SynPAIN: A Synthetic Dataset of Pain and Non-Pain Facial Expressions

2025-07-25

AI Summary

Existing pain detection datasets suffer from insufficient racial/ethnic diversity, underrepresentation of older adults, and privacy constraints—limiting model fairness and clinical applicability. To address these issues, we introduce the first publicly available, synthetically generated pain expression dataset specifically designed for older adults, encompassing multi-ethnic and multi-age-group representation (10,710 images, including 5,355 neutral–pain image pairs). Generated via commercial generative AI, the dataset is validated clinically through Facial Action Unit (AU) analysis to ensure pathological fidelity. We further propose a “synthetic-data-driven bias identification and mitigation” framework that systematically quantifies and exposes performance disparities across demographic subgroups in state-of-the-art models—a first in this domain. When applied to real-world clinical data, synthetic data augmentation improves mean accuracy by 7.0%, significantly enhancing generalizability and algorithmic fairness.

Technology Category

• Computer Vision: Bias, Fairness & Privacy
• Philosophy and Ethics of AI: Bias, Fairness & Equity
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Social Networks and Social Media: Fairness and bias in social network and social media analysis
• Economics, Online Markets and Human Computation: Fairness and ethical considerations in crowd work and in human-in-the-loop AI systems

Abstract

Accurate pain assessment in patients with limited ability to communicate, such as older adults with dementia, represents a critical healthcare challenge. Robust automated systems of pain detection may facilitate such assessments. Existing pain detection datasets, however, suffer from limited ethnic/racial diversity, privacy constraints, and underrepresentation of older adults who are the primary target population for clinical deployment. We present SynPAIN, a large-scale synthetic dataset containing 10,710 facial expression images (5,355 neutral/expressive pairs) across five ethnicities/races, two age groups (young: 20-35, old: 75+), and two genders. Using commercial generative AI tools, we created demographically balanced synthetic identities with clinically meaningful pain expressions. Our validation demonstrates that synthetic pain expressions exhibit expected pain patterns, scoring significantly higher than neutral and non-pain expressions using clinically validated pain assessment tools based on facial action unit analysis. We experimentally demonstrate SynPAIN's utility in identifying algorithmic bias in existing pain detection models. Through comprehensive bias evaluation, we reveal substantial performance disparities across demographic characteristics. These performance disparities were previously undetectable with smaller, less diverse datasets. Furthermore, we demonstrate that age-matched synthetic data augmentation improves pain detection performance on real clinical data, achieving a 7.0% improvement in average precision. SynPAIN addresses critical gaps in pain assessment research by providing the first publicly available, demographically diverse synthetic dataset specifically designed for older adult pain detection, while establishing a framework for measuring and mitigating algorithmic bias. The dataset is available at https://doi.org/10.5683/SP3/WCXMAP

Problem

• Addressing limited diversity in pain detection datasets
• Improving pain assessment in non-communicative older adults
• Mitigating algorithmic bias in existing pain detection models

Innovation

• Generative AI creates diverse synthetic facial expressions
• Synthetic data improves pain detection model performance
• Dataset enables bias detection in pain assessment algorithms