Smartphone Dual-Camera based Blood Pressure Screening Using Pulse Transit Time Between Ear and Finger

The advancement of smartphones, particularly the optical cameras and embedded sensors, has enabled the acquisition of physiological signals from the human body for health screening. This study proposes a framework using a smartphone's dual-camera system to synchronously collect photoplethysmographic (PPG) signals from finger and ear for estimating blood pressure (BP). By calculating the Pulse Transit Time (PTT) between PPG signals from the ear and finger, and extracting heart rate and heart rate variability parameters, we estimate systolic and diastolic BP based on two personalized regression models. These estimates are then compared with the cuff-based reference. Experiments involving 15 participants demonstrated that the best performance was achieved using the physiological information extracted from PPG, such as PTT and heart rate, in combination with a random forest regression model. The mean absolute error for systolic/diastolic BP is 3.74 mmHg and 2.73 mmHg, with Pearson correlation coefficient of 0.877 and 0.868, validating the feasibility of BP screening using a smartphone dual-camera system.