International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 10 Issue: 07 | Jul 2023
p-ISSN: 2395-0072
www.irjet.net
Utilizing Machine Learning, Detect Chronic Kidney Disease and Suggest A Healthy Diet Meghashree M B1, Dr. Shreekumar T2, 1Master in Technology Student, Dept. of Computer Science and Engineering, Mangalore Institute of Technology
and Engineering, Moodbidri.
2Associate Professor, Dept. of Computer Science and Engineering, Mangalore Institute of Technology and
Engineering, Moodbidri. ---------------------------------------------------------------------***--------------------------------------------------------------------smoking, lack of sleeping, hyper tension, improper diet, etc. Abstract – The UN's third sustainable development objective,
Among them diabetes is the more dangerous factor. At the last stage, the patient must take dialysis or do kidney transplantation. One of the best ways to reduce this death rate is early treatment. Therefore, early prediction and proper treatments can possibly stop, or slow the progression of this chronic disease At the conclusion of the procedure, the patient must have dialysis or a patient transplant. Among the best way to reduce this death rate is early therapy. Therefore, quick treatment and appropriate diagnosis may be able to stop or slow the growth of this chronic condition. At least 2.4 million each year deaths occur. Each year, deaths occur, from kidney related disorders, in accordance with 2019 World Kidney Day study. CKD is currently the sixth fastest growing cause of death worldwide, and with an increasing incidence, it evolving into difficult public health issue. The country ranks 138th globally in terms of mortality rates with 0.77% of worldwide deaths. Due to its ageadjusted mortality rate of 8.46 per 100,000 people and growing mortality rate of 12.70 per 100,000 people, the nation is ranked 109 in 2018.
"Good health and well-being," emphasizes the rising importance of non-communicable diseases. One of them is to reduce by half, by 2030, the rate of non-communicable diseaserelated premature death. Chronic kidney disease (CKD), one of the leading causes of morbidity and death from noncommunicable diseases, may affect 10–15% of the world's population. In order to minimize the effects of patient health complications like hypertension, anemia (low blood count), minerals bone disorder, poor nutritional health, and neurological complications with prompt intervention through appropriate medications, early and accurate detection of the stages of CKD is essential. Four prediction models are employed: Decision tree (DT), K-Nearest Neighbor (K-NN), Random Forest (RF), and Support Vector Machine (SVM). Evaluation of difference & recursion characteristics elimination using was employed for feature selection. Using tenfold cross-validation, the models were evaluated. Results of the experiment demonstrating the superior performance of RF utilizing recursive reduction of features with cross-validation over SVM and DT.
2. EXISTING SYSTEM
Key Words: Chronic Kidney Disease (CKD), Machine Learning, Random Forest (RF), Support Vector Machine (SVM), Decision Tree (DT)
To predict diseases, Data science technique using machine learning models are playing a vital role. By making some mathematical approaches, machine learning models extract patterns from data and later these patterns are used for the survival of patients. Support Vector Machine (SVM), Nearest Neighbor (KNN), Decision Tree (DT), Random Forest (RF), etc. are some renowned machine learning methods which were successfully implemented to examine and classify the kidney disease. In recent times, some researchers have been working on CKD by applying different computational techniques for the prediction and diagnosis of this disease.
1. INTRODUCTION Two bean-shaped organs, named kidney, are two important parts in human body. Filtering by the kidney eliminates waste from the blood. Protein can leak into urine and waste materials can stay in blood if this filtration mechanism is compromised. Eventually, the kidney's filtering capacity is lost. Chronic Kidney Disease (CKD), also known as Chronic Nephro Disease, is the term used to describe kidney failure. Kidney failure affects the whole body. People generally experience this disease in accordance with their age, however as of recent years, children and youth as young as 5 years old are also experiencing CKD disease. There are some symptoms which shows kidneys are beginning to fail like muscle cramps, nausea and vomiting, appetite losses, swelling in your feet and ankles, too much urine or not enough urine, trouble catching your breath, trouble sleeping, fever and vomiting. Risk factors of CKD are diabetes,
© 2023, IRJET
|
Impact Factor value: 8.226
3. PROPOSED SYSTEM Several machine learning models are suggested in this section. Various machine learning techniques utilized samples of data for identifying the algorithms before creating the classifiers. In addition, we trained the model using K-Nearest Neighbor Classifier, Decision Tree Classifier, SVM, and Random Forest. Following that, we may compare and decide which of the following approaches can most
|
ISO 9001:2008 Certified Journal
|
Page 1118