K-Nearest Neighbor Based Methodology for Accurate Diagnosis of Diabetes Mellitus

Panwar, M; Acharyya, A; Shafik, R; Biswas, D

doi:10.1109/ISED.2016.7977069

K-Nearest Neighbor Based Methodology for Accurate Diagnosis of Diabetes Mellitus

Lookup NU author(s): Professor Rishad Shafik

Downloads

Accepted version [.pdf]

Licence

This is the authors' accepted manuscript of a conference proceedings (inc. abstract) that has been published in its final definitive form by IEEE, 2016.

For re-use rights please refer to the publisher's terms and conditions.

Abstract

Diabetes is one of the leading causes of death, disability and economic loss throughout the world. Type 2 diabetes is more common (90-95% worldwide) type of diabetes. However, it can be prevented or delayed by taking the right care and interventions which indeed an early diagnosis. There has been much advancement in the field of various machine learning algorithms specifically for medical diagnosis. But due to partially complete medical data sets, accuracy often decreases, results in more number of misclassification that can lead to harmful complications. An accurate prediction and diagnostic of a disease becomes a challenging research problem for many researchers. Therefore, aimed to improve the diagnosis accuracy we have proposed a new methodology, based on novel preprocessing techniques, and K-nearest neighbor classifier. The effectiveness of proposed methodology is validated with the help of various quantitative metrics and a comparative analysis, with previous reported studies using the same UCI dataset focusing on pimadiabetes disease diagnosis. This is the first work of its kind, where 100% classification accuracy is achieved with feature reduction from eight to two that shows the out performance of proposed methodology over existing methods.