Identifying Parkinson’s disease (PD) during its prodromal, non-motor phase remains a barrier to early intervention. Gait impairment represents one of the most disabling and clinically informative manifestations of PD. Subtle and sub-clinical gait impairments may occur during the prodromal phase, being potentially useful for early PD identification. This study developed an interpretable machine-learning framework using wearable inertial gait data to model and quantify high prodromal burden in PD, defined as the anamnestic presence of at least three prodromal symptoms. A total of 275 individuals with PD performed 30-m walking trials using a single lumbar inertial sensor. Thirty-five biomechanical and clinical variables were extracted, and feature selection identified five key predictors: multiscale entropy (MSE) along three axes, vertical improved harmonic ratio (iHRv), and body weight. A Random Forest classifier balanced through Conditional Tabular Generative Adversarial Network (CTGAN) augmentation achieved robust performance (ROCAUC = 0.84, PRAUC = 0.86, F1score = 0.76). Explainability analyses highlighted that increased MSE and reduced iHRv were the strongest contributors to high prodromal burden, indicating elevated gait complexity and altered spatio-temporal symmetry. These findings delineate a gait phenotype associated with prodromal burden in PD, providing mechanistic insight into early disease-related motor alterations.
BACKGROUND:Spinal muscular atrophy (SMA) is a genetic neuromuscular disorder caused by survival motor neuron (SMN1) deletion. While loss of ambulation in SMA type III typically occurs at a median age of 13.4 years, outcomes in the treatment era remain unclear. This study aims to address that gap by investigating ambulation outcomes in individuals with type III receiving disease-modifying therapies. METHODS:This retrospective study analysed prospectively collected international data. Time-dependent Cox models assessed the association between treatment initiation and age at loss of ambulation, adjusting for age at onset, sex, SMN2 copies, birth year and country. Treatment was modelled as a time-dependent covariate to avoid immortal time bias. Descriptive analyses used Mann-Whitney U and χ² tests. RESULTS:Among 555 individuals with type III, treatment halved the risk of ambulation loss (HR=0.50), with median loss at 44 vs 32 years in treated and untreated groups. Later onset, ≥4 SMN2 copies and female sex were also protective. The treatment effect was significant in type IIIA (HR=0.34) but not IIIB, with no significant interactions by sex, country or SMN2, though effects remained directionally protective. CONCLUSIONS:Treatment in type III reduced the risk of ambulation loss by 50%, extending median ambulation by 12 years, with the greatest benefit in type IIIA. Later onset, female sex and higher SMN2 copy number were also protective but did not modify treatment effect. These findings underscore the value of early treatment and support its broad use to preserve ambulation across clinical subgroups.
Rescue stenting (RS) can achieve durable recanalization in cases of acute large vessel occlusion due to underlying intracranial artery stenosis (ICAS), but its clinical effects may be influenced by procedural factors. This study aimed to evaluate whether the severity of stenosis affects the outcomes after RS. In this multicenter retrospective study, patients with acute middle cerebral artery occlusion and underlying ICAS were divided into two groups based on the treatment they received: mechanical thrombectomy (MT) + RS (n = 172) or MT-only (n = 131). Inverse probability of treatment weighting was used to balance baseline characteristics. We systematically evaluated stenosis thresholds from 40
