Professional Documents
Culture Documents
BELGAUM -590014
Project Report On
CHRONIC KIDNEY DISEASE AND STAGES
PREDICTION WITH RECOMMENDATION OF
SUITABLE DIET PLAN
Submitted by:
AKSHATH H KANDLUR (1DT19CS012)
ANKITH KUMAR SINGH (1DT19CS018)
BANUPRIYA B NAIK (1DT19CS025)
CERTIFICATE
This is to certify that the Project “CHRONIC KIDNEY DISEASE AND STAGES
PREDICTION WITH RECOMMENDATION OF SUITABLE DIET PLAN ”
has been successfully carried out by AKSHATH H KANDLUR (1DT19CS012),
ANKITH KUMAR SINGH (1DT19CS018), BANUPRIYA B NAIK (1DT19CS025)
a bonafide students of DAYANANDA SAGAR ACADEMY OF TECHNOLOGY
& MANAGEMENT in partial fulfilment of the requirements for the award of degree
in
Bachelor of Engineering in Computer Science and Engineering of Visvesvaraya
Technological University, Belgaum during academic year 2022-2023. It is certified that
all corrections/suggestions indicated have been incorporated in the report deposited in the
departmental library. The project report has been approved as it satisfies the academic
requirements in respect of project work for the said degree.
Examiners:
1.
2.
ABSTRACT
Chronic kidney disease (CKD) is a type of kidney disease in which there is gradual loss of
kidney function over a period of months or years. Prediction of this disease is one of the most
important problems in medical fields. So automated tool which will use machine learning
techniques to determine the patient’s kidney condition that will be helpful to the doctors in
prediction of chronic kidney disease and hence better treatment. The proposed system extracts
the features which are responsible for CKD , then machine learning process can automate the
classification of the chronic kidney disease in different stages according to its severity. The
objective is to use machine learning algorithm and suggest suitable diet plan for CKD patient
using classification algorithm on medical test records. Diet recommendation for patient will be
given according to potassium zone which is calculated using blood potassium level to slow
down the progression of CKD.
ACKNOWLEDGEMENT
It gives us immense pleasure to present before you our project titled “CHRONIC
KIDNEY DISEASE AND STAGES PREDICTION WITH RECOMMENDATION
OF SUITABLE DIET”. The joy and satisfaction that accompany the successful
completion of any task would be incomplete without the mention of those who made it
possible. We are glad to express our gratitude towards our prestigious institution
DAYANANDA SAGAR ACADEMY OF TECHNOLOGY AND MANAGEMENT
for providing us with utmost knowledge, encouragement and the maximum facilities in
undertaking this project.
We wish to express a sincere thanks to our respected principal Dr. Ravi Shankar M for
all their support.
We express our deepest gratitude and special thanks to Dr. Kavitha C, H.O.D, Dept. Of
Computer Science Engineering, for all her guidance and encouragement.
We sincerely acknowledge the guidance and constant encouragement of our project
guide, Ms.K. Deepa Shree, Asst. Professor, Dept. of CSE, DSATM and also our project
coordinator Dr. Saravana Kumar R, Associate Professor, Dept. of CSE, DSATM.
1.1 Goal 2
1.2 Objective 2
2 LITERATURE SURVEY 11
2.1 AN Empirical Evaluation 11
3 FUNCTIONAL REQUIREMENTS 20
3.1 Interface Requirements 20
REFERENCE 29
Chronic Kidney Diseases Prediction and Recommendation of Suitable Diet
Plan
Chapter-1
INTRODUCTION
The health-care industry is producing copious amounts of data which need to be mined in
order to discover hidden information for effective prediction, diagnosis and decision
making. Currently, kidney disease has been a crucial problem. It is one of the leading
causes of death in India. Chronic kidney disease (CKD), is delineated by the gradual loss
of kidney function. Kidneys filter wastes and excess fluids from your blood, which are
then excreted in your urine. If this disease gets worse, wastes can accumulate in the blood
and can cause difficulties like high blood pressure, anemia, weakening of bones, poor
nutritional health and nerve damage. Also, kidney disease increases the risk of having
heart and blood vessel disease.
The harmful outcomes can be avoided and prevented by early detections, according to
researchers conducted. Awareness of CKD among patients is gradually increasing, but
still low. The Global Burden of Disease (GBD) 2015 ranks chronic kidney disease as the
eighth leading cause of death in India. All over the world, the highest count of patient
with diabetes is in India with the projection figure of 57.2 million cases in 2025and also
the count of patient with hypertension is expected to double from 2000 to 2025, hence
these will make India the reservoir of CKD [1].The burden of CKD management thus
falls largely on primary care providers (PCPs). Hence an accurate, convenient, and
automated CKD detection method is important for clinical practice Undiagnosed CKD
can be identified, predicting the likelihood that patients will develop chronic disease, and
present patient-specific prevention interventions with Machine learning techniques.
Accurate predictive models can be created by health systems, which lower risks and
eventually improve standards.
The data mining techniques of classification, clustering and association helps in extracting
knowledge from large amount of data. Machine learning and data mining techniques
together have been the prime factors in determining and diagnosis of various critical
diseases. Management of diet depends on the current Glomerular Filtration Rate (GFR
rate) and the severity of the disease. We will be classifying the disease in five stages-
Stage 1, stage 2 and stage 3, Stage 4, Stage 5. Stage 1 is safe and requires a lenient diet
plan to be followed. Whereas stage 2, a potential CKD patient will be given a restricted
and strict diet. Keeping the balance of minerals, electrolytes,
To build a real time is gradual loss of kidney function over a period of months or years.
and liquids inside body will be difficult for stage 3 to 5 patient. Therefore, they have to be
under proper dietary guidance.
An important diet for a renal improvement and prevent further harm is essential, which
also helps in keeping balance of electrolytes and water in the body. Other than stages of
severity, many other factors will contribute in shaping the diet. The blood potassium level,
urea level, calcium level, phosphorous level and so on. In this study, to identify suitable
diet plan for a CKD patient the main focus will be on blood potassium level.
1.1 GOAL
Application useful for the hospitals where system is an automation for CKD
prediction.
• Its stages prediction and recommending suitable diet plan for the patients using ML
algorithms.
1.2 OBJECTIVE
The objective of our work is to:
• Chronic kidney disease (CKD) is a type of kidney disease in which there is gradual
loss of kidney function over a period of months or years.
• Prediction of this disease is one of the most important problems in medical fields.
1.4 METHODOLOGY
“Bayesian Algorithm or KNN" is used to predict CKD. GFR used for Stage Prediction.
This is the first step in the prediction process where we collect medical data. Previous
years patients data collected for processing. More than 5000 + data-sets used for
processing. Training data-sets will contain patient details and also parameters that are
required for prediction.
Here medical data analyzed and only relevant data extracted. The data required for
processing extracted and segmented according to the requirement. Required data
extraction is done because entire training data not required for processing and if we input
all data, it requires too much of time for processing, so data processing is done.
Once required data extracted and segmented, we need to train the data, train means
converting the data into the required format such as numerical values or binary or string
etc.. conversion depends on the algorithm type.
Machine Learning
Its a predictive model used for the tasks where it involves prediction of one value using
other values in the data-set. Supervised learning will have predefined labels. It classifies
an object based on the parameters to one of the predefined set of labels.
We have many algorithms to build model in supervised learning such as KNN, Naive
bayes, Decision Tree, ID3, Random Forest, SVM , Regression techniques etc….
Depending of the requirement, labels, parameters and data-set we select the appropriate
algorithm for predictions. Algorithm is used to build a model that makes predictions based
on evidence in the presence of uncertainty.
In this project For prediction we make use to “Bayesian Classifier or KNN algorithm”
which is an efficient and works fine for all different sets of parameters. It also generates
accurate results.
Doctor can access to the core module where system predicts the CKD and Stages for the
new patients based on the inputted parameters. Here system uses “KNN” algorithm or
“Naive Bayes” for Disease prediction.
Step 6: Results
Results generated by the algorithm is checked with the accuracy using confusion matrix
method. Here we validate the results generated by the algorithm “bayesian classifier” and
“KNN algorithm”.
Final outputs represented on GUI. When users gets login to the application system predicts
the disease and displays on a GUI.
Here for each attribute we calculate the probability of occurrence using the following
formula. (mentioned in the next step). For each class(disease) we should apply the
formulae.
sample size
For each class, here we multiple the results of each attribute with p and final results are
used for classification.
Step 5: Compare the values and classify the attribute values to one of the predefined set of
class.
Sample Example
Training Dataset:
A GFR below 60 for three months or more or a GFR above 60 with kidney damage
(marked by high levels of albumin in your urine) indicates chronic kidney
disease. ...Blood or protein in the urine can be an early sign of kidney disease.
GFR - glomerular filtration rate is the best test to measure your level of kidney function
and determine your stage of kidney disease. Your doctor can calculate it from the results
of your blood creatinine test, your age, body size and gender. Your GFR tells your doctor
your stage of kidney disease and helps the doctor plan your treatment. If your GFR
number is low, your kidneys are not working as well as they should. The earlier kidney
disease is detected, the better the chance of slowing or stopping its progression.
https://www.kidney.org/atoz/content/gfr
1.5 DATASET
Data-set Description
CKD prediction is one of the leading disease in the current medical sector. As it is
difficult to predict the CKD disease and types at early stages, this proposed system helps
Parameters List:
Chapter-2
LITERATURE SURVEY
LIMITATIONS:
• Used algorithms generates graphical outputs, not suitable for real time.
METHODOLOGY: They have used readily available data tools such as Rapid Miner tool
for implementation.
LIMITATIONS:
• Using tools like Rapid Miner and other such tools namely R-Tool, Wekaa tool the
results can be easily obtained but the testing of these is not possible.
LIMITATIONS:
Data type is image, images used for prediction which leads to less accurate results.
Less efficient.
LIMITATIONS:
These Regression and SVM techniques produces graphical outputs the distinguishing
will be difficult in the graphical method.
DATA SET USED: The data set used for implementation is only static data available on
the UCI Machine Learning Repository.
LIMITATIONS:
METHODOLOGY USED: In this research study, the effects of using clinical features to
classify patients with chronic kidney disease by using support vector machines algorithm
is investigated.
LIMITATIONS:
Almost all works predicted chronic kidney disease using PYTHON or R Language which
uses ready libraries to train the training datasets. All these works trained only the static
datasets. None of the works done it for dynamic datasets. Stages prediction and diet
recommendations are new to the real time.
Machine Learning
ML concerns with construction and study of system that can learn from data. For example,
ML can be used in E-mail message to learn how to distinguish between spam and inbox
messages.
Functionality:
• A computer program is said to be learn from experience E with respect to some task T
and some performance P only if the program performance increases with experience
E.
• ML is a branch of AI which contains statistical, probabilistic, optimization technique
that can learn from past experience and discover the pattern from large complex data
sets.
• For example, we can apply ML technique in predicting student performance based on
their behaviors. Student performance depends on many factors such as living locality,
SSLC result, PUC result, Family income, Parents education, use of internet, use of
mobile, use of bike, use of Social Networking and other habits.
• We can predict student performance using ML technique before exams so that we can
improve student performance by knowing status of student.
• ML based technique can be applied to classify the employees in an organization either
to be class leave or stay based on their behavior.
ML Problems:
1. Is this disease cancer?
2. Identifying types of cancer.
3. What’s the market value of a House?
4. In Social Networking we can use ML technique to find best friends based on their
interaction.
5. Suggesting the interesting tourist places using ML.
6. Predicting Customer purchasing patterns in Online shopping.
Types of ML:
Supervised learning
Supervised learning is an approach to machine learning that is based on training data that
includes expected answers. An artificial intelligence uses the data to build general models
that map the data to the correct answer.
Example: Sorting
A robot is learning to sort garbage using visual identification. It sits all day picking out
recyclable items from garbage as it passes on a conveyor belt. It places items such as
glass, plastic and metal into 12 bins. Each item is labeled with an identification number on
a sticker. Once a day, human experts examine the bins and inform the robot which items
were improperly sorted. The robot uses this feedback to improve.
UnSupervised learning
Semi-Supervised learning
More on ML Techniques
The ML algorithms can be categorize in two ways as follows,
• The first is a grouping of algorithms by the learning style.
• The second is a grouping of algorithms by similarity in form or function (like
grouping similar animals together).
• Supervised Learning: Input data is called training data and has a known label or
result such as spam or not spam, a stock price at a time.
Unsupervised Learning: Input data is not labeled and does not have a known result.
A model is prepared by deducing structures present in the input data. This may be to
extract general rules. It may through a mathematical process to systematically reduce
redundancy, or it maybe to organize data by similarity.
Example problems are clustering, dimensionality reduction and association rule learning.
Example algorithms include: the Apriori algorithm and k-Means.
There is a desired prediction problem but model must learn the stmust learn the structures
to organize the data as well as make predictions.
Example problems are classification and regression.
METHODOLOGY USED: The data set used for implementation is only static data
available on the UCI Machine Learning Repository. this paper examines the performance
of Naive Bayes, K-Nearest Neighbour (KNN) and Random Forest classifier on the basis
of its accuracy
LIMITATIONS:
Admin creates doctors and receptionists and system can have n number of doctors and
receptionists.
Admin of the system sets unique id and password for each staff (doctor and receptionist)
Admin specifies the type of the disease that we are handling (nothing but CKD)
Admin uploads the required parameters for CKD prediction, there are totaly 24 parameters
used for CKD prediction.
Receptionists uploads the dataset required for CKD prediction and stage prediction.
View the patients history such as disease details and treatment details
Upload Patient Data (New patient) - here doctor inputs the new patient parameters requried
for CKD prediction.
Chronic Kidney Disease Prediction Module [New patient – Navie Bayes Algorithm] - this
the core module where system predicts the CKD for the new patients based on the inputted
parameters. Here system uses “Naive Bayes” algorithm for CKD prediction.
Stage Prediction Module (GFR Method used) - in this module system predicts the stages
for the patients suffering from CKD, system uses GFR method for stage prediction.
Upload Treatment Details - here doctor uploads treatment details for the patients.
• One of the most important things about non-functional requirements is to make them
verifiable. The verification is normally done by measuring various aspects of the system and
seeing if the measurements confirm to the requirements.
• Usability- System is a medical oriented application and system is an automation for kidney
disease prediction and mainly used by doctors and receptionists of the hospitals and as its a
browser based application it can be accessed world wide.
• Reliable-our application provides the services according the users satisfaction and interest,
and designed as per users requirements and more user friendly, so the application is more
reliable compare to other medical sector applications.
• Efficiency - The application provides the efficient results as it uses data mining technique or
machine learning technique for disease prediction. Huge amount of data mined to get more
efficient results.
• Re-usability – The system is a web based application, once the user creates an account; user
can access the system multiple times.
• The second group of non-functional requirements categories constrains the environment and
technology of the system.
C++
VS Code
SQL Sever
• IDE: Visual Studio (tool used for the development of real time applications,
Microsoft technology which supports more libraries, tools and concepts required to
work with real time application compared to other technologies)
• Back End – MS SQL Server (used to store the data, Microsoft technology more
compatible with visual studio)
Hardware Requirements
• RAM: 4GB+
Doctor: Doctor is a one who specifies the necessary inputs for chronic kidney disease
prediction. Doctor is a service receiver. The key service given by the system is “chronic
kidney disease prediction” based on the medical data.
Receptionist: Receptionist is one who maintains the patients registration, billing and
treatment details.
Patient: Patient is a one who receives the services from the application.
• Login Module - here admin gets login to the application by inputting id and password.
• Add Doctors and Receptionists - admin creates doctors and receptionists and system
can have n number of doctors and receptionists.
• Set Id and Password of Staffs - admin of the system sets unique id and password for
each staff (doctor and receptionist)
• Add Parameters - admin uploads the required parameters for CKD prediction, there
are totaly 24 parameters used for CKD prediction.
• Login Module - Here receptionists gets login to the application by inputting id and
pwd.
• Data-set Module (Old Patients and parameters) - here receptionists uploads the
dataset required for CKD prediction and stage prediction.
• Manage Patients History - can view the patients history such as disease details and
treatment details
• Upload Patient Data (New patient) - here doctor inputs the new
patient parameters required for CKD prediction.
• Diet Recommendation
• Patient History - here patients can view the history such as registration
details, treatment details, disease details etc…
Chapter-4
REFERENCES
V . Jha, G. Garcia, and K. Iseki, “Chronic kidney disease: global dimension and
perspectives”, Lancet, vol. 382 no. 9888, pp. 260-272, Jul 2013.
A. Kusiak, B. Dixonb, and Sh. Shaha, "Predicting survival time for kidney dialysis
patients: a data mining approach", Computers in Biology and Medicine, vol. 35, pp.
311–327, 2005
V. Vapnik, "The nature of statistical learning theory" Springer Science and Business
Media, 2013.
C.C. Chang and C.J. Lin, "LIBSVM: a library for support vector machines," ACM
Transactions on Intelligent Systems and Technology (TIST), vol. 2, pp. 27, 2011.
Sh. Shamiluulu, M.M. Boukar, Z. Yussupova. “Medical Tool for Assisting Patients
in Kazakhstan Polyclinics”. Proceedings: 11th IEEE International Conference on