General Disease Prediction Using ML

A
Report submitted
in the partial fulfillment of the requirements for the award of the degree of

Bachelor of Technology
in
Computer Science and Engineering

by
Adarsh Gupta: 1900520109001
Jyoti Maurya: 1900520109004
Zainab Israr: 1900520109006

Under the guidance of

Mr. Natthan Singh
Dr. Aditi Sharma

Department of Computer Science and Engineering

Institute of Engineering and Technology, Lucknow
Dr. A.P.J. Abdul Kalam Technical University,
Lucknow, Uttar Pradesh
2021-22
 CONTENTS

DECLARATION…………………………………………………………………..…..….3
CERTIFICATE………………………………………………………………….…….….4
ACKNOWLEDGMENT ……………………………………………………….….…......5
ABSTRACT…………………………………………………………………………….…6
LIST OF FIGURES………………………………………………………….....….…..….7
LIST OF TABLES………………………………………………………………….……..8
1. INTRODUCTION……………………………………………………………….…...9
2. LITERATURE REVIEW………………………………………………….……..…10
3. METHODOLOGY………………………………………………………….….…….11
3.1 PROPOSED MODAL……………………………………………………….12
3.1.1 DECISION TREE ALGORITHM………………………………...12
3.1.2 NAIVE BAYE’S CLASSIFIER………………….…….…………13
3.1.3 RANDOM FOREST ALGORITHM………………..……..……...14
3.2 REQUIREMENT ANALYSIS……………………………………………....15
4 SYSTEM DESIGN………………………………………………….………………..16
4.1 SYSTEM ARCHITECTURE…………………………………….…………..16
4.2 DATA FLOW DIAGRAM………………………….……………………….16
4.3 SEQENCE DIAGRAM………………………………………………………17
4.4 USE CASE DIAGRAM…………………………………………….………..18
4.5 ACTIVITY DIAGRAM……………………………………………………...19
5 IMPLEMENTATION………….………………………………………………...…..20
6 TESTING………………………………………………………….………………21-22
7 TOOLS AND TECHNOLOGY USED…….…………………………………....23-24
8 RESULTS……………………………………………..………………………..…25-29
9 CONCLUSION AND FUTURE ENHANCEMENT……………………..………...30
9.1 CONCLUSION………………………………………………………………30
9.2 FUTURE ENHANCEMENT…………………………………………..……30
10 REFERENCE…………………………………………………………………...........31

2
 DECLARATION

We hereby declare that this submission is our own work and that, to the best of our belief and
knowledge, it contains no material previously published or written by another person or
material which to a substantial error has been accepted for the award of any degree or
diploma of university or other institute of higher learning, except where the acknowledgement
has been made in the text. The project has not been submitted by us at any other institute for
requirement of any other degree.

Date: 29/05/2022

Submitted by: -

(1) Name: Adarsh Gupta

Roll No.: 1900520109001
Branch: CSE
Signature:

(2) Name: Jyoti

Roll No.: 1900520109004
Branch: CSE
Signature:

(3) Name: Zainab Israr Ansari

Roll No.: 1900520109006
Branch: CSE
Signature:

3
 CERTIFICATE

This is to certify that the project report entitled “General Disease Prediction Using ML”
presented by Adarsh Gupta, Jyoti and Zainab Israr Ansari in the partial fulfillment for the
award of Bachelor of Technology in Computer Science and Engineering, is a record of work
carried out by them under my supervision and guidance at the Department of Computer
Science and Engineering at Institute of Engineering and Technology, Lucknow.
It is also certified that this project has not been submitted at any other Institute for the award
of any other degrees to the best of my knowledge.

Mr. Natthan Singh

Department of Computer Science and Engineering

Institute of Engineering and Technology, Lucknow

Dr. Aditi Sharma

Department of Computer Science and Engineering
Institute of Engineering and Technology, Lucknow

4
 ACKNOWLEDGEMENT

We bow in reverence to God who gave us the required zeal for making the project. We are
deeply indebted to our Head of the Department Dr. Divakar Singh Yadav. We owe,
department gratitude to Mr. Natthan Singh and Dr. Aditi Sharma of IET Lucknow for their
valuable guidance and suggestions and treatment for giving helpful guidelines for the project.
We also thanks to Project Committee for their Proper guidance, support, and suggestion to us
time to time.

We feel highly proud in expressing our coordinate thanks to respected parents, brothers, and
friends who have helped us in this project.

Adarsh Gupta: 1900520109001

Jyoti Maurya: 1900520109004
Zainab Israr Ansari: 1900520109006

5
 ABSTRACT

General Disease Prediction using Machine Learning is a system that predicts the disease on the
basis of symptoms that the user enters into the system and then it provide the accurate result
based on those symptoms that are entered. This system works as an initial phase diagnosis of
disease when the user is not much serious or not able to go hospital or not sure about disease
and he/she wants to know disease. In today’s world health industry plays critical role in curing
the diseases that the patient is suffering from. So this system will be helpful for the health
industry. It is useful for those person who doesn’t want to go to the hospital or any other
clinics, then only by entering the symptoms, he/she can get to know the disease that he/she has
been suffering from and also the healthcare sectors can also use this system and get benefit as
only by asking the symptoms of the patient and entering it in the system and within seconds
the system will tell the exact and accurate diseases. This General Disease Prediction Using
Machine Learning project is a web application, which is based on Django framework and
python language is used for implementation of Machine Learning Model and taking reference
from previously available dataset of hospitals. Using this dataset system will predict the
accurate disease of each and every patient.

6
 LIST OF FIGURES

Fig 3.1 Decision Tree Example.………………………………………………………….12

Fig 3.2 Naïve Baye’s Example………………………………………………………...…13
Fig 3.3 Random Forest Example………………………………………………………....14
Fig 4.1 System Architecture………………………………………………………………16
Fig 4.2 Data Flow Diagram (Level-0)………………………………...…………….....…17
Fig 4.3 Data Flow Diagram (Level-1)……………………………………………………17
Fig 4.4 Sequence Diagram…………………………………………………………….….18
Fig 4.5 Use Case Diagram………………………………………………………………..18
Fig 4.6 Activity Diagram……………………………………………………...………….19
Fig 8.1 Training Data……………………………………………………………………. 25
Fig 8.2 Testing Data………………………………………………………………………25
Fig 8.3 Registration Page…………………………………………………………………26
Fig 8.4 Login Page………………………………………………………………………..26
Fig 8.5 Login Page showing invalid Email id/ Password………………………………..27
Fig 8.5 Dashboard………………………………………………………………………………27
Fig 8.6 Dashboard with chosen Symptoms…………………………………………………….28
Fig 8.7 Dashboard with predicted output………………………………………………………28
Fig 8.8 Past record of patient…………………………………………………………………..29

7
 LIST OF TABLES

Table 6.1 Test Case for User Registration………………………………………….…….21

Table 6.2 Test Case for User Login………………………….……………………….…..22
Table 6.3 Test Case for Prediction of Result……..……………………………….…….. 22

8
1. INTRODUCTION

Nowadays, when anyone suffers from any health-related issues, then the person has to
visit a doctor which takes time and it is costly too. It has been observed mostly that every
2 months, over 70% of the population in India tends to general body disease like viral
fever, cold and cough, etc. Since a lot of people don't realize that the symptoms of these
regular ailments may be symptoms of something more dangerous, 25% of the population
succumbs to death due to ignorance of the early-stage symptoms. Thus, the identification
of the disease in the initial stages is important for the prevention of any unwarranted
casualties. The medical system is mainly devoted to specific areas, known diseases and is
insufficient to identify and accurately diseases based on early-stage symptoms. Also if
the user/patient is not able to reach hospital and is unable to consult a doctor it may be
difficult for the user/patient as the disease can not be identified. So, if the above problems
are resolved by using an automated application that can be less time-consuming as well
as money, it will be very helpful and easier for the user.

The “General Disease Prediction” will be a web application that will give predictions on
the basis of symptoms provided by the user. It will help the user/patient to identify the
disease on the basis of symptoms that he/she will enter into the system and provide
accurate results on the basis of those symptoms.

The application is designed in such a way that it eliminates the errors as much as
possible, while entering the information. It will give suggestions while entering the
information. This application would be very easy to use as there is no formal knowledge
required for a person to use this application. It is a user-friendly system, which leads to an
error-free, reliable, safe, secure and quick prediction system. It helps the users to know
their disease and they can take some precautions.

9
 2. LITERATURE REVIEW

● Pahulpreet Singh Kohli, Shriya Arora [2018], proposed their work as “Application of
Machine Learning in Disease Prediction”. In this paper, the accuracy reaches 87.1% using
logistic Regression and 85.71% using Support Vector Machine [1].

● Dhiraj Dahiwade, Prof. Gajanan Patle, Prof Ektaa Meshram [2019], presented their work
as “DESIGNING DISEASE PREDICTION MODEL USING MACHINE LEARNING
Approach”. There they used two algorithms (K-Nearest and CNN) to work on their
project. It was found out that the accuracy of CNN was 84.5% which was more than KNN
algorithm. The memory and time requirement was found to be more in KNN as compared
to CNN [2].

● Nikita Pawar, Pooja Sonawane, Narendra Gawai[2020] made a web-based application

named “DECISION TREE BASED HEALTH PREDICTION SYSTEM”. In this
application, the user provides the symptoms he/she is facing and checks for further
symptoms. Accordingly the system checks the InfoBase and extracts the data from it and
predicts the accurate disease that the person is affected by. In this method it provide
multiple symptoms option through which the patient to search for the symptom he/she is
facing. multiple symptom options so that the patient could search for every possible If the
symptoms that the user had entered doesn't match any disease in the database, then it
displays the disease that the user could probably have related to his/her symptoms. If the
system isn't ready to provide suitable results, it urges users to travel for biopsy, x-ray, or
CT scan [3].

● Nishant Yede , Ritik Koul , Chetan Harde , Kumar Gaurav , Prof. C.S.Pagar [2021]
proposed their work as “GENERAL DISEASE PREDICTION BASED ON SYMPTOMS
PROVIDED BY PATIENT”. They have applied three algorithms namely Naive Baye’s
Classifiers, Random forest and Decision tree. It was found out that this model have better
accuracy as compared to the existing ones. When the result of different algorithms are
compared, the accuracy of the proposed algorithm was found to be 94.8% having regular
speed which is faster as compared to the unimodal disease risk prediction algorithm [4].

10
3. METHODOLOGY

Since we all know that mankind is involved so much in this competitive era of economic
development that he/she is not much concerned about their health. So, this project General
Disease Prediction using Machine Learning is designed to identify the type of disease in
earlier phase. It is implemented using python and django framework and is converted into
a web application where the users have to register first to get access to the system.

The system has user module only. User is a person who wants to check for the disease
based on the symptoms. If the user is already registered then he/she can log in to the
system otherwise he/she has to firstly register in the system. The user can register into the
system with username, email-id, date of birth and password. All these details of the user
are stored in the database. After successful registration, the user can login into the system.
The login can be done using email address and password which the user has provided
during the time of registration. Authentication is done by the system for each user. If the
details entered regarding email address/password are incorrect then the error message will
prompt stating that incorrect email address/password. So, correct email address and
password both is essential to login into the system.

After logging in the user will reach to the dashboard page where he/she can perform
following functionalities:

a. Entering Symptoms
b. Disease Prediction
c. Previous Disease

Step 1: Entering Symptoms: After logging into the system the main page will appear on
which drop-down menu is given to select the symptoms. The user can select the
symptoms from the list given in the form of drop down menu. To have better accuracy of
the result, the user is required to enter more than three symptoms. In our project, three
algorithms of machine learning are used for prediction of result. These algorithms are
Decision Tree, Random Forest and Naïve Baye’s are there for prediction. The system
allows the patient to enter the symptoms and based on those symptoms, the system will
predict the disease.

Step 2: Disease prediction: After entering all the symptoms the user needs to press the
predict button. The result of the prediction will be outputted on the screen. We have used 3
algorithms to predict the type of disease and in final the result of the algorithms having
highest accuracy will be shown to the user.
The main purpose behind implementing this method is that if the user does not have
experience in the medical profession and want to know about their health conditions,
he/she can quickly find it without help of technical or medical person. We have tried to
design the user interface to be as much interactive so that it is user friendly.

Step 3: Previous Disease: The user can view the previous record of the diseases that he has
been through.

11
3.1. Proposed Modal
Machine learning is the important principle in which the system provides more precise
predictions. Disease Prediction can be implemented using different techniques like
Support Vector Machine, Neural networks, decision tree and Naive Bay’s algorithm, etc.
But, In our project we have used three algorithms namely Decision Tree, Naïve Baye’s
and Random Forest.

3.1.1 Decision tree algorithm

 It is a type of Supervised Machine Learning in which the data is splitted
continuously on the basis of certain parameters.

 It has a tree-like structure having two entities: leaves and decision nodes. The
leaves represent decisions or the final outcomes of the problem and the decision
nodes are where the data is split further nodes.

 Decision trees solve two types of problem that is classification (it is categorical
data type) and Regression (it is continuous data type).

 It has a very good accuracy as compared to other algorithms.

 The accuracy of decision tree is not affected by the presence of redundant

attributes.

Fig 3.1: Decision Tree Example

12
3.1.2 Naive Bay’s classifier

 Naïve Baye’s is a supervised learning Algorithm, which is used for prediction

problem that have categorical level data.
 On the basis of training set and the values in a classifying attribute, it classifies the
class data and uses it in classifying new data that is used for training purpose.
 It uses Bye’s theorem for classification of problems that uses probabilistic approach.
 It works on both continuous value attributes and categorical type dataset.
 In this algorithm, firstly find the probability of an event occurring when the
probability of another event that has already occurred is given. It is based on
following equation:
P(A/B)=P(B|A)P(A)/P(B)
 The working of this algorithm with the dataset is described as:
 It divides the given dataset into two parts: response vector and feature matrix.
 Feature matrix contains vectors which represent rows of the dataset and the value of
dependent features of dataset will be stored and represented by every vector of matrix.
 Response vector consists of values of class variable for every row of feature matrix.
 The fundamental assumption of naïve bay’s classifier is that equal and independent
contribution is made by each.

Fig: 3.2: Naïve Baye’s Example

13
3.1.3 Random Forest Algorithm

 It is a supervised machine learning technique that can be used for both types of
problems namely: Classification and Regression.
 It is based on the concept of ensemble learning that have several decision tree
models that have individual outcome.
 In random forest there are multiple decision trees on different subsets of the
training dataset and to improve the predictive accuracy of the dataset and majority
voting outcome is taken.
 Random forest classifier does not depend on single decision tree, instead it
evaluates the prediction from every decision tree and on the basis of majority
voting of predictions, it predicts the final output based on that.
 It uses Gini Index for determining the final class in each tree.
 Large number of decision trees in the Random Forest Algorithm is used to
achieve better accuracy and to prevent from the problem of overfitting.

Fig 3.3: Random Forest Algorithm Example

14
3.2. Requirement Analysis
Tools/Platform/Software and Hardware Specification:
Hardware Requirement:
 System : Pentium 4, Intel Core i3, i5, i7
 RAM : 512 Mb or above
 Hard Disk : 10 Gb or above
 Input Device : Keyboard and Mouse
 Output Device : Monitor or PC

Software Requirement:
 Operating system : Windows XP, 7, 10 or Higher Versions
 Browser : Google Chrome, Firefox, IE 10.0 or later
 Database : MySql

Developer
 Database : MySql
 IDE : PyCharm
 Documentation Tool: MS Word, MS Power-point
 Front End : HTML, CSS, JavaScript
 Framework : django
 Back End : Xamp
 Programming Language: Python

15
4. SYSTEM DESIGN

4.1 SYSTEM ARCHITECTURE

In the architecture of our project general disease prediction using machine learning have
different datasets on which comparison is done with the symptoms that the user entered
and predicts it. The datasets are converted into the small data sets that is training dataset
and testing dataset, after that the data which is classified is processed into the machine
learning technologies. The disease prediction model using all the input data from the
user and overall processed data compares the relation and predict the final disease
accordingly. After training phase, model uses testing dataset for evaluating the
prediction model.

Fig 4.1: System Architecture

4.2 DATA FLOW DIAGRAM

This dataflow diagram of the project “General disease prediction using machine
learning” shows how the data flows from one step to another in the model, like the
patient enters the details and symptoms into the system. This data goes into the system,
and a comparison is made with the prediction model and if true it predicts the appropriate
result.

16
 Fig 4.2: DFD(Level-0)

Fig 4.3: Data Flow Diagram (Level-1)

4.3 SEQUENCE DIAGRAM

The sequence diagram represents how the model flows from one step to another step, like
the user enters into the system through login then symptoms of that he/she is having, that
enters into the system, then it is compared with the predictive model and if the result turns
out to be true then it predicts the results otherwise it shows the details that the user have
entered incorrectly and it also shows the precautionary steps for the user to follow. Here the
sequences of all the entities are linked to each other where the user gets started with the
system.

17
 Fig 4.4: Sequence Diagram

4.4 USE CASE DIAGRAM

This use case diagram shows the description of the functionality of a system from user
perspective like the user enters the symptoms that goes into the system, and a comparison is
made with the prediction model and it predicts the output.

Fig 4.5: Use Case Diagram

18
4.4 ACTIVITY DIAGRAM
Activity Diagram is a flowchart that shows the flow from one activity to another activity.
The operation of the system is described as an activity. From one activity to other activity,
the flow of control is drawn. In this activity diagram, the activity starts from user where the
user firstly registers into the system to get access of the system then login using the
credentials and then the credentials are verified with the system and if its verified, then the
user proceeds to the main dashboard page where he/she can perform prediction. Then after
entering the symptoms and processing the data from datasets the analysis will happen after
that the correct result of the prediction will be displayed.

Fig 4.6 Activity Diagram

19
5. IMPLEMENTATION
The system is designed in such a way that it is user friendly. Each time when the user
enters into the system, authentication is required. After which the system provides the
result based on the input entered by the user. The implementation of the system is
described below:
 Once user opens the system he/she needs to register itself first to get the access to
the system, if the user is not registered previously.
 For registration user needs to provide some basic details (Username, Email
Address, Date of Birth, and Password) for signup and then the details of user are
saved in system.
 Then user is required to login to have a checkup of his/her health.
 For login, users have to provide Email Address and Password.
 While logging in if the user details are wrong then, the system will show a prompt
message which states that the user incorrect username or password
 Hence it is important for the user to enter the correct email address as well as
password to get access to the system.
 After logging in, the user will be navigated to the dashboard page where he/she
can enter the symptoms that the user is having.
 Based on the symptoms the predicted output will be displayed as result.
 We have used several algorithms which will predict the disease and the result of
the algorithm having best accuracy will be displayed as output.
 The user needs to enter at least 3 symptoms and maximum 5 symptoms to get the
accurate result.
 Data collection and dataset preparation: This involves the collection of
information related to medical from different sources like hospitals or other health
care industries, after that pre-processing is done on that dataset that removes all
the information which is not necessary and negatively affected the output of model
and extract important features from dataset using statistical approaches. We have
collected the dataset from Kaggle.
 Training the datasets: The General Disease Prediction model is trained on the
dataset of diseases to predict accurately. In this system 3 different algorithms were
used:
 Decision Tree Algorithm
 Naïve Bay’s Algorithm
 Random Forest Algorithm

20
6. TESTING

6.1 UNIT TESTING

Unit testing is a type of testing in which test cases are designed in such a way that they
validate the proper functioning of the internal program logic. The input provided to the
program should produce valid outputs. Validation should be done for all the internal code
flow and decision. It tests the individual software units of the application. Unit testing is
performed before integration and after the individual unit is completed. It is a sort of
structural testing as it relies on knowledge of its construction. Testing is performed at the
level of component and tests specific processes or application.

6.2 INTEGRATION TESTING

Integration tests is a type of testing in which testing is done on the integrated software
components to check whether it runs as a one program or not. It is performed after all the
software components are integrated as a single program. Integration testing is done to show
that even after the components are individually tested by unit testing, the combination of each
component is correct and consistent. The purpose of integration testing is to expose the
problems that occur from the combination of components.

6.3 SYSTEM TESTING

System Testing is a type of testing which is performed after the integration of hardware and
software system for the verification that the system meets its specified requirements. System
Testing confirms that all the code modules work properly as specified, and also the system
as a whole performs well on the platform on which it will be deployed.

Description Input Output Remarks

User enters detail for Name, If the details of the user are correct, Test Successful
registering in the Email the user gets registered. If the details
system Address, are incorrect, it displays error
Date of message.
Birth,
Password,

Table 6.1: Test Case for User Registration

21
 Description Input Output Remarks

User enters detail for Username If the details entered for login are Test Successful
Login in the system and correct, the user will get logged in
Password into the system and dashboard page
will be displayed. If the details
entered for login are incorrect then it
shows error message.

Table 6.2: Test case for User Login

Description Input Output Remarks

The user will be Symptoms If user enters all five symptoms Test Successful
required to enter correctly then the accuracy will be
minimum 3 and high. If less than 3 symptoms are
maximum 5 entered, then accuracy will be low.
symptoms
Table 6.3: Test case for Prediction of Disease

22
7. TOOLS AND TECHNOLOGY USED
Python
Python is a multi-paradigm programming language. It supports Object-oriented
programming and structured programming.

HTML
It is known as Hyper Text Markup Language. It describes the structure of the web page . It
provides information in the document by denoting certain text as links, heading, paragraph,
list and so on. It is written in the form of tags, surrounded by angle brackets. It also
describes some semantics and the appearance of the document. It provides functionality to
embed scripting language code which affects the behavior of web browser.

CSS
CSS, an initialize of Cascading Style Sheet, is a simple designing language for the web
page. It is used to make the process of making the web page presentable in a simplified
manner. The functionalities provided by CSS are one can control the text color, font style,
layout and size of columns, display variations for different devices and screen size, space
between paragraphs, layout, designs, color and background images.
CSS provides a way through which the presentation of HTML document can be controlled.
It is easy to understand and learn. It is used in combination with markup languages like
HTML or XHTML.

JAVASCRIPT
It is a text-based programming language which is utilized for both client side and server
side. It allows making interactive web pages. It helps in making static HTML web pages
into dynamic and interactive one. Web Pages can be made dynamic by dynamically
controlling multimedia, updating content, animate images, validating form data.

MYSQL
It is an open source relational database management system. It is developed distributed and
supported by Oracle. It works on client/server and also on embedded systems. It consists of
multithreaded SQL servers which have support for different client programs, back ends,
libraries, administrative tools and a wide range of application programming interfaces
(APIs).

DJANGO
It is a high level Python web framework. It encourages maintainable, secure, clean
pragmatic design and rapid development of websites. It takes care of most of the hassle of
web development, so one can focus on writing an app without having the need to reinvent
the wheel.

23
JUPYTER NOTEBOOK
It is an open source web application. It is used to create and share documents that contain
equations, visualizations, live code. It is a client-server application. It provides
functionalities to perform all type of data science related tasks data cleaning, data
transformation, data visualization, statistical modeling, machine learning, and deep learning.
It can be converted into different types of standard output formats using web interface. It
provides flexibility and ease in sharing the work with others.

It has two components: Front end web page and a Back end kernel. Front End helps in
writing the code and text in the rectangular cells provided. Back end kernel runs this code
which is passed by the browser and returns the result.

PYCHARM
It is hybrid platform and an integrated development environment (IDE) for python which is
used in computer programming. It provides packages, modules and tools to speed up the
Python development. It can be customized according to the requirements and personal
preferences.

24
8. EXPERIMENTAL RESULT

Fig 8.1: Training Data

Fig 8.2: Testing Data

25
Fig 8.3: Registration Page

Fig 8.4: Login Page

26
Fig 8.5 Login page showing Invalid Email or Password

Fig 8.6: Dashboard

27
Fig 8.7: Dashboard with Chosen Symptoms

Fig 8.8: Dashboard Predicting Disease

28
Fig 8.9: Past Record of Patient

29
9. CONCLUSION AND FUTURE ENHANCEMENT

9.1 CONCLUSION

This project “General Disease Prediction using ML” provide prediction for various
diseases that are occurring generally in a person and mostly people ignore this which
sometimes turn into fatal disease and create a lot of problems for the patient and family
also. In the present time, the internet is emerging every day and people are always very
much eager to use different new technologies. People mostly prefer to refer to the internet
if any problem arises. Nowadays, People have very quick access to the internet than
hospitals and doctors as the internet is available all the time and can be accessed from
anywhere. Sometimes, people do not have immediate options for doing anything and
going to the hospital when they suffer from a health-related issue. For those, this
application can be very helpful and they have access to this system with the help of the
internet any time in a day.
In conclusion, this project “General Disease Prediction using Machine Learning” will be
very much helpful in everyone's daily life. Nowadays the health industry plays a major
role in curing the diseases of the patients so this application will provide some help to the
health sectors and also it will be useful for the user in case they don’t want to go to the
hospital or any other clinic. So, just by entering symptoms, the user will get to know
about the disease they are suffering from. The work of the doctor can also be reduced, if
the health industry adopts this project as it can easily predict the disease of the patient.

9.2 FUTURE ENHANCEMENT

 More Interactive user interface

 Suggestions, Precautions to take based on the predicted disease
 We can add doctor module from where the patient can get the information of the doctor
and can directly contact him for medication.
 More details and latest diseases can be inserted.
 It can be converted into Mobile Application.

30
10. REFERENCES

[1] Pahulpreet Singh Kohli, Shriya Arora, “APPLICATION OF MACHINE LEARNING IN

DISEASE PREDICTION”, 4th International Conference on Computing Communication and
Automation (ICCCA), IEEE, 2018.
[2] Dhiraj Dahiwade, Prof. Gajanan Patle, Prof Ektaa Meshram, “DESIGNING DISEASE
PREDICTION MODEL USING MACHINE LEARNING APPROACH”, Proceedings of the
Third International Conference on Computing Methodologies and Communication (ICCMC
2019), IEEE, 2019.
[3] Nikita Pawar, Pooja Sonawane, Narendra Gawai “DECISION TREE BASED HEALTH
PREDICTION SYSTEM”, International Journal for Research in Applied Science &
Engineering Technology (IJRASET) Volume 8 Issue VII ISSN: 2321-9653, 2020.
[4] Nishant Yede , Ritik Koul , Chetan Harde , Kumar Gaurav , Prof. C.S.Pagar, “GENERAL
DISEASE PREDICTION BASED ON SYMPTOMS PROVIDED BY PATIENT” Open
Access International Journal of Science and Engineering, Volume-6, ISSN: 2456-3293, 2021.
DataSet:- https://www.kaggle.com/kaushil268/disease-prediction-using-machine-learning

31