A comparative study for diabetes and hypertension diagnosis using machine learning techniques

Paper ID : 1059-ISCBAS

Authors

Aya Fathy Salheen *1, Abeer Desuky2, Hoda Saleh Ahmad Mohammad3, Yomna M. Elbarawy3 1Al- Azhar University 2All-Azhar University 3Al-Azhar University

Abstract

Abstract Diabetes and hypertension are two of the commonest diseases in the world. As they unfortunately affect people of different age groups, they have become a cause of concern and must be predicted and diagnosed well in advance. The objective is to construct a predictive model to predict and classify diabetes and hypertension diseases. This study used the Bangladesh Demographic and Health Survey (BDHS), 2018 dataset to perform analysis. Various machine learning algorithms like Convolutional Neural Network (CNN), decision tree, random forest, and logistics regression are used for prediction of diabetes and hypertension. The inputs of the network were the factors for each disease, while the output was the prediction of the disease’s occurrence.

Keywords

Machine learning, Diabetes, Hypertension, Classification

Status: Abstract Accepted (Oral Presentation)