A Review of Machine Learning Approaches for Non-Contact Oxygen Saturation (SpO 2 ) and Heart Rate Estimation

Abstract

Non-contact cardiovascular measurement systems have gained widespread interest as an alternative to the conventional contact methods. Of all these methods, facial based techniques that determine heart rate and oxygen saturation (SpO 2 ) hold the greatest promise for real-time use in the healthcare and other sectors. These methods have benefited from the recent advances made in machine learning in terms of accuracy, robustness, and scalability. This review examines the most recent advances in facial-based HR and SpO 2 estimation techniques, focusing especially on the role of ML algorithms. Algorithms, data problems, and comparative performance of facial-based HR and SpO 2 estimation methods, together with the disadvantages associated with these algorithms and ethical questions involved, will be discussed in the article. Future trends in the development of hybrid systems and applications in wearable IoT devices will also be highlighted. The purpose of this review is to familiarize the reader with the recent advances in the field of non-contact HR and SpO 2 estimation systems.