A Multi-Model Analysis of Non-Invasive Oxygen Saturation from Smartphone-Captured Fingertip Video

Abstract

Continuous, non-invasive oxygen saturation $\left(\text{SpO}_{2}\right)$ monitoring is a cornerstone of remote patient monitoring (RPM) and Hospital-at-Home care, yet dedicated pulse oximeter hardware remains a barrier in low-resource and community settings. The most accurate method for assessing oxygen saturation, according to current medical practice, is arterial blood gas (ABG) analysis. The downside of ABG analysis lies in the inherent invasive nature of the procedure- painful, stressful, and requiring clinically specialized staff. Pulse oximetry is the framework for quantifying the amount of Oxygen flowing through the blood cells through a pulse oximeter, which was invented in the 80s. Since then, interdisciplinary research has focused on technological invention and broader application domains. This paper presents a smartphone-based $\text{SpO}_{2}$ estimation system targeting deployment in digital health and telehealth applications, requiring no external sensors. Fingertip photoplethysmography (PPG) signals are extracted from 10-second videos captured on a Google Pixel 2 smartphone (12.2 MP dual-pixel CMOS sensor, LED flashlight), and 45 time-domain, frequency-domain, and derivative-based features are computed per segment. Three regression models—Support Vector Regressor (SVR), Ridge Linear Regression, and Random Forest Regressor (RFR) are compared under 5-fold cross-validated grid search optimization. Reference SpO $_{2}$ measurements were obtained using a Masimo Pronto pulse oximeter across 213 participants at a clinical center in Bangladesh (IRB-approved). The fine-tuned Support Vector Regressor (SVR) model outperforms the other models for $\text{SPO} _{2}$ prediction. This model achieved MAE = 0.23% and MSE = 0.11% on a held-out test set. Limitations, including narrow $\text{S p O}_{2}$ range, single-device scope, and absence of demographic subgroup analysis, are discussed alongside a roadmap for clinically deployable, trustworthy digital health tools.