Towards noninvasive and fast detection of Glycated hemoglobin levels based on ECG using convolutional neural networks with multisegments fusion and Varied-weight

作者：

Highlights：

• An ECG-based approach was firstly proposed for noninvasive HbA1c detection.

• Nine HbA1c levels detection were achieved based on ECG waveform.

• ECG preprocessing using autocorrelation analysis.

• A detection model based on CNN with multisegments fusion and varied-weight.

摘要

•An ECG-based approach was firstly proposed for noninvasive HbA1c detection.•Nine HbA1c levels detection were achieved based on ECG waveform.•ECG preprocessing using autocorrelation analysis.•A detection model based on CNN with multisegments fusion and varied-weight.

论文关键词：Electrocardiogram,Glycated hemoglobin A1c,Noninvasive detection,Convolutional neural networks,Autocorrelation

论文评审过程：Received 2 December 2020, Revised 11 August 2021, Accepted 30 August 2021, Available online 5 September 2021, Version of Record 9 September 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115846