IoT Based Patient Health
Monitoring
.
With
the vastly increasing human populations and medical expenditure, healthcare has
become one of most significant issues for both individuals and governments of
Bangladesh. Meanwhile, according to a report from the World Health Organization
(WHO), the problem of population aging is becoming more serious in Bangladesh.
Health conditions of aged people usually need to be checked more frequently,
which poses a greater challenge to existing medical systems. Therefore, how to
identify human diseases in a timely and accurate manner with low costs has been
paid an increasing attention .Due to the dominance in the diagnosis of
heart-related diseases, electrocardiogram (ECG) monitoring has been widely
applied in both hospitals and medical research .Traditionally, the ECG is
detected through large and stationary equipment in professional medical
institutions. The kind of equipment usually employs 12 lead using 10 electrodes
to collect ECG data due to their good performance in short-term measuring.
|
Lead |
Type |
Calculation |
|
I |
limb |
LA-RA |
|
II |
limb |
LL-RA |
|
III |
limb |
LL-LA |
|
aVR |
augmented |
RA-(LA+LL)/2 |
|
aVL |
augmented |
LA-(RA+LL)/2 |
|
aVF |
augmented |
LL-(RA+LA)/2 |
|
V1 |
precordial |
V1-(RA+LA+LL)/ |
|
V2 |
precordial |
V2-(RA+LA+LL)/3 |
|
V3 |
precordial |
V3-(RA+LA+LL)/3 |
|
V4 |
precordial |
V4-(RA+LA+LL)/3 |
|
V5 |
precordial |
V5-(RA+LA+LL)/3 |
|
V6 |
precordial |
V6-(RA+LA+LL)/3 |
However,
the equipment is unlikely to be portable, which means that patient’s activities
are severely limited during the period of data collection. Moreover, as these
devices are usually too expensive for home use, patients have to go to hospital
frequently, which will inevitably increase the burden of hospitals. Therefore, our
paper used for a long-term ECG signal detection with low costs is highly
desired. Thanks to the development of mobile Internet and wireless sensor
networks (WSNs), wearable ECG monitoring systems have emerged which are able to
detect ECG signals using a non-intrusive sensor and transmit the signal to the
smart phone through wireless transmission techniques, such as Wi-Fi. For the
sake of portability, electrodes of the WSN-based ECG monitoring systems are
usually less than traditional methods. At the expense of accuracy, it is
sufficient to collect the basic information of the heart. These portable
sensors are usually embedded into some wearable textiles, which have little
impact on the user’s daily activities. With the aid of these systems, long-term
ECG can be monitored in a cost-effective manner. However, to the best of our
knowledge, nearly all existing systems cannot work without a smart phone, which
is used as a receiver and processor of the ECG data. Due to limited power and
computational capabilities, the complex tasks of data transportation and
processing may have a great impact on the daily use of the smart phone.
Furthermore, in order to support all the OS platforms of smart terminals, great
efforts are required for the cross-platform development of the mobile
application. In this paper, a health care monitoring
system based on the Internet-of-Things (IoT) cloud is firstly proposed.
Based on this architecture, we design and implement a wearable ECG monitoring
system. The ECG data gathered from the human body will be transmitted directly
to the IoT cloud using Wi-Fi without the need of a mobile terminal. Compared
with Bluetooth or ZigBee, Wi-Fi can provide higher data rates and wider
coverage areas. In order to provide convenient and timely access to ECG data
for users, both the HTTP and MQTT servers are deployed in the IoT cloud. The
gathered data are stored in a non-relational database, i.e., Redis, which can
greatly improve the speed and flexibility of data storage. A web-based
graphical user interface is implemented so that it provides ease of access for
doctors and patient’s alike using smart phones of different OS platforms to
access to the data services provided by the IoT cloud. The proposed system has
been successfully deployed and fully tested with demonstrated effectiveness and
reliability in ECG monitoring. The reminder of this paper is organized as follows.
Section “Architecture of IoT Based Health Care Monitoring System” presents the
architecture of the IoT Based Health Care Monitoring System. The system
implementation is introduced in Section “Implementation of the IoT Based Health
Care Monitoring System”, which includes a monitoring node, the IoT cloud and a
graphic user interface (GUI). In Section “Experimental Results and Analysis”,
we conduct several tests on a healthy volunteer in order to verify the
reliability of the proposed system. Finally, Section “Conclusion” concludes
this paper.[7]
1.1 IoT Cloud
Thanks
to the development of the advanced IoT techniques, ECG data can be stored and analyzed
effectively and efficiently. With the aid of an IoT cloud,
computation-intensive data process and analysis tasks can be carried out in
powerful servers, which greatly eases the burden of smart devices. Generally
speaking, an IoT cloud for Heart Beat monitoring and ECG monitoring usually
consists of four functional modules, i.e., data cleaning, data storage, data
analysis, and disease warning.
v Data
cleaning: Significant features can be extracted from Heart Beat and ECG signals
so as to detect potential heart diseases. However, during the processes of data
collection and transmission, noise may be introduced into the Heart Beat and
ECG signals, which would adversely affect the diagnosis accuracy. Therefore,
the signals are need to be cleaned at first. Commonly, a properly designed
filter is employed to remove the noise outside the band of the ECG signal.
Furthermore, the procedure of data auditing is usually employed to detect data
anomalies and contradictions;
v Data
storage: Heart Beat and ECG data plays a vital role in the diagnosis of heart
diseases. Thus, historical data are needed to be stored in the database for
further analysis. This data often include the time and digitized signal
amplitude. In addition, at least one copy of the data needs to be stored for
disaster recovery;
v Data
analysis: Making the full use of data is one of the most important functions of
the IoT cloud. Therefore, the IoT cloud often provides a data analysis platform
to extract useful information from the Heart Beat and ECG signals. Specific
data mining or machine learning approaches can be applied to these data. For
example, after extracting the significant features of the Heart Beat and ECG
signals, a support vector machine can be established to diagnose certain heart
diseases; and
v Disease
alert: Sudden heart attacks seriously threaten the lives of cardiac patients,
especially when patients are alone. Therefore, disease warning on the IoT cloud
has become important for protecting patients from being injured. Based on the
results of data analysis, the IoT cloud is able to understand the real-time
health conditions of the patient. In the event of any suspicious readings, the
IoT cloud will notify the family of the patient and the doctor in time.[5]
1.3 ECG (Electrocardiograph)
ECG
or Electrocardiography is a system which can record and measure the electrical
activity of the heart over a period of time using electrodes on the skin. Bio
monitoring electrodes have passed through a great evolution and progress from
19th century. In 1883, Carlo Matteucci who was a professor of physics at the
University of Pisa, first time showed and proposed sensors that watch and
monitor the electricity in human body periodically. In 1887, Augustus D.Waller
was presented and published the first human electrocardiogram. He was British
physiologist. In 1901, Willem Einthoven made re infrastructure of Waller’s
technology. Here, he used fine quartz coated with silver in a device which is
called the string galvanometer. Einthoven won noble prize for formulate and
create the electrocardiograph. In present time, bio monitoring electrodes use
in ECG which is made of a plastic substrate covered with a silver chloride
ionic compound. The Ag/Acl electrode is mostly used for all the application in
bio medical electrode system. These electrodes create an electrical potential
and ionic activity in living cells. After connecting the human body, these
potentials are demonstrate on the body surface.[1, 3]
The
heart starts activation at sinoatrial node which is build and produces heart
frequency about 70 cycles per minute. This activation generated to the right
and left muscle tissues. There is delay which use to allow the ventricles to
fill with blood from atrial contraction in the ventricular node.
These
activities help to pump blood to the aorta and to the rest of the body. At
last, the re polarization happen and the cycle is repeated time after time.
When the cycle take place, the trans membrane potential which measure the
voltage difference between the internal and external spaces of the cell
membrane create a changes at the each stages. Voltages differences are measured
by using the surface electrodes. These different peaks P, Q, R, S, T and U are
detect in these stages. in Figure 2.3 it’s shown. [20]
v P wave
In
the normal heart, each beat begins with the discharge (depolarization) of the
sinoatrial (SA) node, high up in the right atrium. This spontaneous event
usually occurs 60-100 times per minute. The first distinguishable wave is
visible when the impulse spreads from the SA node to depolarize the atria. This
is how the P wave is produced. The duration of P wave is 0.06s to 0.12s.
v PR Interval
The
time it takes for the depolarization wave to pass from its origin in the SA
node, across the atria, and through the AV node into ventricular muscle is
called the PR interval. This is measured from the starting point of the P wave
to the starting point of the R wave. The duration of the PR interval ranges
between 0.12s to 0.20s.
v QRS Complex
The
QRS complex signifies the expeditious depolarization of the right and left
ventricles. As the ventricles have a large muscle mass than the atria, the QRS
complex commonly has a much higher amplitude than the P-wave. The duration of
the whole QRS complex is 0.06s to 0.10s.
v ST segment
ST
segment represents the period when the ventricles are depolarized. No more
electrical current can be passed through the myocardium in this transient
period. It starts from the end of the S wave to the starting point of the T
wave. ST segment ranges between 0.08s to 0.12s.
v T wave
Repolarization
(recharging) of the ventricular myocardium to its resting electrical state is
called T wave. The duration of a T wave is 0.01s to 0.25s.
v QT Interval
The
time required for the ventricles to activate and readjust to the normal resting
state is called the QT interval. It is measured from the starting point of the
QRS complex to the end of the T wave. The duration of a QT interval is 0.36s to
0.44s.
v U wave
Although
the origin of the U wave is unresolved, it may represent repolarization of the
interventricular septum or slow repolarization of the ventricles.
1.5 Detection of heart
abnormalities
Any
changes in ECG parameters from their normal values reflect cardiac disorders.
For example, any elongation in PQ segment and QT interval indicate heart block
and congenital disorders. After the extraction of ECG parameters, this system
compares the values with the predefined normal values and indicates
corresponding diseases (if any) from the current ECG. Table 2 shows the normal
values of ECG and Table 3 shows the abnormal ECG values with associate
diseases. Primarily, heart diseases that the proposed system can detect are
enlisted below with the detection technique and the enlisted diseases waveform.[18]
1)
Tachycardia: Resting heart rate exceeds more than 100 bpm. But the upper limit
is 150 bpm. From R-R interval the heart rate (HR) can be calculated to detect
tachycardia.
2)
Bradycardia: HR falls less than 60 bpm and can be detected as mentioned above.
3)
Hypercalcemia: QTc interval time is less than 0.32 sec
4)
Hypocalcemia: QTc interval time is greater than 0.44 sec
5)
Atrioventricular, block: PR interval is greater than 0.20 sec
|
Threshold
values |
|
|
ECG
parameter |
Amplitude(mV) |
|
P-wave |
0.25 |
|
R-wave |
0.8-0.12 |
|
Q-wave |
25%
of R wave |
|
T-wave |
0.1-0.5 |
|
Normal ECG parameters | |