Abnormal Head Movements in Neurological Conditions: A Knowledge-Based Dataset with Application to Cervical Dystonia

2026-04-02

AI Summary

This study addresses the limitation of existing AI-assisted diagnostic approaches, which lack comprehensive resources integrating kinematic data, clinical ratings, and demographic information for abnormal head movements (AHM) across multiple neurological disorders. To bridge this gap, the authors construct NeuroPose-AHM, a knowledge-rich dataset that leverages multiple large language models to extract 2,756 structured patient-group-level records from 1,430 publications, encompassing 57 distinct neurological conditions, thereby establishing the first multi-disorder structured knowledge base for AHM. Focusing on cervical dystonia, they propose a unified clinical severity metric—Head Movement Neurological Severity Index (HNSI)—and develop a four-task analytical framework incorporating multi-label classification, scale normalization, and bridging correlation analysis. Experiments demonstrate an F1 score of 0.856 for AHM type classification, validate HNSI’s plausibility in high-severity ranges, and reveal a significant correlation (p<0.001) between movement-type probabilities and HNSI. The dataset is publicly released.

Abstract

Abnormal head movements (AHMs) manifest across a broad spectrum of neurological disorders; however, the absence of a multi-condition resource integrating kinematic measurements, clinical severity scores, and patient demographics constitutes a persistent barrier to the development of AI-driven diagnostic tools. To address this gap, this study introduces NeuroPose-AHM, a knowledge-based dataset of neurologically induced AHMs constructed through a multi-LLM extraction framework applied to 1,430 peer-reviewed publications. The dataset contains 2,756 patient-group-level records spanning 57 neurological conditions, derived from 846 AHM-relevant papers. Inter-LLM reliability analysis confirms robust extraction performance, with study-level classification achieving strong agreement (kappa = 0.822). To demonstrate the dataset's analytical utility, a four-task framework is applied to cervical dystonia (CD), the condition most directly defined by pathological head movement. First, Task 1 performs multi-label AHM type classification (F1 = 0.856). Task 2 constructs the Head-Neck Severity Index (HNSI), a unified metric that normalizes heterogeneous clinical rating scales. The clinical relevance of this index is then evaluated in Task 3, where HNSI is validated against real-world CD patient data, with aligned severe-band proportions (6.7%) providing a preliminary plausibility indication for index calibration within the high severity range. Finally, Task 4 performs bridge analysis between movement-type probabilities and HNSI scores, producing significant correlations (p less than 0.001). These results demonstrate the analytical utility of NeuroPose-AHM as a structured, knowledge-based resource for neurological AHM research. The NeuroPose-AHM dataset is publicly available on Zenodo (https://doi.org/10.5281/zenodo.19386862).

Problem

• abnormal head movements
• neurological disorders
• AI-driven diagnostics
• clinical severity
• knowledge-based dataset

Innovation

• knowledge-based dataset
• multi-LLM extraction
• abnormal head movements
• Head-Neck Severity Index
• cervical dystonia