Few-Shot Learning for Personalised Automated Pain Assessment

2026-10-07

AI Summary

This study addresses the challenge that significant inter-individual variability in pain perception hinders the cross-subject generalization of population-level classifiers. By formulating the population-to-subject evaluation as a domain shift problem, this work proposes a few-shot adaptation method based on support set conditioning. Specifically, the approach leverages a meta-learning framework combined with a k-shot conditioning mechanism to enable rapid model adaptation, effectively overcoming the personalization challenges posed by inter-subject variability. Experimental evaluations conducted on multiple publicly available databases demonstrate that the proposed method achieves a binary classification accuracy of up to 91.25%, substantially improving the performance of cross-subject automated pain assessment.

Abstract

Pain perception varies substantially across individuals, making it difficult for population-based classifiers to generalise across all subjects in a dataset. One way to account for subject variability is to train personalised classifiers. In this work, we evaluate Few-Shot Learning, a sub-area of Meta-Learning, as an approach to personalisation in automated pain assessment. We re-interpret the shift from population-level to subject-level evaluation as a task-domain shift, where the observed classes remain fixed but the target subject changes. We evaluate our method on the BioVid Pain Database, the SenseEmotion Database, and the PainMonit Experimental Dataset (PMED), reaching 85.75% and 35.49% accuracy on BioVid and 82.37% and 41.88% on SenseEmotion in the binary and multi-class settings under a Leave-One-Subject-Out CV protocol respectively, and 90.47% on PMED, for which only a binary benchmark exists. Using samples to implement k-shot conditioning, the accuracies can be improved to 86.25%, 40.06%, 83.43%, 44.08%, and 91.25%, respectively. To further evaluate the effects and robustness of our method, we provide additional ablation experiments and investigate the personalisation effects. Our results suggest that support-conditioned few-shot adaptation can improve average performance under inter-subject variability.

Problem

• Few-Shot Learning
• Automated Pain Assessment
• Personalisation
• Inter-subject Variability

Innovation

• Few-Shot Learning
• Personalised Pain Assessment
• Meta-Learning
• Task-Domain Shift
• k-shot Conditioning