Key result
Deep-learning autoencoder cuts heart sound error up to ~5-fold, improving accuracy of physiological estimates.
Why the study?
Cardiac vibration signals acquired by implantable devices for remote monitoring in heart failure are frequently corrupted by specific noises related to sensor placement and patient activity.
Does a deep-learning-based denoising autoencoder improve the quality and reliability of heart sound signals from implantable devices in a preclinical pig model?
Does a deep-learning-based denoising autoencoder improve the quality and reliability of heart sound signals from implantable devices in a preclinical pig model?
Effect estimate: reduced mean relative error by up to a factor of five
A deep-learning-based denoising autoencoder significantly improves the quality and reliability of heart sound signals from implantable devices in a preclinical model.
May aid device-based heart sound analysis in preclinical models; leaves open human translation.
In the context of assisting patients with heart failure, implantable devices measuring cardiac mechanical activity offer promising solutions for remote autonomous monitoring of individuals at risk. However, cardiac vibration signals acquired by these implants are often subject to various specific noises associated with sensor placement and patient activity. In this paper, we propose a novel supervised method for cleaning noise-corrupted sequences and improving their pathophysiological interpretation. Our approach involves modeling the characteristics of both clean cardiac components and noise contributions through a qualitative classification of recordings. These models are then utilized to generate a controllable database, which trains a deep-learning-based denoising autoencoder. We have tested this procedure on a preclinical prototype implanted subcutaneously in four healthy pigs. We evaluate the denoising performance of our method using various quantitative and qualitative metrics. Our cleaning process, by reducing the mean relative error by up to a factor of five and enhancing the contrast of heart sounds to levels similar to their clean counterparts, improves the accuracy of physiological estimates such as heart rate or systole and diastole durations.Clinical relevance- Our approach consistently increases the number of signals suitable for further medical analysis. The proposed combination of a data-driven training database and a machine-learning denoising algorithm can significantly improve the quality and reliability of heart sound signals.
No takes yet. Share an insight, caveat, or question.
Tatulli et al. (2025) studied Healthy (preclinical model for heart failure monitoring) (n=4). Deep-learning-based denoising autoencoder vs. Noisy signals was evaluated on Denoising performance (mean relative error and contrast of heart sounds) (reduced mean relative error by up to a factor of five). A deep-learning-based denoising autoencoder reduced the mean relative error of heart sound recordings by up to a factor of five, improving the accuracy of physiological estimates.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: