期刊名称：International Journal of Advanced Computer Science and Applications(IJACSA)
印刷版ISSN：2158-107X
电子版ISSN：2156-5570
出版年度：2019
卷号：10
期号：12
页码：1-5
出版社：Science and Information Society (SAI)
摘要：This work aims to predict and classify patients into
diabetic and nondiabetic subjects based on age and four
independent variables extracted from the analysis of
photoplethysmogram (PPG) morphology in time domain. The
study has two main stages, the first one was the analysis of PPG
waveform to extract b/a, RI, DiP, and SPt indices. These
parameters contribute by some means to the prediction of
diabetes. They were statistically significant and correlated with
the HbA1C test. The second stage was building a neural network
based classifier to predict diabetes. The model showed an
accuracy of 90.2% in training phase and an accuracy of 85.5% in
testing phase. The findings of this research work may contribute
towards the prediction of diabetes in early stages. Also, the
proposed classifier showed a high accuracy in predicting the
existence of diabetes in Saudi people population.
