Prediction of diabetes disease using machine learning algorithms

Monalisa Panda, Debani Prashad Mishra, Sopa Mousumi Patro, Surender Reddy Salkuti

Abstract


Diabetes mellitus is a powerful chronic disease, which is recognized by lack of capability of our body for metabolization of glucose. Diabetes is one of the most dangerous diseases and a threat to human society, many are becoming its victims and, regardless of the fact that they are trying to keep it from rising more, are unable to come out of it. There are several conventional diabetes disease health monitoring strategies. This disease was examined by machine learning (ML) algorithms in this paper. The goal behind this research is to create an effective model with high precision to predict diabetes. In order to reduce the processing time, K-nearest neighbor algorithm is used. In addition, support vector machine is also introduced to allocate its respective class to each and every sample of data. In building any sort of ML model, feature selection plays a vital role, it is the process where we select the features automatically or manually and it contributes most to our desired performance. Overall, four algorithms are used in this paper to understand which can easily evaluate the total effectiveness and accuracy of predicting whether or not a person will suffer from diabetes.

Keywords


Classification; Diabetes; Gradient boost; K-nearest neighbor; Support vector machine

Full Text:

PDF


DOI: http://doi.org/10.11591/ijai.v11.i1.pp284-290

Refbacks

  • There are currently no refbacks.


View IJAI Stats

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.