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

Dimensions overall score 7.0

• The NeuroPose-AHM dataset contains 2,756 patient-group-level records spanning 57 neurological conditions, derived from 846 AHM-relevant papers.result 95%
  Evidencepartial

  The dataset contains 2,756 patient-group-level records spanning 57 neurological conditions, derived from 846 AHM-relevant papers.

  Implicationpartial

  Directly stated in abstract with specific numeric counts

  Verificationpartial

  partial

• Study-level classification in the multi-LLM extraction framework achieved strong agreement with kappa = 0.822.result 95%
  Evidencepartial

  Inter-LLM reliability analysis confirms robust extraction performance, with study-level classification achieving strong agreement (kappa = 0.822).

  Implicationpartial

  Directly stated in abstract with specific statistical measure

  Verificationpartial

  partial

• Multi-label AHM type classification for cervical dystonia achieved F1 score of 0.856.result 95%
  Evidencepartial

  First, Task 1 performs multi-label AHM type classification (F1 = 0.856).

  Implicationpartial

  Directly stated in abstract with specific performance metric

  Verificationpartial

  partial

• The Head-Neck Severity Index (HNSI) was validated against real-world CD patient data with aligned severe-band proportions of 6.7%.result 90%
  Evidencepartial

  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.

  Implicationpartial

  Directly stated in abstract with specific validation result

  Verificationpartial

  partial

• Bridge analysis between movement-type probabilities and HNSI scores produced significant correlations with p < 0.001.result 95%
  Evidencepartial

  Finally, Task 4 performs bridge analysis between movement-type probabilities and HNSI scores, producing significant correlations (p less than 0.001).

  Implicationpartial

  Directly stated in abstract with specific statistical significance

  Verificationpartial

  partial

• The NeuroPose-AHM dataset was constructed through a multi-LLM extraction framework applied to 1,430 peer-reviewed publications.method 95%
  Evidencepartial

  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.

  Implicationpartial

  Directly stated in abstract with specific method description

  Verificationpartial

  partial

• The absence of a multi-condition resource integrating kinematic measurements, clinical severity scores, and patient demographics constitutes a persistent barrier to AI-driven diagnostic tools for abnormal head movements.limitation 85%
  Evidencepartial

  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.

  Implicationpartial

  Directly stated as problem statement in abstract, though presented as background rather than a finding

  Verificationpartial

  partial

• Cervical dystonia is the neurological condition most directly defined by pathological head movement.technical 90%
  Evidencepartial

  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.

  Implicationpartial

  Directly stated in abstract as rationale for focusing on cervical dystonia in the demonstration

  Verificationpartial

  partial

Competitive landscape

A novel knowledge-based dataset of abnormal head movements extracted from medical literature, enabling AI-driven diagnostic tools for neurological conditions.