Measuring arterial oxygen saturation using smartphone cameras and convolutional neural networks achieved a significantly lower mean absolute error (2.02%) than a standard medical pulse oximeter.
Observational (n=39)
Does a smartphone camera using convolutional neural networks reduce the mean absolute error of oxygen saturation measurement compared to a medical pulse oximeter in participants undergoing a breath-holding study?
Smartphone cameras using convolutional neural networks can measure oxygen saturation with a lower mean absolute error than traditional medical pulse oximeters.
Arterial oxygen saturation (Formula: see text) is an indicator of how much oxygen is carried by hemoglobin in the blood. Having enough oxygen is vital for the functioning of cells in the human body. Measurement of Formula: see text is typically estimated with a pulse oximeter, but recent works have investigated how smartphone cameras can be used to infer Formula: see text. In this paper, we propose methods for the measurement of Formula: see text with a smartphone using convolutional neural networks and preprocessing steps to better guard against motion artifacts. To evaluate this methodology, we conducted a breath-holding study involving 39 participants. We compare the results using two different mobile phones. We compare our model with the ratio-of-ratios model that is widely used in pulse oximeter applications, showing that our system has significantly lower mean absolute error (2.02%) than a medical pulse oximeter.
Ding et al. (Mon,) conducted a observational in Arterial oxygen saturation measurement (n=39). Smartphone camera with convolutional neural networks vs. Medical pulse oximeter (ratio-of-ratios model) was evaluated on Mean absolute error of oxygen saturation measurement. Measuring arterial oxygen saturation using smartphone cameras and convolutional neural networks achieved a significantly lower mean absolute error (2.02%) than a standard medical pulse oximeter.