Application of photoplethysmography signals for healthcare systems: An in-depth review

• Published in: Computer methods and programs in biomedicine 2022-04, Vol.216, p.106677-106677, Article 106677
• Main Authors: Loh, Hui Wen, Xu, Shuting, Faust, Oliver, Ooi, Chui Ping, Barua, Prabal Datta, Chakraborty, Subrata, Tan, Ru-San, Molinari, Filippo, Acharya, U Rajendra
• Format: Article
• Language: English
• Subjects: Blood Pressure; Cardiac; Computer-aided diagnosis (CAD); Deep learning; Delivery of Health Care; Diabetes; Heart Rate; Machine Learning; Mental health; Photoplethysmography; Photoplethysmography (PPG); PRISMA; Signal Processing, Computer-Assisted; Sleep
• ISSN: 0169-2607; 1872-7565
• DOI: 10.1016/j.cmpb.2022.106677

•Review on studies that had used photoplethysmography (PPG) for the investigation of various health problems.•The investigated health problems fall into the following six categories: cardiac, blood pressure, sleep health, mental health, diabetes and miscellaneous.•Three routes, namely machine learning, deep learning, and statistical route, were adopted by these PPG studies for the detection of various health problems.•PPG signals can be easily acquired via smartphone and smartwatches which is non-invasive, low-cost and convenient.•PPG signals has the potential to be a potential precision medicine tool that can be employed for the detection of various health problem but more publicly available databases that cover a wide spectrum of health problems needs to be available to create such an indispensable tool of the future. Photoplethysmography (PPG) is a device that measures the amount of light absorbed by the blood vessel, blood, and tissues, which can, in turn, translate into various measurements such as the variation in blood flow volume, heart rate variability, blood pressure, etc. Hence, PPG signals can produce a wide variety of biological information that can be useful for the detection and diagnosis of various health problems. In this review, we are interested in the possible health disorders that can be detected using PPG signals. We applied PRISMA guidelines to systematically search various journal databases and identified 43 PPG studies that fit the criteria of this review. Twenty-five health issues were identified from these studies that were classified into six categories: cardiac, blood pressure, sleep health, mental health, diabetes, and miscellaneous. Various routes were employed in these PPG studies to perform the diagnosis: machine learning, deep learning, and statistical routes. The studies were reviewed and summarized. We identified limitations such as poor standardization of sampling frequencies and lack of publicly available PPG databases. We urge that future work should consider creating more publicly available databases so that a wide spectrum of health problems can be covered. We also want to promote the use of PPG signals as a potential precision medicine tool in both ambulatory and hospital settings.