Acta Polytechnica Hungarica Vol. 16, No.

2, 2019

Revolutionizing Healthcare with IoT and

Cognitive, Cloud-based Telemedicine

Ábel Garai, István Péntek, Attila Adamkó

University of Debrecen, Faculty of Information Technology, Kassai út 26, 4028
Debrecen, Hungary, [email protected], [email protected],
[email protected]

Abstract: Telemedicine instruments and e-Health mobile wearable devices are designed to
enhance patients’ quality of life. The adequate man-and-machine cognitive ecosystem is the
missing link for that in healthcare. This research program is dedicated to deliver the
suitable solution. This research’s goal is the establishment of adaptive informatics
framework for telemedicine. This is achieved through the deployed open telemedicine
interoperability hub-system. The presented inter-cognitive sensor-sharing system solution
augments the healthcare ecosystem through extended interconnection among the
telemedicine, IoT e-Health and hospital information system domains. The general purpose
of this experiment is building an augmented, adaptive, cognitive and also universal
healthcare information technology ecosphere. This study structures the actual questions
and answers regarding the missing links and gaps between the emerging Sensor Hub
technology and the traditional hospital information systems. The Internet-of-Things space
penetrated the personal and industrial environments. The e-Health smart devices are
neither widely accepted nor deployed in the ordinary healthcare service. This paper
reviews the major technological burdens and proposes necessary actions for enhancing the
healthcare service level with Sensor Hub and Internet-of-Things technologies. Hereby we
report the studies on varying simplex, duplex, full-duplex, data package- and file-based
information technology modalities. We establish with that stable system interconnection
among clinical instruments, healthcare systems and eHealth smart devices. Our research is
based on the trilateral cooperation comprising the University of Debrecen Department of
Information Technology, Semmelweis University Second Paediatric Clinic and T-Systems
Healthcare Competence Center Central and Eastern Europe.

Keywords: Cognitive healthcare; telemedicine; telecare; e-health; IoT; sensor hub; hybrid
cloud; healthcare IT

1 Introduction
Today, the information revolution affects all areas of life as people use
continuously electronic devices on a regular basis. These equipments assist their
users to simplify their everyday life, for example avoiding traffic jams or tracking

– 163 –
Á. Garai et al. Revolutionizing Healthcare with IoT and Cognitive, Cloud-based Telemedicine

their fitness activity. These gadgets hold various sensors and built-in interfaces to
share the collected data with external tools and systems. Our aim is to let the
produced data used in as many ways as possible.
The most common and widely used hardware component in smart devices is the
global positioning system (GPS) sensor. Most of the mobile phones have GPS
capability and host multiple mobile applications using this sensor. Navigation
applications collect and analyse the collected GPS coordinates and share these
with further applications running on servers. These server applications process the
received coordinates and calculate the best route to reach the destination or help
the user to avoid traffic jams. Using navigation applications became part of our
everyday life. Another commonly used device group consists of the fitness
activity trackers. These collect health-related data as long as their users wear them
[Figure 1]. Usually, users wear the fitness trackers during fitness activities like
cycling, running, swimming, etc. These trackers are capable of collecting heart
rate values, temperature, air pressure values or even more health-related data.

Figure 1
Biosensory data processing with healthcare IoT devices

Multiple applications can process these measurement values, but most of them are
only simple client applications on the user’s device. Client applications are
working locally on their host mobile device (smartphone) and usually do not share
the measurement results with external systems. If an application shares the
measurement values, mostly it does it just to archive them. The hospital
information systems unfortunately cannot work with large amounts of health-
related measurement values: they cannot access them since they usually remain in
separated, closed systems.
The doctor or specialist could use the tracked data during a medical examination if
it is immediately accessible to him. The measurement values are helpful when the
patient requires treatment, and the doctor needs to examine different parameters to
make a justified decision [1]. For certain medical examination rely on measured

– 164 –
Acta Polytechnica Hungarica Vol. 16, No. 2, 2019

heart rate values: these values can be extracted from fitness trackers or wearable
devices with our solution. Sensor-based wearable devices are producing sufficient
volume of health-related data every day [2]. Our article focuses on sensor data and
describes our developed hub system between the internet of things (IoT) devices
and health-related systems. In particular, the actual phase of our research
concentrates on privacy and the credibility of the measurement chain.

2 Cognitive Telemedicine
This paper derives and adapts the principles of cognitive info-communications [3]
to our described scientific research. The application of the given synergies leads to
the foundation of the cognitive telemedicine. The inter-cognitive sensor-bridging
communication is the specific area, where our research and the cognitive info
communication are interlocked [4]. The human-machine interaction has been
researched since 1976 [5]. The Cognitive Infocommunication presents the next
significant milestone concerning the human-ICT interconnection. Our paper
augments this scientific area with the practical e-Health implementation.
Therefore, our research delivers the operational information technology realization
for the next generation human-machine interaction for the e-Health. In our
research the human patients are interconnected through bio-sensory e-Health
devices to the international information technology landscapes and also to further
human actors.
Our previously proposed private cloud architecture [15] gives room for intra-
cognitive sensor-bridging and inter-cognitive sensor-sharing communications.
This is the suitable category of Cognitive Infocommunications for the enhanced
telemedicine systems allowing doctors to assess remotely patients’ physiological,
psychological and neural state. The cloud architecture provides the link between
the cloud architectural solution for telemedicine systems and the Cognitive
Infocommunications: patient information is directed to the doctor using the
telemedicine cognitive subsystem, while the data is captured by medical sensors.
As telesurgery systems gain ground, the drafted cloud computing architecture
links the human doctor with the remote surgery machine: it concludes an intra-
cognitive sensor-sharing cognitive info communication. [5]
Our research plays a significant role in the enhancement of the Human and Bio-
interfaces chapter of the Cognitive Infocommunication [6] discipline. There were
already significant scientific achievements published in this area, for example:
"The significance of cognitive info-communications in developing assistive
technologies for people with non-standard cognitive characteristics: CogInfoCom
for people with nonstandard cognitive characteristics" [7]. Our presented paper’s
secondary area within the Cognitive Infocommunications is the “Human factors,
E-health, and People with Specific Needs”. Two previous major publications

– 165 –
Á. Garai et al. Revolutionizing Healthcare with IoT and Cognitive, Cloud-based Telemedicine

within this topic are „Cognitive Infocommunication for Monitoring and Improving
Well-being of People” [8] and "Cognitive workload classification using
cardiovascular measures and dynamic features" [9].
Telemedicine involves the distribution of health-related services and information
via electronic information and telecommunication technologies [10]. There is no
single definition for telemedicine systems. Some definitions include all aspects of
medical care including also preventive health care. Others use telemedicine and
telehealth interchangeably. Therefore, our definition of telemedicine is the use of
information technology and telecommunication to provide clinical health care
from a distance. It is used to overcome the distance and to improve access to
health care services where it is not consistently available.

Figure 2
Spirometer devices for telemedicine

Telemedicine systems are also used to provide better outcomes in critical care and
emergency solutions [11]. Telemedicine depends on the 20th Century
telecommunication and information technologies [Figure 2]. These technologies
ensure the communication between patients and medical staff; and they help to
transmit health-related data and images reliably from one site to another. The first
form of telemedicine was relying on simple telephone connections. Later, the
advanced medical diagnostic methods were supported by client-server
applications working with additional telemedicine devices to support in-home
medical examinations.
Telemedicine allows medical contact and healthcare services from distance. It has
many forms: supporting advice-giving, making health-related reminders,
education, remote admissions, remote monitoring and healthcare system
integration. Telemedicine should make learning, supervision and health data

– 166 –
Acta Polytechnica Hungarica Vol. 16, No. 2, 2019

management simpler even when the required expert and the patient are far away
from each other. With telemedicine, the patient and the expert can make clinical
discussion over video conference.
Telemedicine does not purely consist of technology and devices, but it has a
determining social aspect. Telemedicine improves access to health care services
that would often not be consistently available in distant communities [12] [13].
Patients need to transmit important and sensitive messages, personal health
records through a publicly available network connection. It will happen only if
people trust the telemedicine systems and the underlying technologies.
The most important telemedicine or telehealth feature regarding our presented
article is the patient remote monitoring or home monitoring. This feature allows
the expert to follow the patient’s health-related measurement values. While the
patient is using a wearable device or devices the telemedicine system can read the
data measured by the device. To achieve real-time health monitoring, the expert
and the patient must have reliable, uninterrupted internet connection, trusted
wearable healthcare device or devices, and a software to evaluate the
measurement data.

2.1 Sensor-based Adaptive e-health Systems

Telemedicine and information technology allow to create systems that collect,

transform and transmit the data measured by the users’ wearable devices. The
most people have one or more wearable devices which can record health-related
data, these are typically fitness trackers. Fitness trackers can follow multiple
health-related information during a fitness activity. The most fitness tracker can
measure the current heart rate value, air pressure, calories, sleep quality, altitude,
distance, and steps. The most tracker contains GPS locator, it could be useful in
case of urgent medical cases.
The trackers can collect multiple information about the wearer and they could
send them to a telemedicine system that can process the received data and send
notification or alert if it is necessary [14]. These telemedicine systems could be
integrated to any other health-related systems. Hospital information systems or
other medical systems should use the information received from telemedicine
systems. The system vendors are responsible for integrating external telemedicine
systems and using the publicly available and free health-related data. This large
amount of publicly available data is suitable for making a more accurate medical
decision and creating real-time health monitoring systems [Figure 3].

– 167 –
Á. Garai et al. Revolutionizing Healthcare with IoT and Cognitive, Cloud-based Telemedicine

Figure 3
Cloud architecture types for healthcare services

The most tracker has multiple sensors that capable to record different health-
related data, e.g.: heart rate value or calories. Beyond the fitness trackers, there are
several further devices that capable to record health-related data. Smart scale
records the users’ weight as often as the users’ uses that. Blood glucose meter for
home use records the users’ current blood glucose level. Smart blood pressure
meter records the current blood pressure and has multiple interfaces to transfer the
result to external device or system. In a modern home can be found multiple
devices that can collect health-related measurement values: that could be useful
during a medical examination [15].
If the patient trusts the external system and the medical expert handles the
measurement values with reservations, the sensor based telemedicine systems
could be a useful part of the medical- or the hospital information systems.

2.2 Implementing IoT in the Healthcare Supply Chain

Internet of things is the network of devices embedded with multiple sensors and
capability of network connectivity enabling these objects to connect to other
devices or systems sharing information with them. An IoT object can be sensed or
controlled remotely across the existing network infrastructure [16]. It gives the
opportunity for direct integration of these objects into external systems. The
“things” in the IoT expression can refer to any device equipped with sensors and
holding an active network connection [17]. Today, most types of these devices
have sensory and network capability. There are many application areas for the
internet of things as shown in Figure 4:

– 168 –
Acta Polytechnica Hungarica Vol. 16, No. 2, 2019

Figure 4
Application areas for IoT

As it was described earlier in this article most people have multiple devices to
record health-related measurement data or non-health-related measurement values.
If these devices have one or more interfaces to connect external systems or other
devices the measured values can be forwarded for further processing in industrial
healthcare systems. This ability makes the data aggregation reasonable from a
simple wearable sensory device into a commercial telemedicine system.

2.2 Open Telemedicine Hub-Software

Open telemedicine interoperability (OTI) hub is a complex application based on

internet of things devices. It provides a set of publicly available application
programming interfaces (API). OTI hub allows IoT devices to share health-related
measurements with other systems. Through the open API, the health-related
systems use the provided health records. The OTI hub provides the information in
multiple formats. To serve the requests from the hospital information system the
OTI hub uses HL7 formats. This format is widely accepted in the international
healthcare domain. Figure 5 represents the relevant healthcare data sources and
consumers:

– 169 –
Á. Garai et al. Revolutionizing Healthcare with IoT and Cognitive, Cloud-based Telemedicine

Figure 5
Open telemedicine interoperability hub-software’s data-link diagram

The OTI hub collects the measurement values from the health-related devices and
cleans the received data from the measurement errors. The error-free measurement
values are stored for further use. The integrated healthcare systems can create
parameter-based customized reports. The retrieved information is used during
medical examinations and for disease-prediction [18]. The telemedicine
environment was adjusted to meet the requirements of the statistical evaluation of
the captured bio-sensory data [19].
The OTI hub provides useful real-time health monitoring. In our case, the OTI hub
works as a cross-functional channel between the smart end-devices and industrial
healthcare systems. The OTI hub itself does not make medical decisions: it acts as
a proxy transforming and transmitting the measurement values to the integrated
systems in the requested format and structure. Then, the external systems issue
reports, notifications and alerts based on the received values. Figure 6 shows the
OTI hub’s reference architecture:

– 170 –
Acta Polytechnica Hungarica Vol. 16, No. 2, 2019

Figure 6
Open telemedicine interoperability hub-software’s reference architecture

The OTI hub has the following common IoT services:

 Consumption services: these services are responsible for data
aggregation and data transformation. They prepare the captured
measurement values for archiving them. During the transformation
phase, the measurement errors are removed.
 Analytics services: it is responsible for creating analytics on the
historical data-flow and making predictions. The prediction function is
applied during medical examinations. The analytics services are using
machine learning algorithms relying on pattern analysis.
 Presentation services: these services visualize the received
measurement values to the users. Visualization is real-time, and it is
based on current values.

2.3 Research Methodology and Software Technology

Clinical systems interoperability reaches beyond plain data-exchange: it
constitutes interoperability at technical, semantic and at the process level. In the
empirical model of the research the OSI model (ISO/IEC 7498-1:1994 [20]) is
mapped against the aforementioned interoperability levels. Therefore, these three
interoperability modalities are interpreted also at the corresponding information

– 171 –
Á. Garai et al. Revolutionizing Healthcare with IoT and Cognitive, Cloud-based Telemedicine

technology abstraction layer. Technical and semantic interoperability is targeted

within the presented research. Among the technical interoperability modalities
instead of the TCP/IP, the file-based interface connection has been elected: this
option offered significantly more flexibility during the research, as shown in
Figure 7:

Figure 7
Open telemedicine interoperability hub-software’s architecture

The following instruments have been selected and allocated to the research
program: Spirometer PDD-301/shm as clinical telemedicine instrument, Microsoft
Band I and Microsoft Band II smart wristband as eHealth sensory devices, Nokia
Lumia 930 smartphone (Windows 10 Mobile operating system), Dell Latitude
E6520 (Windows 10 32 bit operating system, i5-2520M chipset, 4 GB RAM and
256 GB HDD) primary laptop, Dell Latitude E6220 (Windows 7 64 bit operating
system, i5-2520M chipset, 4 GB RAM, 128 GB SDD) secondary laptop, three
Lenovo MIIX 300-10IBY tablets and an ACER SWITCH SW3-013-12CD tablet.
Each tablet is equipped with 10,1 display (WXGA and HD IPS), 2 GB memory,
64 GB internal storage and Windows 10 operating system. All laptops and tablets
fit the 802.11g WLAN and Bluetooth 4.0 standards. The spirometer is USB-
enabled. The selected smart wristbands are manufactured with built-in- Bluetooth
4.0 communication chipsets. Each instrument of the lab equipment package has
been individually tested prior to the experiment.
A specific communication link over was established between the smartphone and
the bio-sensory healthcare IoT device, as shown in Figure 8.

– 172 –
Acta Polytechnica Hungarica Vol. 16, No. 2, 2019

Figure 8
Communication link for OTI-HS app and bio-sensory device

A specific private cloud was established for the research. This ran on stand-alone
x86-64 architecture equipped with Intel i5 processor, 256GB SSD, and 4 GB
RAM. The operating system for the private Cloud is Red Hat Enterprise Linux 7.0
3.10.0229, the virtualization is provided by VMware Workstation v6.5.0 and the
relational database management system is supplied by MySQL v5.6. The cloud-
based version of the hospital information test system runs in a commercial private
cloud (Telekom Cloud). The Open Telemedicine Interoperability Hub data
transmission module is embedded in a commercial public cloud (Microsoft
Azure).
The HIS runs on J2EE WebSphere Application server V6, relying upon Oracle
RDBMS 10gR2 and Progress V10 OpenEdge RDBMS. The HIS is hosted on
Unix operating system. Floating licenses were made available for reaching the
online, cloud-based edition of the selected HIS through the research tablets. The
Open Telemedicine Interoperability Hub development environment consisted of
the Universal Windows Application Development Tools (1.4.1), Windows 10
Software Development Kit 10.0.25431.01 Update 3 and Microsoft .NET
Framework Version 4.6.01038. The OTI-Hub internal database was developed by
SQL Server Data Tools 14.0.60519.0. The OTI-Hub App was developed with
Visual Studio Tools for Universal Windows Apps 14.0.25527.01. The OTI-Hub
middleware was settled in Microsoft Azure Mobile Services Tools 1.4. Red Hat
Enterprise Linux 7.0 3.10.0-229 provided the operating system for the private
cloud established specifically for the research.
The spirometry desktop program has been installed on a standalone Dell Latitude
E6520 laptop equipped with Windows 10 operating system. The spirometer has
been calibrated by the manufacturer for the research. Forced vital capacity
spirometry test has been undertaken with a healthy individual. Having the test
results stored in the spirometry desktop software, the HL7 v2.3.1 interface file has
been exported. This interface file has been processed by the cloud-based OTI-
Hub. The OTI-Hub appended the spirometry information with the previously

– 173 –
Á. Garai et al. Revolutionizing Healthcare with IoT and Cognitive, Cloud-based Telemedicine

transformed cardio body sensor information captured by the L18 Smart Bluetooth
Wristband. The generated HL7 interface file is imported after parameterization
into the factory acceptance test instance of the MedSol hospital information
system. Both the imported spirometry and cardio test results are retrieved and
displayed in the patient report query of the hospital information system. The
information technology results are validated by the Department of Information
Technology, University of Debrecen and by T-Systems Healthcare Competence
Center Central and Eastern Europe. The clinical results are validated by the
Semmelweis University 2nd Department of Paediatrics.
The implemented system is a distributed, cloud-based and scalable. In case of load
increase, the system can be scaled up by the automatic allocation of new resources
into the OTI-Hub cluster.

2.4 Research Methodology and Software Technology

The OTI-Hub was interconnected to the mirrored HIS industry test system. The
test plan included individual, cluster and integration tests. The individual tests
concerned the single research software environment element: the receiver,
transformational, storage, interpreter and integrational module of the OTI-Hub.
The cluster tests focused both on the eHealth smart device and on the telemedicine
instrument thread of the OTI-Hub.
The clinical spirometer emits elementary data. However, the smart wearable
eHealth device produces continuous time-series. Therefore, a cluster test was
carried out. During this cluster test, primary data both from the spirometer and
from the wearable eHealth device was successfully processed. The integration test
provided the overall quality assurance for the OTI-Hub. The telemedicine
instrument and the eHealth smart device measured real bio-sensory signals of
anonymized individuals and sent it to the OTI-Hub.
The OTI-Hub interpreted, saved, transformed and sent these data to the mirrored
HIS industry test system. The allocated tablets were used to load the Cloud-based
HIS graphical user interface. The tablets were connected via dedicated WLAN to
the HIS industry test system. The results were validated through the GUI on the
tablets by clinical professionals. However, the OTI-Hub module, which is
responsible for the eHealth wearable device signals interception, proved to be
unstable due to the regular mandatory operational system upgrade.
A separate load test was performed regarding the automatic cloud architecture
scaling. For this validation, exponentially increasing number of parallel input was
delivered to the dedicated cloud system. This test was successful as the virtual
cloud infrastructure scaled up automatically to process the significantly increased
workload. The load test was started with five compute-optimized virtual
machines. These virtual machines were predefined with the following parameters:
16 virtual CPU cores, 32 GB allocated RAM and 256 GB allocated disk space.

– 174 –
Acta Polytechnica Hungarica Vol. 16, No. 2, 2019

These tests simulated up to 100 000 concurrent wearable eHealth device data
flows and up to 10 000 simultaneous simplified medical information system data
flows. During these load tests, the virtual-wearable eHealth devices sent the test
measurement values to the OTI-Hub. It processed, transformed and transmitted
the captured measurement values into the simulated simplified medical
information systems. The load test was successful, as the system successfully
transmitted the previously specified number of transactions. A daily total 8 500
000 000 simulated heart rate transaction volume was processed without error
during the load test.

3 Modernizing Medical Solutions with IoT

The modern medical solutions are required to apply the latest medical standards
and to continuously follow the constantly changing laws and regulations. These
circumstances and prerequisites are hard to fulfill by the medical contributors and
vendors. Even market-leading medical solution can hardly keep pace with the
always changing environment, and only a portion of them can integrate IoT
capability [21] [22]. This article does not deal with the ruling healthcare laws and
regulations, but it focuses on the data privacy and security challenges regarding
IoT integration into the healthcare supply chain.

3.1 Personal Assistant Roll-Out

By collecting sensor data, we can continue our proposal with a new and
interesting feature which forms a personal assistant for its users by analyzing data
sets. Without analytics, our solution is only a half one. Analytics could drive our
application and provide value-added services.
We can easily imagine several situations where the combination of different
sources could result in interesting facts. While we are periodically measuring our
heart rate by our smart bracelet we can correlate it with the user's calendar and
GPS position to derive new facts, e.g. when we are on a business meeting its
normal that our pulse could be over the normal values. It means, our system will
not fire an alert when it detects some kind of abnormality in the measured values.
Our system could be extended to learn these conditions, like the above average
pulse on business meetings or on take-outs.
Naturally, the sources are endless. We can easily find smart scales, smart watches,
smart blood pressure and smart blood glucose meters to collect not just the
location, GPS coordinates or pulse from the users. The strength of our extensible
architecture and data integrations is the possibility to derive new and useful
information for our users. Like a recommendation and monitoring system which

– 175 –
Á. Garai et al. Revolutionizing Healthcare with IoT and Cognitive, Cloud-based Telemedicine

could share its data using a common format – in our case its HL7 with other
medical application or Hospital Information Systems. We have made a short
investigation about the used interchange formats in our national hospitals and that
showed us to apply HL7 for export operations from our Med-i-Hub.
Based on the original example, using the calendar and location data we can find
favorite places and events: so if it is connected to an Event management system,
we can get event recommendations. Naturally, this is not the primary goal of our
research just a use-case to expose the possibilities. It will much easier to derive
information about places where users are feeling relaxed. Our assistant could learn
from the location, event and pulse triplet: based on them recommendations could
be provided when detecting abnormal user conditions.
These examples are highlighting that the Analytical module is playing a very
important role in our research and the derived value-added services are forming
the base for a visionary Personal Assistant application. Naturally, we need to find
solutions for storing and analyzing this huge amount of data but the previously
mentioned scalable architecture is full-filling these requirements.

3.2 Solving the Data Privacy Issues for Telemedicine

Available medical solutions are putting emphasis on data security and data privacy
[23] [24]. It is critical to handle the user’s data prudently in a secure manner. It is
common to grant security using secure channels during the communication
between the OTI hub and the end-users’ devices; and also between the OTI hub
and the industrial, integrated medical system.
There are various legal prerequisites and regulations in force to protect personal
data in different geographical regions. However, health-related data protection
rules are even stricter than common personal data protection rules.
The OTI hub communicates through secure channels with external environments
and healthcare devices. The recorded bio-sensory data is handled according to
predefined user’s rules. The data owner classifies the recorded data. External
systems can access the health-related data marked with the flag ‘accessible’
through the OTI hub. The data owner defines multiple rules for data accessibility.
The medical systems can identify the user with the medical identifier. This
identifier is issued by the users’ healthcare institution.
The identifier is the key connecting the OTI hub user-ID with the examined
patient in the medical system. The OTI hub does not require any other
identification information from the external medical system, as it works as a data
provider. In this sense the OTI hub does not handle sensitive personal information,
therefore, it meets the required privacy and security level.

– 176 –
Acta Polytechnica Hungarica Vol. 16, No. 2, 2019

The second method is when the OTI hub acts as a data consumer. In this case, the
health-related data produced by the IoT devices are forwarded to the hub system.
This forwarded health record holds sensitive personal information. Therefore, the
OTI hub system handles these measurement values as sensitive personal
information and these are handled according to the predefined user’s accessibility
rules.

3.3 Safety and Security for Medical IoT Equipment

The IoT revolution’s biggest challenge is data security [25]. IoT devices sense
multiple types of data and they share with external systems. Each type of captured
data should have its own security level. There is also non-sensitive information
transmitted by IoT devices, e.g. temperature or humidity. This kind of information
does not need to be handled protected. However, another type of information, like
GPS coordinates are sensitive. IoT devices do have generally applicable data
security features. They use multiple types of networks where different security
levels are required. The general rule is, that the aggregator system is always
responsible for ensuring the security of the received data [26].
The second data security challenge is trust. The external systems must use the
received information as reliable data received from a reliable source [27] [28].
Therefore, the consumer services use authentication and authorization. The most
important security challenges are shown in Figure 9:

Figure 9
IoT security risks classification for e-health

– 177 –
Á. Garai et al. Revolutionizing Healthcare with IoT and Cognitive, Cloud-based Telemedicine

3.4 Data Reliability for Cognitive Medical Systems

Beyond data security, the hospital information systems must be aware that the
measurement values recorded by consumer IoT smart devices are captured by
from healthcare’s point of view uncertified sensors. Therefore, these values must
be flagged with the estimated quality, and the estimation calculation must be
completed before these are fed into the corresponding industrial medical system
[29]. Alternatively, the healthcare systems evaluate the calculated measurement
quality and the values themselves accordingly.
The OTI hub flags every health-related data with the estimated quality. It stores
the accompanying metadata linked to the health record, e.g. the type of the used
sensor, sample rate, measurement error rate and delta comparison against the last
measurement cycle. The OTI hub provides the metadata to the measurement
values according to the specification in the data request.
The OTI hub also provides measurement statistics, e.g. real-time average. It assists
data series visualization for the patient and general practitioner. The statistics
service increases the measurement values’ level of reliability; however, it also
hides key values unveiling special disease types. The OTI hub supports
parametrization for statistics services. The following expression [Figure 10]
defines the applied real-time (moving) heart-rate average calculation in the OTI
hub:

Figure 10
The real-time heart-rate calculation formula

where n is the number of the values in the series and M is the total number of
healthcare records.
The OTI hub calculates real-time statistics for the captured health-related time
series. The statistics are provided beside the row values when the requesting
application asks for them. These calculated statistics values are not stored in the
Hub, but these are (re)calculated upon request.
Conclusions
Our proposed hybrid cloud architecture assures the essential scalability for the
OTI-Hub in order to bear with the necessarily robust transaction processing
capacity. The illustrated architectural topology and systems integration provides a
technological solution for the integration of bi-directional international body-
sensory, telemedicine, and classical healthcare data exchange.

– 178 –
Acta Polytechnica Hungarica Vol. 16, No. 2, 2019

We learned from the experiment that the biggest challenge is the integration of the
different data structures emitted by e-Health smart devices produced by alternative
manufacturers. The illustrated results offer some optimism; however, current
national healthcare data-related legal prerequisites need international
harmonization to reach the required breakthrough. The illustrated OTI-Hub
solution provides international e-Health data-exchange.
The IoT revolution dictates that industrial healthcare systems will deal with home-
use consumer smart devices equipped with multiple sensors. They are operating
multiple types of bio-sensors and provide health-related bio-sensory raw data.
These wearable devices provide valuable real-time information regarding their
user and their environment. The collected information requires data cleaning and
transformation.
These two steps signify the broken link in the integration of smart IoT devices in
the overall healthcare supply chain. This is the reason, why the IoT technology
still could not revolutionize the healthcare services domain. The next generation
IoT bio-sensory sensors promise increased reliability and accuracy. When their
precision reaches the critical threshold, then the spread of wearable IoT healthcare
devices will be unstoppable.
The second success factor will be the free share and circulation of primary
healthcare information. As people volunteer to share their medical raw
information unanimously just easy as clicking on the pop-up menu at their
smartphone app, new types of population-level disease follow-up and intervention
will come into reality. This will also open new horizons for the human medicine.
References
[1] Huang Y., Kammerdiner A. Reduction of service time variation in patient
visit groups using decision tree method for an effective scheduling,
International Journal of Healthcare Technology and Management, Vol. 14,
No. 1-2, 2013, pp. 3-21
[2] Kartsakli E., Antonopoulos A., Alonso L., Verikoukis C. A cloud-assisted
random linear coding medium access control protocol for healthcare
applications, Sensors, Special Issue on ‘Sensors Data Fusion for
Healthcare’, 2014, pp. 9628-9668
[3] Baranyi P., Csapo A., Sallai Gy. Cognitive Infocommunications
(CogInfoCom), Springer, 2015
[4] Baranyi P., Csapó Á. Definition and Synergies of Cognitive
Infocommunications, Acta Polytechnica Hungarica, Vol. 9, No. 1, 2012
[5] Carlisle, James H. (June 1976) "Evaluating the impact of office automation
on top management communication". Proceedings of the June 7-10, 1976,
National Computer Conference and Exposition. pp. 611-616
[6] www.coginfocom.hu (last visited on 10.6.2018)

– 179 –
Á. Garai et al. Revolutionizing Healthcare with IoT and Cognitive, Cloud-based Telemedicine

[7] Izsó L. The significance of cognitive infocommunications in developing

assistive technologies for people with non-standard cognitive
characteristics: CogInfoCom for people with nonstandard cognitive
characteristics, in Cognitive Infocommunications (CogInfoCom), 6 th IEEE
International Conference on, Győr, 2015
[8] Vagner A. Cognitive Infocommunication for Monitoring and Improving
Well-being of People, 8th IEEE International Conference on Cognitive
Infocommunications, Debrecen, 2017
[9] Magnusdottir E. H., Johannsdottir K. R, Bean C., Olafsson B., Gudnason J.
Cognitive workload classification using cardiovascular measures and
dynamic features, 8th IEEE International Conference on Cognitive
Infocommunications, Debrecen, 2017
[10] Marciniak R. Role of new IT solutions in the future of shared service
model. Pollack Periodica, Vol. 8, No. 2, 2013, pp. 187-194
[11] Matusitz, Jonathan, & Breen, Gerald Mark (2007) Telemedicine: Its Effects
on Health Communication. Health Communication, 21(1), 73-83
[12] Bashshur R. L., Shannon G. W. History of telemedicine: Evolution,
context, and transformation, New Rochelle, NY, Mary Ann Liebert, 2009
[13] Fong B., Fong A. C. M., Li C. K. Telemedicine technologies: Information
technologies in medicine and telehealth, Chichester, Wiley, 2011
[14] Neelakantan P., Reddy A. R. M. Decentralized load balancing in distributed
systems, Pollack Periodica, Vol. 9, No. 2, 2014, pp. 15-28
[15] Garai Á., Péntek I. Adaptive services with cloud architecture for
telemedicine, 6th IEEE Conference on Cognitive Infocommunications,
Győr, Hungary, 19-21 October, 2015, pp. 369-374
[16] Adamkó A., Garai Á., Péntek I. Common open telemedicine hub and
interface standard recommendation, The 10th Jubilee Conference of PhD
Students in Computer Science, Szeged, Hungary, 27-29 June, 2016, pp. 24-
25
[17] Adamkó A., Garai Á., Péntek I. Common open telemedicine hub and
interface standard recommendation, The 10th Jubilee Conference of PhD
Students in Computer Science, Szeged, Hungary, 27-29 June 2016, pp. 24-
25 [11] Adenuga O. A., Kekwaletswe R. M., Coleman A. eHealth
integration and interoperability issues: towards a solution through
enterprise architecture, Health Information Science and Systems, Vol. 3,
No. 1, 2015, pp. 1-8
[18] ISO/IEC 7498-1, 1994 Information technology, Open systems
interconnection, Basic reference model, The basic model (OSI-Model),
International Organization for Standardization (ISO), Web, 6 June 2016

– 180 –
Acta Polytechnica Hungarica Vol. 16, No. 2, 2019

[19] Garai L. Improving HPLC analysis of vitamin A and E: Use of statistical

experimental design, International Conference on Computational Science,
Zürich, Switzerland, 12-14 June, 2017, pp. 1500-1511
[20] Varshney U. Pervasive healthcare and wireless health monitoring, Mobile
Networks and Applications, Vol. 12, No. 2, June 2007, pp. 113-127
[21] Martinez L., Gomez C. Telemedicine in the 21st Century, Applied
biostatistics for the health sciences, Nova Science Publishers, NY, 2008
[22] Poon C. Y., Hung K. F. mHealth: Intelligent closed-loop solutions for
personalized healthcare, in Telehealth and mobile health, Eren H., Webster
J. G. (Eds), CRC Press, 2015, pp. 145-160
[23] Garai L. Improving HPLC Analysis of Vitamin A and E: Use of Statistical
Experimental Design, International Conference on Computational Science,
Zürich, Switzerland, 12-14 June, 2017, pp. 1500-1511
[24] Zarour K (2016) Proposed technical architectural framework supporting
heterogeneous applications in a hospital. International Journal of Electronic
Healthcare 9:19-41
[25] Wootton R (1998) Telemedicine in the National Health Service. J. R. Soc.
Med. 91: 289-292
[26] Wootton R (2012) Twenty years of telemedicine in chronic disease
management an evidence synthesis. J. Telemed. Telecare. 18: 211220. doi:
10.1258/jtt.2012.120219
[27] Vigneshvar S, Sudhakumari C C, Senthilkumaran B, Prakash H (2016)
Recent Advances in Biosensor Technology for Potential Applications An
Overview Front. Bioeng. Biotechnol. 4:11. doi: 10.3389/fbioe.2016.00011
[28] Varshney, U (2007) Pervasive healthcare and wireless health monitoring.
Mobile Networks and Applications 12: 2-3
[29] Rossi R J (2010) Applied Biostatistics for the Health Sciences. Wiley

– 181 –