Wearable-based Fair and Accurate Pain Assessment Using Multi-Attribute Fairness Loss in Convolutional Neural Networks

TL;DR

This paper introduces a CNN model with Multi-attribute Fairness Loss to improve fairness and accuracy in pain assessment from diverse health data, addressing biases related to protected attributes.

Contribution

The paper presents a novel CNN with Multi-attribute Fairness Loss that explicitly accounts for protected attributes to enhance fairness in pain prediction models.

Findings

The proposed model outperforms existing fairness mitigation methods.

Achieves 75-85% accuracy on NIH dataset.

Effectively reduces disparities between privileged and unprivileged groups.

Abstract

The integration of diverse health data, such as IoT (Internet of Things), EHR (Electronic Health Record), and clinical surveys, with scalable AI(Artificial Intelligence) has enabled the identification of physical, behavioral, and psycho-social indicators of pain. However, the adoption of AI in clinical pain evaluation is hindered by challenges like personalization and fairness. Many AI models, including machine and deep learning, exhibit biases, discriminating against specific groups based on gender or ethnicity, causing skepticism among medical professionals about their reliability. This paper proposes a Multi-attribute Fairness Loss (MAFL) based Convolutional Neural Network (CNN) model designed to account for protected attributes in data, ensuring fair pain status predictions while minimizing disparities between privileged and unprivileged groups. We evaluate whether a balance between accuracy and fairness is achievable by comparing the proposed model with existing mitigation methods. Our findings indicate that the model performs favorably against state-of-the-art techniques. Using the NIH All-Of-US dataset, comprising data from 868 individuals over 1500 days, we demonstrate our model's effectiveness, achieving accuracy rates between 75% and 85%.