arXiv subjects

Stewart A. Factor

Publications and source records attributed to Stewart A. Factor.

3 recordsLinked to original sources

arXiv2026

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

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.

cs.CV↗

arXiv2026

Evidence for Phenotype-Driven Disparities in Freezing of Gait Detection and Approaches to Bias Mitigation

Freezing of gait (FOG) is a debilitating symptom of Parkinson's disease (PD) and a common cause of injurious falls. Recent advances in wearable-based human activity recognition (HAR) enable FOG detection, but bias and fairness in these models remain understudied. Bias refers to systematic errors leading to unequal outcomes, while fairness refers to consistent performance across subject groups. Biased models could systematically underserve patients with specific FOG phenotypes or demographics, potentially widening care disparities. We systematically evaluated bias and fairness of state-of-the-art HAR models for FOG detection across phenotypes and demographics using multi-site datasets. We assessed four mitigation approaches: conventional methods (threshold optimization and adversarial debiasing) and transfer learning approaches (multi-site transfer and fine-tuning large pretrained models). Fairness was quantified using demographic parity ratio (DPR) and equalized odds ratio (EOR). HAR models exhibited substantial bias (DPR & EOR < 0.8) across age, sex, disease duration, and critically, FOG phenotype. Phenotype-specific bias is particularly concerning as tremulous and akinetic FOG require different clinical management. Conventional bias mitigation methods failed: threshold optimization (DPR=-0.126, EOR=+0.063) and adversarial debiasing (DPR=-0.008, EOR=-0.001) showed minimal improvement. In contrast, transfer learning from multi-site datasets significantly improved fairness (DPR=+0.037, p<0.01; EOR=+0.045, p<0.01) and performance (F1-score=+0.020, p<0.05). Transfer learning across diverse datasets is essential for developing equitable HAR models that reliably detect FOG across all patient phenotypes, ensuring wearable-based monitoring benefits all individuals with PD.

eess.SP↗

arXiv2020

Multimodal assessment of nigrosomal degeneration in Parkinson's disease

Background: Approximately forty percent of all dopaminergic neurons in SNpc are located in five dense neuronal clusters, named nigrosomes. T2- or T2*-weighted images are used to delineate the largest nigrosome, named nigrosome-1. In these images, nigrosome-1 is a hyperintense region in the caudal and dorsal portion of the T2- or T2*-weighted substantia nigra. In PD, nigrosome-1 experiences iron accumulation, which leads to a reduction in T2-weighted hyperintensity. Here, we examine neuromelanin-depletion and iron deposition in regions of interest (ROIs) derived from quantitative-voxel based morphometry (qVBM) on neuromelanin-sensitive images and compare the ROIs with nigrosome-1 identified in T2*-weighted images. Methods: Neuromelanin-sensitive and multi-echo gradient echo imaging data were obtained. R2* was calculated from multi-echo gradient echo imaging data. qVBM analysis was performed on neuromelanin-sensitive images and restricted to SNpc. Mean neuromelanin-sensitive contrast and R2* was measured from the resulting qVBM clusters. Nigrosome-1 was segmented in T2*-weighted images of control subjects and its location was compared to the spatial location of the qVBM clusters. Results: Two bilateral clusters emerged from the qVBM analysis. These clusters showed reduced neuromelanin-sensitive contrast and increased mean R2* in PD as compared to controls. Cluster-1 from the qVBM analysis was in a similar spatial location as nigrosome-1, as seen in T2*-weighted images. Conclusion: qVBM cluster-1 shows reduced neuromelanin-sensitive contrast and is in a similar spatial position as nigrosome-1. This region likely corresponds to nigrosome-1 while the second cluster may correspond to nigrosome-2.

physics.med-ph↗