GOVERNMENT POLYTECHNIC, SAKOLI

ACADEMIC SESSION 2024-2025

Project Topic: “DISEASE PREDICTION MODEL”

Submitted by:

Name EnroDecision Tree Sign

Modelent number
MR. ADITYA D. CHAUDHARI 2200910007

MR. ANUJ V. KHEDIKER 2200910064

MS. RUCHI N. KHOBRAGADE 2200910080

Prof. A. A. Bajpayee Sir

Lecturer (Computer dept.) Guided by:

Prof. Arif Rehman
( HOD of Computer Department)

DEPARTMENT OF COMPUTER TECHNOLOGY

1
 Abstract

In this era of IT, technology has revolutionized the health domain to a great extent. This project
aims to design a diagnostic model for various diseases relying on their symptoms. This System
has used data mining techniques such as classification in order to achieve such a model.
Datasets consisting of voluminous data about patient diseases are gathered, refined and classified
and were used for training the intelligent agent.

Here, Various Algorithm were used for classification purpose. Naïve Bayes Classifier
calculates the probability of the disease. It's an example where technology and health
knowledgeare sewn into a thread perfectly with a desire to achieve "prediction is better than
cure".

Keywords: Naive bayes, medical data, classification, data mining.

2
 1. Introduction

1.1 Overview:

Nowadays, the use of the internet has been stimulating curiosity among people and, be it of any
kind, they are trying to find a solution to their problems through the internet only. It is a matter
of fact that people have much easier access to the internet than hospitals and doctors. So, with
the help of this system, a user can consult a doctor by sitting at their home itself. There will not
be any fuss of visiting a clinic or hospitals and making your health condition worse. This
Disease Prediction system is a Machine learning application that predicts the most probable
disease of the user in accordance with the given symptoms by the help of the data sets collected
from different health related sites. It often happens that someone nearer or dearer to you may
need a doctor’s help immediately for some serious reasons but the doctor isn’t available for
consultation for some prior commitments or other obvious reasons. That is when the role of this
automated program comes into play.
This Disease Prediction system can be used for urgent guidance on their illness according to the
details and symptoms they will feed to the Machine learning application. Here, we use some
intelligent data processing techniques to get the most accurate disease that would be related to
the patient’s details. This system can be used for a free consultation regarding any illness.

3
1.2 Objective:

 UserCentric Interface and Experience:

• Design an intuitive and visually appealing interface that enhances user

engagement .

• The interface should be easy to navigate, with clear instructions and

logical flow.
 Early Detection :

• Identify potential health issues before they become serious, allowing for
early intervention and prevention strategies.

 Improved Patient Outcomes:

• Improve patient care through timely and accurate predictions, leading to

better management of chronic conditions and reduced complications.

• Enhance the qualityof life for patients by managing diseases more

effectively and preventing severe health events.

 Patient Engagement and Empowerment:

• Empower patients with knowledge about their health risks and

preventive measures.

• Encourage patients to actively participate in their healthcare byproviding

them with tools and information to manage their health.

4
2. Problem statement and Rational

Identification of need

"Develop an AI-powered disease detection system that can accurately diagnose diseases from
medical images, patient data, and clinical symptoms, to assist healthcare professionals in
providing timely and effective treatment."

Specific Challenges

1. Early Detection: Detect diseases at an earlystage, when symptoms are not yet apparent,
to improve treatment outcomes.

2. Accuracy and Reliability: Develop a systemthat can accuratelydiagnose diseases with

high reliability, reducing the risk of false positives or false negatives.

3. Interpretability and Explainability: Provide insights into the decision-making process

of theAI system, enabling healthcare professionals to understand the basis for the
diagnosis.

4. Data Qualityand Availability: Address the challenge of limited and variable-quality

medical data, which can affect the accuracy of the AI system.

5. Scalability and Integration: Develop a system that can be easily integrated into
existing healthcare infrastructure and scaled to accommodate large volumes of data.

5
2.2Market Overview

The global AI market is projected to reach $190 billion by 2025, growing at a CAGR of 38.1%.
The data detection AI market is a subset of the larger AI market and is expected to grow
significantly in the coming years.

Market Size and Growth

The global data detection AI market size is estimated to be around $1.5 billion in 2022 and is
expected to grow at a CAGR of 25% to reach $6.5 billion by 2027.

Market Segmentation

1. Industry: Healthcare, Finance, Retail, Manufacturing, and others.

2. Application: Fraud detection, Anomaly detection, Predictive maintenance, Quality control,
and others.
3. Deployment: Cloud, On-premises, Hybrid.
4. Component: Software, Services.

6
3. Resource Requirement

3.1 Hardware Requirement:

1) Computer system with minimum 6GB RAM

2) Processor Dual Core or Quad Core Processor (2.0 GHz or higher)

3.2 Software Requirement:

1) AnyOperating System of version developed after year 2015

2) Any Editor based Software like Vs Code

3) Any browser which supports Clientside Scripting Language .

4) Machine Learning Libraries like Scikit-learn, TensorFlow, or PyTorch
for implementing predictive model

7
4. CHATBOT FLOWCHART

Fig.1 Chatbot Structure

8
 5. DESIGNS & FEATURES DESCRIPTION

#ADITYA

Fig.2 DISEASE PREDICTION ( INDEX PAGE)

How It Works:
Sign-Up Process:

User submits a username and password.

The password is hashed and stored securely in the database.
Login Process:
The user enters their credentials.
The system checks the username and verifies the password

HTML for Login and Sign-Up Pages

2. PHP Backend for Database Operations

3. Database Structure
Runthe following SQL commands to create the database and table:

9
 Create a New HTML File:
* Open your chosen text editor.
* Create a new file and save it with a .html extension (e.g., index.html).

View Your Web Page:

* Open in a Web Browser: Double-click the HTML file to open it in your default web browser.
* Use a Live Server Extension: Install a Live Server extension in your text editor
to automatically refresh the page in the browser as you make changes.

Fig.3 SIGN UP & LOG IN PAGE

Login Process:
* Enter Credentials: The user enters their username or email and password.
* Validate Credentials: The system verifies the credentials against the database.
* Successful Login: Ifthe credentials are correct, the user is granted access to the protected
areas of webpage
* Failed Login: If the credentials are incorrect, the user is prompted to try again
orreset their password.

10
Signup Process:

* Enter Information: The user provides necessary information like name, email, password,
and other required details.
* Validate Information: The system checks if the information is valid (e.g., email
format, password strength).
* Create Account: Ifthe information is valid, a new user account is created in the database.
* Successful Signup: The user is notified ofsuccessfulaccount creation and may be redirected to
the login page.
* Failed Signup: Ifthere are errors, the user is informed and prompted to correct the information

Fig.4 LOGIN / SIGNUP FLOWCHART

11
Purpose:
This flowchart illustrates the steps a user takes to register and log into a system, as well as the
process for resetting a forgotten password.
Flow:

* Start: The process begins at the "Start" node.

* Registered? A decision diamond is encountered. The user is asked if theyare already registered.
* Yes: The flow proceeds to the "Login" step.
* No: The flow moves to the "New User" step.
* New User: The user proceeds with the registration process.
* Registration: The user provides necessary information (username, password, etc.) and
submits the registration form.
* User Database: The registration information is stored in the "User Database."
* Login: The registered user attempts to log in with their credentials.
* Correct Password? A decision diamond checks if the entered password is correct.
* Yes: The flow proceeds to the "End" node.
* No: The user is prompted to tryagain or request a new password.
* Forget Password? A decision diamond asks if the user has forgotten their password.
* Yes: The flow moves to the "Request New Password" step.
* No: The user can retrythe login process.
* Request New Password: The user provides their registered emailaddress or other
identifying information.
* New Password: The systemgenerates and sends a new password to the user's registered
email address.
* End: The process concludes at the "End" node.

12
Loigc page table(in database)

User_id User_name email password

#ANUJ

6. DATA MANIPULATION
1. Data Collection:

o Gather relevant health data, including symptoms, patient history, and

diagnostic results.

o Use datasets from reliable sources like Kaggle, UCI Machine Learning
Repository, or medical institutions.

2. Data Cleaning:

o Handle missing values by imputation or removal.

o Remove duplicates and irrelevant data points.

o Normalize and standardize data for consistency.

3. Feature Engineering:

o Extract meaningful features from the raw data that can be used
for prediction.

o Create new features based on domain knowledge (e.g., age groups, BMI
categories).

4. Data Splitting:

o Split the dataset into training, validation, and test sets to train and evaluatethe
model.
7. Bot Development:

1. Choosing a Framework:

o Select a suitable framework for building the chatbot, such as Rasa, Flask,
Dialogflow, or Flask

2. Machine Learning Model:

o Train a machine learning model using libraries like Scikit-learn,

TensorFlow,or PyTorch.

o Choose appropriate algorithms (e.g., Decision Trees, Support Vector

Machines, Naïve Bayes) based on the problem.
#RUCHI
8. FLASK FRAMEWORK

Flask is a lightweight and flexible web framework for Python that's great for developing web

applications and APIs. Its simplicity and ease of use make it an excellent choice for

connecting front-end technologies like HTML, CSS, and JavaScript with back-end services,

including machine learning models.

Key Features of Flask:

1. Minimalism:

o Flask follows a minimalist approach, providing the essentials without

unnecessary bloat. This makes it highly customizable and easy to
learn.

2. Extensibility:

o You can add any number of extensions to Flask to enhance its capabilities,
suchas handling forms, authentication, and database integration.

3. Routing:

o Flask provides a powerful routing mechanism to define URL patterns and

associate them with specific functions, making it easy to handle web
requests.

4. Template Engine:

o Flask uses Jinja2, a powerful template engine for rendering HTML. This
allowsyou to dynamically generate HTML pages with embedded Python code.

5. RESTful Request Handling:

o Flask supports RESTful request handling, making it ideal for developing

APIsthat can be consumed by front-end applications.
9. CHAT BOT TESTING

Pre-Testing Preparation

 Define Testing Goals: Identify the chatbot's functionality, features, and intended user
experience.

 Gather Testing Data: Collect sample user inputs, conversations, and edge cases.

 Choose Testing Tools: Select suitable testing tools, such as chatbot testing platforms,
automation frameworks, or manual testing tools.
 10.Timeline:-

No of weeks Week dates Task to be performed

1st week 1 jan-7 jan Developing login page (frontend part only)

2nd week 8 jan-14 jan Database connectivity for login

page(backend part)
3rd week 15 jan-21 jan Creating a valid Datasets for model

4th week 22 jan-28 jan Developing and using different models (i.e. Text
recognition model,etc) for our chatbot

5th week 29 jan-4 feb Developing and using different models

(i.e. Text recognition model,etc) for our
chatbot
6th week 5 feb -11 feb Training a model using Google Colab

7th week 12 feb-18 Deploying model

feb
8th week 19 feb-25 Integrating both pages chatbot page and
feb user Authentication Page
9th week 26 feb-4 mar Module Connectivity

10th week 5 mar-11 Module testing

mar
11th week 12 mar-18 Overall connectivity of Project
mar
12th week 19 mar-25 Testing and fixing of bugs
mar
13th week 26 mar-1 Making Final Report and Submission
april
Figure 2:Timeline

15
 6. Division of Modules :-

 Member 1: ADITYA D. CHAUDHARI

No of weeks Week dates Task to be performed

1st week 1 jan-7 jan  Member 1: Work on the UI design and
layout for the login page.

2nd week 8 jan-14 jan  Member 1: Set up the

database (MySQL/SQL
Server).

3rd week 15 jan-21 jan  Member 1: Research about disease data

4th week 22 jan-28 jan  Member 1: Research and implement

the text recognition model.

5th week 29 jan-4 feb  Member 1: Train the Prediction

Model model on the dataset.

6th week 5 feb -11 feb  Member 1: Prepare VS code

environment and datasets for
training.

7th week 12 feb-18  Member 1: Set up the

feb server/environment for deploying
the model.

8th week 19 feb-25  Member 1: Work on integrating the

feb chatbot UI with the authentication
page.

9th week 26 feb-4 mar  Member 1: Backend Module

Connectivity

16
10th week 5 mar-11  Member 1: Test the functionality of the
mar authentication page.

11th week 12 mar-18  Member 1: Test overall user experience

mar from login to chatbot interaction.

12th week 19 mar-25  Member 1: Identify and fix bugs

mar related to the user authentication and
login process.


13th week 26 mar-1  Member 1: Write the project background,

april objectives, and methodology sections.


17
 Figure 3: Division Of Modules

 Member 2: ANUJ V. KHEDIKER

No of weeks Week dates Task to be performed

1st week 1 jan-7 jan
 Member 2: Implement the front-
end structure (HTML, CSS,
JavaScript).

2nd week 8 jan-14 jan

 Member 2: Write the backend code for
database interaction (connect, validate
users).

3rd week 15 jan-21 jan

 Member 2: Format the data and clean
it (removing irrelevant information).

4th week 22 jan-28 jan

 Member 2: Integration for the chatbot.

18
5th week 29 jan-4 feb
 Member 2: Train the model and
prepare it for integration.

6th week 5 feb -11 feb

 Member 2: Implement the
training algorithms.

7th week 12 feb-18

feb  Member 2: Deploy the model and
ensure it's working in the deployment
environment.

8th week 19 feb-25 .

feb  Member 2: Implement backend
integration between authentication and
chatbot models.

9th week 26 feb-4 mar

 Member 2: Frontend Module
Connectivity

19
10th week 5 mar-11
mar
 Member 2: Test the chatbot functionality

11th week 12 mar-18

mar
 Member 2: Check for smooth
connectivity and seamless flow
between modules.

12th week 19 mar-25

mar
 Member 2: Identify and fix bugs
related to the chatbot models ( Decision
Tree Model).

13th week 26 mar-1

april  Member 2: Write the results, analysis,
and conclusions sections.

20
 Member 3: RUCHI N. KHOBRAGADE
No of weeks Week dates Task to be performed
1st week 1 jan-7 jan

 Member 3: Test the login page and fix

initial bugs.

2nd week 8 jan-14 jan

 Member 3: Test login functionality with
the database and debug.

3rd week 15 jan-21 jan  Member 3: Validate and structure the

data for model input.

4th week 22 jan-28 jan  Member 3: Test the models

individually to ensure they
function
properly.

21
5th week 29 jan-4 feb Member 3: Test models with real
data to check compatibility.

6th week 5 feb -11 feb  Member 3: Monitor the training

process, collect results, and identify any
issues.

7th week 12 feb-18  Member 3: Test the deployed model and

feb report any errors for fixing.

8th week 19 feb-25

feb  Member 3: Test integration between the
pages and ensure smooth user flow.

9th week 26 feb-4 mar

 Member 3: Testing and Debugging

Connectivity

22
10th week 5 mar-11
 Member 3: Perform overall system
mar
tests, including performance testing.

11th week 12 mar-18

 Member 3: Perform a final round
mar
of tests, fix bugs, and improve
UI/UX.

12th week 19 mar-25

 Member 3: Perform end-to-end testing of
mar
the system, ensuring that all issues are
resolved.

13th week 26 mar-1

april  Member 3: Compile the
documentation, add the final testing
report, and prepare the presentation for
submission.

28
11. CONCLUSSION

The Disease Detector AI system represents a significant breakthrough in the field of

healthcare technology. Its potential to revolutionize disease detection and diagnosis
is vast, and we are excited to continue advancing this technology to improve patient
outcomes and transform the healthcare landscape.

This AI-powered system has the potential to transform the way diseases are detected
and diagnosed, enabling healthcare professionals to:

1. Detect diseases at an early stage, reducing the risk of complications

and improving patient outcomes.

2. Diagnose diseases with unprecedented accuracy, minimizing the risk

of misdiagnosis and unnecessary treatments.

3. Personalize treatment plans based on individual patient characteristics,

medical histories, and genetic profiles.

29
12. REFERENCE

o https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9885935/

o https://www.viatrisconnect.in/en-IN/Therapeutic-Areas/Digital-Therapeutics/Disease-Detection-
Using-AI

o https://www.cureus.com/articles/189594-perspective-of-artificial-
intelligence-in-disease- diagnosis-a-review-of-current-and-future-endeavours-
in-the-medical-field

o https://gemini.google.com/

30