1

INTRODUCTION
 we introduce a framework for secure HISs based on big data analytics in mobile
cloud computing environments. This framework provides a high level of integration,
interoperability, and sharing of EHRs among HPs, patients, and practitioners. It
integrates distinct EMRs of a patient from different HPs distracted among different
cities, states, and regions and store them in the Cloud data storage areas. Mobile Cloud
computing technology [57-61] provides a fast Internet access, and provision of EHRs
from anywhere and at any time with high availability. Due to the massive size of
healthcare data, the exponential increase in the speed in which this data is generated
and the complexity of healthcare data type, the proposed framework employs big data
analytics to find useful insights that help practitioners take critical decisions in the
right time. Our proposed framework applies a set of security constraints and access
control that guarantee integrity, confidentiality, and privacy of medical data.
Authenticated healthcare providers, practitioners, and patients are authorized by the
Cloud Service Providers (CSPs) at different levels of privilege and permissions to
securely access EHRs and retrieve patients’ information. We believe that the proposed
framework paves the way for a new generation of lower cost, more efficient healthcare
systems.
 2.
EXISTING SYSTEM
Healthcare Information Technology (HIT) has created the ability to electronically
store, maintain, and move data across the world in a matter of seconds and has the
potential to provide healthcare with tremendous increasing productivity and quality
of services. It permits each provider to have his own database of patients'
Electronic Medical Records (EMRs). One problem in today's EMR systems is that
they are highly centralized, each Healthcare Provider (HP) has its own local EMR
system. This makes health information for any patient dispersed among different
HPs and, therefore, its retrieval will be a challenge.
The revolution in healthcare data size is another problem in today's Healthcare
Information Systems (HISs). This revolution is not just about the massive size of
healthcare data, but we also witness an exponential increase in the speed in which
this data is generated and a complex varieties of data type (i.e., structured, semi
structured, unstructured). The Development of new technologies such as capturing
devices, sensors, and mobile applications is a major source of healthcare data.
Additional sources are added every day; patient social network communications in
digital forms are increasing, collection of genomic information became cheaper
and more medical knowledge/discoveries are being accumulated. Such big
healthcare data is difficult to process or analyze using common database
management tools. Obviously, capturing, storing, searching, and analyzing
healthcare big data to find useful insights will improve the outcomes of the
healthcare systems through smarter decisions and will lower healthcare cost as
well, however, it requires efficient analytical algorithms and powerful computing
environments. Finally, the increased reliance on networked healthcare data brings
new challenges to securing medical records in EHR systems. Authenticating
individuals and authorizing global secure access to patients’ records are vital
security requirements. Physical face-to-face methods of identifying and
authenticating patients and providers no longer apply; methods of electronic
identification and authentication are required. Moreover, electronic records are
susceptible to inappropriate access, compromised data integrity, or widespread
unauthorized distribution. New security measures are needed to secure patients’
records on HISs.
 3
LITERATURE REVIEW
 4
PROPOSED SYSTEM
Due to the massive size of healthcare data, the exponential increase in the speed in
which this data is generated and the complexity of healthcare data type, the
proposed framework employs big data analytics to find useful insights that help
practitioners take critical decisions in the right time. Our proposed framework
applies a set of security constraints and access control that guarantee integrity,
confidentiality, and privacy of medical data. Authenticated healthcare providers,
practitioners, and patients are authorized by the Cloud Service Providers (CSPs) at
different levels of privilege and permissions to securely access EHRs and retrieve
patients’ information. We believe that the proposed framework paves the way for
a new generation of lower cost, more efficient healthcare systems.

4.1 INTEGRATING ELECTRONIC MEDICAL RECORDS

Today, there is a widespread use of EMRs or EHRs systems. These terms are used
interchangeably by many in both healthcare industry and health science literature;
however, they describe completely different concepts according to Health
Information and Management System Society (HIMSS) Analytics [6, 7]. An EMR
is a formatted record of patient health information owned by a hospital or any
healthcare provider. The data in the EMR system is the legal record of what
happened to the patient during his encounter at the CDO and is owned and
managed by one CDO [6]. A significant disadvantage to EMRs is that they cannot
be easily and accurately electronically shared and distributed.

HIMSS defined the EHR as “a longitudinal electronic record of patient health

information generated by one or more encounters in any care delivery setting.
Included in this information are patient demographics, progress notes, problems,
medications, vital signs, past medical history, immunizations, laboratory data, and
radiology reports. The EHR automates and streamlines the clinician's workflow”
[7]. The definition of EHR system is “the set of components that form the
mechanism by which EHRs are created, used, stored, and retrieved” [8, 9]. EHRs
are typically composed of a subset of EMRs maintained by each CDO and is
assigned to a patient. In [10] Zhang and Liu compared between EMR and EHR
from different perspectives. This comparison is shown in Table 1.

Table 1: A comparison between EMRs and EHRs [10]

An EHR provide a mean of communication among clinicians contributing to the

patient’s care by sharing health information between different EMR systems in
different CDOs. The challenge here is how to integrate distinct EMRs scattered in
different CDOs in different cities, states, and regions to create unified EHRs. In
our framework, the Cloud provides a solution for this problem by networking the
CDOs and collecting patients’ EMRs from the interconnected CDOs. It is also
desirable to have a unified standard format for EHRs to support interoperability and
data sharing.
4.2 HEALTHCARE MOBILE CLOUD COMPUTING

Mobile devices have started becoming abundant in many healthcare applications.

The reason for the increasing usage of mobile computing is its ability to provide a
tool to the user when and where it is needed regardless of user movement, hence,
supporting location independence. However, it suffers some inherent problems
such as limited scalability of users and devices, limited availability of software
applications, resources scarceness in embedded gadgets, frequent disconnection
and finite energy of mobile devices. In healthcare sector, the effect of these
limitations is magnified due to the massive size, excessive complexity, and rapid
generation of healthcare data. As a result, a wide range of healthcare
applications are difficult to run in mobile devices such as radiology processing
and recognition, patients' social networking data management, genomic
information and sensor data applications. In addition, progress in interoperation
and sharing data among different EMR systems has been extremely slow due to the
high cost and poor usability. What is needed is an environment that is capable of
capturing, storing, searching, sharing and analyzing healthcare big data efficiently
to provide right intervention to the right patient at the right time.

Cloud computing [15-29] provides an attractive IT platform to cut down the cost of
EHR systems in terms of both ownership and IT maintenance burdens for many
medical practices. Cloud environment can host EHRs and allows sharing,
interoperability, high availability, and fast accessibility of healthcare data. Cloud
Computing (CC) platforms possess the ability to overcome the discrepancies of
mobile computing with their scalable, highly available and resource pooling
computing resources. The main idea behind CC is to offload data and computation
to a remote resource provider (i.e., the Internet) which offers broad network access.
The concept of offloading data and computations in the Cloud, is used to address
the inherent problems in mobile computing by using resource providers (i.e., cloud
resources) other than the embedded devices themselves to host the execution of
user applications and store users’ data. The problems are addressed as follows: 1)
by exploiting the computing and storage capabilities (resource pooling) of the
cloud, mobile intensive applications can be executed on low resource and limited
energy mobile devices,2)the broad network access of the cloud overcomes the
limited availability and frequent disconnection problems since cloud resources are
available in anywhere and at any time, 3) the infrastructure of cloud computing is
very scalable, cloud providers can add new nodes and servers to cloud with minor
modifications to cloud infrastructure, therefore; more services can be added to the
cloud, this allows more mobile users to be served and more portable devices to be
connected .
Mobile cloud computing technology will contribute to healthcare sectors in the
following ways:

 Integrating healthcare data dispersed among different healthcare

organizations and social media.
 Providing a shared pool of computing resources that is capable of storing
and analyzing healthcare big data efficiently to take smarter decisions at the
right time.
 Providing dynamic provision of reconfigurable computing resources which
 can be scaled up and down upon user demand. This will help reduce the
cost of cloud-based healthcare systems.
 Improving user and device scalability and data availability and accessibility
in healthcare systems.

Healthcare cloud can provide two deployment Models. These models describe the
level of data sharing among different CDOs, patients, and practitioners when
using the cloud. These models are:

 Private healthcare cloud: The cloud infrastructure is owned solely by a

CDO. It may be managed by the CDO or a CSP and may exist on or off
premise. The CSP provides the same capability in terms of security and
privacy protection as those in the EMR system running by a CDO.
 Community healthcare cloud: The cloud infrastructure is shared by several
CDOs and supports a specific community that has shared concerns (e.g.,
mission, security, requirements, and policy). It is managed by a CSP or by
the CDOs and may exist on or off premise.

Healthcare services provided by healthcare clouds are classified as follows:

 Software as a Service (SaaS): Healthcare applications, such as EHRs, are

hosted as a service and provided to practitioners, healthcare providers, and
patients across the Internet, with no need to install and run on their own
computer. Hosted applications can be accessed through web browsers from
various client devices such as laptops, PDAs and cell phones. Multiple users
can share the applications and avoid the trouble associated with software
maintenance, upgrading and the need for additional licenses.
 Platform as a Service (PaaS): PaaS is a development platform that allows
healthcare providers to not only deploy but also design, model, develop and
test healthcare applications directly on the Cloud. It supports work in groups
on collaborative healthcare projects where project team members are
geographically distributed. This requires PaaS to provide development
infrastructure including tools and programming languages.
 Infrastructure as a Service (IaaS): healthcare providers can directly use
independent virtual machines that isolate the underlying physical hardware
of the cloud from them. They can dynamically provision/release virtual
computing resources based on their increasing/decreasing resource demand.

4.3 HEALTHCARE BIG DATA

Improving healthcare services and reducing medical cost are the ultimate goals of nations
worldwide. However, the revolution of healthcare data size remains an obstacle that
hinder achieve this goal. In 2012, worldwide digital healthcare data was estimated to be
equal to 500 petabytes and is expected to reach 25,000 petabytes in 2020 [62].
Obviously, capturing, storing, searching, sharing and analyzing such big data to find
useful insights will improve the outcomes of the healthcare systems through smarter
decisions and will lower healthcare cost as well, however, traditional database
management tools are no longer suitable to process these data. New efficient algorithms
are required to accomplish this task. For example, in the United States, more than 71
million individuals are admitted to hospitals each year, according to the latest survey
from the American Hospital Association. Studies have concluded that in 2006 well over
$30 billion was spent on unnecessary hospital admissions. The Heritage Provider
Network (HPN) arises the question: "Can we identify earlier those most at risk and
ensure they get the treatment they need?" and it believes that the answer is "yes". To
achieve its goal of developing a breakthrough algorithm that uses available patient data
to predict and prevent unnecessary hospitalizations, HPN sponsored the Heritage Health
$3 Million Prize Competition. Winning solutions will use a combination of several
predictive models and the winning team will create an algorithm that predicts how many
days a patient will spend in a hospital in the next year. Once known, HPs can develop
new care plans and strategies to reach patients before emergencies occur, thereby
reducing the number of unnecessary hospitalizations. This will result in increasing the
health of patients while decreasing the cost of care.

Big data analytics is motivated in healthcare through the following aspects:

 Healthcare data is now growing very rapidly in terms of size, complexity,

and speed of generation and traditional database and data mining techniques
are no longer efficient in storing, processing and analyzing these data. New
innovative tools are needed in order to handle these data within a tolerable
elapsed time.
 The patient’s behavioral data is captured through several sensors; patients'
various social interactions and communications.
 The standard medical practice is now moving from relatively ad-hoc and
subjective decision making to evidence-based healthcare.
 Inferring knowledge from complex heterogeneous patient sources and
leveraging the patient/data correlations in longitudinal records.
 Understanding unstructured clinical notes in the right context.
 Efficiently handling large volumes of medical imaging data and extracting
potentially useful information and biomarkers.
 Analyzing genomic data is a computationally intensive task and combining
with standard clinical data adds additional layers of complexity.

4.4 SECURITY ISSUES

In cloud-based HIS, security should be the top priority from day one. Patients’ data
should be protected with comprehensive physical security, data encryption, user
authentication, and application security as well as the latest standard-setting security
practices and certifications, and secure point-to-point data replication for data backup.
These security issues have been extensively investigated for cloud computing in general.
A major challenge to healthcare cloud is the security threats including tampering or
leakage of sensitive patient’s data on the cloud, loss of privacy of patient’s information,
and the unauthorized use of this information. Hence, a number of security requirements
should be satisfied by healthcare cloud computing systems. The main security and
privacy requirements for healthcare clouds are discussed below

 Authentication: in a healthcare cloud, both healthcare information offered

by CSPs and identities of users (HPs, practitioners, and patients) should be
verified at the entry of every access using user names and passwords
assigned to users by CSPs.
 Authorization: is an essential security requirement that is used to control
access priorities, permissions and resource ownerships of the users on the
cloud. Each cloud user is granted privileges based on his account. Patient
can allow or deny sharing their information with other healthcare
practitioners or CDOs. To implement patient consent in a healthcare
system, patient may grant rights to users on the basis of a role or attributes
held by the respective user.
 Non-repudiation: implies that one party of a transaction cannot deny having
received a transaction nor can the other party deny having sent a transaction.
In a healthcare system, technologies such as digital signatures, timestamps,
confirmation receipt, and encryption can be used to establish authenticity
and non-repudiation for patients, CDOs, and practitioners.
 Integrity and Confidentiality: integrity means preserving the accuracy and
consistency of data. In the healthcare system, it refers to the fact that EHRs
have not been tampered by unauthorized use. Confidentiality is defined by
the International Organization for Standardization (ISO) in ISO-17799 as
"ensuring that information is accessible only to those authorized to have
access". Confidentiality and integrity can be achieved by access control and
encryption techniques in EHR systems.
 Availability: For any EHR system to serve its purpose, the information must
be available when it is needed. High availability systems aim to remain
available at all times, preventing service disruptions due to power outages,
hardware failures, and system upgrades. Ensuring availability also involves
preventing denial-of-service (DoS) attacks.
4.5 THE PROPOSED FRAMEWORK

One of the most important challenges in developing HISs is to provide

mechanisms to analyze and obtain patients’ information from multiple EMR/EHR
repositories accurately, securely and fast. In the previous sections, we discussed
the requirements for a new generation of secure HIS in a cloud computing
environment based on big data analytics. In this section, we propose a framework
for developing such systems. Figure 1 shows the proposed framework which
consists of the following main components:

The Cloud: the first component is the cloud environment itself that hosts patient
information and provides different types of service to authorized users. The cloud
can be used as private or community environment according to the required level
of data sharing. It makes these records ubiquitously accessible for patients, HPs,
and practitioners. This component was discussed in detail in section 3.

The EHR: the second component is the EHR where distinct patient records are
 integrated from different units (pharmacy, registration, Lab,...) in many CDOs
distracted in a city, state, or region and stored in the cloud. One critical issue here
is the ability to link patients to their records without errors. This is achieved by the
usage of a hybrid linking approach that combine statistical matching and Unique
Patient Identifier (UPI) approach [1, 12, 55, 58]. The statistical algorithm is used
first to retrieve patients’ records from EMRs in different interconnected CDOs.
The records are integrated and stored to form EHRs. UPI for each patient can then
be used as a primary key to filter patient’s information in EHRs and eliminate
errors occur during statistical matching.

The Security Model: the third component is the one that guarantees protecting
security and privacy in HIS. Encryption algorithms such as AES [2] and RC4 [3]
and authentication techniques such as One Time Password (OTP) [4] and Two
Factor Authentication (2FA) [5] can be applied to protect EHR from tampering
and unauthorized access. The healthcare authority can now setup groups of
clinician authorized to access patients’ EHRs. It is also responsible for defining
privileges for each group according to their specialization, disease type and
complexity, and the role they play in treatment. The group may contain specialists,
doctors, nurses, lab technicians, pharmacists, or other practitioners. Group
members can be from different hospitals, cities, or regions; hence, the cloud
facilitates sharing of medical records among group members to give perfect
consultation. The healthcare authority assigns to each group digital signatures to
sign the medical certificates provided by them. Signed medical certificates are
available to the patient and are stored in his/her EHRs. The patient can
authenticate diagnosis and consultations through these digitally signed certificates.
For example, allowing specific group to access the medical record for patient-A,
his family medical records, give the appropriate treatment decision, medications,
and report the status of his health. Each member in one group may have different
privileges according to his job and profession. On other hand, the patient is
allowed to see only his medical records, access the results of medical tests,
validate the integrity of his records, and verify the authenticity of medical
certificate given by a group with a digital signature. The researchers take the
statistical information without knowing the full information about the patients.
The health insurance companies may verify the integrity of treatment decisions to
their customers.

The Big Data Analytics: this component can deploy different tools that analyze multi-
terabyte EHR databases in the cloud and give real-time insights about the data. CSPs
offer many big data analytics tools such as:
 Google Big Query: uses Google’s cloud infrastructure to store and query
massive datasets in few seconds by enabling super-fast SQL like queries.
 MapReduce: is a software tool that enables cloud users to write application
to process in parallel a vast amount of data on large clusters. It is
divided into two parts: Map, a function that splits work to different nodes
in the distributed cluster, and Reduce, another function that collects the
work and resolves the results into a single value.

The CDOs: this component includes different healthcare organizations distributed

across the country. Each organization consists of several clinical and
administrative departments such as Radiology, Lab, Pharmacy, Billing, etc. These
departments are integrated via the EHR unit in the cloud which enable data sharing
and interoperability. Communications between different CDOs departments and
the EHR is made possible using HL7 protocol which is a structured standard that is
used as a means of exchanging information between healthcare applications. It
defines a format for the transmission of health-related information [63].

The proposed framework for a new generation HISs aims to achieve the following
goals:

 Provide healthcare services of high quality and low cost to the patients
using a combination of big data, cloud computing and mobile computing
technologies.
 Take advantage of the massive amounts of healthcare data and provide right
intervention to the right patient at the right time.
 Provide personalized healthcare to the patient.
 Protect the security and the privacy of healthcare data.
 Bridge big data, mobile-cloud computing, information security and medical
informatics communities to foster interdisciplinary works between them.

FIG. 1: A FRAMEWORK FOR EHR BASED ON MOBILE CLOUD COMPUTING AND BIG DATA ANALYTICS
 5.
ADVANTAGES

 High Quality and Low Cost.

 Right Intervention to the right patient at right time.
 Security and Privacy of healthcare data.
5
CONCLUSION
6
FUTURE WORK
 6
REFERENCES
 Ahmed E Youssef and Manal Alage “ A Framework For Secure Cloud
Computing “ Department of Information Systems, King Saud
University Riyadh, 11543,KSA in 2012.

 Rashid Mahmood, Houbing song “ Mobile Cloud Computing Model

and Big Data Analysis For Healthcare application “ Department of
Electrical and Computer Engineering, West Virginia University, WV
26506,USA in 2013.

 Tae Soongh Kim, Kaand Ho Park, Sang Hoon Yi, Heels Check Kim “
Big Data Framework For U- Healthcare System “ Department of
computer Education, Solla University in 2014.

 Benjamin Fabian, Tatiana Ermakova, Philipp Junghanns “Collaborative

And Secure Sharing Of Healthcare Data in Multi- Clouds” Technical
University of Berlin, Information and Communication Management,
Strassedes 17 juni 135,10623 Berlin Germany, in 2014.

 Yin Zhang, Mohammad Meredith Hassan”Health CPS-Healthcare

Cyber-Physical System “assisted by Cloud and Big data in 2015.