You are on page 1of 15

Madhuben & Bhanubhai Patel Institute of Technology

(A Constituent College of CVM University )


Faculty Of Engineering And Technology

Department of Information Technology


Academic Year: 2023-24 (II)

DIABETES PREDICTION SYSTEM

COURSE: 102040601 - MINI PROJECT


SEMESTER: 6th
Group Id : MP08
Prepared By:
Project Guide: AYUSH CHAUHAN(12102080701014)
Prof. Mehul Thakkar DEEPKUMAR PATEL(12102080701017)
OUTLINE

• Abstract - Idea
• Introduction
• Modules
• S/W and H/W Requirements
• DataSet
• Conclusion
• References
ABSTRACT

• This project develops a Diabetes Prediction System


integrating machine learning with a user-friendly
website.

• Utilizing a reliable dataset from health organizations, the


system predicts diabetes likelihood based on user-
inputted health parameters.

• The output includes clear predictions and insights,


empowering users to proactively manage their health.
The project's impact lies in early detection to improved
healthcare outcomes.
Introduction
• This project addresses the pressing issue of diabetes by
developing a streamlined and user-friendly Diabetes Prediction
System.

• With the rising global prevalence of diabetes, early detection


becomes crucial for effective intervention and improved health
outcomes.

• we aim to create a predictive model that analyzes relevant


health parameters, providing individuals with personalized
predictions on their likelihood of developing diabetes.
Introduction
• This Diabetes Prediction System is crafted using machine learning,
where we create, train, and test the predictive model with a CSV
file containing relevant health data.

• The backend is powered by Python, ensuring robust data


processing and machine learning capabilities.

• For the frontend, we employ the classic trio of HTML, CSS, and
JavaScript, offering a seamless and intuitive user interface for
individuals to input their health information and receive
personalized predictions.
Modules

Machine learning
Web interface

Data processing
Intregation
Module 1 – Data Processing Module
Input: CSV file with health parameters data.

• Processing Steps:
• Handle missing values and outliers.
• Normalize or scale features for consistent model training.

• Output: Preprocessed and cleaned dataset ready for machine


learning model training
Module 2 – Machine Learning Module
Module 3 – Web Interface

Input: User-entered health parameters.

• Processing Steps:
• Validate user inputs on the frontend.
• Send the validated data to the backend for prediction.

• Output: Display of predictions and insights on the


website in a user-friendly format.
Module 4 – Integration
Input: Trained machine learning model, user inputs.

• Processing Steps:
• Receive user inputs from the web interface.
• Utilize the trained model to predict the likelihood of diabetes.
• Return predictions and insights to the web interface.

• Output: Integrated system providing real-time predictions and insights on the web interface.
S/W & H/W Requirements
• S/W Requirement
1)Python
2)Django
3)Machine Learning toolkit
4)web browser
5)Integrated Development Environment (IDE) for coding, such as VSCode,
PyCharm.

• H/W Requirement
1)A multi-core processor (e.g., Intel i5 or equivalent)
2)Minimum of 8 GB RAM for handling large datasets and model training
3)Adequate storage space for storing datasets, trained machine learning
models.
4)Internet connection and web browser
Database Design / Dataset
• Number of tables
1)diabetes_woman – (Pregnancies,Glucose, Blood Pressure,Skin Thickness,
Insulin,BMI, Age, Outcome)
Conclusion
• The project promotes proactive healthcare management.

• The seamless integration of technology not only


facilitates risk assessment but empowers individuals to
take informed steps toward better health outcomes,
exemplifying the potential of accessible machine learning
solutions in healthcare.
References

• https://www.youtube.com/watch?v=E0gaPgiISoU&list=PLQRwhZe4lltkA6KaWkSYMrl63
YaFEeLz&ab_channel=MorgenCoder

• https://www.kaggle.com/datasets/uciml/pima-indians-diabetes-database

• https://www.analyticsvidhya.com/blog/2022/01/diabetes-prediction-using-machine-learning
/

• https://ieeexplore.ieee.org/document/10128216
THANK
YOU

You might also like