You are on page 1of 13

Department of Information Technology,

MET’s Institute of Engineering, Adgaon, Nashik


Savitribai Phule Pune University
2022-23

Synopsis

on

DIABETES PREDICTION USING MACHINE LEARNING

Submitted by

Sakshi Gore
Mayank Gupta
Prince Karavadiya
Shubham Ubale

Prof. Kanchan Dhomse


Project Guide

Dr. P. S. Lahane Dr. S. V. Gumaste


Project Coordinator HOD
INDEX

Sr. No Title Pg. No

1 Introduction 1

2 Literature Survey 2

3 Problem Statement 3

4 Aim and Objectives 3

5 Motivation 4

6 System Architecture 4

7 Project Plan 5

8 Project Methodology 5

9 Software and Hardware Requirements 7

10 Functional & Nonfunctional Requirements 8

11 Applications 9

12 Conclusion 10

13 References 11
[1] Introduction
• Diabetes is the fast-growing disease among the people even among the
youngsters. In understanding diabetes and how it develops, we need to
understand what happens in the body without diabetes. Sugar (glucose)
comes from the foods that we eat, specifically carbohydrate foods.
• Carbohydrate foods provide our body with its main energy source
everybody, even those people with diabetes, needs carbohydrate.
Carbohydrate foods include bread, cereal, pasta, rice, fruit, dairy
products and vegetables (especially starchy vegetables).
• When we eat these foods, the body breaks them down into glucose.
The glucose moves around the body in the bloodstream. Some of the
glucose is taken to our brain to help us think clearly and function.
• The remainder of the glucose is taken to the cells of our body for
energy and also to our liver, where it is stored as energy that is used
later by the body. For the body to use glucose for energy, insulin is
required. Insulin is a hormone that is produced by the beta cells in the
pancreas.
• Insulin works like a key to a door. Insulin attaches itself to doors on
the cell, opening the door to allow glucose to move from the blood
stream, through the door, and into the cell.
• If the pancreas is not able to produce enough insulin (insulin
deficiency) or if the body cannot use the insulin it produces (insulin
resistance), glucose builds up in the bloodstream (hyperglycaemia) and
diabetes develops.

1
[2] Literature Survey

Sr. Authors Title Implementation Technical Findings /


No. (Advantage dis-
advantage)

1 Malini M Diabetic Patient Using Machine Learning Machine Learning


Prediction Algorithm, 2021 Smart algorithms and statistics
Technologies, are used to predict the
Communication and disease with the help of
Robotics (STCR) current and past data

2 B.V. Baiju Disease Using Medical Data Set A Disease Influence


Influence Using Data Mining, Measure (DIM) based
Measure Based 2019 1st International diabetic prediction has
Diabetic Conference on been presented
Prediction. Innovations in
Information and
Communication
Technology (ICIICT)

3 Siddharekh S. Implementation Using Data Mining, 2019 We use neural network


Patil of Diabetic 3rd International (NN) and naïve bayes
Retinopathy Conference on for classification.
Prediction Computing
System. Methodologies and
Communication
(ICCMC).

4 Lifeng Qiao Diabetic Using Prognosis of Easy to used, but has


Retinopathy Microaneurysm and low accuracy as
Detection Early Diagnosis System compare to other system
for Non-Proliferative
Diabetic Retinopathy
Based on Deep Learning
Algorithms, IEEE
Access (Volume: 8)

2
[3] Problem statement
The diabetes is one of lethal diseases in the world. It is additional an
inventor of various varieties of disorders for example: coronary failure,
blindness, urinary organ diseases etc. In such case the patient is required to
visit a diagnostic center, to get their reports after consultation. Due to every
time they have to invest their time and currency.

[4] Aim
Aim: Diabetics Prediction Using Machine Learning at early stage.
Objectives: -
• To predict the diabetics at early stage.
• To Avoid the Time-consuming task of feature extraction.
• To Effectively increase the accuracy to 80-85 %.
• To provide a cost-effective solution in market.

3
[5] Motivation

Diabetes is emerging as a predominant disease in the developing


countries like India. The disease is becoming very serious and cause many
other problems in the human body. Many factors are remaining as a cause
for this disease in human body. The disease is not curable and can only be
controlled.

[6] System Architecture

Fig 1: System Architecture

4
[7] Project plan

Sr.NO Activity Schedule Duration


SEMESTER 1
1 Registration of Project Group Week 2
2 Project Topic Revisit and submission Week 3
3 Allocation of Guide Week 4
4 Submission of Abstract to Project Guide and Project Week 4
Coordinator in the prescribed Format
5 Project Review-1 Week 6
6 Project Review-2 Week 10
7 Verification of Project Work Book by Internal Guide Week 11
(before submission of Preliminary Project Report)
8 Submission of Final Preliminary Project Report in Week 12
Prescribed Format
9 Term-Work Evaluation As per Departmental
Schedule

[8] Project Methodology

Problem Solving Methods are concerned with efficient realization of


functionality. This is an important characteristic of Problem-Solving Methods
and should be deal with it explicitly.
Problem Solving Methods achieve this efficiency by making
assumptions about resources provided by their context (such as domain
knowledge) and by assumptions about the precise definition of the task.
It is important to make these assumptions explicit as it gives the reason
about Problem Solving Methods. The process of constructing Problem
Solving Methods is assumption-based. During this process assumptions are
added that facilitate efficient operationalization of the desired functionality.

5
• Here is how the J48 Algorithm works: -

We live in the world of technology; the internet has opened the doors for vast
knowledge and research being available at everyone’s fingertips. Continuous
innovation and advancement have opened many doors as a result we are
generating loads and loads of useful and meaningful data in every aspect of
our life. The question is what do we do with this data, how do we use it to our
advantage, how do we dig deeper into the data to see what it is telling us. This
is where the power of machine learning and artificial intelligence comes into
play. These techniques provide smart alternatives to analysing large volumes
of data. By developing fast and efficient algorithms and data-driven models
for real-time processing of data, machine learning can produce accurate results
and analysis.

J48 Algorithm

6
J48 algorithm is one of the most widely used machine learning algorithms to
examine the data categorically and continuously. The C4.5 algorithm (J48) is
mostly used among many fields for classifying data for example interpreting
the clinical data for the diagnosis of Diabetes, classifying E-governance data,
and many more.

• Classification

The machine learning process has two main phases: a learning phase, where
the classification algorithm is trained, and a classification phase, where the
algorithm labels new data. Classification is a data mining task that maps the
data into predefined groups and classes, also known as supervised learning.

[9] Software/Hardware Requirements

Hardware:
RAM 3 GB or Above
Hard Disk 250 GB or Above
Processor i3 or Above
Technology:
MySQL 3.2 or Above
Windows Operating System 7
Python 3.7 or above
Tools:
Notepad ++ / VS Code
Pycharm / Jupyter
7
[10] Functional & Nonfunctional Requirements

Non-Functional Requirements

• There should be minimal lag between taking of the input and result
• The processing should be as efficient with maximum accuracy.
• The system should give valid result for positive as well as negative
test cases.

Functional Requirements

• The System should be able to retrieve the results stored on database


by using algorithm
• The system application of modules must able to detect Diabetics.

8
[11] Applications

[1] Hospital: - In hospitals this can be used. As we know that the traditional
method of diabetes prediction is very time consuming. When we come across
any symptom, we need to test for it. In such case the patient is required to
visit a diagnostic center, to get their reports after consultation. If this system
is used in hospitals, diabetes can be easily predicted with an accuracy of 80-
85%. This can not only save time but also the money. Just by entering the data
of our reports it can give the results with maximum accuracy.

[2] Personal: - Going to Doctor just to show the report can be a little time
consuming for the patient. If we use this system for the personal use than we
can see if we have diabetes or not. This can be used at home also just by
entering the data from our reports.

9
[12] Conclusion

Hence, we are overcoming the drawback of existing system, and


providing a smart system that will not only monitor and control our data with
security but also supply it too whenever necessary. We are trying achieved
more than 85% detection accuracy.

10
REFERENCES

1. Dhomse Kanchan B., M.K.M., 2016. Study of Machine Learning


Algorithms for Special Disease Prediction using Principal of
Component Analysis, in: 2016 International Conference on Global
Trends in Signal Processing, Information Computing and
Communication, IEEE. pp. 5–10
2. Aljumah, A.A., Ahamad, M.G., Siddiqui, M.K., 2013. Application of
data mining: Diabetes health care in young and old patients. Journal of
King Saud University - Computer and Information Sciences 25, 127–
136. doi: 10.1016/j.jksuci.2012.10.003.
3. Choubey, D.K., Paul, S., Kumar, S., Kumar, S., 2017. Classification of
Pima Indian diabetes dataset using naive bayes with genetic algorithm
as an attribute selection, in: Communication and Computing Systems:
Proceedings of the International Conference on Communication and
Computing System (ICCCS 2016), pp. 451– 455
4. Bamnote, M.P., G.R., 2014. Design of Classifier for Detection of
Diabetes Mellitus Using Genetic Programming. Advances in Intelligent
Systems and Computing 1, 763–770. doi:10.1007/978-3- 319-11933-5.
5. [9]. https://www.kaggle.com/johndasilva/diabetes

11

You might also like