Exploring Remote Photoplethysmography for Neonatal Pain Detection from Facial Videos

2026-04-28

AI Summary

This study addresses the critical need for objective, non-contact assessment of neonatal pain, which, if undetected, can lead to developmental delays. The authors propose a novel multimodal approach that fuses remote photoplethysmography (rPPG) signals extracted from facial videos with audio features to detect pain without physical contact. Innovatively, they introduce a region-of-interest (ROI) quality metric to select areas least affected by skin deformation and optimize rPPG signal quality using signal-to-noise ratio as the objective function. Notably, this work provides the first empirical validation of the superior performance of the blue color channel for rPPG-based neonatal pain detection. Experimental results demonstrate that the proposed method significantly outperforms unimodal baselines, confirming both the efficacy of rPPG in this context and the added value of multimodal fusion.

Abstract

Unaddressed pain in neonates can lead to adverse effects, including delayed development and slower weight gain, emphasising the need for more objective and reliable pain assessment methods. Hence, automated methods using behavioural and physiological pain indicators have been developed to aid healthcare professionals in the Neonatal ICU. Traditional contact-based methods for physiological parameter estimation are unsuitable for long-term monitoring and increase the risk of spreading diseases like COVID-19. We introduce a novel approach using remote photoplethysmography (rPPG) to estimate pulse signals in a non-contact manner and employ them for neonatal pain detection. The temporal signals acquired from regions-of-interest (ROIs) affected by skin deformations may exhibit lower quality and provide erroneous rPPG signals. Therefore, we incorporated a quality parameter to select the temporal signals obtained from ROIs that are least affected by skin deformations. Further, we employed signal-to-noise ratio as a fitness parameter to extract the rPPG signal corresponding to the clip that is least affected by noise. Experimental findings demonstrate that the rPPG signals provide useful information for neonatal pain detection, and signals extracted from the blue colour channel outperform those extracted from other colour channels. We also show that combining rPPG and audio features provides better results than individual modalities.

Problem

• neonatal pain detection
• remote photoplethysmography
• non-contact monitoring
• physiological signals
• pain assessment

Innovation

• remote photoplethysmography
• neonatal pain detection
• non-contact monitoring
• signal quality assessment
• multimodal fusion