Name
Title | ||
|---|---|---|
A Deep Neural Network Application for Improved Prediction of <inline-formula><tex-math notation="LaTeX">$\text{HbA}_{\text{1c}}$</tex-math></inline-formula> in Type 1 Diabetes |
Abstract | ||
|---|---|---|
HbA
<sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1c</sub>
is a primary marker of long-term average blood glucose, which is an essential measure of successful control in type 1 diabetes. Previous studies have shown that HbA
<sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1c</sub>
estimates can be obtained from 5-12 weeks of daily blood glucose measurements. However, these methods suffer from accuracy limitations when applied to incomplete data with missing periods of measurements. The aim of this article is to overcome these limitations improving the accuracy and robustness of HbA
<sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1c</sub>
prediction from time series of blood glucose. A novel datadriven HbA
<sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1c</sub>
prediction model based on deep learning and convolutional neural networks is presented. The model focuses on the extraction of behavioral patterns from sequences of self-monitored blood glucose readings on various temporal scales. Assuming that subjects who share behavioral patterns have also similar capabilities for diabetes control and resulting HbA
<sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1c</sub>
, it becomes possible to infer the HbA
<sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1c</sub>
of subjects with incomplete data from multiple observations of similar behaviors. Trained and validated on a dataset, containing 1543 real world observation epochs from 759 subjects, the model has achieved the mean absolute error of 4.80 ± 0.62 mmol/mol, median absolute error of 3.81 ± 0.58 mmol/mol and R
<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>
of 0.71 ± 0.09 on average during the 10 fold cross validation. Automatic behavioral characterization via extraction of sequential features by the proposed convolutional neural network structure has significantly improved the accuracy of HbA
<sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1c</sub>
prediction compared to the existing methods. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1109/JBHI.2020.2967546 | IEEE Journal of Biomedical and Health Informatics |
Keywords | DocType | Volume |
Adult,Aged,Deep Learning,Diabetes Mellitus, Type 1,Diagnosis, Computer-Assisted,Female,Glycated Hemoglobin A,Humans,Male,Middle Aged | Journal | 24 |
Issue | ISSN | Citations |
10 | 2168-2194 | 0 |
PageRank | References | Authors |
0.34 | 0 | 6 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Aleksandr Zaitcev | 1 | 0 | 0.34 |
| Mohammad R Eissa | 2 | 0 | 1.69 |
| Zheng Hui | 3 | 0 | 0.34 |
| Tim Good | 4 | 112 | 8.79 |
| Jackie Elliott | 5 | 0 | 1.69 |
| M. Benaissa | 6 | 9 | 3.47 |