AI and Neurological Rare & Neuroimmune Diseases ── Basic research ── 2026-11-12
Neurodegeneration and neuroimmunology research and AI
- Abstract
Background: Machine learning in tremor time-series analysis has so far been applied to differentiate tremor disorders. Respective analytical approaches can similarly be geared to explore therapeutic interventions, which conventionally are assessed by their induced amplitude changes. This may overlook subtle signal alterations. Feature-based machine learning offers the potential to explore much more granular tremor signal changes induced by therapeutic interventions.
Objective: To investigate multidimensional time-series signal changes associated with tremor-modulating interventions, and to identify shared and distinct intervention-specific patterns across tremor conditions.
Methods: Sixty-six participants (Essential Tremor (ET): propranolol n = 13, deep brain stimulation (DBS) n = 10; Parkinson’s Disease (PD): levodopa n = 23; enhanced Physiological Tremor (ePT): caffeine n = 20) were assessed in therapeutic OFF and ON states using high-resolution tri-axial accelerometry. In addition to established tremor characteristics, advanced time-series features were extracted from raw recordings. Machine Learning (ML) approaches, including ensemble classification and Principal Component Analysis (PCA), were applied to detect intervention-related changes.
Results: Significant clinical and signal-based intervention effects were observed across cohorts with the strongest tremor suppression following DBS in ET and expected tremor enhancement following caffeine in ePT. While amplitude-related features decreased consistently after therapeutic interventions, dopaminergic treatment in PD was additionally associated with changes in frequency-related characteristics. Caffeine-induced tremor modulation formed a distinct multidimensional signal pattern, whereas therapeutic interventions showed partially overlapping effects. No single feature consistently characterized successful tremor modulation across all interventions.
Conclusion: Feature-based ML reveals intervention-specific tremor patterns beyond conventional measures, supporting data-driven approaches for objective tremor characterization.
Journal IF-equivalent: 3.7 (OpenAlex 2-year mean citedness, value as of 2026-11-11, retrieved 2026-11-12; not the official Clarivate IF)Reference: Köhler L, Müller J, Chen YS, Selzam V, Häring V, Volkmann J, et al. Multi-dimensional signal exploration on the effect of tremor interventions. Front Neurol. 2026 Nov 10;17:1954245. doi:10.3389/fneur.2026.1954245.Checked: Abstract only - Abstract
In axons, mitochondrial transport is essential for neuronal function and survival, and its disruption is increasingly recognized as an early pathological hallmark in multiple neurodegenerative diseases. Despite its importance, quantitative analysis of mitochondrial transport dynamics remains challenging due to complex and heterogeneous motility patterns and reliance on labor-intensive manual tracking methods. Here, we present a deep learning-assisted framework for semiautomated quantification of mitochondrial axonal transport. Using time-lapse confocal imaging of individual in vivo axons in the well-established Drosophila nervous system, we comprehensively validated transport parameters, including displacement and velocity. We further assessed the fidelity of our method in recapitulating expert-derived measurements and its potential to overcome the limitations of conventional manual tracking. Notably, our framework enables detailed characterization of dynamic behaviors during transport, including intensity-based variations and concurrent morphological changes within individual mitochondria, potentially reflecting mitochondrial physiological states that were difficult to resolve with traditional approaches. Collectively, our study establishes the feasibility of next-generation analysis for axonal transport and highlights its potential to uncover previously inaccessible aspects of mitochondrial dynamics, providing a scalable and objective framework for investigating mitochondrial in vivo transport dysfunction in neurodegenerative disease models.
Journal IF-equivalent: 6.2 (OpenAlex 2-year mean citedness, value as of 2026-11-11, retrieved 2026-11-12; not the official Clarivate IF)Reference: Park JY, Chae M, Sung H. Leveraging Deep Learning to Reveal Fine-Scale In Vivo Mitochondrial Dynamics and Axonal Transport. Yale J Biol Med. 2026 Nov 4;99(3):558-75. doi:10.59249/zsdt8892.Checked: Abstract only