Professional Documents
Culture Documents
SUBMITTED BY
2022-2023
1
CERTIFICATE
This is to certify that the project report entitles
is a bonafide student of this institute and the work has been carried out by him/her under the
supervision of Dr. S.D. Babar and it is approved for the partial fulfillment of the requirement of
Savitribai Phule Pune University, for the award of the degree of Bachelor of Engineering
(Computer Engineering).
Place: Lonavala
Date:
2
ACKNOWLEDGEMENT
It gives us great pleasure in presenting the preliminary project report on ‘Kidney Disease
Detection’. I would like to take this opportunity to thank my internal guide Prof. Guide Name for
giving me all the help and guidance I needed. I am really grateful to them for their kind support.
Their valuable suggestions were very helpful. I am also grateful to Prof. HOD Name, Head of
Computer Engineering Department, College Name for his indispensable support, suggestions. In
the end our special thanks to Other Person Name for providing various resources such as
laboratory with all needed software platforms, continuous Internet connection for Our Project.
Project Associates:
Mr. Rutik Erole
Mr. Pratik Fulse
Mr. Abhishek Shelke
3
ABSTRACT
Chronic kidney disease (CKD), also known as chronic renal disease. Chronic kidney
disease involves conditions that damage your kidney and decrease their ability to keep you
healthy. You may develop complications like high blood pressure, anemia (low blood count),
weak bones, poor nutritional health and nerve damage. Early dedication and treatment can often
keep chronic kidney disease from getting worse. Data Mining is the term used for knowledge
discover from large databases. The task of data mining is to make use of historical data, to
discover regular patterns and improve future decisions, follows from the convergence of several
recent trends: the lessening cost of large data storage devices and the ever-increasing ease of
collecting data over networks; the expansion of robust and efficient machine learning algorithms
to process this data; and the lessening cost of computational power, enabling use of
computationally intensive methods for data analysis. Machine learning, has already created
practical applications in such areas as analyzing medical science outcomes, detecting fraud,
detecting fake users etc. Various data mining classification approaches and machine learning
algorithms are applied for prediction of chronic diseases. The objective of this research work is
to introduce a new decision support system to predict chronic kidney disease. The aim of this
work is to compare the performance of Support vector machine (SVM) and K-Nearest Neighbor
(KNN) classifier on the basis of its accuracy, precision and execution time for CKD prediction
4
TABLE OF CONTENTS
CERTIFICATE I
ACKNOWLEDGEMENT II
ABSTRACT III
CHAPTER
01 Introduction 08
1.1 Motivation 10
1.2 Problem Definition 10
1.3 Objective 11
1.4 Project Scope 12
1.5 Methodologies of Problem solving 12
02 Literature Survey 13
5
CHAPTER TITLE PAGE NO
NO.
05 OTHER SPECIFICATION 32
5.1 Advantages 32
5.2 Limitations 32
5.3 Limitations 32
06 Results 33
6.1 Screen Shots 34
07 Conclusions 37
7.1 Conclusions 38
7.2 Future Work 38
7.3 Applications 38
08 References 39
6
LIST OF FIGURES
FIGURE ILLUSTRATION PAGE NO.
7
CHAPTER 1
INTRODUCTION
8
INTRODUCTION
We all knows, that Kidney is essential organ in human body. Which has main
functionalities like excretion and osmoregulation. In simple words we can say that all the toxic
and unnecessary material from the body is collected and thrown out by kidney and excretion
system. It is a dangerous disease of the kidney which produces gradual loss in kidney
functionality. CKD is a slow and periodical loss of kidney function over a period of several
years. If CKD is not detected and cured in early stage then patient can show following
Symptoms: Blood Pressure, anemia, week bones poor nutrition health and nerve damage,
decreased immune response because at advanced stages dangerous levels of fluids, electrolytes,
and wastes can build up in your blood and body. Hence it is essential to detect CKD at its early
stage but it is unpredictable as its Symptoms develop slowly and aren’t specific to the disease.
Some people have no symptoms at all so machine learning can be helpful in this problem to
predict that the patient has CKD or not. Machine learning does it by using old CKD patient data
to train predicting model. and determine the chronic kidney disease.
9
1.1 MOTIVATION
Motivation for change often depends on the existence of a discrepancy between the
patients’ current behavior and important values or goals.
Empowering Patients: Machine learning algorithms can assist patients in monitoring their health
by analyzing real-time data from wearable devices, such as smartwatches or fitness trackers. This
empowers individuals to actively participate in their own care and make informed decisions to
manage their kidney health effectively.
Research Advancements: By utilizing machine learning techniques, researchers can uncover
hidden patterns and insights in large datasets, leading to a better understanding of kidney disease
progression, risk factors, and potential new treatment avenues. This can drive further scientific
advancements and contribute to the development of more effective therapies.
Global Impact: Kidney disease affects millions of people worldwide, causing significant
morbidity and mortality. Machine learning-based detection and prediction models can be easily
implemented across different healthcare settings, including resource-limited areas, making them
a valuable tool to combat kidney disease on a global scale.
Chronic kidney disease (CKD) is a slowly progressive problem in the kidneys which takes time
to advance to later stage. The condition in which there is a damage on the filtering units of the
kidneys which leads to the excessive loss of proteins from the body. The sudden failure of
kidneys to perform the functions. It is a serious condition and mainly occurs during the last stage
of the disease or in time of treatment. It has become common for the people of all ages to
develop one or the other kidney problems, particularly in their middle and old age. If the kidneys
get damaged, it leads to an increase in the toxicity in the body. If such a condition is not treated
on time, it can eventually lead to kidney failure and may also harm the other organs of the body.
10
1.3 OBJECTIVE
1. Early Detection: Build a model that can identify early signs and symptoms of kidney
disease, allowing for timely intervention and treatment to prevent or slow down the
progression of the disease.
2. Accurate Classification: Develop a classifier that can accurately differentiate between
individuals with kidney disease and those without, based on relevant medical features such
as patient demographics, medical history, laboratory test results, and imaging data.
3. Risk Stratification: Create a predictive model that can assess the risk of kidney disease
progression or complications, enabling healthcare professionals to prioritize high-risk
patients for further evaluation and personalized care.
4. Feature Importance: Identify the most important features contributing to kidney disease
development or progression, providing insights into the underlying factors and potential
interventions.
5. Automation and Efficiency: Build an automated system that can quickly process and
analyze large volumes of patient data, facilitating early detection and reducing the burden
on healthcare professionals.
11
1.4 Project Scope
The scope projects are highly experienced in the management of older multi-morbidity
subjects at risk for renal impairment and related clinical complications, including changes in
functional status.
In this system, the user must first login and register. If registration is successful, the user
can use the SVM algorithm to determine whether the cyber thread or not. machine learning,
Artificial Intelligence domains.
Dependencies: Python is commonly used for developing websites and software, task automation,
data analysis, and data visualization. Since it’s relatively easy to learn, Python has been adopted
by many non-programmers such as accountants and scientists, for a variety of everyday tasks,
like organizing finances.
Python is a general-purpose programming language, so it can be used for many things. Python is
used for web development, AI, machine learning, operating systems, mobile application
development, and video games. Python is a relatively easy programming language to learn and
follows an organized structure.
Python is a general purpose and high level programming language. You can use Python for
developing desktop GUI applications, websites and web applications. The simple syntax rules of
the programming language further make it easier for you to keep the code base readable and
application maintainable.
12
CHAPTER 2
LITERATURE SURVEY
13
2. LITERATURE SURVEY
A research paper is a document of a scientific article that contains relevant ex- per tise,
including substantive observations, and also references to a specific subject of philosophy and
technique. Use-secondary references are reviewed in literature and no current or initial
experimental work is published.
1.Paper Name: Prediction of Chronic Kidney Disease using Adaptive Hybridized Deep
Convolutional Neural Network on the Internet of Medical Things Platform.
14
2.Paper Name: Diagnostic Decision Support System of Chronic Kidney Disease Using Support
Vector Machine.
3.Paper Name: Early Prediction of Chronic Kidney Disease Using Machine Learning Supported
by Predictive Analytics.
15
parameters to feed machine learning to build a set of predictive models. This study starts with 24
parameters in addition to the class attribute, and ends up by 30% of them as ideal sub set to
predict Chronic Kidney Disease. A total of 4 machine learning based classifiers have been
evaluated within a supervised learning setting, achieving highest performance outcomes of AUC
0.995, sensitivity 0.9897, and specificity 1. The experimental procedure concludes that advances
in machine learning, with assist of predictive analytics, represent a promising setting by which to
recognize intelligent solutions, which in turn prove the ability of predication in the kidney
dis ease domain and beyond.
16
5.Paper Name: Extraction of Action Rules for Chronic Kidney Disease using Naive Bayes
Classifier.
17
CHAPTER 3
SOFTWARE REQUIREMENT
SPECIFICATION
18
3.1 Functional Requirements:
In order to find a solution which can be used as a part of the Rag SOC system, it is
necessary to allow its integration with other modules. Research on anomaly-based intrusion
detection systems is the most often carried out on the preexisting data sets or in laboratory
environments in which simplification concerning infrastructure, data collection or services have
been applied. Due to legal and technical limitations, our solution will detect threats through the
analysis of Net Flow data and headers from network protocols. In addition, in the real
environment it is not possible to obtain labeled teaching and validation datasets, which forces the
introduction of adaptation mechanisms already at the deployment stage. In our approach we will
try to prepare a suitably scaled model on the basis of the available datasets and then to adjust it in
the following steps to the existing network. The models prepared and tuned this way will later
become reference models during the implementation of the anomaly detection module in the
subsequent networks
When interacting with user interfaces, do users always get what they expect? For each
user interface element in thousands of Desktop App, we extracted the desktop application they
invoke as well as the text shown on their screen. This association allows us to detect outliers: User
interface elements whose text, context or icon suggests one action, but which actually are tied to
other actions.
19
3.2.2 Hardware Interfaces:
Language: Python
20
3.4 Non-Functional Requirements:
Kidney disease detection is the process of finding outliers in a given dataset. Outliers are
the data objects that stand out amongst other objects in the dataset and do not conform to the
normal behavior in a dataset. Anomaly detection is a data science application that combines
multiple data science tasks like classification, regression, and clustering. The target variable to be
21
predicted is whether a transaction is an outlier or not. Since clustering tasks identify outliers as a
cluster, distance-based and density-based clustering techniques can be used in anomaly detection
tasks
• Availability: This software is freely available to all users. The availability of the software is
easy for everyone.
• Maintainability: After the deployment of the project if any error occurs then it can be easily
maintained by the software developer.
• Reliability: The performance of the software is better which will increase the reliabilityof the
Software.
• User Friendliness: Since, the software is a GUI application; the output gener ated is much user
friendly in its behavior.
• Integrity: Integrity refers to the extent to which access to software or data by unauthorized
persons can be controlled.
• Security: Users are authenticated using many security phases so reliable secu- rity is provided.
The Database Requirements involves the use of a lot of information, some which will be
needed several times and the most appropriate form of storage of this data is in a database. This
22
will allow data to be saved from input to the Database Requirements and retrieved to be used by
the Database Requirements. As an important aspect of this project is use of Time Control
System. In this section several databases are reviewed for their suitability to this project
RAM: 8 GB
Processor: Intel i5 Processor
IDE: Spider Coding
Language: Python Version 3.8
Operating System: Windows 10
23
CHAPTER 4
SYSTEM DESIGN
24
4. System Design:
25
4.2 Data Flow Diagram:
In Data Flow Diagram, we Show that flow of data in our system in DFD0 we show
that base DFD in which rectangle present input as well as output and circle show our
system, In DFD1 we show actual input and actual output of system input of our system is
text or image and output is rumor detected likewise in DFD 2 we present operation of user
as well as admin.
26
4.3 UML Diagram:
Unified Modeling Language is a standard language for writing software blueprints. The
UML may be used to visualize, specify, construct and document the artifacts of a soft- ware
intensive system UML is process independent, although optimally it should be used in
process that is use case driven, architecture-centric, iterative, and incremental The Number of
UML Diagram is available.
27
Figure 4.6: Activity Diagram
28
Figure 4.7: Class Diagram
29
Figure 4.8: sequence Diagram
30
CHAPTER 5
OTHER SPECIFICATION
31
5.1 ADVANTAGES
Easy to handle.
5.2 LIMITATIONS
If the training not get successful or get interrupt because of any reason, then
system cannot work proper.
5.3 APPLICATIONS
In Hospital
In Office
In Banking
All User
32
CHAPTER 6
RESULTS
33
6.1Screenshots:
34
SIT, Department of Computer Engineering 2022-23
35
SIT, Department of Computer Engineering 2022-23
36
CHAPTER 7
CONCLUSIONS
37
7.1 Conclusion:
As we have already seen the applications of data mining and machine learning in
medical sector. In this project, a SVM is implemented for prediction of CKD. Al- though
the classifiers worked efficiently in prediction of other diseases also. In this project,
Chronic Kidney Disease is predicted using SVM Algorithm and a comparative study of
their performance is done. From the analysis we found that, out of one classifiers. SVM
classifier performed better than the other. The rate of prediction ofCKD is improved.
The future scope of kidney disease detection using machine learning (ML) holds great promise.
ML algorithms can be further enhanced to improve accuracy and achieve early detection of
kidney dysfunction. Personalized medicine can be enabled through ML models that analyze
individual characteristics and provide tailored risk assessments and treatment recommendations.
Integration with wearable devices allows for continuous monitoring of kidney health, while
predictive analytics tools forecast disease progression. ML algorithms can also assist clinicians
through decision support systems, facilitate telemedicine and remote monitoring, and enable data
integration and collaboration. Furthermore, ML can contribute to public health planning, drug
discovery, and treatment optimization.
38
References:
[2] Manish Kumar (2016), “Prediction of Chronic Kidney Disease Using Random Forest
Machine Learning Algorithm”, International Journal of Computer Science and Mobile
Computing, Vol. 5, Issue.
[3] Mohammed Siyad B and Manoj M, “Fused Features Classification for the Effec- tive
Prediction of Chronic Kidney Disease”, International March 2016.
[4] Naganna Chetty, Kunwar Singh Vaisla and Sithu D Sudarsan, “Role of attributes
selection in classification of Chronic Kidney Disease patients”, International Con-
ference on Computing, Communication and Security (ICCCS), 4-5 Dec, 2015.
39