Prediction of Diabetes Using Machine Learning Algorithms in Healthcare

Muhammad Azeem Sarwar, Nasir Kamal, Wajeeha Hamid, Munam Ali Shah

2018 · 232 citations · 20 references

Concepts

TL;DR

Machine learning techniques enable predictive analytics over big data, and in healthcare they can help practitioners make timely, data‑informed decisions about patient health and treatment. The study aims to help doctors and practitioners predict diabetes early by applying six machine learning algorithms to healthcare data. The authors applied six machine learning algorithms to a patient medical record dataset and compared their performance and accuracy. The comparison identifies the algorithm best suited for predicting diabetes.

Abstract

There are several machine learning techniques that are used to perform predictive analytics over big data in various fields. Predictive analytics in healthcare is a challenging task but ultimately can help practitioners make big data-informed timely decisions about patient's health and treatment. This paper discusses the predictive analytics in healthcare, six different machine learning algorithms are used in this research work. For experiment purpose, a dataset of patient's medical record is obtained and six different machine learning algorithms are applied on the dataset. Performance and accuracy of the applied algorithms is discussed and compared. Comparison of the different machine learning techniques used in this study reveals which algorithm is best suited for prediction of diabetes. This paper aims to help doctors and practitioners in early prediction of diabetes using machine learning techniques.

References

20