IoT-Based Applications in Healthcare Devices

Abstract

The last decade has witnessed extensive research in the field of healthcare services and their technological upgradation. To be more specific, the Internet of Things (IoT) has shown potential application in connecting various medical devices, sensors, and healthcare professionals to provide quality medical services in a remote location. This has improved patient safety, reduced healthcare costs, enhanced the accessibility of healthcare services, and increased operational efficiency in the healthcare industry. The current study gives an up-to-date summary of the potential healthcare applications of IoT- (HIoT-) based technologies. Herein, the advancement of the application of the HIoT has been reported from the perspective of enabling technologies, healthcare services, and applications in solving various healthcare issues. Moreover, potential challenges and issues in the HIoT system are also discussed. In sum, the current study provides a comprehensive source of information regarding the different fields of application of HIoT intending to help future researchers, who have the interest to work and make advancements in the field to gain insight into the topic.

Full text

Review Article
IoT-Based Applications in Healthcare Devices
Bikash Pradhan ,
1
Saugat Bhattacharyya ,
2
and Kunal Pal
1
1
Department of Biotechnology and Medical Engineering, National Institute of Technology, Rourkela 769008, India
2
School of Computing,Engineering & Intelligent System, Ulster University, Londonderry, UK
Correspondence should be addressed to Kunal Pal; kpal.nitrkl@gmail.com
Received 25 December 2020; Revised 13 February 2021; Accepted 10 March 2021; Published 19 March 2021
Academic Editor: Mian Muhammand Sadiq Fareed
Copyright ©2021 Bikash Pradhan et al. is is an open access article distributed under the Creative Commons Attribution
License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is
properly cited.
e last decade has witnessed extensive research in the field of healthcare services and their technological upgradation. To be more
specific, the Internet of ings (IoT) has shown potential application in connecting various medical devices, sensors, and
healthcare professionals to provide quality medical services in a remote location. is has improved patient safety, reduced
healthcare costs, enhanced the accessibility of healthcare services, and increased operational efficiency in the healthcare industry.
e current study gives an up-to-date summary of the potential healthcare applications of IoT- (HIoT-) based technologies.
Herein, the advancement of the application of the HIoT has been reported from the perspective of enabling technologies,
healthcare services, and applications in solving various healthcare issues. Moreover, potential challenges and issues in the HIoT
system are also discussed. In sum, the current study provides a comprehensive source of information regarding the different fields
of application of HIoT intending to help future researchers, who have the interest to work and make advancements in the field to
gain insight into the topic.
1. Introduction
In recent years, the healthcare industry has shown rapid
growth and has been a major contributor to revenue and
employment [1]. A few years ago, the diagnosis of diseases
and abnormality in the human body was only being possible
after having a physical analysis in the hospital. Most of the
patients had to stay in the hospital throughout their treat-
ment period. is resulted in an increased healthcare cost
and also strained the healthcare facility at rural and remote
locations. e technological advancement that has been
achieved through these years has now allowed the diagnosis
of various diseases and health monitoring using miniatur-
ized devices like smartwatches. Moreover, technology has
transformed a hospital-centric healthcare system into a
patient-centric system [2, 3]. For example, several clinical
analyses (such as measuring blood pressure, blood glucose
level, pO
2,
level, and so on) can be performed at home
without the help of a healthcare professional. Further, the
clinical data can be communicated to healthcare centers
from remote areas with the help of advanced telecommu-
nication services. e use of such communication services in
conjunction with the rapidly growing technologies (e.g.,
machine learning, big data analysis, Internet of things (IoT),
wireless sensing, mobile computing, and cloud computing)
has improved the accessibility of the healthcare facilities.
IoT has not only enhanced the independence but also
diversified the ability of the human to interact with the
external environment. IoT, with help of futuristic protocol
and algorithms, became a major contributor to global
communication. It connects a large number of devices,
wireless sensors, home appliances, and electronic devices to
the Internet [4]. e application of IoT can be found in the
field of agriculture [5], automobiles [6, 7], home [8], and
healthcare [1, 9]. e growing popularity of the IoT is due to
its advantage of showing higher accuracy, lower cost, and its
ability to predict future events in a better way. Further,
increased knowledge of software and applications, with the
upgradation of mobile and computer technologies, easy
availability of wireless technology, and the increased digital
economy have added to the rapid IoT revolution [10]. e
IoT devices (sensors, actuators, and so on) have been in-
tegrated with other physical devices to monitor and ex-
change information using different communication
Hindawi
Journal of Healthcare Engineering
Volume 2021, Article ID 6632599, 18 pages
https://doi.org/10.1155/2021/6632599

protocols such as Bluetooth, Zigbee, IEEE 802.11 (Wi-Fi),
and so on. In healthcare applications, the sensors, either
embedded or wearable on the human body, are used to
collect physiological information such as temperature,
pressure rate, electrocardiograph (ECG), electroencephalo-
graph (EEG), and so on [11] from the patient’s body. Ad-
ditionally, environmental information such as temperature,
humidity, date, and time can also be recorded. ese data
help in making meaningful and precise inferences on the
health conditions of the patients. Data storage and acces-
sibility also play an important role in the IoT system as a
large amount of data are acquired/recorded from a variety of
sources (sensors, mobile phones, e-mail, software, and ap-
plications). e data from the aforesaid sensing devices are
made available to doctors, caregivers, and authorized parties.
e sharing of these data with the healthcare providers
through cloud/server allows quick diagnosis of the patients
and medical intervention if necessary. e cooperation
between the users, patients, and communication module is
maintained for effective and secure transmission. Most of
the IoT systems use a user interface that acts as a dashboard
for medical caregivers and performs user control, data vi-
sualization, and apprehension. An ample amount of research
has been discovered in the literature that has reported the
progress of the IoTsystem in healthcare monitoring, control,
security, and privacy [12]. ese accomplishments illustrate
the effectiveness and propitious future of IoT in the
healthcare sector. However, the main concern while de-
signing an IoT device is maintaining the quality of service
matrices that include privacy of information sharing, se-
curity, cost, reliability, and availability.
Intending to maximize the employability of IoT in
healthcare systems, many countries have adopted new
technology and policies. is transformed the current re-
search in the healthcare sector into a more beneficial field to
explore. e motivation of this paper is to summarize the
advancement of state-of-the-art studies in IoT-based
healthcare systems and to provide a systematic review of its
enabling technologies, services, and applications.
2. Architecture of Healthcare IoT (HIoT)
e framework of the IoT that is applied for healthcare
applications aids to integrate the advantages of IoT tech-
nology and cloud computing with the field of medicine. It
also lays out the protocols for the transmission of the pa-
tient’s data from numerous sensors and medical devices to a
given healthcare network. e topology of an HIoT is the
arrangement of different components of an IoT healthcare
system/network that are coherently connected in a health-
care environment. A basic HIoT system contains mainly
three components (Figure 1) such as publisher, broker, and
subscriber [14]. e publisher represents a network of
connected sensors and other medical devices that may work
individually or simultaneously to record the patient’s vital
information. is information may include blood pressure,
heart rate, temperature, oxygen saturation, ECG, EEG,
EMG, and so on [13]. e publisher can send this infor-
mation continuously through a network to a broker. e
broker is responsible for the processing and storage of the
acquired data in the cloud. Finally, the subscriber indulges in
the continuous monitoring of the patient’s information that
can be accessed and visualized through a smartphone,
computer, tablet, etc. Herein, the publisher can process these
data and give feedback after the observation of any physi-
ological anomaly or degradation in the patient’s health
condition. e HIoT assimilates discrete components into a
hybrid grid where a specific purpose is dedicated to each
component on the IoT network and cloud in the healthcare
network. Since the topology for an HIoT depends on the
healthcare demand and application, it is hard to suggest a
universal structure for HIoT. Numerous structural changes
have been adopted in the past for an HIoT system [15–17]. It
is crucial to list out all associated activities related to the
desired health application while designing a new IoT-based
healthcare system for real-time patient monitoring. e
success of the IoT system depends on how it is satisfying the
requirements of healthcare providers. Since each disease
needs a complex procedure of healthcare activities, the to-
pology must follow the medical rules and steps in the di-
agnosis procedure.
3. HIoT Technologies
e technologies that are used to develop an HIoT system is
crucial. is is because the use of specific technology can
enhance the ability of an IoT system [18]. Hence, to integrate
different healthcare applications with an IoT system, various
state-of-the-art technologies have been adopted. ese
technologies can broadly be categorized into three groups,
namely, identification technology, communication tech-
nology, and location technology (Figure 2).
3.1. Identification Technology. A practical consideration in
designing an HIoT system is the accessibility of the pa-
tient’s data from the authorized node (sensor), which may
be present at remote locations. is can be carried out
with effective identification of the nodes and sensors that
are present in the healthcare network. Identification
follows the process of assigning a unique identifier (UID)
to each authorized entity so that it can be easily identified
and unambiguous data exchange can be achieved. In
general, every resource associated with the healthcare
system (hospital, doctor, nurses, caregivers, medical de-
vices, and so on) is accompanied by a digital UID [19].
is ensures the identification of the resources as well as
the connection among the resources in a digital domain.
In the literature, numerous standards for identification
have been reported [20]. e Open Software Foundation
(OSF) has developed two different identifiers, namely, a
universally unique identifier (UUID) and a globally de-
veloped unique identifier (GUID). UUID, a part of Dis-
tributed Computing Environment (DCE), can be operated
without the requirement of centralized coordination [21].
In a healthcare network, the sensors and actuators are
identified and addressed separately which helps in the
proper functioning of the system. However, there may be a
2Journal of Healthcare Engineering

chance that the unique identification of a component may
change throughout the life cycle of the IoT system due to
the continuous upgradation of the IoT-based technolo-
gies. Hence, the device must have a provision to update
this information to maintain the integrity of the health-
care device/system. is can be reasoned to the fact that
the change in the configuration not only affects the
process of tracking the network component(s) but also
may result in a flawed diagnosis. Additionally, the ap-
plication of IoT in healthcare demands new technologies
that have the capability to (1) locate things based on a
global identification number, (2) safely manage the
identity of the components using different encryption and
authentication techniques, and (3) build a global directory
search for efficient discovery of IoT services under the
UUID scheme.
3.2. Communication Technology. Communication technol-
ogies ensure the connection among different entities in an
HIoT network. ese technologies can be broadly divided
into short-range and medium-range communication tech-
nology. e short-range communication technologies are
the protocols that are used to establish a connection among
the objects within a limited range or a body area network
(BAN), whereas the medium-range communication tech-
nologies usually support communication for a large dis-
tance, e.g., communication between a base station and the
central node of a BAN. e distance of communication may
vary from a few centimeters to several meters in the case of
short-range communication. In most of the HIoT applica-
tions, short-range communication technology is preferred.
Some of the most widely used communication techniques
include RFID, Wi-Fi, Zigbee, Bluetooth, etc.
Publisher
Wear a b l e
devices Medical
home
Sensors
Subscriber
Broker
Connection
Pharmaceutical
scientist
Medical
research
Insurance
provider
Hospital
staff
Patient’s
guardian
Figure 1: Architecture of an HIoT framework (reproduced from [13] under Creative Commons License).
HIoT technology
Identification
technology
Communication
technology
Location
technology
Figure 2: Classification of IoT technology.
Journal of Healthcare Engineering 3

Radio-Frequency Identification (RFID). RFID is used for
short-range communication (10 cm–200 m). It consists of a
tag and a reader. e tag is developed using a microchip and
antenna. It is used to uniquely identify an object/device
(healthcare equipment) in the IoT environment. e reader
transmits or receives information from the object by
communicating with a tag using radio waves. In the case of
IoT, the data used in the tag are in the form of an electronic
product code (EPC). RFID enables healthcare providers to
quickly locate and track healthcare equipment. e main
advantage of RFID is that it does not need an external power
source. However, it is a highly insecure protocol and may
show compatibility issues while connecting with a
smartphone.
Bluetooth. Bluetooth is also a short-distance wireless com-
munication technology that uses UHF (ultra-high fre-
quency) radio waves. is technology allows wireless
connection between two or more medical devices. e
frequency range of Bluetooth is 2.4 GHz. e Bluetooth
protocol presents a communication range of up to 100 m.
Bluetooth gives data protection in the form of authentication
and encryption. e advantage of Bluetooth lies in its low
cost and energy efficiency. It also ensures a lower inter-
ference among the connected devices during data trans-
mission. However, when the healthcare application
demands long-range communication, this technology fails
to meet the requirement.
Zigbee. Zigbee is one of the standard protocols that inter-
connects medical devices and transmits information back
and forth. e frequency range of Zigbee is similar to
Bluetooth (2.4 GHz). However, it possess a higher com-
munication range than that of Bluetooth devices. is
technology adopts a mesh network topology. It consists of
end nodes, routers, and a processing center. e processing
center is responsible for data analysis and aggregation. e
mesh network ensures uninterrupted connection among
other devices even when there is a fault in one or two devices.
e advantages of Zigbee lies in its low power consumption,
high transmission rate, and high network capacity.
Near-Field Communication (NFC). e basic concept of
NFC is the electromagnetic induction between the two-loop
antennas that are placed near to each other. is technology
is similar to RFID that also uses electromagnetic induction
for data transmission. e NFC devices can be operated in
two modes: active and passive. In the case of passive mode,
only one device generates the radiofrequency while the other
device acts as a receiver. In the case of active mode, both
devices can produce the radiofrequency simultaneously and
can transmit data without pairing [22]. e main advantages
of NFC are its easy operability and an efficient wireless
communication network. However, it is applicable for a very
short range of communication.
Wi-Fi. Wireless Fidelity (Wi-Fi) is a wireless local area
network (WLAN) that follows the IEEE 802.11 standard. It
provides a higher transmission range (within 70 ft.) as
compared to Bluetooth. Wi-Fi builds a network very quickly
and easily. Hence, it is mostly used in hospitals. e wide
application of Wi-Fi lies in its easy compatibility with
smartphones and its provision to support robust security
and control. However, it shows a relatively higher power
usage and the network performs inconsistently.
Satellite. Satellite communication is found to be more ef-
fective and beneficial in remote and widely separated geo-
graphical areas (such as rural areas, mountains, peaks,
oceans, and so on) where other modes of communication
cannot reach easily. e satellite receives signals from the
land, amplifies those signals, and then resends them to Earth.
More than 2000 satellites are orbiting around the Earth. e
advantage of satellite communication technology includes
high-speed data transfer, instant broadband access, stability,
and compatibility of the technology. However, the power
consumption associated with satellite communication is
very high as compared to other communication techniques.
3.3. Location Technology. e real-time location system
(RTLS) or location technologies are used to identify and
track the position of an object within the healthcare network.
It also tracks the treatment process based on the distribution
of available resources. One of the most widely used tech-
nologies is the Global Positioning System, which is com-
monly known as GPS. It makes use of satellites for tracking
purposes. An object can be detected through GPS as long as
there exists a clear line of sight between the object and four
different satellites. In HIoT, it can be employed to detect the
position of the ambulance, healthcare provider, caregivers,
patients, etc. However, the application of GPS is only limited
to outdoor applications as the surrounding infrastructures
can act as an obstruction to the communication between the
object and the satellite. In such cases, a local positioning
(LPS) network can be effectively used. LPS can track an
object by sensing the radio signal that is emitted from the
traveling object to an array of predeployed receivers [23].
Various short-distance communication technologies such as
RFID, Wi-Fi, Zigbee, and so on can also be used to employ
LPS. However, ultra-wideband (UWB) radio is preferred
due to its advantage of higher temporal resolution. is
enables the receiver to accurately measure the arrival time.
Young [24] and Zetik [25] have employed UWB-based
localization system that uses the time difference of arrival
(TDOA) for tracking. In the literature, other measuring
parameters have also been reported in designing a UWB-
based localization system such as relative and differential
time of arrrival [26], round trip time of flight [20], and so on.
GPS, along with the different high bandwidth communi-
cation technologies, may be explored in the future to develop
smart healthcare networks.
4. Services and Application of HIoT
e recent advancement in the IoT technology has enabled
the medical devices to make real-time analysis that was not
possible for doctors a few years ago. It has also supported the
4Journal of Healthcare Engineering

healthcare centers to reach more people at a time and deliver
excellent healthcare service at a minimal cost. e appli-
cation of big data and cloud computing has also made
communication between the patient and doctors more re-
liable and easier. is resulted in an enhanced patient’s
engagement in the treatment process with a reduced fi-
nancial burden on the patient. e considerable impact of
IoT, which has been witnessed in recent years, is contrib-
uting to the evolution of HIoT applications that includes
disease diagnosis, personal care for pediatric and elderly
patients, health and fitness management, and supervision of
chronic diseases. For a better grasp of these applications, it
has been divided into two basic categories, namely, services
and applications. e former includes the concepts that are
being used while developing an HIoT device and the latter
includes the healthcare applications in either diagnosis of a
specific health condition or measurements of health pa-
rameters. e following sections have included an detailed
description of the services and applications of HIoT.
4.1. Services. Services and concepts have transformed the
healthcare industry by providing solutions to various
healthcare problems. More services are added day-by-day
with a rise in healthcare demands and upgradation of
technology. ese are now becoming an integral part of
designing an HIoT system. Each service in an HIoT envi-
ronment provides a set of healthcare solutions. e defi-
nition of these concepts/services is not unique. e
uniqueness of the HIoT systems lies in their applications.
Hence, it is hard to outline a generalized definition of each
concept. However, to give an insight into the topic, some of
the most widely used IoT healthcare services (Figure 3) have
been described in the subsequent section.
4.1.1. Ambient Assisted Living. Ambient assisted living
(AAL) is a specialized branch of artificial intelligence that
integrates with IoTand is used for assisting aging people. e
main purpose of AAL is to help elderly people to live in-
dependently at home with convenience and safety. AAL
provides a technique for real-time monitoring of these
patients and making sure that they will receive human
service-like assistance in case of a medical emergency. is is
possible with the engagement of advanced AI technologies,
big data analysis, machine learning, and their application in
healthcare industries. In general, three basic domains of
AAL, namely, activity recognition, environment recogni-
tion, and vital monitoring, have been explored by the re-
searchers. However, activity recognition got the utmost
interest as it deals with detecting potential threats or
emergency health conditions that may affect the well-being
of elderly patients. e basic architecture of a smart
healthcare framework for AAL is represented in Figure 4.
Numerous studies have reported the application of IoT in
AAL [28–31]. Shahamabadi [32] proposed a framework that
dispenses healthcare solutions to elderly people. e author
designed a modular architecture for automation, security,
and communication for the AAL. During implementation,
IPv6-based low-power wireless personal area networks
(6LoWPAN) [33], RFID, and NFC were used as the com-
munication protocol. e device employs a closed-loop
communication service to connect the patient with the
healthcare providers. e aforesaid architecture was later
used as a basis for the development of the more advanced
protocol, which can be used to design advanced IoT-based
AAL systems (smart objects, devices, and kits). In a recent
study, Sandeepa developed an emergency detector for el-
derly people that assists in monitoring chronic conditions
and other potential health-related emergencies. Moreover,
the system alerted the caregivers in case of an emergency
[34]. IoT-based healthcare systems are now able to track
indoor air quality with help of assistive robots. ese systems
check the quality of air in the environment where the patient
resides [35, 36] and trigger alerts to the caregivers when
there is a reduction in the air quality below a standard value.
In [37], cloud computing has been integrated with IoT to
propose a secure, open, and flexible platform for AAL where
an IoT-based gateway was employed. e gateway helped in
addressing various issues that are associated with security,
data storage, and interoperability in the IoT system.
4.1.2. Mobile IoT. Mobile IoT or m-IoT depicts the asso-
ciation of mobile computing, sensors, communication
technologies, and cloud computing to track patient’s health
information and other physiological conditions (Figure 5).
In other words, it provides a communication interface be-
tween the personal area networks and mobile networks
(such as 4G and 5G) to provide an efficient Internet-based
healthcare service [33]. e use of mobile has made the HIoT
services more accessible to the healthcare practitioner who
can access the patient’s data, diagnose, and swiftly provide
treatment. Several pieces of research have been reported on
the application of mobile computing in healthcare [38–40].
Istepanian et al. [41] have developed an m-IoT based system
that could monitor the glucose level in diabetic patients
which helped in hypoglycemia management. In another
study, a mobile gateway-based HIoT system called
“AMBRO” was designed where several sensors were used for
fall detection and heart rate control. Further, it could locate
the patients using an integrated GPS module. In [42], an
IoT-based real-time monitoring system has been reported
that detects an abnormality in the heart activity and alerts
the patient when the heart rate goes beyond 60–100 beats per
minute. e security and privacy of the user and user data is
an important issue in an m-IoT system. In [43], various
methods have been proposed that can be used to address
these aforesaid issues including physical and technical
safeguards, network security, audit reports, and technical
policies.
4.1.3. Wearable Devices. Wearable devices help healthcare
professionals and patients to deal with various health
issues at a reduced cost. ese devices are noninvasive
and can be developed by integrating various sensors with
wearable accessories used by humans such as watch,
wristband [44], necklace, shirt, shoes, handbag, caps, and
so on [45]. e sensor attached is used to collect the
Journal of Healthcare Engineering 5

environmental and patient’s health information. is
information is then uploaded to the server/databases.
Some wearable devices are also connected with mobile
phones through health applications. Various studies have
been reported in the literature showing the use of these
wearable devices (Figure 6) and mobile computing in
real-time monitoring [46–49]. Castillejo et al. have
proposed an activity recognition method by integrating
wearable devices in a wireless sensor network for remote
monitoring of patients through an e-health mobile
Tra i n
Test
Health
information
Machine learning
Cloud and data analysis layer Application layerPerception layer
Physical activity results
Figure 4: A smart healthcare framework for AAL (reproduced from [27], license no. 496010299387).
Ambient
assisted living
HIoT services
Mobile IoT Blockchain
Cognitive
computing
Community-
based
healthcare
services
Wear a b l e
devices
Child health
information
Adverse drug
reaction
Figure 3: Widely used HIoT services.
6Journal of Healthcare Engineering

application [50]. In a similar study, Jie Wan et al. have
developed an IoT-enabled health monitoring device
where several sensors (including heartbeat, body tem-
perature, and blood pressure sensors) have been em-
bedded to provide remote health monitoring. Biosignals
such as electrocardiograph (ECG) and electromyography
(EMG) signals were also analyzed with the help of IoT-
enabled wearable systems to extract patient’s vital in-
formation [51]. e interconnectivity of these wearable
devices with a mobile application enhances the compu-
tational power of the device. e application can be
further used for easy processing and visualization of the
collected information.
4.1.4. Community-Based Healthcare Services.
Community-based healthcare monitoring is a concept of
creating a healthcare network that covers a local community
such as a private clinic, a small residential area, a hotel, and
so on to monitor the health conditions of the people residing
in that area. In a community-based network, various net-
works are concatenated and can work cooperatively to give a
collaborative service. In [52], an IoT-based cooperative
medical network was set up to provide healthcare moni-
toring in remote areas. To establish a secure connection
between the networks, different authentication and autho-
rization mechanisms were employed. In another study [51],
a community medical network was proposed that was
Motion detection
sensors
Glucose level
monitoring GPS: smart soles Wireless fetal
monitoring Smart clothing
Pressure sensor Temperature sensor Chest strap: ECG
sensor
Figure 6: Wearable sensors (reproduced from [27], license no. 496010299387).
Sensing
Collected data from
diverse sources
{api}
Analysis and
visualization
Internet of things
Cloud computing
GUI
IoT
Preprocesing tasks
Figure 5: A generalized m-IoT environment (reproduced from [38] under Creative Common License).
Journal of Healthcare Engineering 7

considered as a “virtual hospital.” is helped to provide
medical facilities to the needy from a remote location. A
resident health network has been proposed in [52]. Herein, a
four-layer structural framework was designed for sharing
health information that includes medical records of the
patients. is information can be accessed by the health
centers to provide proper medical advice to the patients who
are residing in the locality.
4.1.5. Cognitive Computing. Cognitive computing refers to
the process of analyzing a problem the way the human brain
does. With recent advancements in sensor technology and
artificial intelligence, IoT devices are now integrated with
sensors that can mimic the human brain in solving prob-
lems. Cognitive computing in an IoT system helps in ana-
lyzing hidden patterns that are present in a large volume of
data [53]. Further, it enhances the ability of a sensor to
process healthcare data and automatically adapt to the
surrounding. In a cognitive IoT network, all sensors col-
laborate with other smart gadgets and provide efficient
health services. e use of cognitive computing in an IoT
system helps the healthcare providers to make an effective
observation of the patient’s data and provide proper treat-
ment. In [54], an EEG-based smart healthcare monitoring
system has been proposed that uses cognitive computing to
decide the pathological condition of the patient. e EEG
data, along with other sensor data such as speech, gesture,
body movement, and facial expressions, were used to assess a
patient’s condition. Further, it facilitates emergency help in
case of pathogenic conditions. Kumar et al. have proposed a
cognitive data transmission method that can effectively
detect, record, and analyze patient’s health data. During an
emergency, the data of the patient, under critical condition,
are transmitted with the utmost priority [55].
4.1.6. Adverse Drug Reaction. An adverse drug reaction
(ADR) can be characterized as a side effect of taking a med-
ication. e reaction may occur either after a single dose or a
long-term administration. is can also be possible due to the
adverse reaction when two different medicines are ingested at
the same time. ADR does not depend on the type of medicine
or the disease and it varies from person to person. In an IoT-
based ADR system, a unique identifier/barcode is used to
identify each medicine at the patient’s terminal [56]. e in-
formation about the drug’s compatibility with the patient’s
body can be checked using a pharmaceutical intelligent in-
formation system. e information system stores the allergy
profile of each patient using e-health records. After analyzing
the allergy profile and other vital health information, a decision
is made whether the medication is suitable for a patient or not.
In a similar study [57], an IoT-based prescription adverse drug
event (prescADE) system has been proposed, which can im-
prove patient safety by reducing the ADE.
4.1.7. Blockchain. e sharing of data among different medical
devices and healthcare providers plays a crucial role in an HIoT
network. However, one of the major issues in secure data
sharing is data fragmentation. Data fragmentation may lead to a
gap in information across healthcare providers, who are as-
sociated with a single patient. Insufficient information may
hamper the treatment process. Blockchain technology is used to
solve the problem of data fragmentation and helps the
healthcare centers to establish a connection among the data
repositories that are present in the network [58]. is further
ensures secure and protective sharing of sensitive medical in-
formation and increases transparency between the doctors and
patients. Blockchain technology also promotes collaboration
among healthcare providers and organizations to do qualitative
research (Figure 7). e secure transmission in blockchain
technology can be due to three factors. First, it contains an
immutable “ledger” that can be accessed and controlled by
people. It ensures that once a record is stored in the ledger, it
cannot be modified. Further, each transaction in the ledger must
follow certain predefined rules. Second, blockchain is a dis-
tributed technology and operates simultaneously from multiple
devices, computers, etc. ird, blockchain follows the agree-
ment rules and data exchange policies with a smart contract
mechanism. e smart contract manages identity and sets out
permissions to access different electronic medical reports
(EMRs) that are stored in the blockchain. It means doctors are
only allowed to go through those EMRs to which they have been
permitted. Numerous blockchain projects have been established
in the healthcare industry in recent years for the management of
EMR, medicine prescription, and clinical pathways [60–62].
Yue et al. have developed an app called healthcare data gateway
(HDG) that uses blockchain technology and provides authority
to patients to share their information. Herein, the patient can
control and share their information without violating the
privacy policy [63].
4.1.8. Child Health Information. Child health information
(CHI) is a concept that deals with creating awareness for a
child’s well-being. e main purpose of CHI is to educate
and empower children and their parents on the child’s
overall health including their nutritional values, emotional
and mental state, and behavior. e application of IoT has
helped researchers to achieve this goal with the development
of a platform that can monitor and regulate a child’s health.
Nigar and Chowdhury have developed an IoT-based
framework where a child’s mental and physical state can be
monitored [64]. Further, necessary measures can be taken
with the help of doctors and parents in case of an emergency.
In a similar study [65], an IoT-based medical network was
developed that connects a medical device with a mobile app.
e system collects five different body parameters: height,
temperature, SpO
2
, weight, and heart rate. is information
is made available to the doctors and health professionals by
the app. In [66], the use of an m-health service has been
proposed to monitor the food habit of children by the
teachers and parents. e app was used to attain good
nutritional values in the children.
4.2. Applications. e HIoT services/concepts are used for
the development of different IoT-based applications. Re-
searchers working in the said fields have proposed different
8Journal of Healthcare Engineering

concepts to the service of mankind. In simple words, con-
cepts are more developer-centric, whereas applications are
user-centric. e rapid development in the IoT-technology
has led to the development of more affordable and user-
friendly wearable sensors, portable gadgets, and medical
devices. ese systems can be used to collect patient’s in-
formation, diagnose diseases, monitor the health of the
patients, and generate alerts in case of a medical emergency
(Figure 8). In the following section, some of the most recent
commercially available devices have been discussed. Further,
various HIoT-based applications have been addressed in-
cluding both single condition and multiple conditions
(Figure 9).
4.2.1. ECG Monitoring. Electrocardiogram (ECG) repre-
sents the electrical activity of the heart due to the depo-
larization and repolarization of atria and ventricles. An ECG
provides information about the basic rhythms of the heart
muscles and acts as an indicator for various cardiac ab-
normalities. ese abnormalities include arrhythmia, pro-
longed QT interval, myocardial ischemia, etc. e use of IoT
technology has found potential application in the early
detection of heart abnormalities through ECG monitoring.
Numerous studies in the past have employed IoT in ECG
monitoring [67–72]. e study reported in [72] has pro-
posed an IoT-based ECG monitoring system that is com-
posed of a wireless data acquisition system and a receiving
processor. It employed a search automation method that was
used to detect cardiac abnormality in real time. In [73], a
small wearable low-power ECG monitoring system was
proposed that was integrated with a t-shirt. It used a
biopotential chip to collect good quality ECG data. e
recorded data were then transmitted to the end-users
through Bluetooth. e recorded ECG data could be visu-
alized using a mobile app. e proposed system could be
operated with a minimal power of 5.2 mW. Real-time
monitoring in an IoTsystem can be possible after integrating
it with big data analytics to manage higher data storage.
Bansals and Gandhi have proposed an ECG monitoring
system that can handle long-term and continuous
Smartwatch
Heart rate
monitoring
Temperature
sensor
Smartphone
applications
Table-2 Table-1
Table-3
Hospital-3
Hospital-2
Body sensors
Hospital-1 Blockchain
IoT sensors and boards
IoT
IoT
Logistic information
Patient’s information
Product and
location
details
Patient Doctor Test report Pharma
Patient-1 Doctor-1 Test report-1 Pharma-1
Patient-2 Doctor-2 Test report-2 Pharma-2
------ ------ ------ ------
Figure 7: A blockchain-based health monitoring system (modified from [59] under Creative Commons License).
Data center
performs data
analysis
Analyze the
measurement
Smart health system
Send data to and
from cloud
User gets health
information from
the data center Monitor user’s health
Figure 8: Application of HIoT (reproduced from [40]).
Journal of Healthcare Engineering 9

monitoring by integrating the concept of nanoelectronics,
big data, and IoT [74]. It is worthy to note that in [75], the
authors have tried to resolve the issue of power consumption
associated with a wearable ECG monitoring system. ey
have proposed a unique method called compressive sensing
that can optimize power consumption and provide optimal
performance in ECG monitoring. IoT-based fall detection
and ECG monitoring system has also been reported in [76]
that uses a cloud-based server and a mobile application. is
system was designed to provide real-time monitoring to
elderly patients by continuously checking their ECG and
accelerometer data.
4.2.2. Glucose Level Monitoring. Diabetes is the condition in
which the blood glucose level in the body remains high for a
prolonged period. It is one of the most common diseases in
humans. ree major types of diabetes are generally found,
namely, type-I diabetes, type-2 diabetes, and gestational
diabetes. e disease and its types can be identified following
three tests, namely, random plasma glucose test, fasting
plasma glucose test, and oral glucose tolerance test. How-
ever, the most widely used diagnostic method for the de-
tection of diabetes is “fingerpicking” followed by the
measurement of blood glucose level. e recent develop-
ment in IoT technologies has been used in designing various
wearable gadgets for blood glucose monitoring that is
noninvasive, comfortable, convenient, and safe [77–80]. In
[81], m-IoT-based noninvasive glucometer has been pro-
posed for real-time monitoring of blood glucose levels.
Herein, the wearable sensors and the healthcare providers
were linked through IPv6 connectivity. Alarc´
on-Paredes
et al. have designed a glove for the measurement of blood
glucose level that is integrated with a Raspberry Pi camera
and a visible laser beam. A set of pictures taken from the
fingertip was used for detecting the diabetic condition of the
patients [82]. In another study [83], an algorithm based on a
double moving average was employed in the IoT architecture
for the measurement of the glucose level. It is worth
specifying that optical sensors such as infrared LED and
near-infrared photodiode have also been used for glucose
level measurement. Herein, the light signal reflected from
the human body is used to compute the glucose level in the
human body [84].
4.2.3. Temperature Monitoring. Human body temperature is
an indicator of the maintenance of homeostasis and is an
important part of many diagnostic processes. Additionally, a
change in body temperature can be a warning sign in some
illnesses such as trauma, sepsis, and so on. Keeping track of
the change in temperature over time helps the doctors to
make inferences about the patient’s health condition in
many diseases. e conventional way of measuring tem-
perature is using a temperature thermometer that is either
attached to the mouth, ear, or rectum. But, the low com-
fortability of the patient and the high chances of contracting
an infection is always an issue with these methods. However,
the recent development in IoT-based technologies has
proposed various solutions to this problem. In [85], a 3D-
printed wearable device was proposed that could be worn on
the ear, which tracks the core body temperature from the
tympanic membrane using an infrared sensor. e device
was integrated with a wireless sensor module and data
processing unit. Herein, the measured temperature is not
affected by the environment and other physical activities.
Gunawan has developed an IoT-based temperature moni-
toring system using Arduino and Raspberry Pi. e tem-
perature data were stored in the database and were displayed
on a web page, which could be accessed through a desktop or
a mobile phone [86]. In another study [87], wearable and
lightweight sensors were used for real-time measurement of
the body temperature in infants. It can also alert the parents
whenever there is a rise in temperature above a critical value.
4.2.4. Blood Pressure Monitoring. One of the compulsory
procedures in any diagnostic process is the measurement of
blood pressure (BP). e most accustomed method of
measurement of blood pressure requires at least one person
to do the recording. However, the integration of IoT and
other sensing technology has transformed the way BP was
previously monitored. For example, in [88], a wearable
cuffless gadget has been proposed that can measure both
systolic and diastolic pressure. e recorded information can
be stored in the cloud. Further, the efficiency of this device
was tested on 60 persons and the accuracy was validated.
Guntha has implemented cloud computing and fog com-
puting in the IoT-based BP measurement system [89]. is
prepared the system for long-term real-time monitoring.
e device could also store the recorded data for future
references. In a similar study [90], a deep learning-based
CNN model with time-domain characteristics was used for
the evaluation of systolic and diastolic blood pressure. e
measurement of BP using the ECG signal and photo-
plethysmogram (PPG), recorded from the fingertip, has been
HIoT
applications
Rehabilitation
Other
notable
applications
ECG
monitoring BP
monitoring
Temperature
monitoring
Asthma
monitoring
Mood
monitoring
Medication
management
Wheelchair
management
Glucose
level
monitoring
Oxygen
saturation
monitoring
Figure 9: Category of HIoT application.
10 Journal of Healthcare Engineering

proposed in [91]. Herein, the BP was computed using the
attached microcontroller module and then the recorded data
were sent to the cloud storage.
4.2.5. Oxygen Saturation Monitoring. Pulse oximetry is the
noninvasive measurement of oxygen saturation and can be
used as a vital parameter in healthcare analysis. e non-
invasive method eliminates the issues related to the con-
ventional approach and provides real-time monitoring. e
advancement in the pulse oximetry that comes from the
integration of IoT-based technology has shown potential
application in the healthcare industry. In [92], a noninvasive
tissue oximeter was proposed that could measure the blood
oxygen saturation level, along with heart rate, and pulse
parameters. Further, the recorded information could be
transmitted to the server using various communication
technologies such as Zigbee or Wi-Fi. Based on the recorded
data, a medical intervention decision was made. In another
study [93], an alarm system that can alert the patients when
the oxygen saturation reaches a critical level was reported.
e system was integrated with a pulse oximeter and WLAN
router that were connected using the Blynk server. More-
over, Von Chong et al. have proposed a multispectral sensor
that reduces the adverse effect of a single LED [94]. A low-
power and cost-effective remote patient monitoring system
has been proposed in [95]. e device can be effectively used
for real-time monitoring.
4.2.6. Asthma Monitoring. Asthma is a chronic illness that
can affect the airways and may cause difficulty in breathing.
In asthma, the airways shrink due to the swelling of the air
passage. is follows many health issues such as wheezing,
coughing, chest pain, and shortness of breath. ere is no
suitable time for an asthma attack to come, and an inhaler or
nebulizer is the only lifesaver at that moment. Hence, there is
a potential need for real-time monitoring of this condition.
Numerous IoT-based systems for asthma monitoring have
been proposed in recent years [96–98]. In [99], a smart HIoT
solution for asthma patients was proposed that was used to
record respiratory rate using a smart sensor. e health
information was stored in a cloud server that gives access to
caregivers for diagnostic and monitoring purposes. Raji
proposed a respiratory monitoring and alarm system where
an LM35 temperature sensor was used to measure the re-
spiratory rate [100]. is was achieved by monitoring the
temperature of the inhaled and exhaled air. e respiration
data were sent to the health center and were displayed on a
web server. e proposed system also triggered an alarm and
automatically sent a message to the patient once a threshold
value was reached. In another study [101], the proposed
system not only monitored and warned the patients about
the asthma condition but also suggested the patients about
the right amount of the medication to be administered.
Further, the system was capable to analyze the environ-
mental conditions and direct the patient to move from a
place that is not suitable for his health. Machine learning,
cloud computing, and big data analysis techniques have also
been integrated with IoT-based devices to effectively track
asthma [102, 103]. A list of features that can be added while
thinking about future development in the IoT-based asthma
monitoring system has been proposed in [104]. Some of the
most potential features include peak flows, pollen, humidity,
air temperature, and asthma symptoms.
4.2.7. Mood Monitoring. Mood tracking provides vital in-
formation regarding a person’s emotional state and is used
to maintain a healthy mental state. It also assists healthcare
professionals while dealing with various mental diseases
such as depression, stress, bipolar disorder, and so on. Self-
monitoring of the emotional state enhances a person’s
understanding of their mental condition.In [105], a mood
mining approach was reported that uses a CNN network to
evaluate and categorize a person’s mood in 6 categories:
happy, excited, sad, calm, distressed, and angry. In a similar
study [106], the real-time mood measurement was achieved
using an interactive system called “Meezaj.” e app also
showed the importance of happiness in decision making and
assists the policymaker in identifying those important fac-
tors that play a crucial role in defining a person’s happiness.
With the integration of an advanced machine learning al-
gorithm, now stress can be detected beforehand with the
help of heartbeat rate. Further, the system can communicate
with the patient about their stress condition [107]. It is
interesting to note that the analysis of the stress condition
can also be useful in designing an IoT-based system that can
prevent an accident. Jasleen et al. have proposed a wearable
device that can estimate four negative emotions/moods
(anger, stress, terror, and sadness) of a person/driver. By
analyzing the variation in these emotions, the intelligent
system decides whether the driver is in a subconscious state
or not. e system stops the dc motor of the vehicle once a
driver achieved the subconscious state.
4.2.8. Medication Management. Medication adherence is a
common issue in the healthcare industry. Nonadherence to
the medication schedule may increase the adverse health
complications in patients. Medication nonadherence is
mostly found in elderly people as they develop clinical
conditions like cognitive decline, dementia, and so on as the
age progresses. Hence, it is difficult for them to strictly follow
the prescriptions of doctors. Numerous research in the past
has focused on tracking the patient’s compliance with
medication through the application of IoT [108–111]. In
[112], a smart medical box was developed that can remind
people of their medication. e box has three trays where each
tray contains the medicine for three different times (morning,
afternoon, and evening). e system also measures some of
the vital health parameters (blood glucose level, blood oxygen
level, temperature, ECG, and so on). All the recorded data are
then sent to the cloud server. A mobile app was used to
establish communication between the two end-users. e
recorded information can be accessed by doctors and patients
using the mobile app. In another study [113], the information
about the storage condition of the medicine such as tem-
perature and humidity was also recorded. is helped the
patients to maintain the required storage environment. One
Journal of Healthcare Engineering 11

of the more specific examples of medication management is
“Saathi” [114]. is pill monitoring system was specifically
designed for the woman going through in vitro fertilization
(IVF) treatment. Since the IVF process demands a strict
medication schedule, the proposed device gives women the
facility to remind their daily medication and injections, track
real-time medicine consumption, and communicate with the
healthcare providers. Moreover, an adaptive IoT-based smart
medication system was reported in [115] that uses fuzzy logic
to analyze the data collected from the temperature sensor. e
system is efficient to treat fever by continuous monitoring of
body temperature and then automatically adjust the time and
dose of medicine during treatment.
4.2.9. Wheelchair Management. A wheelchair is an insepa-
rable part of the life of patients with restricted mobility. It
provides them physical as well as psychological support.
However, the application of a wheelchair is limited when the
disability is due to brain damage. Hence, new research is
focusing on integrating the navigation and tracking system
with these wheelchairs. IoT-based systems are now showing
potential results in achieving this goal [116–119]. In [120], an
IoT-based steering system, integrated with a real-time ob-
stacle avoidance system, has been proposed. e steering
system can detect obstacles by employing image processing
techniques on the recorded real-time videos. e use of
mobile computing has enabled wheelchair management to be
more interactive and easy for patients. A smart wheelchair as
represented in [121] was developed by the integration of
various sensors, mobile technologies, and cloud computing.
e system includes a mobile app that can help the patients to
interact with the wheelchair and the caregivers. e app also
enables caregivers to monitor the wheelchair from a distance.
In another study [122], an IoT-based wheelchair monitoring
system has been proposed that used hand gestures for con-
trolling the wheelchair. e designed model is especially
applicable for patients having quadriplegia. e hand gesture
information was recorded using the RF sensor that was
present in the hand gloves and was used to control the
wheelchair. Further, the sensor data were transmitted to the
server and could be stored in the cloud. e doctors/care-
givers can access the data from the cloud and can use this
information for diagnosis. It is worth specifying that in [123],
a more advanced and automated smart wheelchair was re-
ported that not only monitored the wheelchair movement but
also provided an umbrella, foot mat, head mat, and obstacle
detection features. Herein, the designed system provided
more efficient interaction with the living environment.
4.2.10. Rehabilitation System. Physical medicine along with
rehabilitation is effective in restoring the functional ability of
a patient with a disability. Rehabilitation involves identifying
the problem and helping the patients to regain their normal
life. e application of IoT in rehabilitation is diverse and
can be seen in the treatment of cancer, sports injury, stroke,
and other physical disabilities [124–127]. A smart walker
rehabilitation system has been proposed in [128] that used a
multimodal sensor to monitor the walking pattern of the
patient and evaluate the movement metrics. When a patient
used the smart walker, it measured different movement
matrices such as orientation angle, elevation, force, and so
on. A mobile app was used by the doctors to access these data
and to provide diagnostic reports. Moreover, a stroke re-
habilitation system was developed by integrating a smart
wearable armband, robotic hand, and machine learning
algorithm [129]. e armband was designed using a low-
power IoT-based textile electrode that can measure, pre-
process, and transmit the biopotential signal. Further, the
3D-printed robotic arm analyzed the muscle activity and
assisted the patient to correct their motion pattern during
the after-stroke recovery period. In another study, a sports
rehabilitation system was reported that monitored tem-
perature, motion posture, electromyography (EMG), elec-
trocardiography (ECG), and so on and provided feedback to
the athletes. e recorded information could be used by
healthcare professionals to predict the patients’ recovery and
formulate rehabilitation programs.
4.2.11. Other Notable Applications. e application of HIoT
is disparate and not limited to the aforesaid functions. With the
rapid growth of technology, the number of HIoTapplications is
increasing significantly. Some of the research areas where the
integration of IoT devices was not explicitly demonstrated
previously are now using this technology efficiently. is may
include cancer treatment, remote surgery, abnormal cellular
growth, hemoglobin detection, etc. In [130], a new IoT-based
framework for cancer treatment was proposed that integrated
various stages of cancer treatment including chemotherapy and
radiotherapy. A mobile app was used for online consultation
from the doctors. e lab-test results of patients were stored in
the cloud server and could be accessed by the healthcare
provider to decide the time and dosage of medication. Another
potential application is the detection of lung cancer using
various state-of-the-art machine learning algorithms with an
IoT-based system [131–133]. Moreover, a recent piece of re-
search also suggested the detection of skin lesions using an IoT-
based system [134]. Cecil et al. have employed IoTin designing
the next-generation surgical training framework [135]. e
device used virtual reality to develop a training environment
and also provided a platform to interact with other surgeons
from different locations. In [136], a human-robot collaborative
system has been proposed that can effectively perform mini-
mally invasive surgery. Using a portable device, the hemoglobin
level in the blood can be monitored [137]. e device employed
photoplethysmography (PPG) sensors, a light-emitting diode
(LED), and photodiodes for the measurement of hemoglobin.
e efficiency of the device was further validated by comparing
the results with the established colorimetric test.
5. Challenges, Limitations, and Future Scope
In the last few years, the healthcare industry has witnessed
remarkable technological development and its application in
solving healthcare-related issues. is has significantly im-
proved the healthcare services, which have now been
brought at the fingertip. With the application of smart
12 Journal of Healthcare Engineering

sensors, cloud computing, and communication technolo-
gies, IoT has successfully revolutionized the healthcare in-
dustry. Like other technologies, IoT also has certain
challenges and issues that provide potential scope for future
research. Some of the issues have been discussed in the
subsequent section.
5.1. Servicing and Maintenance Cost. Of late, there are rapid
technological advancements that would require continuous
upgradation of the HIoT-based devices from time to time.
Every IoT-based system involves a large number of con-
nected medical devices and sensors. is involves high
maintenance, servicing, and upgradation costs that may
impact the financials of not only the company but also the
end-users. Hence, the inclusion of sensors that can be op-
erated with a lower maintenance cost is required.
5.2. Power Consumption. Most of the HIoT devices run on
battery. Once a sensor is put on, the replacement of the
battery is not easy. Hence, a high-power battery was used to
power such a system. However, currently, researchers
worldwide are trying to design healthcare devices that can
generate power for themselves. One such potential solution
may be the integration of the IoT system with renewable
energy systems. ese systems can help in alleviating the
global energy crisis to a certain extent.
5.3. Standardization. In the healthcare industry, a large
number of vendors are manufacturing a varying range of
products. Most of these products claim to follow standard
rules and protocols in the design process. However, there is a
lack of validity. Hence, the construction of a dedicated group
is required that can standardize these HIoT devices based on
the communication protocols, data aggregation, and gate-
way interfaces. e validation and standardization of elec-
tronic medical records (EMRs) recorded by the HIoTdevices
are also to be considered extensively. is can be achieved
when various organizations and standardization bodies such
as Information Technology and Innovation Foundation
(IETF), the European Telecommunications Standards In-
stitute (ETSI), the Internet Protocol for Smart Objects
(IPSO), and so on can collaborate with the researchers to
form working groups for the standardization of the devices.
5.4. Data Privacy and Security. e integration of cloud
computing has transformed the idea of real-time monitoring.
But, this also has made healthcare networks more vulnerable to
cyberattacks. is may lead to mishandling of patients’ valuable
information and may affect the process of treatment. To
prevent an HIoT system from this malicious attack, several
preventive measures must be taken while designing a system.
e medical and sensing devices included in an HIoT network
must evaluate and employ identity authentication, secure
booting, fault tolerance, authorization management, white-
listing, password encryption, and secure pairing protocols to
avoid an attack. Similarly, the network protocols such as Wi-Fi,
Bluetooth, Zigbee, and so on must be integrated with secured
routing mechanisms and message integrity verification tech-
niques. Since IoT is a connected network where each user is
linked to the server, any glitch in the security services of IoT
may compromise the privacy of the patient. is could be fixed
with the creation of a more secure environment through the
integration of advanced and protected algorithms and
cryptographies.
5.5. Scalability. Scalability represents the ability of a
healthcare device that can adapt to the changes in the en-
vironment. A system with higher scalability works smoothly
without any delay and makes efficient use of the available
resources. Hence, it is crucial to design a device with higher
scalability. is further makes a system more efficient for
present and future uses. An HIoT system is the intercon-
nection of different medical devices, sensors, and actuators,
which are used to share information through the Internet.
e lack of uniformity among the connected devices of an
HIoT system decreases the scalability of the system and
hence must be managed efficiently.
5.6. Identification. Healthcare professionals deal with
multiple patients and caregivers at the same time. Similarly,
when a patient deals with multiple health issues, he interacts
with multiple doctors. us, it is crucial to exchange the
identity of the patient, caregiver, and doctors among each
other during a single treatment process to avoid confusion
and maintain the smooth functioning of the healthcare
system.
5.7. Self-Configuration. e IoT devices must give more
power to the users by including the feature like manual
configuration. is will enable the users to change the system
parameters according to the application demand and also
with the change in the environmental conditions.
5.8. Continuous Monitoring. Many healthcare situations
demand long-term monitoring of the patient during treat-
ment as in the case of chronic diseases, heart diseases, etc. In
such situations, the IoT device must be able to perform real-
time monitoring efficiently.
5.9. Exploration of New Diseases. With the rapid growth in
mobile technology, new healthcare apps are added with
passing days. ough a large number of mobile apps are
available for healthcare applications, the types of diseases for
which these apps were designed are still limited. Hence,
there is a need to include more diseases that were either
neglected or got inadequate consideration in the past. is
will add up to the diversity of the HIoT applications.
5.10. Environmental Impact. e development of an HIoT
system requires the integration of various biomedical sen-
sors with semiconductor-rich devices. e manufacturing
and fabrication mostly require the use of earth metal and
other toxic chemicals. is may create an adverse effect on
Journal of Healthcare Engineering 13

the environment. Hence, a proper regulatory body must be
created to control and regulate the manufacturing of the
sensors. Further, more research must be devoted to making
sensors using biodegradable materials.
6. Conclusion
e current review investigated different aspects of the HIoT
system. Comprehensive knowledge about the architecture of
an HIoT system, their component, and the communication
among these components has been discussed herein. Ad-
ditionally, this paper provides information about the current
healthcare services where the IoT-based technologies have
been explored. By employing these concepts, the IoT-
technology has helped healthcare professionals to monitor
and diagnose several health issues, measure many health
parameters, and provide diagnostic facilities at remote lo-
cations. is has transformed the healthcare industry from a
hospital-centric to a more patient-centric system. We have
also discussed various applications of the HIoT system and
their recent trends. Further, the challenges and issues as-
sociated with the design, manufacturing, and use of the
HIoT system have been provided. ese challenges will form
a base for future advancement and research focus in the
upcoming years. Moreover, a comprehensive up-to-date
knowledge on the HIoT devices has been provided for the
readers who are not only willing to initiate their research but
also make advancements in the said field.
Data Availability
No data were used to support this study.
Conflicts of Interest
e authors declare that they have no conflicts of interest.
Acknowledgments
We acknowledge Prof. Slawomir Wilczynski, Medical
University, Silesia, Poland, for his help in improving the
English writing of this manuscript.
References
[1] Z. Ali, M. S. Hossain, G. Muhammad, and A. K. Sangaiah,
“An intelligent healthcare system for detection and classi-
fication to discriminate vocal fold disorders,” Future Gen-
eration Computer Systems, vol. 85, pp. 19–28, 2018.
[2] G. Yang, L. Xie, M. Mantysalo et al., “A health-IoT platform
based on the integration of intelligent packaging, unobtru-
sive bio-sensor, and intelligent medicine box,” IEEE
Transactions on Industrial Informatics, vol. 10, no. 4,
pp. 2180–2191, 2014.
[3] Y. Yan, “A home-based health information acquisition
system,” Health Information Science and Systems, vol. 1, p. 12,
2013.
[4] M. Khan, K. Han, and S. Karthik, “Designing smart control
systems based on internet of things and big data analytics,”
Wireless Personal Communications, vol. 99, no. 4,
pp. 1683–1697, 2018.
[5] P. J. Nachankar, “IOT in agriculture,” Decision Making,
vol. 1, no. 3, 2018.
[6] V. G. Menon, “An IoT-enabled intelligent automobile sys-
tem for smart cities,” Internet of ings, p. 100213, 2020.
[7] E. Qin, “Cloud computing and the internet of things:
technology innovation in automobile service,” in Proceedings
of the International Conference on Human Interface and the
Management of Information, pp. 173–180, Las Vegas, NV,
USA, July 2013.
[8] I. Froiz-M´
ıguez, T. Fern´andez-Caram´es, P. Fraga-Lamas,
and L. Castedo, “Design, implementation and practical
evaluation of an IoT home automation system for fog
computing applications based on MQTT and ZigBee-WiFi
sensor nodes,” Sensors, vol. 18, no. 8, p. 2660, 2018.
[9] P. S. Mathew, “Applications of IoT in healthcare,” in Cog-
nitive Computing for Big Data Systems over IoT, pp. 263–288,
Springer, Berlin, Germany, 2018.
[10] V. Jagadeeswari, “A study on medical Internet of ings and
Big Data in personalized healthcare system,” Health Infor-
mation Science And Systems, vol. 6, p. 14, 2018.
[11] H. Peng, Y. Tian, J. Kurths, L. Li, Y. Yang, and D. Wang,
“Secure and energy-efficient data transmission system based
on chaotic compressive sensing in body-to-body networks,”
IEEE Transactions on Biomedical Circuits and Systems,
vol. 11, no. 3, pp. 558–573, 2017.
[12] A. Gatouillat, Y. Badr, B. Massot, and E. Sejdic, “Internet of
medical things: a review of recent contributions dealing with
cyber-physical systems in medicine,” IEEE Internet of ings
Journal, vol. 5, no. 5, pp. 3810–3822, 2018.
[13] L. M. Dang, M. J. Piran, D. Han, K. Min, and H. Moon, “A
survey on internet of things and cloud computing for
healthcare,” Electronics, vol. 8, no. 7, p. 768, 2019.
[14] B. Oryema, “Design and implementation of an interoperable
messaging system for IoT healthcare services,” in Proceedings
of the 2017 14th IEEE Annual Consumer Communications &
Networking Conference (CCNC), pp. 45–52, Las Vegas, NV,
USA, January 2017.
[15] A. Ahad, M. Tahir, and K.-L. A. Yau, “5G-based smart
healthcare network: architecture, taxonomy, challenges and
future research directions,” IEEE Access, vol. 7,
pp. 100747–100762, 2019.
[16] M. N. Birje and S. S. Hanji, “Internet of things based dis-
tributed healthcare systems: a review,” Journal of Data, In-
formation and Management, vol. 2, 2020.
[17] K. T. Kadhim, “An overview of patient’s health status
monitoring system based on internet of things (IoT),”
Wireless Personal Communications, vol. 114, pp. 1–28, 2020.
[18] Y. Yuehong, “e internet of things in healthcare: an
overview,” Journal of Industrial Information Integration,
vol. 1, pp. 3–13, 2016.
[19] G. Shanmugasundaram and G. Sankarikaarguzhali, “An
investigation on IoT healthcare analytics,” International
Journal of Information Engineering and Electronic Business,
vol. 9, no. 2, p. 11, 2017.
[20] J.-Y. Lee and R. A. Scholtz, “Ranging in a dense multipath
environment using an UWB radio link,” IEEE Journal on
Selected Areas in Communications, vol. 20, pp. 1677–1683,
2002.
[21] H. Aftab, K. Gilani, J. Lee, L. Nkenyereye, S. Jeong, and
J. Song, “Analysis of identifiers in IoT platforms,” Digital
Communications and Networks, vol. 6, no. 3, pp. 333–340,
2020.
[22] G. Cerruela Garc´
ıa, I. Luque Ruiz, and M. G´omez-Nieto,
“State of the art, trends and future of bluetooth low energy,
14 Journal of Healthcare Engineering

near field communication and visible light communication
in the development of smart cities,” Sensors, vol. 16, no. 11,
p. 1968, 2016.
[23] R. Peng and M. L. Sichitiu, “Angle of arrival localization for
wireless sensor networks,” in Proceedings of the 2006 3rd
Annual IEEE Communications Society on Sensor and Ad Hoc
Communications and Networks, pp. 374–382, Reston, Vir-
ginia, September 2006.
[24] D. P. Young, “Ultra-wideband (UWB) transmitter location
using time difference of arrival (TDOA) techniques,” in
Proceedings of the e rity-Seventh Asilomar Conference on
Signals, Systems & Computers, pp. 1225–1229, Pacific Grove,
CA, USA, November 2003.
[25] R. Zetik, “UWB localization-active and passive approach
[ultra wideband radar],” in Proceedings of the 21st IEEE
Instrumentation and Measurement Technology Conference
(IEEE Cat. No. 04CH37510), pp. 1005–1009, Como, Italy,
May 2004.
[26] R. J. Fontana and S. J. Gunderson, “Ultra-wideband precision
asset location system,” in Proceedings of the 2002 IEEE
Conference on Ultra Wideband Systems and Technologies
(IEEE Cat. No. 02EX580), pp. 147–150, Baltimore, MD, USA,
May 2002.
[27] L. Syed, S. Jabeen, M. S., and A. Alsaeedi, “Smart healthcare
framework for ambient assisted living using IoMT and big
data analytics techniques,” Future Generation Computer
Systems, vol. 101, pp. 136–151, 2019.
[28] G. Marques and R. Pitarma, “An indoor monitoring system
for ambient assisted living based on internet of things ar-
chitecture,” International Journal of Environmental Research
and Public Health, vol. 13, no. 11, p. 1152, 2016.
[29] A. Dohr, “e internet of things for ambient assisted living,”
in Proceedings of the 2010 Seventh International Conference
on Information Technology: New Generations, pp. 804–809,
Las Vegas, NA, USA, April 2010.
[30] C. Tsirmpas, A. Anastasiou, P. Bountris, and D. Koutsouris,
“A new method for profile generation in an internet of things
environment: an application in ambient-assisted living,”
IEEE Internet of ings Journal, vol. 2, no. 6, pp. 471–478,
2015.
[31] R. Maskeli�unas, “A review of Internet of ings technologies
for ambient assisted living environments,” Future Internet,
vol. 11, p. 259, 2019.
[32] M. S. Shahamabadi, “A network mobility solution based on
6LoWPAN hospital wireless sensor network (NEMO-
HWSN),” in Proceedings of the 2013 Seventh International
Conference on Innovative Mobile and Internet Services in
Ubiquitous Computing, pp. 433–438, Taichung, Taiwan, July
2013.
[33] R. Tabish, “A 3G/WiFi-enabled 6LoWPAN-based U-healthcare
system for ubiquitous real-time monitoring and data logging,”
in Proceedings of the 2nd Middle East Conference on Biomedical
Engineering, pp. 277–280, Doha, Qatar, February 2014.
[34] C. Sandeepa, “An emergency situation detection system for
ambient assisted living,” in Proceedings of the 2020 IEEE
International Conference on Communications Workshops
(ICC Workshops), pp. 1–6, Anchorage, AL, USA, June 2020.
[35] G. Marques, I. M. Pires, N. Miranda, and R. Pitarma, “Air
quality monitoring using assistive robots for ambient assisted
living and enhanced living environments through internet of
things,” Electronics, vol. 8, no. 12, p. 1375, 2019.
[36] G. Marques and R. Pitarma, “A cost-effective air quality
supervision solution for enhanced living environments
through the internet of things,” Electronics, vol. 8, no. 2,
p. 170, 2019.
[37] X. M. Zhang and N. Zhang, “An open, secure and flexible
platform based on internet of things and cloud computing
for ambient aiding living and telemedicine,” in Proceedings of
the 2011 International Conference on Computer and Man-
agement (CAMAN), pp. 1–4, Wuhan, China, May 2011.
[38] H. Mora, D. Gil, R. M. Terol, J. Azor´
ın, and J. Szymanski, “An
IoT-based computational framework for healthcare moni-
toring in mobile environments,” Sensors, vol. 17, no. 10,
p. 2302, 2017.
[39] S. Tyagi, “A conceptual framework for IoT-based healthcare
system using cloud computing,” in Proceedings of the 2016
6th International Conference-Cloud System and Big Data
Engineering (Confluence), pp. 503–507, Noida, India, January
2016.
[40] S. Nazir, “Internet of ings for Healthcare using effects of
mobile computing: a systematic literature review,” Wireless
Communications and Mobile Computing, vol. 2019, Article
ID 5931315, 20 pages, 2019.
[41] R. S. H. Istepanian, D. Casiglia, and J. W. Gregory, “Mobile
health (m-Health) for diabetes management,” British Journal
of Healthcare Management, vol. 23, no. 3, pp. 102–108, 2017.
[42] L. Chuquimarca, “Mobile IoT device for BPM monitoring
people with heart problems,” in Proceedings of the 2020
International Conference on Electrical, Communication, and
Computer Engineering (ICECCE), pp. 1–5, Istanbul, Turkey,
June 2020.
[43] S. H. AlMotiri, “Mobile health (m-health) system in the
context of IoT,” in Proceedings of the 2016 IEEE 4th Inter-
national Conference on Future Internet of ings and Cloud
Workshops (FiCloudW), pp. 39–42, Vienna, Austria, August
2016.
[44] Y. Zhang, J. Cui, K. Ma, H. Chen, and J. Zhang, “A wristband
device for detecting human pulse and motion based on the
internet of things,” Measurement, vol. 163, 2020.
[45] K. Singh, “Role and impact of wearables in IoT healthcare,”
in Proceedings of the ird International Conference on
Computational Intelligence and Informatics, pp. 735–742,
Springer, Berlin, Germany, 2020.
[46] M. Mendonça, “An IoT-based healthcare ecosystem for
home intelligent assistant services in smart homes,” in
Proceedings of the EAI International Conference on IoT
Technologies for HealthCare, pp. 142–155, Braga, Portugal,
December 2019.
[47] T. Mauldin, M. Canby, V. Metsis, A. Ngu, and C. Rivera,
“SmartFall: a smartwatch-based fall detection system using
deep learning,” Sensors, vol. 18, no. 10, p. 3363, 2018.
[48] D. Kraft, K. Srinivasan, and G. Bieber, “Deep learning based
fall detection algorithms for embedded systems, smart-
watches, and IoT devices using accelerometers,” Technolo-
gies, vol. 8, no. 4, p. 72, 2020.
[49] N. S. Erdem, “Gait analysis using smartwatches,” in Pro-
ceedings of the 2019 IEEE 30th International Symposium on
Personal, Indoor and Mobile Radio Communications (PIMRC
Workshops), pp. 1–6, Istanbul, Turkey, September 2019.
[50] P. Castillejo, J.-F. Martinez, J. Rodriguez-Molina, and
A. Cuerva, “Integration of wearable devices in a wireless
sensor network for an E-health application,” IEEE Wireless
Communications, vol. 20, no. 4, pp. 38–49, 2013.
[51] A. Kelati, “Biosignal monitoring platform using Wearable
IoT,” in Proceedings of the 22st Conference of Open Inno-
vations Association FRUCT, pp. 9–13, Petrozavodsk, Russia,
May 2018.
Journal of Healthcare Engineering 15

[52] W. Wang, “e internet of things for resident health in-
formation service platform research,” in Proceedings of the
IET International Conference on Communication Technology
and Application (ICCTA 2011), Beijing, China, May 2011.
[53] R. K. Behera, P. K. Bala, and A. Dhir, “e emerging role of
cognitive computing in healthcare: a systematic literature
review,” International Journal of Medical Informatics,
vol. 129, pp. 154–166, 2019.
[54] S. U. Amin, M. S. Hossain, G. Muhammad, M. Alhussein,
and M. A. Rahman, “Cognitive smart healthcare for pa-
thology detection and monitoring,” IEEE Access, vol. 7,
pp. 10745–10753, 2019.
[55] M. A. Kumar, R. Vimala, and K. R. A. Britto, “A cognitive
technology based healthcare monitoring system and medical
data transmission,” Measurement, vol. 146, pp. 322–332,
2019.
[56] A. J. Jara, “A pharmaceutical intelligent information system to
detect allergies and adverse drugs reactions based on internet of
things,” in Proceedings of the 2010 8th IEEE International
Conference on Pervasive Computing and Communications
Workshops (PERCOM Workshops), pp. 809–812, Mannheim,
Germany, April 2010.
[57] Z. Nakhla, K. Nouira, and A. Ferchichi, “Prescription adverse
drug events system (PrescADE) based on ontology and in-
ternet of things,” e Computer Journal, vol. 62, no. 6,
pp. 801–805, 2019.
[58] K. P. Satamraju and B. Malarkodi, “Proof of concept of
scalable integration of internet of things and blockchain in
healthcare,” Sensors, vol. 20, no. 5, p. 1389, 2020.
[59] A. Sharma, R. Tomar, N. Chilamkurti, and B.-G. Kim,
“Blockchain based smart contracts for internet of medical
things in e-healthcare,” Electronics, vol. 9, no. 10, p. 1609,
2020.
[60] X. Zhang and S. Poslad, “Blockchain support for flexible
queries with granular access control to electronic medical
records (EMR),” in Proceedings of the 2018 IEEE Interna-
tional conference on communications (ICC), pp. 1–6, Kansas
City, MO, USA, May 2018.
[61] X. Zhang, “Block-based access control for blockchain-based
electronic medical records (EMRs) query in eHealth,” in
Proceedings of the 2018 IEEE Global Communications Con-
ference (GLOBECOM), pp. 1–7, Abu Dhabi, UAE, December
2018.
[62] L. Nørfeldt, “Cryptopharmaceuticals: increasing the safety of
medication by a blockchain of pharmaceutical products,”
Journal of Pharmaceutical Sciences, vol. 108, pp. 2838–2841,
2019.
[63] X. Yue, H. Wang, D. Jin, M. Li, and W. Jiang, “Healthcare
data gateways: found healthcare intelligence on blockchain
with novel privacy risk control,” Journal of Medical Systems,
vol. 40, p. 218, 2016.
[64] N. Nigar and L. Chowdhury, “An intelligent children
healthcare system by using ensemble technique,” in Pro-
ceedings of International Joint Conference on Computational
Intelligence, pp. 137–150, Budapest, Hungary, November
2019.
[65] E. Sutjiredjeki, N. C. Basjaruddin, D. N. Fajrin, and F. Noor,
“Development of NFC and IoT-enabled measurement de-
vices for improving health care delivery of Indonesian
children,” Journal of Physics Conference Series, vol. 1450,
2020.
[66] M. Vazquez-Briseno, “A proposal for using the internet of
things concept to increase children’s health awareness,” in
Proceedings of CONIELECOMP 2012, 22nd International
Conference on Electrical Communications and Computers,
pp. 168–172, Cholula, Mexico, February 2012.
[67] T. Tekeste, “Ultra-low power QRS detection and ECG
compression architecture for IoT healthcare devices,” IEEE
Transactions on Circuits and Systems I: Regular Papers,
vol. 66, pp. 669–679, 2018.
[68] J. B. Bathilde, “Continuous heart rate monitoring system as
an IoT edge device,” in Proceedings of 2018 IEEE Sensors
Applications Symposium (SAS), pp. 1–6, Seoul, Korea, March
2018.
[69] B. J. Drew, R. M. Califf, M. Funk et al., “Practice standards for
electrocardiographic monitoring in hospital settings,” Cir-
culation, vol. 110, no. 17, pp. 2721–2746, 2004.
[70] P. Dash, “Electrocardiogram monitoring,” Indian Journal of
Anaesthesia, vol. 46, pp. 251–260, 2002.
[71] E. Agu, “e smartphone as a medical device: assessing
enablers, benefits and challenges,” in Proceedings of the 2013
IEEE International Workshop of Internet-of-ings Net-
working and Control (IoT-NC), pp. 48–52, New Orleans, LA,
USA, June 2013.
[72] M.-L. Liu, “Internet of ings-based electrocardiogram
monitoring system,” Chinese Patent, vol. 102, p. 118, 2012.
[73] T. Wu, “A wearable, low-power, real-time ECG monitor for
smart t-shirt and IoT healthcare applications,” in Advances
in Body Area Networks I, pp. 165–173, Springer, Berlin,
Germany, 2019.
[74] M. Bansal and B. Gandhi, “IoT & big data in smart healthcare
(ECG monitoring),” in Proceedings of the 2019 International
Conference on Machine Learning, Big Data, Cloud and
Parallel Computing (COMITCon), pp. 390–396, Faridabad,
India, February 2019.
[75] H. Djelouat, M. Al Disi, I. Boukhenoufa et al., “Real-time
ECG monitoring using compressive sensing on a hetero-
geneous multicore edge-device,” Microprocessors and
Microsystems, vol. 72, p. 102839, 2020.
[76] A. Al-Kababji, “IoT-based fall and ECG monitoring system:
wireless communication system based firebase realtime
database,” in Proceedings of the 2019 IEEE SmartWorld,
Ubiquitous Intelligence & Computing, Advanced & Trusted
Computing, Scalable Computing & Communications, Cloud
& Big Data Computing, Internet of People and Smart City
Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/
IOP/SCI), pp. 1480–1485, Leicester, UK, August 2019.
[77] T. N. Gia et al., “Energy efficient fog-assisted IoT system for
monitoring diabetic patients with cardiovascular disease,”
Future Generation Computer Systems, vol. 93, pp. 198–211,
2019.
[78] G. M. Bhat and N. G. Bhat, “A novel IoT based framework
for blood glucose examination,” in Proceedings of the 2017
International Conference on Electrical, Electronics, Com-
munication, Computer, and Optimization Techniques (ICE-
ECCOT), pp. 205–207, Mysuru, India, December 2017.
[79] T. N. Gia, M. Ali, I. B. Dhaou et al., “IoT-based continuous
glucose monitoring system: a feasibility study,” Procedia
Computer Science, vol. 109, pp. 327–334, 2017.
[80] B. Sargunam and S. Anusha, “IoT based mobile medical
application for smart insulin regulation,” in Proceedings of
the 2019 IEEE International Conference on Electrical, Com-
puter and Communication Technologies (ICECCT), pp. 1–5,
Erode, India, October 2019.
[81] R. S. Istepanian, “e potential of Internet of m-health
ings “m-IoT” for non-invasive glucose level sensing,” in
Proceedings of the 2011 Annual International Conference of
16 Journal of Healthcare Engineering

the IEEE Engineering in Medicine and Biology Society,
pp. 5264–5266, Boston, MA, USA, March 2011.
[82] A. Alarc ´
on-Paredes, V. Francisco-Garc´
ıa, I. P. Guzm´
an-
Guzm´
an, J. Cantillo-Negrete, R. E. Cuevas-Valencia, and
G. A. Alonso-Silverio, “An IoT-based non-invasive glucose
level monitoring system using raspberry pi,” Applied Sci-
ences, vol. 9, no. 15, p. 3046, 2019.
[83] F. Valenzuela, A. Garc´
ıa, E. Ruiz, M. V´azquez, J. Cortez, and
A. Espinoza, “An IoT-based glucose monitoring algorithm to
prevent diabetes complications,” Applied Sciences, vol. 10,
no. 3, p. 921, 2020.
[84] S. Sunny and S. S. Kumar, “Optical based non invasive
glucometer with IoT,” in Proceedings of the 2018 Interna-
tional Conference on Power, Signals, Control and Compu-
tation (EPSCICON), pp. 1–3, rissur, India, January 2018.
[85] H. Ota, M. Chao, Y. Gao et al., “3D printed “earable” smart
devices for real-time detection of core body temperature,”
ACS Sensors, vol. 2, no. 7, pp. 990–997, 2017.
[86] I. Gunawan, “Design and development of telemedicine based
heartbeat and body temperature monitoring tools,” in
Proceedings of the IOP Conference Series: Materials Science
and Engineering, p. 012018, Gambang, Malaysia, November
2020.
[87] N. A. Zakaria, “IoT (Internet of ings) based infant body
temperature monitoring,” in Proceedings of the 2018 2nd
International Conference on Biosignal Analysis, Processing
and Systems (ICBAPS), pp. 148–153, Kuching, Malaysia, July
2018.
[88] Q. Xin and J. Wu, “A novel wearable device for continuous,
non-invasion blood pressure measurement,” Computational
Biology and Chemistry, vol. 69, pp. 134–137, 2017.
[89] R. Guntha, “IoT architectures for noninvasive blood glucose
and blood pressure monitoring,” in Proceedings of the 2019
9th International Symposium on Embedded Computing and
System Design (ISED), pp. 1–5, Kollam, India, December
2019.
[90] P. C.-P. Chao and T.-Y. Tu, “Using the time-domain
characterization for estimation continuous blood pressure
via neural network method,” in Proceedings of the Infor-
mation Storage and Processing Systems, San Francisco, CA,
USA, August 2017.
[91] A. Dinh, “Blood pressure measurement using finger ECG
and photoplethysmogram for IoT,” in International Con-
ference on the Development of Biomedical Engineering in
Vietnam, pp. 83–89, Springer, Berlin, Germany, 2017.
[92] Y. Fu and J. Liu, “System design for wearable blood oxygen
saturation and pulse measurement device,” Procedia
Manufacturing, vol. 3, pp. 1187–1194, 2015.
[93] L. Agustine, “Heart rate monitoring device for arrhythmia
using pulse oximeter sensor based on android,” in Pro-
ceedings of the 2018 International Conference on Computer
Engineering, Network and Intelligent Multimedia (CENIM),
pp. 106–111, Surabaya, Indonesia, November 2018.
[94] A. Von Chong, M. Terosiet, A. Histace, and O. Romain,
“Towards a novel single-LED pulse oximeter based on a
multispectral sensor for IoT applications,” Microelectronics
Journal, vol. 88, pp. 128–136, 2019.
[95] E. C. Larson, “SpiroSmart: using a microphone to measure
lung function on a mobile phone,” in Proceedings of the 2012
ACM Conference on Ubiquitous Computing, pp. 280–289,
New York, NY, USA, September 2012.
[96] ˙
I. G¨uler, “Real-time abnormal detection for asthma patients
with internet of things technology,” in Proceedings of the
2018 3rd International Conference on Computer Science and
Engineering (UBMK), pp. 269–274, Sarajevo, Bosnia and
Herzegovina, September 2018.
[97] B. Li, Q. Dong, R. S. Downen et al., “A wearable IoT aldehyde
sensor for pediatric asthma research and management,”
Sensors and Actuators B: Chemical, vol. 287, pp. 584–594,
2019.
[98] L. Gurbeta, A. Badnjevic, M. Maksimovic, E. Omanovic-
Miklicanin, and E. Sejdic, “A telehealth system for automated
diagnosis of asthma and chronical obstructive pulmonary
disease,” Journal of the American Medical Informatics As-
sociation, vol. 25, no. 9, pp. 1213–1217, 2018.
[99] S. T. U. Shah, “Cloud-assisted IoT-based smart respiratory
monitoring system for asthma patients,” in Applications of
Intelligent Technologies in Healthcare, pp. 77–86, Springer,
Berlin, Germany, 2019.
[100] A. Raji, “Respiratory monitoring system for asthma patients
based on IoT,” in Proceedings of the 2016 Online Interna-
tional Conference on Green Engineering and Technologies (IC-
GET), pp. 1–6, Coimbatore, India, November 2016.
[101] S. Gundu, “A novel IoT based solution for monitoring and
alerting bronchial asthma patients,” International Journal of
Research in Engineering, Science and Management, vol. 3,
no. 10, pp. 120–123, 2020.
[102] T. G. AL-Ja and E. H. Al-Hemiary, “Internet of ings based
cloud smart monitoring for asthma patient,” Qalaai Zanist
Journal, vol. 2, pp. 359–364, 2017.
[103] A. K. Prasad, “SMART asthma alert using IoT and predicting
threshold values using decision tree classifier,” in Applica-
tions of Internet of ings, pp. 141–150, Springer, Berlin,
Germany, 2020.
[104] C. Y. Hui, B. Mckinstry, O. Fulton, M. Buchner, and
H. Pinnock, “What features do patients and clinicians
‘want’in the future Internet-Of-ings (IoT) systems for
asthma: a mixed method study,” European Respiratory
Journal, vol. 56, 2020.
[105] M. G. R. Alam, “CNN based mood mining through IoT-
based physiological sensors observation,” 한국정보과학회
학술발표논문집, pp. 1301–1303, 2017.
[106] E. Ahmad, “Meezaj: an interactive system for real-time mood
measurement and reflection based on internet of things,”
International Journal of Advanced Computer Science and
Applications, vol. 11, 2020.
[107] P. S. Pandey, “Machine learning and IoT for prediction and
detection of stress,” in Proceedings of the 2017 17th Inter-
national Conference on Computational Science and its Ap-
plications (ICCSA), pp. 1–5, Trieste, Italy, July 2017.
[108] M. Aldeer, M. Javanmard, and R. Martin, “A review of
medication adherence monitoring technologies,” Applied
System Innovation, vol. 1, no. 2, p. 14, 2018.
[109] G. Latif, “I-CARES: advancing health diagnosis and medi-
cation through IoT,” Wireless Networks, vol. 4, pp. 1–15,
2019.
[110] N. Sahlab, “Development of an intelligent pill dispenser
based on an IoT-approach,” in Proceedings of the Interna-
tional Conference on Human Systems Engineering and De-
sign: Future Trends and Applications, pp. 33–39, Munich,
Germany, September 2019.
[111] A. Shreyas, “IoT-enabled medicine bottle,” in Emerging
Research in Computing, Information, Communication and
Applications, pp. 127–139, Springer, Berlin, Germany, 2019.
[112] S. A. Bharadwaj, “Enhancing healthcare using m-care box
(monitoring non-compliance of medication),” in Proceedings
of the 2017 International Conference on I-SMAC (IoT in
Journal of Healthcare Engineering 17

Social, Mobile, Analytics and Cloud)(I-SMAC), pp. 352–356,
Coimbatore, India, February 2017.
[113] D. Karagiannis and K. S. Nikita, “Design and development of
a 3D Printed IoT portable Pillbox for continuous medication
adherence,” in Proceedings of the 2020 IEEE International
Conference on Smart Internet of ings (SmartIoT),
pp. 352-353, Beijing, China, August 2020.
[114] P. Wadibhasme, “Saathi—a smart IoT-based pill reminder
for IVF patients,” in Proceedings of the International Con-
ference on Information and Communication Technology for
Intelligent Systems, pp. 697–705, Ahmedabad, India, August
2020.
[115] J. Medina, M. Espinilla, ´
A. L. Garc´
ıa-Fern´andez, and
L. Mart´
ınez, “Intelligent multi-dose medication controller
for fever: from wearable devices to remote dispensers,”
Computers & Electrical Engineering, vol. 65, pp. 400–412,
2018.
[116] A. Ghorbel, N. B. Amor, and M. Jallouli, “A survey on
different human-machine interactions used for controlling
an electric wheelchair,” Procedia Computer Science, vol. 159,
pp. 398–407, 2019.
[117] A. Carrasquilla-Batista, “An Internet of ings (IoT) ap-
plication to control a wheelchair through EEG signal pro-
cessing,” in Proceedings of the 2017 International Symposium
on Wearable Robotics and Rehabilitation (WeRob), p. 1,
Houston, TX, USA, November 2017.
[118] D. J. DSouza, “IoT based smart sensing wheelchair to assist in
healthcare,” Methods, vol. 6, 2019.
[119] K. Ramya, S. Nargees, S. A. Tabasuum, S. Khan, and
M. Shiny, “A survey onSmart automated WheelChair system
with voice controller using IOT along with health monitoring
for physically challenged persons,” International Scientific
Journal of Contemporary Research in Engineering Science and
Management, vol. 5, pp. 95–98, 2020.
[120] Y. K. Lee, “Real time image processing based obstacle
avoidance and navigation system for autonomous wheel-
chair application,” in Proceedings of the 2017 Asia-Pacific
Signal and Information Processing Association Annual
Summit and Conference (APSIPA ASC), pp. 380–385, Kuala
Lumpur, Malaysia, December 2017.
[121] A. Ghorbel, “Cloud based mobile application for remote
control of intelligent wheelchair,” in Proceedings of the 2018
14th International Wireless Communications & Mobile
Computing Conference (IWCMC), pp. 1249–1254, Limassol,
Cyprus, June 2018.
[122] U. Garg, “Design and implementation of smart wheelchair
for quadriplegia patients using IOT,” in Proceedings of the
2018 First International Conference on Secure Cyber Com-
puting and Communication (ICSCCC), pp. 106–110,
Jalandhar, India, December 2018.
[123] D. Kumar, R. Malhotra, and S. R. Sharma, “Design and
construction of a smart wheelchair,” Procedia Computer
Science, vol. 172, pp. 302–307, 2020.
[124] A. Onasanya and M. Elshakankiri, “Smart integrated IOT
healthcare system for cancer care,” Wireless Networks,
pp. 1–16, 2019.
[125] M. Lapresa, “A smart solution for proprioceptive rehabili-
tation through M-IMU sensors,” in Proceedings of the 2020
IEEE International Workshop on Metrology for Industry 4.0 &
IoT, pp. 591–595, Kuala Lumpur, Malaysia, December 2020.
[126] S. V. Adamovich, A. S. Merians, R. Boian et al., “A virtual
reality-based exercise system for hand rehabilitation post-
stroke,” Presence: Teleoperators and Virtual Environments,
vol. 14, no. 2, pp. 161–174, 2005.
[127] J. Qi, P. Yang, A. Waraich, Z. Deng, Y. Zhao, and Y. Yang,
“Examining sensor-based physical activity recognition and
monitoring for healthcare using Internet of ings: a sys-
tematic review,” Journal of Biomedical Informatics, vol. 87,
pp. 138–153, 2018.
[128] C. Nave and O. Postolache, “Smart walker based IoTphysical
rehabilitation system,” in Proceedings of the 2018 Interna-
tional Symposium in Sensing and Instrumentation in IoT Era
(ISSI), pp. 1–6, Shanghai, China, September 2018.
[129] G. Yang, J. Deng, G. Pang et al., “An IoT-enabled stroke
rehabilitation system based on smart wearable armband and
machine learning,” IEEE Journal of Translational Engineering
in Health and Medicine, vol. 6, pp. 1–10, 2018.
[130] M. Heshmat and A.-R. S. Shehata, “A framework about using
internet of things for smart cancer treatment process,” in
Proceedings of the International Conference on Industrial
Engineering and Operations Management, pp. 1206–1211,
Washington, DC, USA, September 2018.
[131] J. P. Rajan, “Fog computing employed computer aided
cancer classification system using deep neural network in
internet of things based healthcare system,” Journal of
Medical Systems, vol. 44, p. 34, 2020.
[132] K. Pradhan and P. Chawla, “Medical Internet of things using
machine learning algorithms for lung cancer detection,”
Journal of Management Analytics, vol. 7, no. 4, pp. 591–623,
2020.
[133] Z. Liu, C. Yao, H. Yu, and T. Wu, “Deep reinforcement
learning with its application for lung cancer detection in
medical Internet of ings,” Future Generation Computer
Systems, vol. 97, pp. 1–9, 2019.
[134] D. d. A. Rodrigues, R. F. Ivo, and S. C. Satapathy, “A new
approach for classification skin lesion based on transfer
learning, deep learning, and IoTsystem,” Pattern Recognition
Letters, vol. 136, 2020.
[135] J. Cecil, A. Gupta, M. Pirela-Cruz, and P. Ramanathan, “An
IoMT based cyber training framework for orthopedic sur-
gery using Next Generation Internet technologies,” Infor-
matics in Medicine Unlocked, vol. 12, pp. 128–137, 2018.
[136] H. Su, “Internet of things (IoT)-based collaborative control
of a redundant manipulator for teleoperated minimally in-
vasive surgeries,” in Proceedings of the 2020 IEEE Interna-
tional Conference on Robotics and Automation (ICRA),
pp. 9737–9742, Paris, France, August 2020.
[137] K. Bhatia and M. Singh, “Towards development of portable
instantaneous smart optical device for hemoglobin detection
non invasively,” Health and Technology, vol. 9, no. 1,
pp. 17–23, 2019.
18 Journal of Healthcare Engineering