Key result
Wrist photoplethysmography with machine learning for blood pressure estimation achieved a mean absolute error of 1.1 mmHg in a personalized scenario and 8.7 mmHg in an uncalibrated scenario.
Why the study?
Most wearable medical devices entering the market are not standardized, not medically approved, and highly inaccurate.
Does a cuff-less blood pressure estimation system using wrist photoplethysmography provide accurate measurement of systolic and diastolic blood pressure?
Does a cuff-less blood pressure estimation system using wrist photoplethysmography provide accurate measurement of systolic and diastolic blood pressure?
Effect estimate: MAE 1.1mmHg (personalized), 8.7mmHg (uncalibrated)
A novel cuff-less blood pressure estimation method using wrist photoplethysmography and machine learning demonstrates low mean absolute error, particularly in personalized scenarios.
Hypothesis-generating for cuffless wrist BP estimation; prospective validation required before clinical use.
One of the most promising and at the same time rapidly growing sectors in healthcare is that of wearable medical devices. Population ageing constantly shifts towards a higher number of senior and elderly people with increased prevalence of chronic diseases often requiring long-term care and a need to decrease hospitalization time and cost. However, today most of the devices entering the market are not standardized nor medically approved, and they are highly inaccurate. In this work we present a system and a method to provide accurate measurement of systolic and diastolic blood pressure (BP) based solely on wrist photoplethysmography. We map morphological features to BP values using machine learning and propose ways to select high quality signals leading to an accuracy improvement of up to 33.5%, if compared against no signal selection, a mean absolute error of 1.1mmHg in a personalized scenario and 8.7mmHg in an uncalibrated leave-one-out scenario.
No takes yet. Share an insight, caveat, or question.
Pediaditis et al. (2021) studied Blood pressure estimation. Wrist photoplethysmography with machine learning vs. No signal selection was evaluated on Accuracy of systolic and diastolic blood pressure measurement (MAE 1.1mmHg (personalized), 8.7mmHg (uncalibrated)). Wrist photoplethysmography with machine learning for blood pressure estimation achieved a mean absolute error of 1.1 mmHg in a personalized scenario and 8.7 mmHg in an uncalibrated scenario.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: