Key result
Machine learning algorithms for estimating blood pressure from photoplethysmography might actually be learning to identify persons instead of predicting blood pressure.
Why the study?
To prevent overestimation of machine learning results in blood pressure estimation from photoplethysmography by investigating how intra- and inter-subject variabilities affect algorithm performance.
Highlights a critical methodological flaw in machine learning models for PPG-based blood pressure estimation, where models may learn subject identity rather than physiological blood pressure.
Highlights potential flaw in photoplethysmography blood pressure models; leaves open whether they predict values or identify individuals.
Cardiovascular diseases are the leading causes of death in humans, and blood pressure (BP) monitoring is an important procedure to prevent, diagnose, assess, and treat these diseases, thereby avoiding more severe conditions. The most reliable and common techniques of measuring BP use sphygmomanometers, but they are more suited to single measurements than continuous ones. A more promising approach is the use of photoplethysmography (PPG), a low-cost, opto-electronic technique that, in the form of wearable devices, allows the acquisition of a modulated light signal highly correlated to BP. In this context, many works have reported methods to estimate BP from PPG, achieving impressive results. In order to prevent overestimation of these results, we investigate—by considering two different data arrangements—how intra- and inter-subject variabilities in BP can affect the results of machine learning algorithms. We also compare the outcomes of these algorithms with the outcome of a regression using age, sex, weight and subject index number as attributes. Our general conclusion is that those algorithms might actually be learning to identify persons instead of predicting BP, showing that the split of data is a very important step.
No takes yet. Share an insight, caveat, or question.
Costa et al. (2022) studied Blood pressure monitoring. Machine learning algorithms for blood pressure estimation from photoplethysmography vs. Regression using age, sex, weight and subject index number was evaluated on Effect of intra- and inter-subject variabilities on machine learning algorithm results. Machine learning algorithms for estimating blood pressure from photoplethysmography might actually be learning to identify persons instead of predicting blood pressure.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: