Research on type 2 diabetes prediction algorithm based on photoplethysmography_Journal of Biomedical Engineering

Authors：

HU Mingying ,  WU Quanyu , CAO Yifan , CAO Jin , ZHAO Yifan , ZHANG Lin , LIU Xiaojie

School of Electrical and Information Engineering, Jiangsu University of Technology, Changzhou, Jiangsu 213001, P. R. China;

Corresponding author：

WU Quanyu, Email: wuquanyu@jsut.edu.cn

Keywords：

Photoplethysmography; Type 2 diabetes; Generative adversarial networks; Self-attention; Data augmentation

DOI：

10.7507/1001-5515.202501006

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

To address the current issues of data imbalance and scarcity in photoplethysmography (PPG) data for type 2 diabetes mellitus (T2DM) prediction, this study proposes an improved conditional Wasserstein generative adversarial network with gradient penalty (CWGAN-GP). The algorithm integrated gated recurrent unit (GRU) networks and self-attention mechanisms to construct a generator, aiming to produce high-quality PPG signals. Various data augmentation methods, including the improved CWGAN-GP, were employed to expand the PPG dataset, and multiple classifiers were applied for T2DM prediction analysis. Experimental results showed that the model trained on data generated by the improved CWGAN-GP achieved the optimal prediction performance. The highest accuracy reached 0.895 0, and compared with other data enhancement methods, this approach exhibited significant advantages in terms of precision and F1-score. The generated data notably enhances the accuracy and generalization ability of T2DM prediction models, providing a more reliable technical basis for non-invasive early T2DM screening based on PPG signals.

Citation： HU Mingying, WU Quanyu, CAO Yifan, CAO Jin, ZHAO Yifan, ZHANG Lin, LIU Xiaojie. Research on type 2 diabetes prediction algorithm based on photoplethysmography. Journal of Biomedical Engineering, 2025, 42(5): 1005-1011. doi: 10.7507/1001-5515.202501006 Copy

1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.
13.	Sisman B, Zhang M, Sakti S, et al. Adaptive wavenet vocoder for residual compensation in gan-based voice conversion// 2018 IEEE SLT. Athens: IEEE, 2018: 282-289.
14.
15.	Zhang A, Su L, Zhang Y, et al. EEG data augmentation for emotion recognition with a multiple generator conditional Wasserstein GAN. Complex Intell Syst, 2021: 1-13.
16.
17.	Chang J, Hu F, Xu H, et al. Data augmentation of wrist pulse signal for traditional chinese medicine using Wasserstein GAN// Proceedings of the 2nd International Symposium on Artificial Intelligence for Medicine Sciences. New York: Association for Computing Machinery, 2021: 426-430.
18.
19.
20.
21.
22.
23.

1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.
13. Sisman B, Zhang M, Sakti S, et al. Adaptive wavenet vocoder for residual compensation in gan-based voice conversion// 2018 IEEE SLT. Athens: IEEE, 2018: 282-289.
14.
15. Zhang A, Su L, Zhang Y, et al. EEG data augmentation for emotion recognition with a multiple generator conditional Wasserstein GAN. Complex Intell Syst, 2021: 1-13.
16.
17. Chang J, Hu F, Xu H, et al. Data augmentation of wrist pulse signal for traditional chinese medicine using Wasserstein GAN// Proceedings of the 2nd International Symposium on Artificial Intelligence for Medicine Sciences. New York: Association for Computing Machinery, 2021: 426-430.
18.
19.
20.
21.
22.
23.

Next Article
A study on heart sound classification algorithm based on improved Mel-frequency cepstrum coefficient feature extraction and deep Transformer

Journal of Biomedical Engineering

Research on type 2 diabetes prediction algorithm based on photoplethysmography

Abstract Full text Figures/Tables Video References Cited by

Next Article

Format

Content