BCSP – 064

AI HealthCare Management
by
Sajal Kushwaha
EN. No: 2250659206

Under Guidance of
ABINASH ALOK

Submitted to the School of Computer and Information

Sciences, IGNOU in partial fulfilment of the requirements
for the award of the degree
Bachelor of Computer Applications
(BCA)-2024

Indira Gandhi National Open University

Enrollment No: 2250659206 BCSP-064

 TABLE OF CONTENTS

1. Acknowledgement 3

2. Title of the synopsis 4

3. Introduction 5

4. Objective 7

5. Project category 8

6. Hardware and Software Requirements 10

7. Problem definition and requirements 14

8. Project planning 18

9. Use CASE Diagram 20

10. Data Flow Diagram 21

11. Collaboration Diagram 26

12. Complete structure of project(MODULE) 29

13. Process Logic 32

14. System testing and Security 33

15. Limitation of the Project 35

16. Future scope 36

17. Conclusion 37

18. Bibiliography 38

*******************

Enrollment No: 2250659206 BCSP-064

 ACKNOWLEDGEMENT

With a deep sense of gratitude and respect I would like to extend my heartiest thanks to all those
who provided me immense help and guidance during in our 6th Semester in BCA, IGNOU.

I would like thanks Mr. Abinash Alok (Sr. Research Officer, IBM Research Lab, Vasant Kunj,
Delhi) for providing a guideline for a developing an “AI HealthCare Management” System for my
University IGNOU.

Mr. Abinash Alok for providing a vision about the system, their patience and suggestions on
improving our skill set through their constant guidance during this project. We have greatly
benefited from their regular review and inspiration throughout the work.

Last but not the least I would like to mention here that I am greatly indebted to each and everybody
of my study center colleague and trainer who has been associated with my project at any stage but
whose name dose not finds in this Acknowledgement.

Enrollment No: 2250659206 BCSP-064

 TITLE OF SYNOPSIS

AI HEALTHCARE MANAGEMENT

Enrollment No: 2250659206 BCSP-064

 INTRODUCTION
Artificial intelligence simplifies the lives of patients, doctors and hospital administrators by
performing tasks that are typically done by humans, but in less time and at a fraction of the cost.
In 2015, misdiagnosing illness and medical error accounted for 10% of all Indian deaths. In light of
that, the promise of improving the diagnostic process is one of AI's most exciting healthcare
applications. Incomplete medical histories and large caseloads can lead to deadly human errors.
Immune to those variables, AI can predict and diagnose disease at a faster rate than most medical
professionals. In one study, for example, an AI model using algorithms and deep learning diagnosed
breast cancer at a higher rate than 11 pathologists.
What is artificial intelligence in healthcare?
The widespread data explosion over the last several years is driving a push to develop tools with
artificial intelligence (AI) so that companies can use more of their data and extract meaningful
insights to help with problem solving and informed decision making.
Healthcare could benefit tremendously from AI and machine learning due to the vast amounts of
medical data and other types of information that health organizations collect and maintain. Machine
learning could help organizations sort through the large libraries of data they may have to identify
what medical data is most meaningful for problem solving and refining their care or business
processes. With a deeper level of insight, they could make better decisions or explore new ideas and
sources of competitive advantage.
How and Who are using AI in healthcare:
AI has never been actually involved in the medical diagnosis process, only in assisting with
identifying treatment options for patients who have already been diagnosed. Basically, IBM
developed a system called as IBM Watson Software that is used as cancer diagnose with the help of
Artificial Intelligence.
IBM Watson Health is a division of the International Business Machines Corporation, (IBM), an
American multinational information technology company headquartered in Armonk, New York. It
helps clients facilitate medical research, clinical research, and healthcare solutions, through the use
of artificial intelligence, data, analytics, cloud computing, and other advanced information
technology.
In healthcare, my project uses natural language, hypothesis generation, and evidence-based learning
capabilities are being investigated to see how AI HealthCare may contribute to clinical decision
support systems and the increase in artificial intelligence in healthcare for use by medical
professionals. To aid physicians in the treatment of their patients, once a physician has posed a query
to the system describing symptoms and other related factors, Watson first parses the input to identify
the most important pieces of information; then mines patient data to find facts relevant to the
patient's medical and hereditary history; then examines available data sources to form and test
hypotheses; and finally provides a list of individualized, confidence-scored recommendations. The
sources of data that Watson uses for analysis can include treatment guidelines, electronic medical
record data, notes from healthcare providers, research materials, clinical studies, journal articles and
patient information. Despite being developed and marketed as a "diagnosis and treatment advisor",
AI has never been actually involved in the medical diagnosis process, only in assisting with
identifying treatment options for patients who have already been diagnosed.
My Project AI HealthCare is developing machine learning to assist pathologists in making more
accurate diagnoses. The company's current goals include reducing error in cancer diagnosis and
developing methods for individualized medical treatment.
In September 2011, IBM and WellPoint (now Anthem) announced a partnership to utilize Watson's
data crunching capability to help suggest treatment options to physicians. Then, in February 2013,

Enrollment No: 2250659206 BCSP-064

IBM and WellPoint gave Watson its first commercial application, for utilization management
decisions in lung cancer treatment at Memorial Sloan–Kettering Cancer Center.
Machine learning has revolutionized our way of life, from language recognition, image retrieval,
handwriting recognition, weather forecasting and GPS routes to online search engines. It is now
time to concentrate on successes in machine learning for biological discovery to benefit human
health. Artificial Intelligence is a branch of computer science which has the potential to analyzing
complex data. Their potential is to extract out meaningful relationship with a data set and it can be
used in the diagnosis, treatment and predicting outcome in many clinical scenarios. The purpose of
Artificial Intelligence is to make computers more useful and to understand the principles. Non-
communicable diseases (NCDs), also known as chronic diseases, are not passed from person to
person. They are of long duration and generally slow progression. The four main types of non-
communicable diseases are cardiovascular diseases (like heart attacks and stroke), cancers, chronic
respiratory diseases (such as chronic obstructed pulmonary disease and asthma) and diabetes will
resolve best with the help of AI HealthCare Solutions.

Enrollment No: 2250659206 BCSP-064

 OBJECTIVE
The Objective or main target is to develop a user-friendly and Artificial Intelligence based
health care Management. Artificial intelligence in healthcare is an overarching term used to describe
the utilization of machine-learning algorithms and software, or artificial intelligence (AI), to emulate
human cognition in the analysis, interpretation, and comprehension of complicated medical and
healthcare data. Specifically, AI is the ability of computer algorithms to approximate conclusions
based solely on input data.
The primary goal of health-related AI applications is to analyze relationships between
prevention or treatment techniques and patient outcomes. AI programs are applied to practices such
as diagnosis processes, treatment protocol development, drug development, personalized medicine,
and patient monitoring and care. AI algorithms can also be used to analyze large amounts of data
through electronic health records for disease prevention and diagnosis.

In this project we are trying to implement which parts of a AI project for Health Care
management are equal or highly similar across different hospitals used this AI Health Care (at least
in the same national healthcare system). This allows us to design several Artificial Intelligence
algorithms used for proper health care, and it will be portable and perfection across several hospitals
with less human effort, thus dramatically reducing the time to implement an AI program in a new
hospital can use for proper diagnose.
Taken all of these considerations into account, we propose the following general scheme for an
automated AI based tool for Health Care Management.
X- ray of a hand, with automatic calculation of bone age by a computer
software uses Artificial Intelligence and generate the accurate result. Large
technology companies such as IBM and Google, have also developed AI
algorithms for healthcare. Additionally, hospitals are looking to AI software
to support operational initiatives that increase cost saving, improve patient
satisfaction, and satisfy their staffing and workforce needs. So among all the
above requirements and market demands I am developing the AI Health Care
Management.
The Following objectives to make this project are as follows:
1. AI is predicted to decrease medical costs as there will be more
accuracy in diagnosis and better predictions in the treatment plan as well as more prevention
of disease.
2. AI include Brain-computer Interfaces (BCI) which are predicted to help those with trouble
moving, speaking or with a spinal cord injury. The BCIs will use AI to help these patients
move and communicate by decoding neural activates.
3. Artificial intelligence has led to significant improvements in areas of healthcare such as
medical imaging, automated clinical decision-making, diagnosis, prognosis, and more.
Although AI possesses the capability to revolutionize several fields of medicine, it still has
limitations and cannot replace a bedside physician.
4. Healthcare is a complicated science that is bound by legal, ethical, regulatory, economical,
and social constraints. In order to fully implement AI within healthcare, there must be
"parallel changes in the global environment, with numerous stakeholders, including citizen
and society.
5. Using this we want to developed a WhatsApp chatbot in future which answers questions
associated with the deadly coronavirus in India with the help of AI HealthCare Management.

Enrollment No: 2250659206 BCSP-064

 PROJECT CATEGORY
My project is basically depending on the purpose of Artificial Intelligence is to make computers
more useful in solving problematic healthcare challenges and by using computers we can interpret
data which is obtained by diagnosis of various chronic diseases like Alzheimer, Diabetes,
Cardiovascular diseases and various types of cancers like breast cancer, colon cancer etc. It helps in
early detection of various chronic diseases which reduces economic burden and severity of disease.
Various automated systems and tools like Brain-computer interfaces (BCIs), arterial spin labeling
(ASL) imaging, ASL-MRI, biomarkers, Natural language processing (NLP)and various algorithms
helps to minimize errors and control disease progression. The computer assisted diagnosis, decision
support systems, expert systems and implementation of software may assist physicians to minimize
the intra and inter-observer variability. To streamline the process of diagnosis artificial intelligence
methods specifically artificial neural networks (ANN), Fuzzy approach can be implemented to
handle diverse type of medical data. ANN technique discovers the hidden patterns and correlation
in medical data and effective in designing support system in clinical field. The application of AI
facilitates interpretation of results with high accuracy and speed.
This project is basically based on Artificial Intelligence based algorithm implementation to manage
the HealthCare tools with the help of java, machine learning tools with oracle database that will
store the tools information that helps for diagnosing different disease.
The benefits of a database system over any traditional system are obvious as database is integrated
as well as shared, thus a database eliminates redundancy and also as a consequence, database lets
multiple users access the same piece of data. Some Google API’s and IBM Databases we will
manage a well-known application Verily developed by Google specializes in forecasting both
noncontagious and hereditary genetic diseases. Such apps enable health experts to anticipate
potential threats and avoid them in the future, taking appropriate measures today. Moreover,
predictive analytics improves the operational management of healthcare facilities.

Benefits and Risk of AI Based Health Care Management is as follows:

Facilities offered by RDBMS/ Cloud Databases for AI Based Project:

Enrollment No: 2250659206 BCSP-064

 ➢ Creation of files, Addition of data, Deletion of data, Modification of data.
➢ Retrieving data collectively or selectively.
➢ The data stored can be sorted or indexed at user’s discretion or direction.
➢ Various reports can be produced from the system. These may either be standardized reports
or that may be specifically generated according to specific user definition.
➢ Mathematical function can be performed and the data stored in the database can be
manipulated with functions to perform the desired calculations.
➢ To maintain data integrity and database use.
➢ Data integrity for multiple users.
➢ Providing question-based data interface for easy accessibility and data entry.

Enrollment No: 2250659206 BCSP-064

 Hardware and Software Requirement Specifications

SOFTWARE SPECIFICATION
Name of component Specification

Operating System Windows 10, Linux, Mac OS

Language JAVA, SERVLET, JSP

Database MONGODB, GOOGLE ML Cloud, Oracle

Browser Any of Mozilla, Opera, Chrome, Safari etc.

Webserver GOOGLE, Apache

Progressive Web App, API API’s IBM, Google

Scripting language Enable JavaScript, HTML,

Tools NetBeans, RATIONAL ROSE, TensorFlow Tool (AI)

HARDWARE SPECIFICATION
Name of component Specification

Processor Quad Processor ,Pentium or above i3/i5

Hard Disk / External Disk / Card 1 TB / 8 GB

Memory 4GB or 8 GB and above

Monitor /TABLET / MOBILE LED 17 inch/ i-Ph. Mobile/ Android Mob./ Android TV/
Apple Notebook etc.
Printer HP Color/ USB Supportive / Wifi Support/ Bluetooth
Support
Net Ethernet Supportive

Software Requirement
Why Java and Machine Learning Tools?
Java can be used for Artificial Intelligence (AI), then, many brilliant Java developers in one voice
will say a “YES”. These developers also have the opinion that Java is one of the best programming
languages after Python for developing Artificial Intelligence solutions. One thing you need to realize
is, there is no individual language only to develop Artificial Intelligence solutions. In spite of that,
the existing tools help developers achieve great results when developing AI Solutions.
Today, we’ll see the prevalence of Artificial Intelligence in most of the technologies we use. From
search algorithms to artificial neural networks, Smartphone applications, genetic programming and
robotics, the presence of Artificial Intelligence has created a helpful impact in the lives of humans.
But, how is Java used in AI and what benefits can Java bring to Artificial Intelligence solutions.
This blog will provide you with an answer to help your queries.
How is Java used in AI?

Enrollment No: 2250659206 BCSP-064

When you want to start implementing AI using Java, a basic knowledge of traditional algorithms
and concepts are a must. You can learn these through AI courses, specialized books and websites.
In order to use Java AI libraries which are extremely helpful when developing applications, a
theoretical background in AI is necessary. There are a large number of AI Libraries in Java and can
be used for a variety of usages. There are AI Libraries in Java for Expert Systems, Neural Networks,
for Natural Language Processing, for Genetic Algorithms and for Automatic Programming.
Benefits of Using Java for AI
Java is already a popular programming language which offers an AI developer the following
benefits:
 Ease of debugging
 Ease of use
 Large-scale projects simplification
 Representation of data in graphics
 Better interaction with the user
The Virtual Machine Technology of Java allows Java developers to create a single version of the
app which is then enabled by running it in the Java supported platforms. It will thus add value to
your business. The incorporation of the Standard Widget Toolkit such as Swing and SWT will make
the interfaces and graphics in Java to look more appealing and at the same time sophisticated.
Strengths of Java
If you’re choosing Java to develop Artificial Intelligence Applications then, you’ll never be worried
about its Maintainability, Transparency and Portability
Maintainability
When you use Java for AI, its precise programming features with spaces, access modifiers, and
indentation help the code to be maintained easily. When you test the application for all loopholes it
will make sure that the code is secure and bug-free. Java applications become highly maintainable
if you optimize it with proper documentation.
Portability
When you want to transfer a Java Program from an operating system on which it was developed to
another, it doesn’t require much rework. The portability nature of Java Programming is its most
attractive aspect. For example, a given Java program exhibits the same results on different CPUs
and Operating Systems.
Security
With the frequent updates in the Java programming language, the security features become more
stringent. This will impress anyone who is a technology enthusiast.
How to make Intelligent Business Solutions Using Java?

Enrollment No: 2250659206 BCSP-064

Java can be called as one of the best languages for AI projects. It is also one of the most loved and
commonly used by programming languages. Choosing Java for building AI powered intelligent
business solutions can easily bring a digital transformation within your business.
Java for artificial intelligence programming is mostly used to create machine learning solutions,
genetic programming, search algorithms, neural networks and multi-robot systems.
Java’s must-have features for AI projects are its object-orienteers and scalability. Virtual machine
technology makes Java portable, transparent and maintainable. It will enable you to build a single
app version that can run on all Java-supported platforms and thus adding value to your business.
Since artificial intelligence is tightly connected with algorithms, Java in AI programming offers the
ability to code different types of algorithms. Java is supported by a large community of developers
that makes a diverse range of algorithms to be coded efficiently. While the automation and machine
learning capabilities of Java changes the way you use technology in business, it offers the most
advanced features for developing intelligent products and services.
Java’s technology infrastructure is equipped with intelligent software that can take your business to
new heights. You may start hiring Java developers who can build the desired AI solutions and make
your business smarter.
Some Features of Java which make it advantageous for developing AI Applications are listed below:
 Cross-platform
 Easy to learn and use
 Easy-to-code Algorithms
 Built-in garbage collector
 Swing and Standard Widget Toolkit
 Simplified work with large-scale projects
 Better user interaction
 Easy to debug
 Reliable community
 Multiple free tutorials
 Scalable
Machine Learning API’s as Google / Amazon Cloud ML Engine
If we’re training our classifier on a plenty of data, our PC or laptop might work quite well. However,
if we have millions or billions of training data? Or, the algorithm is quite sophisticated and take a
long time in proper execution? We should use Google Cloud ML Engine for our rescue. It is a hosted
platform where machine learning app developers and data scientists create and run optimum quality
machine learning models.

Here are top features:

Enrollment No: 2250659206 BCSP-064

  Provides machine learning
model training, building, deep
learning and predictive
modeling.
 The two services viz. prediction
and training can be used
independently or jointly.
 This software is widely used by
enterprises, i.e., detecting
clouds in a satellite image,
responding faster to emails of
customers.
 It can be widely used to train a complex model.

Enrollment No: 2250659206 BCSP-064

 Problem Definition
The origin of most software systems is in the need of a client, who either wants to automate
and existing manual system or desires a new software system. The software system itself is created
by the developer finally the completed system will be used by the end user. Thus, there are three
major parties interested in a new system: the client, the users, and the developer. The requirements
for the system that will satisfy the need of the clients and the concerns of the user have to
communicate to the developer.
The problem is that the client usually does not understand software or the software
development process, and the developer often does not understand the client’s problem and
application area. This causes a communication gap between the parties involved in the development
project. A basic purpose of software requirement specification is to bridge this communication gap.
SRS is the medium through which the client and the user need are accurately specified; indeed, SRS
forms the basis of software development. A good SRS should satisfy all the parties-something very
hard to achieve and involves trade-offs and persuasion.
Commonly, the application of the expert system approach in medical software programming is seen
in Clinical Decision Support Systems (CDSS). Simply put, CDSS are software programs that enable
clinicians to make clinician decisions. CDSS provides customized assessment or advice based on
analysis of patient data sets. An early version of CDSS was the MYCIN program developed in the
1970s. MYCIN was a CDSS focusing on the management of infectious disease patients. Infectious
disease knowledge was represented in the form of production rules, which are conditional statements
as to how observations can be inferred appropriately. However, MYCIN had less emphasis on
diagnosis and more on the management of patients with infectious diseases. In a later evaluation of
the MYCIN system, it was found it compared favorably with the advice provided by infectious
disease experts. MYCIN paved the way for the development of knowledge-based systems and the
commercialization of rule-base approaches in medicine and other fields. Another CDSS that was
initially developed around the same time period as MYCIN but continues to be used is the QMR
system.

The core of the expert system is the inference engine, which transforms the inputs into actionable
outputs. Such an existing system uses will develop phase wise for one phase to another phase

LIMITATION OF EXISTING SYSTEM

 Manual Approach are tedious and slow.
 Accuracy of the report are less comparatively the new System that is AI based.
 Existing system time consuming for both for patients and Doctors.

Enrollment No: 2250659206 BCSP-064

REQUIREMENTS
AI based project is not a singular technology, but rather an umbrella term. Al includes using methods
such as deep learning, machine learning (ML) and natural language processing (NLP) to perform
"smart" tasks we often associate with the human mind such as learning and reasoning. The main
reason of modeling generally focuses on the problem structure, not its external behaviors.
Consequently, thing’s like user interfaces are rarely modeled, whereas thy frequently from a major
component of the SRS.

Similarly, performance constraints, design constraints, standards compliance, recovery, etc.

are specified clearly in the SRS because the designer must know about there to properly design the
system.
To properly satisfy the basic goals, an SRS should have certain properties and should contain
diff type of req. A good SRS is [iEE87, IEE94]: complete if everything the software is supposed to
and responses to the software to all classes of input data are specified in the SRS.
Correctness and completeness go hand in hand an SRS in unambiguous if and only if every
requirement stated has one and only one interpretation, requirements often written in natural
language.
An SRS is verifiable if and only if every stated requirement is verifiable. A requirement is
verifiable if there exists some cost-effective process that can check whether the final software meets
those requirements. An SRS is consistent if there is no requirements that with another.
Writing and SRS is an iterative process. Even when requirement of system are specified
they are later modified as the need of the client change. Hence an SRS should be easy to modify.
An SRS is traceable if the origin of each of its requirements is clear and if it facilitates the
referencing of each requirement in future development.
One of the most common problems in requirement specification is when some of the
requirements of the client are not specified. This necessitates addition and modifications to the
requirements later in the development cycle, which are often expensive to incorporate.

Enrollment No: 2250659206 BCSP-064

There are a lot of software requirements specifications included in the functional requirements of
the HealthCare Management System, which contains various process, namely Registration, Check
out, Report Generation, and Database.

Registration Process of SRS (Software Requirements Specification)

Adding Patients: The Health Care Management enables the staff in the front desk to include new
patients to the system.

Assigning an ID to the patients: The HCMS enables the staff in the front desk to provide a unique
ID for each patient and then add them to the record sheet of the patient. The patients can utilize the
ID throughout their hospital stay.

Check Out of SRS:

Deleting Patient ID: The staff in the administration section of the ward can delete the patient ID
from the system when the patient's checkout from the hospital.

Adding to beds available list: The Staff in the administration section of the ward can put the bed
empty in the list of beds-available.

Report Generation of SRS:

Information of the Patient: The Health Care Management System generates a report on every patient
regarding various information like patient’s name, Phone number, bed number, the doctor's name
whom its assigns, ward name, and more with the help of Artificial Intelligent System automatically.

Availability of the Bed: The Healthcare Management system also helps in generating reports on the
availability of the bed regarding the information like bed number unoccupied or occupied, ward
name, and more with the AI.

Database of SRS:

Mandatory Patient Information: Every patient has some necessary data like phone number, their
first and last name, personal health number, postal code, country, address, city, 'patient's ID number,
etc.

Updating information of the Patient: The health care management system enables users to update
the information of the patient as described in the mandatory information included.

FUNCTIONAL REQUIREMENTS
 Artificial Intelligence can automate some of the computer tasks that take up much of medical
practice today. Providers spend a tremendous amount of time dealing with electronic
medical records, reading screens, and typing on keyboards, even in the exam room.
 If AI systems can queue up the most relevant information in patient records and then distill
recordings of appointments and conversations down into structured data, they could save
substantial time for providers and might increase the amount of facetime between providers
and patients and the quality of the medical encounter for both.
 Managing patients and medical resources. Finally, and least visibly to the public, AI can be
used to allocate resources and shape business. For instance, AI systems might predict which
departments are likely to need additional short-term staffing, suggest which of two patients

Enrollment No: 2250659206 BCSP-064

 might benefit most from scarce medical resources, or, more controversially, identify
revenue-maximizing practices.
NON-FUNCTIONAL REQUIREMENTS
There are a lot of software requirements specifications included in the non-functional requirements
of the Health Care Management, which contains various process, namely Security, Performance,
Maintainability, and Reliability.
Security:

 Patient Identification: The system needs the patient to recognize herself or himself using the
phone.

 Logon ID: Any users who make use of the system need to hold a Logon ID and password.

 Modifications: Any modifications like insert, delete, update, etc. for the database can be
synchronized quickly and executed only by the ward administrator.

 Front Desk Staff Rights: The staff in the front desk can view any data in the Health Care
Management system, add new patients record to the HMS but they don't have any rights alter
any data in it.

 Administrator rights: The administrator can view as well as alter any information in the
Health Care Management System.

Performance:

 Response Time: The system provides acknowledgment in just one second once the 'patient's
information is checked.

 Capacity: The system needs to support at least 1000 people at once.

 User-Interface: The user interface acknowledges within five seconds.

 Conformity: The system needs to ensure that the guidelines of the Microsoft accessibilities
are followed.

Maintainability:

 Back-Up: The system offers the efficiency for data backup.

 Errors: The system will track every mistake as well as keep a log of it.

Reliability:

 Availability: The system is available all the time.

Enrollment No: 2250659206 BCSP-064

 PROJECT PLANNING
To say that the role of Artificial Intelligence in Healthcare is intriguing, would be an understatement.
AI and Machine Learning can bring about changes that have a substantial impact on healthcare
processes and administration & while there is a lot, we have to overcome to reach the stage of AI-
dependent healthcare, there is sufficient potential in the technology today to drive governments,
healthcare institutions, and providers to invest in AI-powered solutions.

In any project planning we keep some points in our mind that

 Good design removes 50% of your security worries. Incorporate security activities into your
design phase to prevent costly vulnerabilities later in the SDLC.

 Carefully select your open-source components. Use adequate security and testing measures

when selecting open-source code to avoid vulnerabilities and legal complications. Knowing
what risks might be hidden in your code is imperative.
 Automate security testing during implementation.

Enrollment No: 2250659206 BCSP-064

  Project planning involves plotting project activities against a time frame. One of the first
steps in planning is developing a road map structure or a network based on analysis of the
tasks that must be performed to complete the project.

AI-powered healthcare is driving meaningful changes across the entire patient journey
Applications of Artificial Intelligence in Healthcare primarily revolves around Making
healthcare providers efficient and productive. Providing a far more streamlined and robust
experience to in patients and out patients Making back-end processes effective and organized

JAN FEB MAR MAY JUN JUL AUG SEP

GANTT CHART OF AI HealthCare Management

Enrollment No: 2250659206 BCSP-064

 USE CASE DIAGRAM
USE CASE Diagram for AI Health Care Management System as:

Departments

OutPatient

AI Based All facilities

Enrollment No: 2250659206 BCSP-064

 DATA FLOW DIAGRAMS
The Data Flow Diagram is one of the most improvement tools used by the system analyst DeMarco
(1978) Nad Gand Sarson (1979) popularized the use if the data flow diagram as modeling tools
through their structured system analysis methodologies. A data flow diagram should be the first tool
used by system analyst to model system components. These components are the system processes;
the data used by this processes and external entities that interact with the system and the information
flows in the system. It is also known as a bubble chart. A DFD depicts information flow and
transform that are applied as data moves from input. Use of DFD helps to clarify the system
requirements. DFD are drawn surging analysis and are the starting point for the design phase. A
DFD could be used represent a physical system, at the beginning of analysis, or a logical system at
alter point in the system development life cycle. Being graphical, it is easy to understand.

Process
Process show what system does. Each process has one or more data inputs and produce one or
more data output, Circles in a data flow diagram represent process. Each process has unique name
and number. This name and number appear inside the circle that represents the processes in a data
flow diagram.
This process is represented as circle

Data Stores:
File or data store is depositary of data. They contain data that is retained in the system. Processes
can enter the data into a data store or retrieve data from the data store. Each data store is
represented by thin line in the data flow diagram and each data store has a unique name.
The data store is represented in form of a line

Or

External Entities:
External entities are outside the system but they either supply input data into the system or use
the system output, they are entities which the designer has no control. Square or rectangle may
represent external entities that supply data into a system or sometimes called sources. External
entities that use the system data are sometimes called sinks.

Data Flows:
Dataflow model the passage of data in the system and are represented lines joining system
components. An arrow indicates the direction of the flow and the line labeled by the name of
the data flow.

Enrollment No: 2250659206 BCSP-064

 Context Diagram (0 - Level-DFD)

Level zero is basic process of the project

Health Device
Status Store

Patient Status

Patient

AI Health
Care
Management Report INFO
Doctors

Diagnose Status
AI HealthCare Device

Enrollment No: 2250659206 BCSP-064

 Level 1
Patient and Health Status Management..

Patient MASTER
Patient
SIGN-IN MANAGE
MENT
Patient/REGISTER
DETAILS
Patient

HealthCar
Diagnose MASTER
e
UPDATED Patient MASTER
Managem
ent
HEALTHY DETAILS

AI Tools MASTER
DEATH DETAILS

Tools
MANAG
EMENT

Diagonse MASTER

Report DETAILS

Enrollment No: 2250659206 BCSP-064

 Level 2 Diagonse
AI HealthCare Management Master
Submit
Checks
Verifies Health
Access
Details

Patient Check
Health
Management New
Care
Diseases

Updated
Disease
Details

Diseases Report
Doctor

New Tools
Avilability

Store

Tools Master and AI

Details

Enrollment No: 2250659206 BCSP-064

 COLLABORATION DIAGRAM

Collaboration Diagram for Administrator

18: 18.Processing

Collaboration Diagram for patients

Enrollment No: 2250659206 BCSP-064

 18: Processing

Collaboration Diagram for Patient

Enrollment No: 2250659206 BCSP-064

Collaboration Diagram for public

12: Processing

Enrollment No: 2250659206 BCSP-064

 COMPLETE STRUCTURE OF PROJECT
My Project the “AI HealthCare Management” has several different headings, number of modules
and its description, data structure [Tables] of all modules, process logic, testing process, report
generation. These structures give the actual layout of all modules of this project which are as
follows-

Several Modules as:

 Department Module: Used for managing the Department details
 Employee Module: Used for managing the details of Employee
 Doctor Module: Used for managing the details of Doctors with department wise.
 Room Module: Used for managing the information and details of the Room.
 AI Test Module: Used for managing the AI Test Report details
 Disease Module: Used for managing the Disease Module
 Bed Module: Used for managing the Bed and their status (Vacant, Occupied, Cleaning etc.)
 Test Module: Used for managing the updating details of the testing applied in our project.
 Ward Type Module: Used for managing the Ward Details or Department.
 Inpatient Module: Used for managing the Incoming patient for health care.
 Outpatient Module: Used for managing the outgoing patient for health care.
DATA STRUCTURES TABLES OF ALL MODULES
Database tables
Type Constraints
Name
Did Number Primary Key

Dname Varchar2(25)
Location Varchar2(25)
Table 1 Dept

Name Type Constraints

Pid Number
Ptype Varchar2(1)
AITid Number
AITresult Varchar2(20)
AITdate Date
Did Number Foreign key

Table 2 Test Result

Enrollment No: 2250659206 BCSP-064

 Name Type Constraints
Eid Number Primary Key
Ename Varchar2(25)
Desg Varchar2(20)
Did Number Foreign Key
DOJ Date
Table 3 Emp
Name Type Constraints
Docid Number Primary Key
Docname Varchar2(25)
Did Number Foreign Key
Exp Number
Desg Varchar2(25)
Time Varchar2(20)
Post Varchar2(1)
DOJ Date
Table 4 Doctor
Name Type Constraints
Rid Number Primary Key
Floor Number
NOFB Number
Ward Varchar2(1)
Status Varchar2(1)
Rent Number
Did Number Foreign Key
Table 5 Room
Name Type Constraints

AITid Number Primary Key

AITname Varchar2(25)

Table 6 AITest
Name Type Constraints
Disid Number Primary Key
Disname Varchar2(25)
Did Number Foreign Key

Table 7 Disease

Name Type Constraints

Bedid Number Primary Key
Rid Number Foreign Key
Status Varchar2(1)
Table 8 Beds

Enrollment No: 2250659206 BCSP-064

 Name Type Constraints
Pid Number Primary Key
Pname Varchar2(25)
Address Varchar2(75)
Phno Number (11)
Rid Number Foreign Key
DOA Date
DOD Date
TOD Number
Docid Number Foreign Key
Bid Number Foreign Key
Did Number Foreign Key

Table 9 Inpatient

Name Type Constraints

Slno Number Primary Key
Pname Varchar2(25)
Depid Number Foreign Key
Docid Number Foreign Key
Curdate Date
Disid Number Foreign Key
Table 10 Outpatient

Name Type Constraints

Wid Varchar2(1)
Wtype Varchar2(7)
Table 11 Ward Type

Enrollment No: 2250659206 BCSP-064

 PROCESS LOGIC
Process logic define that how each module is interrelated to each other and work with them as
integration of patients, doctor, clinic, tests, report, diagnose, work of AI tools, AI diagnose report
etc.

So, AI based healthcare uses several modules each module has their individual tables and that table
is stored the data in healthcare data center so that fetching data and report concurrently and sense
the accurate data report give the chance to doctor for more accurate diagnoses of the patients.

The given diagram shows the each level the process flow required and AI algorithm works.

Enrollment No: 2250659206 BCSP-064

 SYSTEM TESTING
The process of executing a system with the intent of finding an error. Testing is defined as the
process in which defects are identified, isolated, subjected for rectification and ensured that product
is defect free in order to produce the quality product and hence customer satisfaction.
 Quality is defined as justification of the requirements
 Defect is nothing but deviation from the requirements
 Defect is nothing but bug.
 Testing --- The presence of bugs.
 Testing can demonstrate the presence of bugs, but not their absence.
 Debugging and Testing are not the same thing.
 Testing is a systematic attempt to break a program or the AUT.
 Debugging is the art or method of uncovering why the script /program did not execute
properly.
Testing Methodologies
 Black box Testing: is the testing process in which tester can perform testing on an
application without having any internal structural knowledge of application.
o Usually Test Engineers are involved in the black box testing.
 White box Testing: is the testing process in which tester can perform testing on an
application with having internal structural knowledge.
o Usually The Developers are involved in white box testing.
 Gray Box Testing: is the process in which the combination of black box and white box
techniques are used.
Levels of Testing

Module1 Module2 Module3

Units Units Units

i/p Integration o/p i/p Integration o/p

System Testing: Presentation + business +Databases

UAT: user acceptance testing

Types of Testing
Smoke Testing: is the process of initial testing in which tester looks for the availability of all the
functionality of the application in order to perform detailed testing on them.

Enrollment No: 2250659206 BCSP-064

Sanity Testing: is a type of testing that is conducted on an application initially to check for the proper
behavior of an application that is to check all the functionality are available before the detailed testing is
conducted by on them.
 Regression Testing: is one of the best and important testing. Regression testing is the
process in which the functionality, which is already tested before, is once again tested
whenever some new change is added in order to check whether the existing functionality
remains same.
 Re-Testing: is the process in which testing is performed on some functionality which is
already tested before to make sure that the defects are reproducible and to rule out the
environment’s issues if at all any defects are there.
 Static Testing: is the testing, which is performed on an application when it is not been
executed. ex: GUI, Document Testing
 Dynamic Testing: is the testing which is performed on an application when it is being
executed. ex: Functional testing.
 Alpha Testing: it is a type of user acceptance testing, which is conducted on an application
when it is just before released to the customer.
 Monkey Testing: is the process in which abnormal operations, beyond capacity operations
are done on the application to check the stability of it in spite of the users abnormal
behavior.
 Compatibility testing: it is the testing process in which usually the products are tested on
the environments with different combinations of databases (application servers,
browsers…etc) In order to check how far the product is compatible with all these
environments platform combination.
 Installation Testing: it is the process of testing in which the tester try to install or try to
deploy the module into the corresponding environment by following the guidelines
produced in the deployment document and check whether the installation is successful or
not.
 Adhoc Testing: Adhoc Testing is the process of testing in which unlike the formal testing
where in test case document is used, without that test case document testing can be done
of an application, to cover that testing of the future which are not covered in that test case
document. Also it is intended to perform GUI testing which may involve the cosmotic issues.

Enrollment No: 2250659206 BCSP-064

 LIMITATION OF THE PROJECT
Each Project has several
limitations so as in our
System/App has also the
following limitation:
The titular truth in “The
‘inconvenient truth’ about AI
in healthcare,” is “that at
present the algorithms that
feature prominently in
research literature are in fact
not, for the most part,
executable at the frontlines of
clinical practice.”
LIMITATIONS OF THE
SYSTEM/APP
 The limitations of the
system are: Only it
diagnoses the disease of the patients not solve all curiosity.
 Not easily available to all remote area and hospital for all types of AI Health Care.
 Training is required Initially with reports.
The major drawbacks of existing system are: -
Technological advancements are rapidly changing the face of healthcare, offering a range of benefits
but also some serious drawbacks but there are several drawbacks with existing system as.
 Distributional shift — A mismatch in data due to a change of environment or circumstance
can result in erroneous predictions. For example, over time, disease patterns can change,
leading to a disparity between training and operational data.
 Insensitivity to impact — Existing system doesn't yet have the ability to take into account
false negatives or false positives.
 Black box decision-making — With manual, predictions are not open to inspection or
interpretation. For example, a problem with training data could produce an inaccurate X-ray
analysis that the AI system can produces good result and all factor in.
Problem with AI as
Unsafe failure mode — Initially unlike a human doctor, an AI system can diagnose patients
without having confidence in its prediction, especially when working with insufficient
information.

Enrollment No: 2250659206 BCSP-064

 FUTURE SCOPE OF PROJECT
AI in healthcare has huge and wide-reaching potential with everything from mobile coaching
solutions to drug discovery falling under the umbrella of what can be achieved with machine
learning. The role of artificial intelligence in healthcare has been a huge talking point in recent
months and there’s no sign of the adoption of this technology slowing down, well, ever really.
That being said, many healthcare executives are still too shy when it comes to experimenting with
AI due to privacy concerns, data integrity concerns or the unfortunate presence of various
organizational silos making data sharing next to impossible. We’ve covered the main barriers to
adopting AI in healthcare here.
However, the future of healthcare & the future of machine learning and artificial intelligence are
deeply interconnected. There are three categories for applications of AI in health care as AI finds
its way into everything from our smartphones to the supply chain, applications in health care fall
into three broad groupings:
 Patient-oriented AI
 Clinician-oriented AI
 Administrative- and operational-oriented AI
The future of AI in health care could include tasks that range from simple to complex—everything
from answering the phone to medical record review, population health trending and analytics,
therapeutic drug and device design, reading radiology images, making clinical diagnoses and
treatment plans, and even talking with patients.
FURTHER ENHANCEMENT
The future of artificial intelligence in health care presents:
A health care-oriented overview of artificial intelligence (AI), natural language processing (NLP),
and machine learning (ML) Current and future applications in health care and the impact on patients,
clinicians, and the pharmaceutical industry
A look at how the future of AI in health care might unfold as these technologies impact the practice
of medicine and health care over the next decade.
The main scopes and future enhancements are as follows-
 App based as well as web-based application so that it is approachable to all types of
hospitals and doctors with easy to operate with patients too.
 Its availability is also easy to the end user.

Enrollment No: 2250659206 BCSP-064

 CONCLUSION
The growing quality demand in the hospital sector makes it necessary to exploit the whole
potential of stored data efficiently, not only the clinical data, in order to improve diagnoses and
treatments, but also on management, in order to minimize costs and improve the care given to
the patients with accuracy result in their reports with less human report maximum benefits with
Artificial Intelligent System tools that is beneficial in two aspects
1. Save the time quantum
2. Produces the Accurate result
3. Memory Intelligence if they previously status of their health
4. Further lots of way suggest to prevent from their disease.
In this sense, Artificial Intelligence (AI) can contribute with important benefits to the health
sector, as a fundamental tool to analyze the data gathered by AI Health Care Information
Systems (HCIS) and obtain models and patterns which can improve patient assistance and a
better use of resources and pharmaceutical expense.
Goals:
 Reduced entry work and track the patient’s problem with the help of AI technique to generate
accurate result with less time.
 Web enabled
 Reduced errors due to human intervention
 User friendly screens and sense to enter the data for secured place that is free or safe from
other manual or more lab works.
 Easy retrieval of information.
 Help for safety concern and helpful for doctors or technician too.
 Easy to access and approachable due to app based
 Time to time updating automatically due to GOOGLE ML Engine.
 Notification concern of the sign-in technician so gathered updated information.

Enrollment No: 2250659206 BCSP-064

 BIBILIOGRAPHY
Sites searched and referenced from their:

1. https://www.ibm.com/in-en/watson-health/learn/artificial-intelligence-healthcare

2. www.ignou.ac.in

3. www.google.com

4. https://spectrum.ieee.org/biomedical/diagnostics/how-ibm-watson-overpromised-and-

underdelivered-on-ai-health-care

5. https://thehealthcareblog.com/blog/category/health-tech/artificial-intelligence/

6. https://en.wikipedia.org/wiki/Artificial_intelligence_in_healthcare

7. https://s3-prod.modernhealthcare.com/2019-12/us-lshc-artificial-intelligence.pdf

Others References: -

1. Google ML for Problem Solving and Google Images for easy exploration.

2. Machine Learning and AI for Healthcare, Big Data for Improved Health Outcomes

Authors: Panesar, Arjun

Enrollment No: 2250659206 BCSP-064

3.4 Introduction to Tools used in Project

3.4.1 Introduction of Html

Hyper-Text Mark-up Language (HTML) is a simple mark-up system used to create hypertext
documents that are portable from one platform to another.

HTML documents are SGML documents with generic semantics that are appropriate for
representing information from a wide range of applications. HTML mark-up can represent
hypertext news, mail, documentation, and hypermedia; menus of options; database query
results; simple structured documents with in-lined graphics; and hypertext views of existing
bodies of information. Advantages of Html

1 It is widely used.

2 Every browser supports HTML language.

3 Easy to learn and use.

4 It is by default in every window so we don’t need to purchase extra software.

3.4.2 Introduction of CSS

Cascading Style Sheets, fondly referred to as CSS, is a simply designed language intended to
simplify the process of making web pages presentable. CSS allows you to apply styles to web
pages. More importantly, CSS enables you to do this independent of the HTML that makes up
each web page.

Advantages of CSS

1. Greater consistency in design.

2. Ease of presenting different styles to different viewers.

3.4.3 About PHP:

PHP: Hypertext Pre-processor is a widely used, general-purpose scripting language that was
originally designed for web development to produce dynamic web pages. For this purpose,
PHP code is embedded into the HTML source code and can be interpreted but a web server
with PHP processor module, which helps to generate web page document. PHP is a
generalpurpose scripting language that is especially suited to server-side web development
where PHP generally runs

on a web server. It can also be used for command line scripting and client- side GUI
application. Many operating system and platforms, can be used with many relational database
management systems. It is also free of charge.
3.4.4 Working with PHP:

When a client requests web page containing PHP code from the server, then the requested
PHP pages are passed under PHP environment and interaction with database is made if
required. After server-side processing, the resulting HTML pages are passed to client and
displayed on the browser. In this way the working of PHP is complete.

3.4.5 Connecting PHP Application with MySQL Database

ª Make a connection variable with the database:

$conn =

mysql_connect(“localhost”,“servername”,“password”); Here $conn is a connection variable to

database.

ª Select a database over that connection variable:

$db=mysqli_select_db(“databasename”

,“$conn”); ª Prepare a sql query to execute:

$query = Select * from databasename;

ª Run the sql query:

$result = mysqli_query ($query);

ª Iterate over the result:

while ($row = mysqli_fetch_array($result)

//statements

}
3.4.6 Introduction to MySQL:

MySQL is a Relational Database Management System (RDBMS) that runs as a server

providing multi-user access to a number of databases. MySQL is pronounced (“My S- Q-L”)

MySQL development project has made its source available under the terms of General Public
License. MySQL is owned and sponsored by a single for profit firm, the Swedish company
MySQL AB, now owned by Sun Microsystem, a subsidiary of Oracle

Corporation.

MySQL works on many different system platforms including AIX, BSD i, FreeBSD, HPUX,
i5/OS, Linux, Mac OS X, Net BSD, Novell NetWare, Open BSD, Open Solaris, e com Station
, OS/2 Wrap, QNX, IRIX, Solaris, Symbian, SunOS, SCO Open Server, SCO Unix Ware,
Sano’s, Tru64 and Microsoft Windows. A port of MySQL to Open VMS also exits. All major
programming languages with language-specific APIs include Libraries for accessing MySQL
database.

3.4.7 Introduction to APACHE SERVER

In this project Apache server is user to parse and execute PHP pages, before deploying
websites on the server, the website should be tested at the developer’s side to get a feel of how
the website will work on actual server. Therefore, Apache server is like a local server on the
developer side, Apache server should be informed about the environment on which it should
work. In our project Apache server is configured to work with PHP, in this way all the PHP
pages are parsed and executed by the server.