PANIMALAR ENGINEERING COLLEGE

Department of computer and communication Engineering

CHRONIC DISEASE PREDICTION

USING MACHINE LEARNING

Batch No: 12

Batch Members: Internal Guide:

ANISH KUMAR M M (211421118004)) Dr. A.Dhanalakshmi, M.E., Phd.,
LOKESH S (211421118028) Assistant Professor,
SAI HARI E (211421118046) Department of CCE,
Panimalar Engineering College.

1
 ORGANIZATION

 Objective of the Project

 Introduction
 Literature Survey
 Problem Identification
 Proposed work
 Proposed system – Flow chart and Use Case Diagram
 Result
 Conclusion and Future work
 References

2
 OBJECTIVE OF THE PROJECT

• The primary objective of a disease prediction project using machine learning

is to develop accurate models that predict an individual's risk of developing a
specific disease based on their medical history, genetics, and lifestyle data.

• This aims to enable early disease detection, personalized medical

interventions, and preventive strategies.

• By analyzing diverse data sources and employing machine learning

algorithms, such projects seek to enhance healthcare by optimizing resource
allocation, contributing to medical research, and improving public health
initiatives, ultimately leading to better patient outcomes and reduced
healthcare costs.

3
 INTRODUCTION

• Medicine and healthcare are some of the most crucial parts of the economy and
human life.
• There is a tremendous amount of change in the world we are living in now and
the world that existed a few weeks back.
• In this situation, where everything has turned virtual, the doctors and nurses are
putting up maximum efforts to save people’s lives even if they have to danger
their own.
• A disease predictor can be called a virtual doctor, which can predict the disease
of any patient without any human error.
• The primary goal was to develop numerous models to define which one of them
provides the most accurate predictions.
4
 LITERATURE SURVEY

SNO DISEASE ALGORITHM USED PERFORMANCE LIMITATIONS

1 Heart Disease Logistic Regression, Accuracy-84% Limited generality

SVM due to small dataset

2 Diabetic Artificial Neural Sensitivity -99.65% High computational

Retinopathy Network Specificity- 97.80% cost

3 Chronic Kidney Decision Tree, Accuracy-99.4% Lack of

Disease Random Forest interpretability

5
 LITERATURE SURVEY

SNO DISEASE ALGORITHM USED PERFORMANCE LIMITATIONS

4 Breast Cancer K-nearest Neighbours Accuracy-97.4% Sensitive to outliers

5 Liver Disease Naïve Bayes, Random Accuracy-94% Requires a large

Forest amount of high quality
data

6
 EXISTING SYSTEM

• In the Existing system , Big Data & CNN Algorithm is used for predicting
diseases.
• The accuracy of the System is up to 90%.
• Existing paper, we streamline machine learning algorithms for effective
prediction of chronic disease outbreak in disease-frequent communities.

7
 PROBLEM IDENTIFICATION/
LIMITATIONS OF EXISTING SYSTEM

PROBLEM STATEMENT

 The classical diagnosis method is a process where the patient has to visit a
doctor, undergo various medical tests, and then come to a conclusion. This
process is very time-consuming. To save time required for the initial process of
diagnosis symptoms, this project proposes an automated disease prediction
system that relies on user input. The system takes input from the user and
provides a list of probable diseases.

8
 PROPOSED WORK

• This system leverages machine learning algorithms including Decision Trees,

Random Forests, and Naïve Bayes to predict diseases.
• Decision Trees offer interpretable insights, Random Forests handle noise
effectively, and Naïve Bayes deals with continuous data.
• Model performance is evaluated using metrics like accuracy and precision.
• The best-performing algorithm is deployed for real-time disease prediction in
healthcare systems, adhering to ethical and regulatory standards.

9
 PROPOSED WORK

ADVANTAGES:

• Accuracy rate is very high, up to 95%.

• Does not need much resources for prediction.
• This project highlights the potential of Decision Tree, Naive Bayes, and
Random Forest algorithms in disease prediction.

10
FLOW CHART OF PROPOSED SYSTEM

13
 USE CASE DIAGRAM OF
PROPOSED SYSTEM

Registration

Enter the Details

Server

Collects Data

Extract the features

User

Match the values

Classify the data

Predict the Disease

Send the Report

13
 RESULT

IMPORT DATASET

Importing Libraries

Importing CSV files

13
 RESULT

DATASET

14
 RESULT

FINAL OUTPUT

15
 CONCLUSION AND FUTURE WORKS

• The project is designed in such a way that the system takes symptoms from the user
as input and produces output i.e. predict disease. The user can select a minimum of
one to a maximum of five symptoms. Less accuracy will be attained if only one
symptom is entered. More the number of symptoms, the greater is the accuracy.

• In conclusion, the project on disease prediction using machine learning, employing

the Decision Tree, Naive Bayes, and Random Forest algorithms, has yielded
promising results and showcased the potential of these methods in the realm of
healthcare.

• These models have the capacity to make a substantial impact on disease prevention
and management, ultimately contributing to the improvement of public health and
the healthcare ecosystem.
16
 REFERENCES

1. Chae. S, K won. S, Lee. D, predicting infectious disease using deep learning and
big data, International journal of environmental research and public health
15(8), 1596 (2018).
2. Chen. M, Hao Y, Hwang. K, Wang. L, Wang .L, Dis ease prediction by machine
learning over big data from healthcare communities, IEEE Access 5, 8869
(2017).
3. Khourdifi .Y, Bahaj .M, Heart disease prediction and classification using
machine learning algorithms optimized by particle swarm optimization and ant
colony optimization, Int. J. Intell. Eng. Syst. 12(1), 242 (2019).
4. Mohan. S, Thirumalai .C, Srivastava. G, Effective heart disease prediction using
hybrid machine learning tech niques, IEEE Access 7, 81542 (2019).
17
18