Comparison of Various Machine Learning Algorithms for Diabetes Disease Prediction
Ashwni Kumar
, Mariya Khatoon
Diabetes Disease Prediction, Machine Learning, Support Vector Machine, Decision Tree, Random Forest, Naïve Bayesian, Simple CART
More than 31 million people in India suffer from diabetes and many people are at risk. People with diabetes are at increased risk of heart disease, stroke, eye problems and liver damage. Current hospital practice collects the information needed to diagnose diabetes through various tests and provides appropriate treatment based on the diagnosis. Big Data Analytics plays an important role in the healthcare industries. There is a comprehensive database of health care industries. Using big data analysis, you could study huge data sets and discover hidden information, hidden schemes to discover knowledge of data, and predict results accordingly. In this research paper, we have introduced the diabetes prediction model for better classification of diabetes, in which the patient is told with greater accuracy. Therefore, five machine learning classifications are used in this experiment, to identify diabetes, namely Naïve Bayesian, Decision Tree, Random Forest, Simple CART, and Support Vector Machine. The experiment is performed using the Pima Indian diabetes database that is sourced from the UCI machine learning repository on the WEKA tool. The performance of the five algorithms is evaluated on various measures such as Accuracy, Precision, Recall and F-measure. The obtained result shows a far better performance of the Support Vector Machine with the maximum accuracy of 79.87% compared to the other algorithms.
"Comparison of Various Machine Learning Algorithms for Diabetes Disease Prediction ", IJSDR - International Journal of Scientific Development and Research (www.IJSDR.org), ISSN:2455-2631, Vol.5, Issue 6, page no.309 - 314, June-2020, Available :https://ijsdr.org/papers/IJSDR2006051.pdf
Volume 5
Issue 6,
June-2020
Pages : 309 - 314
Paper Reg. ID: IJSDR_191942
Published Paper Id: IJSDR2006051
Downloads: 000347240
Research Area: Engineering
Country: varanasi, Uttar Pradesh, India
ISSN: 2455-2631 | IMPACT FACTOR: 9.15 Calculated By Google Scholar | ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 9.15 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Publisher: IJSDR(IJ Publication) Janvi Wave
