Highly Sensitive Perovskite Photoplethysmography Sensor for Blood Glucose Sensing Using Machine Learning Techniques

Yongjian Zheng; Zhenye Zhan; Qiulan Chen; Jianxin Chen; Jianwen Luo; Juntao Cai; Yang Zhou; Ke Chen; Weiguang Xie

doi:10.1002/advs.202405681

Highly Sensitive Perovskite Photoplethysmography Sensor for Blood Glucose Sensing Using Machine Learning Techniques

Adv Sci (Weinh). 2024 Sep 20:e2405681. doi: 10.1002/advs.202405681. Online ahead of print.

Authors

Yongjian Zheng¹, Zhenye Zhan¹, Qiulan Chen², Jianxin Chen³, Jianwen Luo¹, Juntao Cai⁴, Yang Zhou¹, Ke Chen¹, Weiguang Xie^{1

5}

Affiliations

¹ Siyuan Laboratory, Guangdong Provincial Engineering Technology Research Center of Vacuum Coating Technologies and New Energy Materials, College of Physics & Optoelectronic Engineering, Jinan University, Guangzhou, Guangdong, 510632, China.
² Department of Medical Devices, Guangdong Food and Drug Vocational College, Guangzhou, 510520, China.
³ Department of Cardiovascular Medicine, The First Affiliated Hospital of Jinan University, Guangzhou, Guangdong, 510630, China.
⁴ Guangzhou Research Institute of Optical, Mechanical and Electronical Technologies Co.,Ltd, Guangzhou, Guangdong, 510663, China.
⁵ Guangdong Provincial Key Laboratory of Optical Fiber Sensing and Communications, Jinan University, Guangzhou, Guangdong, 510632, China.

PMID: 39303203
DOI: 10.1002/advs.202405681

Abstract

Accurate non-invasive monitoring of blood glucose (BG) is a challenging issue in the therapy of diabetes. Here near-infrared (NIR) photoplethysmography (PPG) sensor based on a vapor-deposited mixed tin-lead hybrid perovskite photodetector is developed. The device shows a high detectivity of 5.32 × 10¹² Jones and a large linear dynamic range (LDR) of 204 dB under NIR light, guaranteeing accurate extraction of eleven features from the PPG signal. By a combination of machine learning, accurate prediction of blood glucose level with mean absolute relative difference (MARD) as small as 2.48% is realized. The self-powered PPG sensor also works for real-time outdoor healthcare monitors using sunlight as a light source. The potential for early diabetes diagnoses by the perovskite PPG sensor is demonstrated.

Keywords: blood glucose monitoring; machine learning; near‐infrared; perovskite photodetectors; vapor deposition.

Abstract

Grants and funding