Blood Oxygen Saturation Measurement: A Survey

Abstract

Although advanced technologies are available to handle complex health issues, the outbreak of COVID-19 is still affecting humans around the globe mentally and physically. To prevent such an outbreak, one approach is to measure oxygen saturation to predict severity early. Therefore, several methods have been developed for predicting accurate oxygen saturation measurements. Due to the non-availability of benchmark and standard approaches, diversified methods have been developed. This leads to confusion about the results, statements, and conclusions. In addition, it hampers the invention of new approaches to address the challenges of oxygen saturation measurement. This motivated us to study different methods of oxygen saturation measurement in this work. The work aims to analyze diverse methods for identifying the strengths and weaknesses of models so that appropriate models can be chosen for specific situations and cases. Furthermore, researchers can have a clear understanding of the state of the art to develop new approaches to address open challenges. The work provides a comprehensive review of different models, their strengths and weaknesses, and a discussion of new challenges, applications, and directions. This can be used as a reference, benchmark, or model for further investigation. To the best of our knowledge, this is the first survey on blood oxygen saturation measurement. 

Received: 24 July 2025 | Revised: 30 December 2025 | Accepted: 29 May 2026

Conflicts of Interest

Palaiahnakote Shivakumara is the Editor-in-Chief and Umapada Pal is an Advisory Board Member for Artificial Intelligence and Applications, and they were not involved in the editorial review or the decision to publish this article. The authors declare that they have no conflicts of interest in this work. 

Data Availability Statement

The data that support the findings of this study are openly available in VIPL at https://vipl.ict.ac.cn/en/resources/databases/201811/t20181129_32716.html, in ImViA at https://sites.google.com/view/ybenezeth/ubfcrppg, in idiap at https://publications.idiap.ch/index.php/publications/show/3688, in GitHub at https://github.com/ubicomplab/rPPG-Toolbox, and in arXiv at https://arxiv.org/pdf/2602.23771. 

Author Contribution Statement

Rakesh Dey: Conceptualization, Methodology, Investigation, Writing – original draft, Visualization. Shivakumara Palaiahnakote: Conceptualization, Methodology, Investigation, Writing – original draft, Writing – review & editing, Visualization, Supervision. Umapada Pal: Writing – review & editing, Supervision. Sukalpa Chanda: Validation. Yue Lu: Validation.