Scopus Indexed Publications

Paper Details


Title
Prediction of Type II Diabetes Using Machine Learning Approaches
Author
Tasmiah Rahman, Anamika Azad, Sheikh Abujar,
Email
Abstract

Diabetes is a major threat all over the world. It is rapidly getting worse day by day. It is found that about 90% of people are affected by type 2 diabetes. Now, in this COVID-19 epidemic there is a terrible situation worldwide. In this situation, it is very risk to go hospital and check diabetes properly. In this era of technology, several machine learning techniques are utilized to evolve the software to predict diabetes more accurately so that doctors can give patients proper advice and medicine in time, which can decrease the risk of death. In this work, we tried to find an efficient model based on symptoms so that people can easily understand that they have diabetes or not and they can follow a proper food habit which can reduce the risk of health. Here, we implement four different machine learning algorithms: Decision tree, Naïve Bayes, Random Forest, and K-Nearest Neighbor. After comparing the performance by using different parameter, the experimental results showed that Naïve Bayes algorithm performed better than other algorithms. We find the highest 90.27% accuracy from Naïve Bayes algorithm.

Keywords
Machine learning Risk Decision tree Naïve Bayes Random forest K-Nearest neighbor Diabetes
Journal or Conference Name
Lecture Notes in Networks and Systems
Publication Year
2022
Indexing
scopus