CVSPMay 30

An explainable hierarchical self attention-based approach for tremor detection in the time domain

arXiv:2606.0046161.7h-index: 12
Predicted impact top 55% in CV · last 90 daysOriginality Synthesis-oriented
AI Analysis

For clinicians diagnosing tremor, this work provides a proof-of-concept for data-driven time-domain detection with interpretability, but performance is below existing frequency-domain methods.

The authors proposed an explainable hierarchical self-attention framework for tremor detection from 3D kinematic time-series data, achieving an average F1-score of 0.765 across nine body parts, which is lower than the frequency-domain state-of-the-art (0.909).

Tremor is a common movement disorder associated with conditions like Parkinson's disease and Essential tremor, traditionally diagnosed through expert clinician assessment. Current automated detection methods rely on frequency-domain features informed by clinical expertise. In this work, we present an explainable, two-stage hierarchical framework for tremor detection in the time domain that learns tremor patterns directly from 3D kinematic marker time-series data across entire tremor-provoking trials. Our framework combined a deep convolutional and long short-term memory network to learn tremor representations from short, discrete, non-overlapping time segments of kinematic time series data from trials, which are then processed by a vision transformer that models their long-term temporal dynamics of time segment features for trial (session) level classification. Evaluated across nine body parts, the framework achieved F1-scores of 0.594 - 0.947 depending on body parts (average: 0.765), falling short of the frequency-domain state-of-the-art performance (0.909) while requiring minimal preprocessing. Attention weights and gradient-based class activation maps (Grad-CAM) identified time-domain features of tremor across body parts. This proof of concept demonstrated the feasibility of data-driven time-domain modeling for tremor detection across anatomically diverse body parts, while reducing reliance on expert-engineered spectral features and providing posthoc interpretability of temporal and anatomical patterns of tremor.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes