Continuous cuffless and non-invasive measurement of arterial blood pressure-concepts and future perspectives

Hypertension diagnosis is one of the most common and important procedures in everyday clinical practice. Its applicability depends on correct and comparable measurements. Cuff-based measurement paradigms have dominated ambulatory blood pressure (BP) measurements for multiple decades. Cuffless and non-invasive methods may offer various advantages, such as a continuous and undisturbing measurement character. This review presents a conceptual overview of recent advances in the field of cuffless measurement paradigms and possible future developments which would enable cuffless beat-to-beat BP estimation paradigms to become clinically viable. It was refrained from a direct comparison between most studies and focussed on a conceptual merger of the ideas and conclusions presented in landmark scientific literature. There are two main approaches to cuffless beat-to-beat BP estimation represented in the scientific literature: First, models based on the physiological understanding of the cardiovascular system, mostly reliant on the pulse wave velocity combined with additional parameters. Second, models based on Deep Learning techniques, which have already shown great performance in various other medical fields. This review wants to present the advantages and limitations of each approach. Following this, the conceptional idea of unifying the benefits of physiological understanding and Deep Learning techniques for beat-to-beat BP estimation is presented. This could lead to a generalised and uniform solution for cuffless beat-to-beat BP estimations. This would not only make them an attractive clinical complement or even alternative to conventional cuff-based measurement paradigms but would substantially change how we think about BP as a fundamental marker of cardiovascular medicine. PLAIN LANGUAGE SUMMARY This concept review wants to highlight the current state of non-invasive cuffless continuous blood pressure estimation. Cuffless blood pressure measurement devices usually rely on pulse wave velocity. Pulse wave velocity is mostly calculated via measuring pulse arrival time. Using pulse transit time instead of pulse arrival time showed improved results. Additional biomarkers like heart rate, photoplethysmogram intensity ratio or heart rate power spectrum ratio can be used to improve measurement precision. For cuffless and cuff-based devices intended for 24-hour BP measurements, a more refined validation protocol is required. The ESH assesses the measurement accuracy of cuffless devices as unclear and does not recommend hypertension diagnosis based on cuffless devices. Machine Learning and Deep Learning applications are a powerful tool to generate complex algorithms, which can be used to estimate blood pressure. Selecting biomarkers like pulse wave velocity, heart rate, etc. as input features for Deep Learning systems would be a very promising approach to measure blood pressure more precise.