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

Abstract Glycated hemoglobin A1c (HbA1c) is regarded as a gold standard to evaluate long-term blood glucose control, and it is also a crucial metric in diabetes screening, diagnosis, and management. However, thus far, the HbA1c measurement methods are invasive and painful. Considering that HbA1c levels are associated with cardiovascular autonomic neuropathy, in this paper, a novel Electrocardiogram (ECG)-based approach was presented for noninvasive and fast detection of HbA1c levels using 60-second, single-lead ECG waveform. For this purpose, a total of 317,105 ECG datasets encompassing 370 patients with diabetes were obtained using wearable devices. Furthermore, the ECG preprocessing was based on autocorrelation analysis. The convolutional neural networks with multisegment fusion and varied-weight (CNN-MFVW) were proposed to achieve ECG feature extraction and HbA1c detection. The results showed that the average accuracy, precision, recall, and F1-score of the proposed algorithm were 0.9015, 0.9051, 0.8991 and 0.9013 respectively. Moreover, the area under the curve (AUC) was up to 0.9899, which was higher than other algorithms of conventional CNN and CNN-LSTM. Therefore, we conclude that the proposed approach for noninvasive and fast detection of HbA1c levels has potentials in practical applications.