Rabia Aziza, Elisa Ferrer, Fereshteh Poursaeed, Vivian Maas, Jennifer Faber, Arian Taheri Amin, Katharina Hill, Matthis Synofzik, Lisa H Graf, Dagmar Timmann, Andreas Thieme, Paola Giunti, Hector Garcia-Moreno, Magda M Santana, Jeannette Hübener-Schmid, Elin H Davies, Thomas Klockgether, Marcus Grobe-Einsler
{"title":"Remote Video Assessment of Ataxia via SARA<sup>home</sup>: Correlation of Pose-Derived Endpoints with Clinician Severity Ratings.","authors":"Rabia Aziza, Elisa Ferrer, Fereshteh Poursaeed, Vivian Maas, Jennifer Faber, Arian Taheri Amin, Katharina Hill, Matthis Synofzik, Lisa H Graf, Dagmar Timmann, Andreas Thieme, Paola Giunti, Hector Garcia-Moreno, Magda M Santana, Jeannette Hübener-Schmid, Elin H Davies, Thomas Klockgether, Marcus Grobe-Einsler","doi":"10.1002/mdc3.70854","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Remote assessment of ataxia is increasingly important for patient-centered care and clinical research. SARA<sup>home</sup>, a validated video-based adaptation of the Scale for the Assessment and Rating of Ataxia (SARA), enables self-administration of key motor tasks at home.</p><p><strong>Objective: </strong>The aim was to evaluate the correlation of pose-derived gait and stance endpoints from SARA<sup>home</sup> videos with clinician-rated severity.</p><p><strong>Methods: </strong>In a multisite observational study, participants recorded SARA<sup>home</sup> tasks on consumer mobile devices via the Atom5<sup>TM</sup> app. Clinicians rated videos using standardized criteria, blinded to automated outputs. Kinematic measures were extracted via pose estimation and aggregated to video-level features. Videos were aggregated per participant before correlation using Spearman's ρ and Kendall's τ, with 95% cluster-bootstrap confidence intervals.</p><p><strong>Results: </strong>We analyzed 5418 gait and stance videos from 58 participants across 4 sites (gait n = 2205, stance n = 3213). Score distribution was skewed toward lower severity. For gait, clearance variability (ρ = 0.52 [0.37-0.64]) and median-normalized base of support (ρ = 0.51 [0.35-0.66]) correlated most strongly with item ratings, followed by shoulder sway root mean square (ρ = 0.43 [0.24-0.60]). Adjusted foot clearance (worse limb) correlated negatively (ρ = -0.35 [-0.52 to -0.15]). For stance, anteroposterior sway (ρ = 0.51 [0.36-0.65]), leg alignment variability (ρ = 0.51 [0.36-0.65]), and composite sway (ρ = 0.48 [0.32-0.62]) were most associated with severity. Base of support widened monotonically with severity and was the most reliable gait feature (intraclass correlation coefficient [ICC] = 0.88).</p><p><strong>Conclusions: </strong>Pose-derived digital endpoints from home-captured SARA<sup>home</sup> videos show robust, clinically interpretable correlation with severity, supporting scalable remote phenotyping. Findings motivate longitudinal validation toward clinical and regulatory utility.</p>","PeriodicalId":19029,"journal":{"name":"Movement Disorders Clinical Practice","volume":" ","pages":""},"PeriodicalIF":3.4000,"publicationDate":"2026-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13675665/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Movement Disorders Clinical Practice","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1002/mdc3.70854","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"CLINICAL NEUROLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Background: Remote assessment of ataxia is increasingly important for patient-centered care and clinical research. SARAhome, a validated video-based adaptation of the Scale for the Assessment and Rating of Ataxia (SARA), enables self-administration of key motor tasks at home.
Objective: The aim was to evaluate the correlation of pose-derived gait and stance endpoints from SARAhome videos with clinician-rated severity.
Methods: In a multisite observational study, participants recorded SARAhome tasks on consumer mobile devices via the Atom5TM app. Clinicians rated videos using standardized criteria, blinded to automated outputs. Kinematic measures were extracted via pose estimation and aggregated to video-level features. Videos were aggregated per participant before correlation using Spearman's ρ and Kendall's τ, with 95% cluster-bootstrap confidence intervals.
Results: We analyzed 5418 gait and stance videos from 58 participants across 4 sites (gait n = 2205, stance n = 3213). Score distribution was skewed toward lower severity. For gait, clearance variability (ρ = 0.52 [0.37-0.64]) and median-normalized base of support (ρ = 0.51 [0.35-0.66]) correlated most strongly with item ratings, followed by shoulder sway root mean square (ρ = 0.43 [0.24-0.60]). Adjusted foot clearance (worse limb) correlated negatively (ρ = -0.35 [-0.52 to -0.15]). For stance, anteroposterior sway (ρ = 0.51 [0.36-0.65]), leg alignment variability (ρ = 0.51 [0.36-0.65]), and composite sway (ρ = 0.48 [0.32-0.62]) were most associated with severity. Base of support widened monotonically with severity and was the most reliable gait feature (intraclass correlation coefficient [ICC] = 0.88).
Conclusions: Pose-derived digital endpoints from home-captured SARAhome videos show robust, clinically interpretable correlation with severity, supporting scalable remote phenotyping. Findings motivate longitudinal validation toward clinical and regulatory utility.
期刊介绍:
Movement Disorders Clinical Practice- is an online-only journal committed to publishing high quality peer reviewed articles related to clinical aspects of movement disorders which broadly include phenomenology (interesting case/case series/rarities), investigative (for e.g- genetics, imaging), translational (phenotype-genotype or other) and treatment aspects (clinical guidelines, diagnostic and treatment algorithms)