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

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.

Figure 1

Preparation and optimization of perovskite photodetector. A) The vapor deposition of the perovskite photodetector and the structure of the perovskite photodetector. B) Current density–voltage characteristics of the device with PEAI and without PEAI. The device with PEAI shows only slight attenuation after being placed in the N₂ atmosphere for 6 days. C) Comparison of steady PL spectra of perovskite thin film with and without PEAI. D) Nyquist plots of devices with and without PEAI at V = 0 V in the dark.

Figure 2

Performance of perovskite photodetector. A) Current density–voltage characteristics. B) External quantum efficiency (EQE) and spectra responsivity (SR) (A W⁻¹). C) Photocurrent curves under varied light intensities, LDR reaches 204 dB. D) Photocurrent on‐off switching properties of 0.156 nW cm⁻². E) Specific detectivity of the perovskite photodetector at 1Hz and the insert shows the noise current spectrum. F) Photo‐transient response of the device under an optical modulation frequency of 100 kHz. G) Continuous tracking of photoresponse stability during a period of 5200 s under modulated illumination intensity of 0.22 µW cm⁻². The above device is encapsulated and working under zero bias (self‐powered mode) in air under the illumination of 860 nm if not mentioned.

Figure 3

Measurement of PPG signals. A) Schematic of PPG signal measurement and the developed PPG sensor. The device is powered under both indoor and outdoor illumination, and the complete PPG signals can be detected under the light with an NIR band. B) PPG signals under different concentrations of blood glucose. C) PPG signals under different weather.

Figure 4

Feature extraction from the PPG signal and training for blood glucose measurement. A) Definition of 11 PPG features as X‐feature, personal information of patient as P‐feature, and corresponding reference blood glucose value y as the label. Each PPG feature is extracted separately from the PPG signal. B) Principle of gradient boosting decision tree regressor which has the best prediction result in our work. C) Three typical PPG features that show a strong correlation with blood glucose. The red point is measured under high blood glucose, and the blue one is under low blood glucose (systolic peak (SP), diastolic peak (DP), dicrotic notch (DN), bottom (Bot)).

Figure 5

Measurement by PPG sensor. A) Comparison of measurement accuracy using different trained models. B) and C) Comparison and the Clarke Error Grid between the values from the blood glucose meter and the PPG measured values using an 860 nm laser. D) and E) Comparison and the Clarke Error Grid between the blood glucose and the PPG measured values using a solar simulator. F) and G) Comparison and the Clarke Error Grid between the blood glucose and the PPG measured values of different diabetic patients using an 860 nm laser. (n is the sample size of the testing set).