Privacy-Preserving Patient-Centric Clinical Decision Support System on Naive Bayesian

Classification

Abstract

Clinical decision support system, which uses advanced data mining techniques to help clinician
make proper decisions, has received considerable attention recently. The advantages of clinical
decision support system include not only improving diagnosis accuracy but also reducing
diagnosis time. Specifically, with large amounts of clinical data generated every day, naive
Bayesian classification can be utilized to excavate valuable information to improve clinical
decision support system. Although clinical decision support system is quite promising, the
flourish of the system still faces many challenges including information security and privacy
concerns. In this paper, we propose a new privacy-preserving patient-centric clinical decision
support system, which helps clinician complementary to diagnose the risk of patients’ disease in
a privacy-preserving way. In the proposed system, the past patients’ historical data are stored in
cloud and can be used to train the naiıve Bayesian classifier without leaking any individual
patient medical data, and then the trained classifier can be applied to compute the disease risk for
new coming patients and also allow these patients to retrieve the top-k disease names according
to their own preferences.
INTRODUCTION

Healthcare industry, extensively distributed in the global scope to provide health services for
patients, has never faced such a massive amounts of electronic data or experienced such a sharp
growth rate of data today. As stated by Institute for Health Technology Transformation (iHT2 ),
U.S. health care data alone reached 150 exabytes (1018 bytes) in 2011 and would soon reach
zettabyte (1021 bytes) scale and even yottabytes (1024 bytes) in the future. However, if no
appropriate technique is developed to find great potential economic values from big healthcare
data, these data might not only become meaningless but also requires a large amount of space to
store and manage. Over the past two decades, the miraculous evolution of data mining technique
has imposed a major impact on the revolution of human’s lifestyle by predicting behaviors and
future trends on everything which can convert stored data into meaningful information. These
techniques are well suitable for providing decision support in the healthcare setting. To speed up
the diagnosis time and improve the diagnosis accuracy, a new system in healthcare industry
should be workable to provide a much cheaper and faster way for diagnosis. Clinical Decision
Support System (CDSS), with various data mining techniques being applied to assist physicians
in diagnosing patient diseases with similar symptoms, has received a great attention recently.
Naïve Bayesian classifier, one of the popular machine learning tools, has been widely used
recently to predict various diseases in CDSS. Despite its simplicity, it is more appropriate for
medical diagnosis in healthcare than some sophisticated techniques.

The e-Health cloud can be regarded as a standard platform that offers standardized services to
manage large volumes of health-data. The e-Health cloud ensures the service provision for
storage and processing of different types of health records that are originated and utilized by
multiple providers and other participating entities, such as pharmacies, laboratories, and
insurance providers. Typically the health records in an e-Health system include the EMRs, the
EHRs, and the PHRs. Each of the aforementioned type of health records are the electronic
versions of patient health information. However, there are certain differences that are should be
understood. The EMR is the electronic version of a patient’s health information that is created,
used, and maintained by the healthcare providers or care delivery organizations. The EMRs
contain information about the diagnosis obtained through the clinical decision support system,
clinical notes, and medication. The EHRs on the other hand present a broader view of the
patients’ health information. A subset of the information contained in the EMRs is also present in
the EHRs. However, the EHRs are shared for the purpose of consultation and treatment among
multiple healthcare providers belonging to different care delivery organizations. The PHRs are
the health records that are managed by the patients themselves and comprise of the information
instigated from diverse sources. The typical information that a PHR may contain includes,
treatments and diagnosis, surgeries, laboratory reports, insurance claims data, and patients’
personal notes and wellness charts to keep track of the health themselves.

Healthcare information systems are designed today for the convenience of the user who obtains
its benefits efficiently. Accessibility and availability are the criteria on which an application is
designed for its success in the IT market. The data has to be accessible from anywhere in the
world at any time and the easy transaction of data to the mobile devices. Transparency in the data
storage, transaction and maintenance can be achieved through the cloud computing concept. In
the earlier days, physical storage of data and its maintenance was a major problem to build such
medical applications. With the advancement of technology, cloud computing enables for the
convenient storage of user data, through sharing of resources and framework. Through cloud
computing, healthcare services can be provided through the cloud network and operations can be
performed without any delay. Mobile devices today, are used in abundance by the common man.
As these devices are equipped with robust features, it is necessary to make them a vital source
for providing information. By integrating the cloud computing and a mobile device the
healthcare services can be easily utilised and operated by the patient. The technology can be
effectively applied for maintaining medical image data in a cloud computing environment and
mobile device supporting Android OS. The paper describes implementation details of a Hospital
Management System (HMS) and the results of the application. With the feasibility of the medical
data management in such an environment established, the paper describes some challenges and
future work planned.

Android is a software stack for mobile devices that includes an operating system, middleware
and key applications. It allows developers to write managed code in the Java language,
controlling the device via Google-developed Java libraries. Applications written in C and other
languages can be compiled to ARM native code and run, but this development path is not
officially supported by Google. Cloud Computing is a model for enabling convenient, ondemand
network access to a shared pool of configurable computing resources such as networks, servers,
storage, applications, and services that can be rapidly provisioned and released with minimal
management effort or service provider interaction. This cloud model promotes availability and is
composed of essential characteristics, deployment models, and various service models. A VPN is
a private network that uses a public network to connect remote sites or users together. By using a
VPN, businesses ensure security anyone intercepting the encrypted data can't read it. An Android
hospital management application system will be developed for Cloud Server within the Virtual
Private Network of public network. In which establishes the flow of data between cloud server
and android application securely.

Electronic health records (EHR) and electronic billing systems have been proposed as
mechanisms to curb the rising costs of healthcare and also helps to detect the fraudulent practices
in the traditional healthcare system[1]. Many healthcare professionals, hospitals and insurance
agencies maintains the paper-based records, billing of the patients which is been converted later
into computer-based billing and records which can be abused, modified or lost for malpractice
done by frauds either for money or grudge. Hence the personal information of the patients is
revealed, bogus information are entered and misused in traditional Healthcare system. Moreover
Traditional healthcare system depends on the centralized server which is unreliable, insecure in
accessing, storing medical data regardless of time, cost and location. Hence it is more complex
and lack privacy and cost involved in integrating medical information is expensive. Given this
scenario, Electronic Health Records (EHR) and Electronic Medical Billing (EMB) have been
proposed as a mechanism which reduces healthcare disparities and ensures adequate privacy and
security. One potential solution for addressing all aforementioned issues is the introduction of
Cloud Computing concept in electronic healthcare systems. This mechanism pursued the idea of
using open-source public cloud computing Technologies and mobile plus cloud paradigm [2] to
build an affordable, secure and scalable platform that supports billing as well as EHR operations.
We call this platform as MedBook and in this paper we present the proposed architecture and
implementation status of this system. MedBook is a cloud solution that provides patients,
healthcare professionals/providers and healthcare payers a platform for exchange of electronic
information about billing activities, benefit inquiries and EHR operations such as insert delete
and update record using open source cloud services and Android operating system(OS).
MedBook is Software–as-a-Service (SaaS) platform built on top of open source public cloud
technologies and running on the top of an Infrastructure-as-a Service (IaaS) platform. Generally
the server applications are implemented as a collection of web services and web applications
using MySQL, Tomcat 6or7 server, Apache web server. All the web services run on virtual
machines powered by Windows XP or Ubuntu Our project Advanced Hospital Management
System includes registration of patients, storing their details into the system and also
computerized billing in the pharmacy, and labs. Our software has the facility to give a unique id
for every patient and stores the details of every patient and the staff automatically. It includes a
search facility to know the current status of each room. User can search availability of a doctor
and the details of a patient using the id. The Advanced Hospital Management System can be
entered using a username and password. It is accessible either by an administrator or receptionist.
Only they can add data into the database. The data can be retrieved easily. The interface is very
user-friendly. The data are well protected for personal use and makes the data processing very
fast Before computerized Hospital Management System came into practice, it was difficult to
keep proper records of the daily activities of hospitals, patient information, maintenance schedule
of equipments in the hospital, and how funds are being allocated and used. This resulted in waste
of money, time and manpower. Hospital Management System is an information management
system designed to help manage the various aspects of a hospital (administrative, clinical and
financial). It helps in monitoring and controlling the hospital’s daily transactions, as well as the
hospital’s performance. It also helps to address the critical requirements of the hospital. Hospital
Management System enables access to the right information and automation of complex task,
thereby allowing staff to spend more time caring for patients. Hospital Management System is
custom built to meet the specific requirements of the medium and large size hospitals across the
globe.

Management has been defined as the process, comprised of social and technical functions and
activities, occurring within organizations for the purpose of accomplishing predetermined
objectives through humans and other resources (Longest, Rakich & Darr, 2000). Healthcare
quality and patient safety are the common mantra of all primary and secondary health care
providers. In hospitals, over the years, a variety of models and schemes for hospital interventions
and development have been deployed (Friesner, 2009). Hospital Management System provides
the benefits of streamlined operations, enhanced administration & control, superior patient care,
strict cost control and improved profitability. There are different modules in the process of
Hospital Management System. These include:

 Patient management

 Services management

 Appointment scheduling

 Store management

 Pharmacy management
OBJECTIVE OF THE STUDY

To identify the key performance indicators and standards of CloudE - Hospital Management (E –
HMS) & Hospital Information Systems (HIS).

To identify the key components of CloudE - Hospital Management solutions.

The Hospital management system software is user-friendly software. The main objectives of the
system is which shows and helps you to collect most of the information about Hospitality and
Medical Services The system

is very simple in design and to implement. The system requires very low system resources and
the system will work in almost all configurations. The main objectives of the proposed system
can be enumerated as follows:

 Patients are easily allocated to the doctors.

 Doctors Search is possible.

 Today’s patient list help doctors to search their patients

NEED FOR CLOUD E – HOSPITAL MANAGEMENT & HIS

Hospital Services are needed on an emergency and daily basis and HIS plays a crucial role.
Hospital services are customer and society sensitive and the quality of HIS and service of
hospital staff needs to be precise and of highest standards. Today‘s hi-tech Hospital services are
predominantly provided by private players in the market at increased costs despite low cost
competition by public sector hospitals. OECD report (2012) finds that attempts to control costs
by regulatory means, such as reducing fees paid to healthcare providers and rationing user
access, have typically only been temporarily successful. E-Hospital Management System
provides the benefits of streamlined operations, enhanced administration & control, superior
patient care, strict cost control and improved profitability. Due to business and legal demands—
like the Healthcare Insurance Portability and Accountability Act (HIPAA) of the United States as
a Global norm —healthcare organizations are fully realizing the urgency to integrate their
businesses. Unfortunately, most of the health information systems are still proprietary and often
only serve one specific department within a healthcare business. This represents a significant
obstacle to business integration.

• The Software is for the automation of Hospital Management.

• It maintains two levels of users:-

Administrator Level User Level

• The Software includes:-

 Maintaining Patient details.

 Providing Prescription,
 Precautions and Diet advice.
 Providing and maintaining all kinds of tests for a patient.
 Billing and Report generation.
SUMMARY

A Hospital is a place where Patients come up for general diseases. Hospitals provide facilities
like:-

 Consultation by Doctors on Diseases.

 Diagnosis for diseases.
 Providing treatment facility.
 Facility for admitting Patients (providing beds, nursing, medicines etc.)
 Immunization for Patients/Children.

Various operational works that are done in a Hospital are:-

 Recording information about the Patients that come.

 Generating bills.
 Recording information related to diagnosis given to Patients.
 Keeping record of the Immunization provided to children/patients.
 Keeping information about various diseases and medicines available to cure them.

These are the various jobs that need to be done in a Hospital by the operational staff and Doctors.
All these works are done on papers.

The work is done as follows:-

Information about Patients is done by just writing the Patients name, age and gender.

 Whenever the Patient comes up his information is stored freshly.

 Bills are generated by recording price for each facility provided to Patient on a separate
sheet and at last they all are summed up.
 Diagnosis information to patients is generally recorded on the document, which contains
Patient information.
 It is destroyed after some time period to decrease the paper load in the office.
 Immunization records of children are maintained in pre-formatted sheets, which are kept
in a file.
 Information about various diseases is not kept as any document.
  Doctors themselves do this job by remembering various medicines.

All this work is done manually by the receptionist and other operational staff and lot of papers
are needed to be handled and taken care of. Doctors have to remember various medicines
available for diagnosis and sometimes miss better alternatives as they can’t remember them at
that time.
EXISTING SYSTEM

Over the past two decades, the miraculous evolution of data mining technique has imposed a
major impact on the revolution of human’s lifestyle by predicting behaviors and future trends on
everything which can convert stored data into meaningful information. These techniques are well
suitable for providing decision support in the healthcare setting. To speed up the diagnosis time
and improve the diagnosis accuracy, a new system in healthcare industry should be workable to
provide a much cheaper and faster way for diagnosis. Clinical Decision Support System (CDSS),
with various data mining techniques being applied to assist physicians in diagnosing patient
diseases with similar symptoms, has received a great attention recently. Naive Bayesian
classifier, one of the popular machine learning tools, has been widely used recently to predict
various diseases in CDSS. Despite its simplicity, it is more appropriate for medical diagnosis in
healthcare than some sophisticated techniques.

Existing system refers to the system that is being followed till now. Presently all the hospital
functionalities are done manually. That is if a patient want to consult a doctor he can visit their
till his chance called. This is make the person very difficult. Outpatient and In_Patient tickets are
distributed directly. The main disadvantage is time consuming.

According to NIST “ Cloud computing is a pay per use model for enabling convenient, on
demand network access to a shared pool of configurable computing resources (e.g., networks,
servers, storage, applications, and services) that can be rapidly provisioned and released with
minimal management effort or service provider interaction[6]. Cloud Computing provides the
following Key Characteristics:

(a)Broad network access Capabilities are available over the network and accessed through
standard mechanisms that promote use by heterogeneous thin or thick client platforms (e.g.,
mobile phones, laptops, and PDAs).

(b)Resource pooling The provider’s computing resources is pooled to serve multiple consumers
using a multitenant model; Multi-tenancy enables sharing of resources and costs across a large
pool of users thus allowing for:
 Centralization of infrastructure in locations with lower costs (such as real estate, electricity,
etc.)

 Peak-load capacity increases (users need not engineer for highest possible load-levels)

 Utilisation and efficiency improvements for systems that are often only 10–20% utilised.
Examples of resources include storage, processing, memory, network bandwidth, and virtual
machines.

(c)Application programming interface (API) accessibility to software that enables machines to

interact with cloud software in the same way the user interface facilitates interaction between
humans and computers. Cloud computing systems typically use REST-based APIs.

(d)Cost is claimed to be reduced when using cloud infrastructure.

(e)Reliability is improved if multiple redundant sites are used, which makes well-designed cloud
computing suitable for business continuity and disaster recovery.

(f)Security could improve due to centralization of data, increased security-focused resources,

etc., but concerns can persist about loss of control over certain sensitive data, and the lack of
security for stored kernel. Cloud computing has three service models to deliver various services
namely, Software as a Service (SaaS), Platform as a Service (PaaS), Infrastructure as a Service
(IaaS). Software as a Service (SaaS) In this Service model, an application software is hosted in
the cloud and thus the users can access the application through Mobile apps, emails, PC’s. The
users need not have to control the cloud infrastructure since the model itself employs the multi-
tenancy system architecture for accessing the application and provides optimization in terms of
speed, security, availability, disaster recovery and maintenance. Example of SaaS includes
Google Mail, Google Docs, Salesforce.com, ZOHO and so forth. Platform as a Service (PaaS) In
this Service model, the users has to deploy onto the cloud infrastructure created using
programming languages and tools and configuration management supported by the provider. The
users need not have to control the cloud infrastructure including network, servers, operating
systems, or storage. PaaS model offers a development platform to host both the completed and
in- progress cloud application. Example of PaaS includes Google AppEngine, AWS.
Infrastructure as a Service (IaaS) In this Service model, the users directly use processing,
storage, networks, and other computing resources provided in the IaaS cloud which employs
Virtualization in order to integrate/decompose physical resources as per user requirements. The
users need not have to manage or control the cloud infrastructure but has control over operating
systems, storage, deployed applications. Example of IaaS includes Amazon’s EC2, Sun
Microsystems.

Given the characteristics of Cloud Computing and its service models, thus improves the ability
of accessing the information by the users being able to rapidly and inexpensively re-provision
technological infrastructure resources. Device and location independence enable users to access
systems using a web browser regardless of their location or what device they are using (e.g.,
mobile phones). Multi-tenancy enables sharing of resources and costs across a large pool of users
thus allowing for centralization of infrastructure in locations with lower costs. Reliability
improves through the use of multiple redundant sites, which makes Cloud Computing suitable
for business continuity and disaster recovery. Security typically improves due to centralization of
data and increased security-focused resources. Sustainability comes about through improved
resource utilization, more efficient systems. Electronic health information is accessed by all the
participants of healthcare system such as patients, healthcare providers, healthcare payer using
open source cloud which acts as a server that faces several challenges, like data storage and
management (e.g., physical storage issues, availability and maintenance), interoperability and
availability of heterogeneous resources, security and privacy (e.g., permission control, data
anonymity, etc.), unified and ubiquitous access. The mobile apps such as Google’s Android
operating system is used as a client which focus towards achieving two specific goals [10]: the
availability of e-health applications and medical information anywhere and anytime and the
invisibility of computing. Mobile apps basically support electronic billing and EHR activities of
patient and their medical history which can be accessed individually by patient, healthcare
provider, healthcare payer by authenticating themselves with MedBook cloud server.

Many studies have demonstrated that there is a very limited access to patient-related information
in hospital system which is available, during decision-making and the communication among
patient observation team members are usual causes of medical errors in healthcare ([8], [9]).
Thus, there is a need for the pervasive and ubiquitous access to healthcare data is considered to
be most essential for the proper diagnosis and treatment procedure for the patient. Cloud
Computing is a model for enabling convenient, on-demand network access to a shared group of
configurable computing resources (e.g., networks, servers, storage, applications, and services)
that can be rapidly provisioned and released with minimal management effort or service provider
interaction. This cloud model promotes availability and is composed of five essential
characteristics, three service models, and four deployment models. The major characteristics of
Cloud Computing can be summarized into the following

(A) On-demand selfservice. A consumer can unilaterally obtain access to computing

capabilities, such as server computing time and/or network storage, as needed automatically
without requiring human interaction with each service’s provider;

(B) Broad network access: Resources are available over the network and accessed through
standard mechanisms that promote use by heterogeneous thin or thick client platforms (e.g.,
smart phones);

(C) Resource pooling: The provider’s computing resources are pooled to serve multiple
consumers using a multi-tenant model, with different physical and virtual resources dynamically
assigned and reassigned according to consumer demand. Examples of resources include storage,
processing, memory, network bandwidth, and virtual machines;

(D) Rapid elasticity: Resources can be rapidly and elastically provisioned, in some cases
automatically, to quickly scale out and rapidly released to quickly scale. Given the characteristics
of Cloud Computing and the flexibility of the services that can be developed, a major benefit is
the agility that improves with users being able to rapidly and inexpensively re-provision
technological infrastructure resources. Device and location independence enable users to access
systems using a web browser regardless of their location or what device they are using (e.g.,
mobile phones). Multi-tenancy enables sharing of resources and costs across a large pool of users
thus allowing for centralization of infrastructure in locations with lower costs. Reliability
improves through the use of multiple redundant sites, which makes Cloud Computing suitable
for business continuity and disaster recovery. Security typically improves due to centralization of
data and increased security-focused resources. Sustainability comes about through improved
resource utilization, more efficient systems. A number of Cloud Computing platforms are
already available for pervasive management of user data.
The VPN protect data while it's traveling on the public network. If intruders attempt to capture
the data, they should be unable to read or use it. The VPN provide the same quality of connection
for each user even when it is handling its maximum number of simultaneous connections. It is
able to extend its VPN services to handle that growth without replacing the VPN technology
altogether. The purpose of the tunneling protocol is to add a layer of security that protects each
packet on its journey over the Internet. The packet is traveling with the same transport protocol it
would have used without the tunnel; this protocol defines how each computer sends and receives
data over its ISP. Each inner packet still maintains the passenger protocol, such as Internet
protocol (IP) or AppleTalk, which defines how it travels on the LANs at each end of the tunnel.
The tunneling protocol used for encapsulation adds a layer of security to protect the packet on its
journey over the Internet. The electronic hospital management system provides a way in which
the patient details are available anytime , anywhere whenever required and these data is highly
secured because of VPN connections.

This section discusses the main features of the application and presents implementation details.
The prevalent functionality of the application is to provide medical experts and patients with a
mobile user interface for managing healthcare information more securely. The latter interprets
into storing, querying and retrieving patient health records and patient-related medical data (e.g.,
biosignals). The data may reside at a distributed Cloud Storage facility, initially uploaded/stored
by medical personnel through a Hospital Information System (HIS). In order to be interoperable
with a variety of Cloud Computing infrastructures, the communication and data exchange has to
be performed through non-proprietary, open and interoperable communication standards.
Electronic hospital management utilizing Web Services connectivity and Android OS supports
the following functionality: Seamless connection to Cloud Computing storage: The main
application allows users to retrieve, modify and upload medical content (medical images, patient
health records and biosignals) utilizing Web Services and the REST API. The content resides
remotely into the distributed storage elements but access is presented to the user as the resources
are located locally in the device. Patient Health Record Management: Information regarding
patient’s status, related biosignals and image content can be displayed and managed through the
application’s interface. Image viewing support: The DICOM medical image protocol is
supported, while the JPEG2000 standard has been implemented to support loss and lossless
compression, progressing coding and Region of Interest (ROI) coding. The progressive coding
allows the user to decode large image files at different resolution levels optimizing this way
network resources and allowing image acquisition even in cases network availability is limited.
The code for performing wavelet decoding on mobile devices in has been modified to support
the JPEG2000 standard on the Android platform. Image annotation is also supported, using the
multi-touch functions of the Android OS.

Cloud computing helps in providing resources to client on an on-demand basis through the web
service interface. Mobile cloud computing is a type of cloud computing in which some of the
devices that are used for providing the services, are mobiles. Mobile devices have many
constraints imposed upon them because of the desirability of smaller sizes, lower weights, longer
battery life and other features. These constraints cause inflexibility in hardware and software
development for these devices. Cloud computing can be used to allow the mobile devices to
avoid these constraints by making the resource intensive tasks and complex functions to be
performed on desktop systems and having the end results sent to the device. This enables the
Mobile Cloud Computing to be a very efficient and effective way to develop robust applications
in the healthcare sector. The end user will benefit, as they can share resources and applications
without high capital expenditure on hardware and software resources. The end users can easily
run the applications from the mobile without any costly hardware to run applications as the
operations are run within the cloud. Here the HMS application been developed using the Android
mobile operating system. Since it is an open source operating system and very flexible for
building applications, it becomes a robust platform for the healthcare applications.

The HMS application is designed to make available the prescriptions and health records, medical
image records (like scanned images etc.) of patients, on their Android powered mobile phones.
The health records are stored and managed in the cloud OS. The records are transferred from the
cloud to the mobile device, where it is displayed. EyeOS is the cloud platform used to build this
application. This cloud OS can be easily downloaded for free. Since Android powered mobile
devices are available in the market at affordable rates, they can be easily used in such healthcare
applications. Several authors have already presented ideas of mobile platforms for information
exchange (like text and images) over internet. The MADIP system is a distributed information
platform allowing wide-area health information exchange based on mobile agents. But most of
them are based on expensive and inflexible communication methods that require the installation
of software and hardware components. These issues are solved using the cloud computing
concept, as there is no need for extra storage and computation medium. The information that
resides in the cloud is managed by the hospital management staff and the doctors (for uploading
prescriptions and medical image records). The Android OS supports the connection to the Cloud
OS that allows the patient to retrieve, modify, manage and upload medical images and text data
using the internet services and REST API concepts like HTTP URLs. The image support is
provided by DICOM protocol and the pixel data of images are compressed by the JPEG
standard. The progressive coding allows the user to decode large image files at different
resolution levels optimizing these way network resources and allowing image acquisition even in
cases network availability is limited. The code for performing wavelet decoding on mobile
devices in has been modified to support the JPEG2000 standard on the Android platform.
LIMITATIONS OF EXISTING SYSTEM

 Lack of security of data.

 Time consuming.
 Consumes large volume of paper work.
 Manual work
 No direct role for the higher officials.
 To avoid all these limitations and make the system working more accurately it needs to
be computerized.

PROBLEM DEFINITION

Problems with conventional system

1. Lack of immediate retrievals: -The information is very difficult to retrieve and to find
particular information like- E.g. - To find out about the patient’s history, the user has to go
through various registers. This results in inconvenience and wastage of time.

2. Lack of immediate information storage: - The information generated by various transactions

takes time and efforts to be stored at right place.

3. Lack of prompt updating: - Various changes to information like patient details or

immunization details of child are difficult to make as paper work is involved.

4. Error prone manual calculation: - Manual calculations are error prone and take a lot of time
this may result in incorrect information. For example calculation of patient’s bill based on
various treatments.

5. Preparation of accurate and prompt reports: - This becomes a difficult task as information is
difficult to collect from various registers.
PROPOSED SYSTEM

In order to achieve the secure medical decision for undiagnosed patient under the
aforementioned model, our system design will fulfill privacy and performance guarantees as
follows:

• The proposed system should achieve privacypreserving requirements. As stated above, if CDSS
does not consider the privacy requirements, patient’s highly sensitive information (symptom and
disease information) will be disclosed to PU, CP, and unauthorized parties in the patient’s
medical decision. It will let patient unwillingly provide its own data to CDSS. In addition, PU is
always a profit company which prevents his own data from leaking to other party’s in the
system. Therefore, the proposed system should achieve the privacy of PA and PU
simultaneously.

• The proposed system should achieve computation effi- ciency. The patient always has limited
computational resources which cannot support overburden computation. To support patient-
centric diagnosis results retrieval from CP in time, the proposed system should consider
computation efficiency Therefore, it is important to allow PA to retrieve diagnosis results in real-
time.

In our system, we mainly focus on how to securely train na¨ıve Bayesian classifier and use the
classifier to clinical decide patients’ disease without leaking their private information.
Specifically, we define the system model by dividing PPCD into five parties: Trusted Authority
(TA), Cloud Platform (CP), Data Provider (DP), Processing Unit (PU), and Undiagnosed Patient
(PA). The overall system model of our PPCD can be found in Fig. 1. we present our PPCD
system for predicting patient’s disease risk, which mainly consists of the following three phases:
privacy-preserving training na¨ıve Bayesian classifier (Phase A), privacy-preserving computing
patient of disease risk (Phase B), privacy-preserving retrieving top-k diagnosed results (Phase
C)..

In this phase, DP should provide his historical medical data to PU for training na¨ıve Bayesian
classifier and these data should be sent to CP for storage. We firstly construct a new
cryptographic tool called Additive Homomorphic Proxy Aggregation scheme (AHPA) to
securely aggregate the message to solve the collusion problem between PU and CP. Then, we
use the tool to train na¨ıve Bayesian classifier privately.

Advantage:
 Integrated and Efficient Patient Care
 Better Management of Data
 Cost Effectiveness
 Privacy
 The system is very simple in design and to implement.
 The system requires very low system resources and the system will work in almost all
configurations.
 Security of data.
 Ensure data accuracy’s.
 Administrator controls the entire system.
 Reduce the damages of the machines.
 Minimize manual data entry.
 Greater efficiency.
 User friendly and interactive.
 Minimum time required
MODULES

1) Trusted Authority (TA): TA is the indispensable entity which is trusted by all entities
involved in the system, who is in charge of distributing and managing all the private keys
involve in the system.

2) Cloud Platform (CP): CP contains unlimited storage space which can store and manage all
the data in the system. Other parties who have limited storage space can outsource their data to
CP for storing. In addition, CP has some computation abilities to perform some calculations over
the stored data.

3) Data Provider (DP): DP can provide historical medical data that contain patients’ symptoms
and confirmed diseases, which are used for training na¨ıve Bayesian classifier. All these data are
outsourced to CP for storing.

4) Processing Unit (PU, representing as service provider in the previous section): PU can be
a company or hospital which can provide online direct-to-consumer service and offer individual
risk prediction for various diseases based on client’s symptoms. PU uses historical medical data
to construct na¨ıve Bayesian classifier and then use the model to predict the disease risk of
undiagnosed patients.

5) Undiagnosed Patient (PA): PA has some symptom information which is collected during
doctor visits or directly provided by patient (e.g., blood pressure, heart rate, weight, etc). The
symptoms can be sent to PU for diseases diagnosis.
DATA FLOW

The most important tasks in hospital information systems can be summarized as follows,

(1) Storage and monitoring of patient‘s condition:

• Accurate and electronically stored medical records of patients (e.g. drug allergies) are
provided

• Visual and auditory warning systems are generated in the event of abnormal test results or
other important data

• Time intervals and / or testing periods for tests on patients to be specified

• Data Processing and analysis for statistical purposes and research oriented purposes

(2) Management and Data Flow:

• Support automated patient data transfers between departments and institutions

• Enable graphic or digitized diagnostic images from the hospital database based on the
integrated retrieval system

• Digital signatures, in order to create internal orders electronically

• Communication by Laboratory Information System

• Registration of human resources and their properties

(3)Financial Aspects:

• Efficient administration of finances

• Use and monitoring of medicines and effectively of the ordering process

• Expected and actual treatment costs are listed and reported

• Automated representation of the needs of the nursing staff

ARCHITETURE
Hardware Requirements:

• System : Pentium IV 2.4 GHz.

• Hard Disk : 40 GB.

• Floppy Drive : 1.44 Mb.

• Monitor : 15 VGA Colour.

• Mouse : Logitech.

• RAM : 256 Mb.

Software Requirements:

• Operating system : - Windows XP.

• Front End : - JSP

• Back End : - SQL Server

Software Requirements:

• Operating system : - Windows XP.

CONCLUTION

In this paper, we have proposed a privacy-preserving patient-centric clinical decision support

system using na¨ıve Bayesian classifier. By taking the advantage of emerging cloud computing
technique, processing unit can use big medical dataset stored in cloud platform to train na¨ıve
Bayesian classifier, and then apply the classifier for disease diagnosis without compromising the
privacy of data provider. In addition, the patient can securely retrieve the top-k diagnosis results
according to their own preference in our system. Since all the data are processed in the encrypted
form, our system can achieve patient-centric diagnose result retrieval in privacy preserving way.

MODIFICATION

In this Paper we are going to Add Cryptography Mechanism that will Increase the data security
in the Cloud. This was very confidential for the patient related application. Then we are also
going to add common problems and that syndromes and solution for that thing in the projects we
are going to add some necessary test lie the blood pressure calculator and the some other tests in
the project.

MODIIFIED TITLE

A Novel Cloud Based Architecture for the Patient Accessible mechanism for the Large
Scale Hospitals.
REFERENCES

[1] “Transforming health care through big data strategies for leveraging big data in the health
care industry,” http://ihealthtran.com/wordpress/2013/03/iht%C2%B2-releases-bigdata-research-
report-download-today/, 2013.

[2] E. S. Berner, Clinical Decision Support Systems. Springer, 2007.

[3] M. A. Musen, B. Middleton, and R. A. Greenes, “Clinical decisionsupport systems,” in

Biomedical informatics. Springer, 2014, pp. 643– 674.

[4] H. Monkaresi, R. A. Calvo, and H. Yan, “A machine learning approach to improve

contactless heart rate monitoring using a webcam,” IEEE J. Biomedical and Health Informatics,
vol. 18, no. 4, pp. 1153–1160, 2014.

[5] C. Schurink, P. Lucas, I. Hoepelman, and M. Bonten, “Computerassisted decision support

for the diagnosis and treatment of infectious diseases in intensive care units,” The Lancet
infectious diseases, vol. 5, no. 5, pp. 305–312, 2005.

[6] I. Kononenko, “Machine learning for medical diagnosis: history, state of the art and
perspective,” Artificial Intelligence in medicine, vol. 23, no. 1, pp. 89–109, 2001.

[7] N. Lavrac, I. Kononenko, E. Keravnou, M. Kukar, and B. Zupan, ˇ “Intelligent data analysis
for medical diagnosis: using machine learning and temporal abstraction,” AI Communications,
vol. 11, no. 3, pp. 191– 218, 1998.

[8] Y. Elmehdwi, B. K. Samanthula, and W. Jiang, “Secure k-nearest neighbor query over
encrypted data in outsourced environments,” arXiv preprint arXiv:1307.4824, 2013.

[9] K. M. Leung, “Naive bayesian classifier,” Polytechnic University Department Of Computer

Science/Finance and Risk Engineering, Copyright c, mleung@ poly. edu, 2007.

[10] P. Paillier, “Public-key cryptosystems based on composite degree residuosity classes,” in

Advances in Cryptology - EUROCRYPT ’99, International Conference on the Theory and
Application of Cryptographic Techniques, Prague, Czech Republic, May 2-6, 1999, Proceeding,
1999, pp. 223–238.

Use Case Diagram

SEQUENCE DIAGRAM
COMPANANT DIAGRAM
DEPLOYMENT DIAGRAM
Entity Relationship Diagram
LITERATURE REVIEW

Transforming Health Care through Big Data

At the heart of many health care industry debates is what to do about data: how to realize its
value for quality care, bending the cost curve, how to share it and how to secure it. Health care
providers face significant obstacles in implementing analytics, BI tools and data warehousing.
Health data is diverse and distributed in hard-to-penetrate silos owned by a multitude of
stakeholders. To complicate matters, each stakeholder has different interests and business
incentives while still being closely intertwined. While other industries are already leveraging
their data assets to improve efficiencies and make more informed decisions, the health care
sector has perhaps the most work to do but can also benefit the most by effectively leveraging
big data. A 2011 McKinsey report estimated that the health care industry can potentially realize
$300 billion in annual value by leveraging big data. Health care organizations can create
tremendous value by digitizing, combining and effectively using these pools of data. For
example, the U.S. Department of Veterans Affairs, Kaiser Permanente, and the United
Kingdom’s National Health Service have all demonstrated early success by capturing value from
big data. In order to do so the health care industry must establish proven strategies and best
practices to conduct the advanced analysis necessary to generate real insights because health data
is rarely standardized, often fragmented, or generated in legacy IT systems with incompatible
formats.

Clinical Decision Support Systems

Early CDS systems were derived from expert systems research, with the developers striving to
program the computer with rules that would allow it to “think” like an expert clinician when
confronted with a patient.17 From this early research there was growing recognition that these
systems might be useful beyond research, that they could be used to assist clinicians in decision
making by taking over some routine tasks, warning clinicians of potential problems, or providing
suggestions for clinician consideration.5,18 This review focuses on CDS systems of a type
known as knowledge-based CDS because they include compiled clinical knowledge. There have
been several descriptions of types of CDS and their characteristics.18-22 Osheroff and
colleagues have provided a detailed taxonomy of CDS functions.18 Many of the early CDS
systems provided expert consultation to the clinician for diagnosis and medication selection.
CDS today also encompasses a range of options, from general references, through specific
guidelines for a given condition, to suggestions that take into account a patient’s unique clinical
data. CDS can include nationally recommended guidelines at one end of the continuum and
customized order sets designed by an individual clinician at the other.

A machine learning approach to improve contactless heart rate monitoring using a webcam

Unobtrusive, contactless recordings of physiological signals are very important for many health
and human-computer interaction applications. Most current systems require sensors which
intrusively touch the user's skin. Recent advances in contact-free physiological signals open the
door to many new types of applications. This technology promises to measure heart rate (HR)
and respiration using video only. The effectiveness of this technology, its limitations, and ways
of overcoming them deserves particular attention. In this paper, we evaluate this technique for
measuring HR in a controlled situation, in a naturalistic computer interaction session, and in an
exercise situation. For comparison, HR was measured simultaneously using an
electrocardiography device during all sessions. The results replicated the published results in
controlled situations, but show that they cannot yet be considered as a valid measure of HR in
naturalistic human-computer interaction. We propose a machine learning approach to improve
the accuracy of HR detection in naturalistic measurements. The results demonstrate that the root
mean squared error is reduced from 43.76 to 3.64 beats/min using the proposed method.

Computer-assisted decision support for the diagnosis and treatment of infectious diseases
in intensive care units

Diagnosing nosocomial infections in critically ill patients admitted to intensive care units (ICUs)
is a challenge because signs and symptoms are usually non-specific for a particular infection. In
addition, the choice of treatment, or the decision not to treat, can be difficult. Models and
computer-based decision-support systems have been developed to assist ICU physicians in the
management of infectious diseases. We discuss the historical development, possibilities, and
limitations of various computer-based decision-support models for infectious diseases, with
special emphasis on Bayesian approaches. Although Bayesian decision-support systems are
potentially useful for medical decision making in infectious disease management, clinical
experience with them is limited and prospective evaluation is needed to determine whether their
use can improve the quality of patient care.

Machine learning for medical diagnosis: history, state of the art and perspective,” Artificial
Intelligence in medicine

The paper provides an overview of the development of intelligent data analysis in medicine from
a machine learning perspective: a historical view, a state of the art view and a view on some
future trends in this subfield of applied artificial intelligence. The paper is not intended to
provide a comprehensive overview but rather describes some subeareas and directions which
from my personal point of view seem to be important for applying machine learning in medical
diagnosis. In the historical overview I emphasize the naive Bayesian classifier, neural networks
and decision trees. I present a comparison of some state of the art systems, representatives from
each branch of machine learning, when applied to several medical diagnostic tasks. The future
trends are illustrated by two case studies. The first describes a recently developed method for
dealing with reliability of decisions of classifiers, which seems to be promising for intelligent
data analysis in medicine. The second describes an approach to using machine learning in order
to verify some unexplained phenomena from complementary medicine, which is not (yet)
approved by the orthodox medical community but could in the future play an important role in
overall medical diagnosis and treatment.

Intelligent data analysis for medical diagnosis: using machine learning and temporal
abstraction

Extensive amounts of knowledge and data stored in medical databases request the development
of specialized tools for storing and accessing of data, data analysis, and effective use of stored
knowledge and data. This paper focuses on methods and tools for intelligent data analysis, aimed
at narrowing the increasing gap between data gathering and data comprehension. The paper
sketches the history of research that led to the development of current intelligent data analysis
techniques, discusses the need for intelligent data analysis in medicine, and proposes a
classification of intelligent data analysis methods. The main scope of the paper are machine
learning and temporal abstraction methods and their application in medical diagnosis. A
selection of methods and diagnostic domains is presented, and the performance and usefulness of
approaches discussed. The paper concludes with the evaluation of selected intelligent data
analysis methods and their applicability in medical diagnosis.