Deep Learning Pose Estimation for Multi-Label Recognition of Combined Hyperkinetic Movement Disorders

2026-01-29

AI Summary

This study addresses the clinical challenge of accurately identifying hyperkinetic movement disorders—such as dystonia, tremor, and chorea—which are often confounded by symptom fluctuation, intermittency, and co-occurrence, leading to subjective assessment bias. Leveraging routine outpatient videos, the work proposes a novel, equipment-free approach that integrates deep learning–based pose estimation with multidimensional kinematic feature engineering. By extracting statistical, time-domain, frequency-domain, and complexity features from time-series data of human body keypoints, the authors develop a multi-label classification model capable of objectively and automatically detecting coexisting hyperkinetic movement disorders. The method demonstrates strong scalability and offers a practical, automated solution for clinical evaluation and longitudinal monitoring without requiring specialized hardware.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Intelligent Robots: State Estimation
• Computer Vision: Motion & Tracking

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Hyperkinetic movement disorders (HMDs) such as dystonia, tremor, chorea, myoclonus, and tics are disabling motor manifestations across childhood and adulthood. Their fluctuating, intermittent, and frequently co-occurring expressions hinder clinical recognition and longitudinal monitoring, which remain largely subjective and vulnerable to inter-rater variability. Objective and scalable methods to distinguish overlapping HMD phenotypes from routine clinical videos are still lacking. Here, we developed a pose-based machine-learning framework that converts standard outpatient videos into anatomically meaningful keypoint time series and computes kinematic descriptors spanning statistical, temporal, spectral, and higher-order irregularity-complexity features.

Problem

• Hyperkinetic movement disorders
• Multi-label recognition
• Pose estimation
• Clinical video analysis
• Movement phenotyping

Innovation

• pose estimation
• hyperkinetic movement disorders
• multi-label recognition
• kinematic descriptors
• deep learning