In-ear audio sensing via earbuds estimated stroke volume with a mean absolute error of 5.24 ml and a Pearson correlation of r=0.94 compared to clinically validated devices.
Does a deep learning system using in-ear audio from earbuds accurately estimate stroke volume compared to clinically validated devices in healthy participants?
In-ear audio sensing using earbuds combined with deep learning can accurately estimate cardiac stroke volume, potentially enabling scalable and affordable out-of-clinic cardiovascular monitoring.
Effect estimate: MAE 5.24 ml, r=0.94
Stroke volume, the volume of blood ejected by the left ventricle during a contrac- tion, is a key metric of cardiovascular health. Currently, stroke volume is measured in clinic with specialised equipment. While purpose-made wearables exist to mea- sure stroke volume, no solution relies solely on commodity devices. We present a deep learning system for stroke volume estimation from in-ear audio of earbuds. We combine generative self-supervised/transfer learning, a transformer-based autoencoder, to predict average stroke volume in unseen subjects. With data from 23 healthy participants, we compare our estimations to clinically validated device estimations. We achieve a mean absolute error of 5.24 ml, a Pearson correlation of r=0.94 between average predicted stroke volume and average true stroke vol- ume, and a Percentage Error in the limits of agreement of 11.05% (within clinical range for stroke volume measurement devices). These findings open the doors to longitudinal, scalable and affordable cardiovascular measurement out of clinic.
Mascolo et al. (Tue,) conducted a other in Healthy (n=23). In-ear audio sensing via earbuds with deep learning vs. Clinically validated device estimations was evaluated on Average stroke volume estimation (MAE 5.24 ml, r=0.94). In-ear audio sensing via earbuds estimated stroke volume with a mean absolute error of 5.24 ml and a Pearson correlation of r=0.94 compared to clinically validated devices.