Deep Learning-based Animal Behavior Analysis: Insights from Mouse Chronic Pain Models

2025-08-07

AI Summary

Current behavioral assessment of chronic pain relies on manual annotation, yet key phenotypic markers remain ill-defined, hindering detection of subtle, sustained behavioral alterations. To address this, we propose a label-free, generalizable behavioral feature extraction framework that automatically models mouse behavior from raw videos via a universal action-space projector, enabling unsupervised discrimination between neuropathic and inflammatory pain. Our method reveals, for the first time, zero-shot differential pharmacological responses to gabapentin across these pain modalities—supporting objective therapeutic evaluation. In a 15-class pain classification task, our approach achieves 48.41% accuracy—significantly surpassing human experts (21.33%) and B-SOiD (30.52%). For a three-class task, it attains 73.1% accuracy—outperforming human experts (48.0%) and B-SOiD (58.43%). These results demonstrate superior discriminative power and biological plausibility.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Computer Vision: Video Understanding & Activity Analysis
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Assessing chronic pain behavior in mice is critical for preclinical studies. However, existing methods mostly rely on manual labeling of behavioral features, and humans lack a clear understanding of which behaviors best represent chronic pain. For this reason, existing methods struggle to accurately capture the insidious and persistent behavioral changes in chronic pain. This study proposes a framework to automatically discover features related to chronic pain without relying on human-defined action labels. Our method uses universal action space projector to automatically extract mouse action features, and avoids the potential bias of human labeling by retaining the rich behavioral information in the original video. In this paper, we also collected a mouse pain behavior dataset that captures the disease progression of both neuropathic and inflammatory pain across multiple time points. Our method achieves 48.41% accuracy in a 15-class pain classification task, significantly outperforming human experts (21.33%) and the widely used method B-SOiD (30.52%). Furthermore, when the classification is simplified to only three categories, i.e., neuropathic pain, inflammatory pain, and no pain, then our method achieves an accuracy of 73.1%, which is notably higher than that of human experts (48%) and B-SOiD (58.43%). Finally, our method revealed differences in drug efficacy for different types of pain on zero-shot Gabapentin drug testing, and the results were consistent with past drug efficacy literature. This study demonstrates the potential clinical application of our method, which can provide new insights into pain research and related drug development.

Problem

• Automatically discover chronic pain features without human labels
• Improve accuracy in classifying mouse pain behaviors
• Analyze drug efficacy differences for pain types

Innovation

• Automatically discovers chronic pain features
• Uses universal action space projector
• Outperforms human experts in classification