is dependable and efficient for
collecting real time ECG data which can be very helpful in diagnose heart diseases. This IoT-based low cost device
can be reliably used to reduce the risk of disability and mortality rate due to cardiovascular diseases..
Index Terms:-ECG, Heart Bat, IoT, , ECG telemonitoring, healthcare, Internet of Things (IoT), telehealth care,
wearable monitoring system, wearable sensors
1. INTRODUCTION
The Internet of Things (IoT) has many purposes in medical areas such as distant patient monitoring, dietary
program, testimony of chronic diseases, elderly people care etc. The elderly population is rising continually both in
rural and urban areas, so observing their health regularly with the desire of staying at home and at low cost is one of
the basic appeal. Healthcare personnel can assess, diagnose and prescribe elderly people by gathering medical
information from remote regions by using IoT. The significant part of IoT can be used in so many medical
equipment, sensors and imaging devices to primarily determine the patient’s health statuses and to deliver them
proper care in a shortest possible time. IoT-based healthcare services can be implemented at low cost hereby
maximizing the user contentment. Thus, the main purpose of IoT-based healthcare system is its cost effectiveness
and secures interconnection for individuals, clinics and different healthcare institutions. Health conditions of aged
people needed to be checked in regular basis which is a greater challenge both in medical research and hospitals
[1].In medical institutes or hospitals, conventional 12 leads systems are used to collect ECG signals from patient’s
body. This device is too expensive to use at home or personal use and cannot be used as portable. It takes huge
amount of time for routine checkup during each visit to hospitals and manual recording can also cause human made
error. In such a manner, a low cost portable system for continuous ECG monitoring is highly required. Most of the
available ECG monitoring devices use smart phones for secondary data processing [2]. The uses of smart phones in
data transfer and processing have great consequences on regular use due to its limitations of power and
computational effectiveness. In our study, a wearable ECG monitoring system has been proposed and implemented
occupying Internet of Things (IoT). This customized device can directly sent ECG data collected from patient’s
body to IoT cloud using Wi-Fi. Wi-Fi has wider coverage areas and higher data transfer rate than Bluetooth or
ZigBee. The whole work is done by connecting Raspberry Pi with internet. Here, ECG sensor AD8232 has been
used for ECG monitoring. Data have been processed in Raspberry Pi which uses processing software and a band
pass filter is used for eliminating different noises to form an electrocardiogram (ECG) graph. An automatic email
will be sent to the users and authorized doctors in case of abnormalities found in patient’s body. This device is
hazard free and cost effective for the remote patients as they do not need to visit the doctors regularly. We have
compared our customized device with standard 12 lead ECG modular in generating heart rates and waveforms and
the result shows that, our system can be used reliably. The rest of the paper is organized in following sections. In
section II, background and related works is discussed. In section III, system architecture of IoT based ECG
monitoring system has been proposed and being explained. In section IV, shows the flowchart and implementation
of IoT based ECG monitoring system. We conduct several tests on patients in order to verify the reliability of the
system and it is discussed as experimental results and analysis in section finally we conclude the paper in section VI
and also discussed about the future scopes in the field of medical science using Internet of Things (IoT).
2. LITERATURE SURVEY
Jun Liu;YaqiZhou concluded Using the ECG analog front-end and ARM Cortex-M3 processor to develop a portable
ECG monitor. The STM32 as the core unit, the ADS1292 as the acquisition analog front-end, it also includes a
touch screen display module, an SD card storage module and a voltage conversion module. Automatic ECG analysis
algorithms including QRS complex detection, QRS width detection and ST segment detection. ECG can be divided
into four kinds of heart beat and eight kinds of arrhythmia rhythm using the extracted ECG parameters. The results
have been evaluated on the MIT-BIH Arrhythmia Database, the sensitivity of QRS complex detection was 99% and
the sensitivity of heart beat classification was above 95%. The monitor can display the real-time ECG waveform and
the current heart rate, to make recommendations for the subjects, and it stored the abnormal ECG waveform that
provided to physicians for further analysis and diagnosis. Ultimately the monitor gives a composite score based on
heart rate, arrhythmia and ST segment to facilitate subjects for heart health.
AbhinayVishwanatham;NarendraCh. stated Cardiovascular diseases are the major cause of mortality rate in India
with more than 50 % of the patients coming from a rural background. IoT plays a crucial role in developing point of
care devices which cater to the healthcare demands of the rising rural populace. ECG monitoring system plays a key
role as a diagnostic tool for cardiac abnormalities. Thus it becomes important to develop a portable point of care
(POC) device at an affordable price so as to monitor the patients' cardiac health without interfering in their daily
schedule. We developed an end to end health care workflow comprising three important modules. Firstly, a
Bluetooth Low Energy (BLE) enabled portable 5-lead ECG monitor system with small form factor. Next, a smart
phone based android application, which receives, plots and analyzes the data sent from ECG device. Finally, a
remote server where the patient data and analysis reports are stored for future reference of a professional medical
practitioner. The device was tested using real time data from a rural hospital and further the obtained ECG
signatures were compared with standard GE and SIEMENS ECG machines. The results were validated by a
cardiologist of a super specialty hospital.
JakobJustesen;Soren Christian Madsen describd Recent miniaturization of ECG sensors and other health monitoring
systems potentially allowing remote monitoring of certain diseases in the patients own home. Exploiting the full
potential of this technology poses several design challenges for both the miniaturized ECG sensor, as well as the
required infrastructure for data transport, storage and diagnosis. This paper proposes an ECG sensor prototype
allowing experimentation on sensor technology and signal processing as well as infrastructure. The prototype is
based on the Blackfin processor from Analog Devices, and uses Bluetooth for wireless communication.
JihongChai stated that
With the increasing requirements of mobile ECG monitoring, a convenient mobile ECG monitoring system solution
is proposed in this paper. The monitoring terminal is designed by using MSP430 to achieve ECG signal acquisition,
amplification and A/D conversion. CC2540 integrating low-power Bluetooth 4.0 BLE-Stack is also used. System
has the function of mobile ECG data transmission from the monitoring terminal to the smart phone. This design can
use in home healthcare, community healthcare due to the characteristics of low power consumption, small size and
reliability.AmitWalinjkar; John Woods Continuous monitoring of an individual's health using wearable biomedical
devices is becoming a norm these days with a large number of wearable kits becoming easily available. Modern
wearable health monitoring devices have become easily available in the consumer market, however, real-time
analyses and prediction along with alerts and alarms about a health hazard are not adequately addressed in such
devices. Taking ECG monitoring as a case study the research paper focusses on signal processing, arrhythmia
detection and classification and at the same time focusses on updating the electronic health records database in
realtime such that the concerned medical practitioners become aware of an emergent situation the patient being
monitored might face. Also, heart rate variability (HRV) analysis is usually considered as a basis for arrhythmia
classification which largely depends on the morphology of the ECG waveforms and the sensitivity of the
biopotentialmeasurements of the ECG kits, so it may not yield accurate results. Initially, the ECG readings from the
3-Lead ECG analog front-end were de-noised, zero-offset corrected, filtered using recursive least square adaptive
filter and smoothed using Savitzky-Golay filter and subsequently passed to the data analysis component with a
unique feature extraction method to increase the accuracy of classification. The machine learning models trained on
MITDB arrhythmia database (MIT-BIH Physionet) showed more than 97% accuracy using kNN classifiers.
Neuralnet fitting models showed mean-squared error of as low as 0.0085 and regression value as high as 0.99. ECG
abnormalities based on annotations in MITDB could be classified and these ECG observations could be logged to a
server implementation based on FHIR standards. The instruments were networked using IoT (Internet of Things)
devices and ECG event observations were coded according to SNOMED coding system and could be accessed in
Electronic Health Record by the concerned medic to take appropriate and timely decisions. The system emphasizes
on `preventive care rather than remedial cure' as the next generation personalized health-care monitoring devices
become available.t.

3.METHODOLOGY

The proposed system on the architecture we design an ECG based heart rate monitoring system .The collected ECG
data will be directly sent to the database server using Wi-Fi module. Wi-Fi has been used here because it can
provide larger cover areas and higher data rates. Wi-Fi is used here that it can send email to the doctors or relatives
in case of patient’s emergency health conditions.

Figure 1 proposed block diagramt of the system

The architecture of the IoT-based ECG monitoring system is illustrated in “Fig.1”, which mainly consists of three
parts, i.e., the ECG sensing network, IoT cloud, and GUI. The components used in ECG Sensing network are: ECG
AD8232 Sensor, Raspberry Pi Model ECG Sensing Network: ECG sensing network is set for assembling
physiological data from the body surface and pass on these data to IoT cloud through a wireless channel. In our
equipment wearable ECG sensor has used to gather data from patients body over long hours. Then the ECG signals
are processed through amplification and filtering etc. to improve the signal quality. The ECG data gathered from
sensors are transmitted to the IoT cloud via a specific wireless protocol such as Bluetooth, Wi-Fi, ZigBee etc. [7].
With satisfying energy consumption all these three protocols can transfer enough data rates for transmitting ECG
signals. Moreover, due to limited communication ranges of Bluetooth and ZigBee, Wi-Fi is used in our proposed
system .Comparisons among various types of ECG sensing networksIoT Cloud: With the help of IoT cloud in ECG
monitoring system we can store data, modify data and all the patients information’s are saved here. It can also send
disease warning and protecting patients from getting injured. C. GUI: Graphical User Interface (GUI) is used for
data imagination management. It contributes easy entry of the data in the IoT cloud. Users can log onto the cloud to
acquire visualized ECG data in real time. Generally mobile applications and web pages are the two kinds of GUI’s
are available for users to visualize ECG data. Although mobile app can ensure immediate response but web pages
are the best options in terms of protection and up-gradation
4.IMPLEMENTATION
A 3-lead placement is adequate to analysis the primary features of ECG signal [9] compared to conventional 12-
lead ECG monitoring device used in hospitals. In order to best sample the ECG signal, the electrodes need to be
placed around the heart and form a triangle.
Abnormalities are found when the two conditions are not valid. Finally, if any disorders are found then an
emergency email has been sent to the users or doctors that, they can take emergency steps to prevent severe damage
of the patients. This can reduce mortality rate and any kind of damages that causes due to heart failure. To get the
most proper data for sudden analysis of patient’s condition 3 lead electrodes are placed in a triangular shape around
the heart. “Fig.2”, shows, the ECG data collected from healthy person. It is evident that the
 Figure 2. a triangular shape around the heart.

We have developed a prototype system and tested our device with a 12-lead ECG machine and the experimental
result shows the reliability of our system Percent Difference in “Equation (1)” is used to determine the relative
difference between 12 lead and 3 lead portable ECG system.
% difference = | 𝐸𝑥𝑝𝑒𝑐𝑡𝑒𝑑−𝐴𝑐𝑡𝑢𝑎𝑙𝐸𝑥𝑝𝑒𝑐𝑡𝑒𝑑+𝐴𝑐𝑡𝑢𝑎𝑙 2 | *100%

Where, Expected = ECG value gained from 12-lead ECG machine and Actual = ECG value gained from ECG
device prototype we can observe that, the value of our prototype is quite similar with expected value collected from
12-lead ECG device. To determine the efficiency rate of our device "Equation 2" is used to test the number of
successful attempts vs. the total number of attempts.
% reliability = | 𝑛𝑢𝑚𝑏𝑒𝑟𝑜𝑓𝑠𝑢𝑐𝑐𝑒𝑠𝑠𝑓𝑢𝑙𝑎𝑡𝑡𝑒𝑚𝑝𝑡𝑠𝑡𝑜𝑡𝑎𝑙𝑛𝑢𝑚𝑏𝑒𝑟𝑜𝑓𝑎𝑡𝑡𝑒𝑚𝑝𝑡𝑠 | *100%

Figure 3. Hardware output

5. CONCLUSION
The implemented prototype of our IoT-based ECG monitoring system is highly efficient, low cost device and it
reduces the time and cost for regularly visiting the doctors at healthcare institutions. We have collected data from
different ages’ patients by using three electrodes placements in their body and achieved 80% accuracy in our system.
The data collected from our device has been directly sent to IoT cloud using Wi-Fi. The IoT cloud has been used for
visualizing the data to users and store it for future analysis. By using the system ECG signal can be monitored
continuously. The regular use of device is very helpful for preliminary detection of heart diseases and to reduce
severe damage and mortality rate due to cardiovascular diseases. Similar to this user-friendly ECG monitoring
System, additional health monitoring systems such as temperature measurement, Blood Pressure, Diabetes, etc., can
be developed using IoT that will greatly help decrease existing health care problems to a certain amount. The
proposed system is successfully developed and tested to examine the effectiveness and reliability of the system. This
is a low cost smart device which can be used for patient’s health monitoring so that doctors can take precautions at
proper time to avoid sudden death due to cardiovascular diseases.

References:

[1] Abadi, M., Subramanian, R., Kia, S., and et al., DECAF: MEG-based multimodal database for decoding
affective physiological responses. IEEE Trans. Affect. Comput. 6:209–222, 2015.
[2] Miao, F., Cheng, Y., He, Y., and et al., A wearable contextaware ECG monitoring system integrated with built-in
kinematic sensorsof the smartphone.Sensors 15:11465–11484, 2015.
[3] E. Span, S. Di Pascoli and G. Iannaccone, “Low-Power Wearable ECG Monitoring System for Multiple- Patient
RemoteMonitoring’’ in IEEE Sensors Journal, July 1, 2016.
[4] S. Sneha and U. Varshney, "A Wireless ECG Monitoring System for Pervasive Healthcare," in International
Journal of Electronic Healthcare, 3(1), 32-50, 2007.
[5] Kim H, Kim S, Van Helleputte N et al. (2014) A configurable and low power mixed signal SoC for portable
ECG monitoring applications. IEEE Transactions on Biomedical Circuits and Systems 8:257-267.
[6] J. Dong and H. Zhu, "Mobile ECG detector through GPRS/Internet," presented at Computer-Based Medical
Systems, 2004. CBMS 2004.Proceedings.17th IEEE Symposium on, 2004.
[7] Palattella, M., Dohler, M., Grieco, A., and et al., Internet of Thingsthe 5G era: Enablers, architecture, and
business models. IEEE J. Select. Areas Commun. 34:510–527, 2016.
[8] Wang Y et al. Design and evaluation of a novel wireless reconstructed 3-lead ECG monitoring system. In: Proc.
IEEE 2013 Biomedical Circuits and Systems Conference (BioCAS), Rotterdam, Oct. 2013, pp. 362-365.
[9] ECGlibrary.com: Normal adult 12-lead ECG. In: Ecglibrary.com, http://www.ecglibrary.com/norm.php.
Accessed 18, Sept. 2016.
[10] Gertsch M The Normal ECG and its (Normal) variants. In: The ECG manual. Springer, London, pp. 17-
36,2009.