Back to Search
Start Over
WITHDRAWN: Predictive machine learning model for early detection and analysis of diabetes
- Source :
- Materials Today: Proceedings.
- Publication Year :
- 2020
- Publisher :
- Elsevier BV, 2020.
-
Abstract
- Diabetes is a long-lasting disease which has the ability to cause a worldwide health calamity. International Diabetes Federation (IDF) has proven that 3820 lakhs people in the world are living with diabetes and this number can be doubled in the next 15 years. Diabetes, also known as Diabetes Mellitus is a chronic disease caused due to the increase of glucose level in the blood. This disease can be diagnosed using various physical and chemical tests. However, untreated and undiagnosed diabetes could damage human body organs such as eye, heart, kidneys, foot, nerves and can also lead to the death of the human. So, early prediction and analysis of Diabetes can reduce the death rate to some extent. Thus, the proposed work aims at designing a model which predicts the diabetes in human with maximum accuracy using machine learning classifiers like Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Logistic Regression (LR), Navies Bayes (NB), Gradient Boosting (GB) and Random Forest (RF) Classifier. Analysis is done on Pima Indian Diabetes Database (PIDD), a dataset taken from Kaggle data repository. The performance of all the six classifiers is compared using Accuracy score, Receiver Operating Curve (ROC), Precision, Recall, F-measure evaluated from each model.
- Subjects :
- 010302 applied physics
Receiver operating characteristic
business.industry
02 engineering and technology
Disease
021001 nanoscience & nanotechnology
Logistic regression
Machine learning
computer.software_genre
medicine.disease
01 natural sciences
Random forest
Support vector machine
Bayes' theorem
Diabetes mellitus
0103 physical sciences
medicine
Artificial intelligence
Gradient boosting
0210 nano-technology
business
computer
Subjects
Details
- ISSN :
- 22147853
- Database :
- OpenAIRE
- Journal :
- Materials Today: Proceedings
- Accession number :
- edsair.doi...........64e4ffe27755fb71931b0dc03dacc4f0
- Full Text :
- https://doi.org/10.1016/j.matpr.2020.09.522