Accuracy and Reliability of At-Home Quantification of Motor Impairments Using a Computer-Based Pointing Task with Children with Ataxia-Telangiectasia

ACM Transactions on Accessible Computing, Journal Year: 2023, Volume and Issue: 16(1), P. 1 - 25

Published: Jan. 25, 2023

Methods for obtaining accurate quantitative assessments of motor impairments are essential in accessibility research, design adaptive ability-based assistive technologies, as well clinical care and medical research. Currently, such typically performed controlled laboratory or settings under professional supervision. Emerging approaches collecting data unsupervised have been shown to produce valid when aggregated over large populations, but it is not yet established whether measures research significance can be collected accurately reliably individuals. We conducted a study with 13 children ataxia-telangiectasia 9 healthy analyze the validity, test-retest reliability, acceptability at-home use recent active digital phenotyping system, called Hevelius. Hevelius produces 32 derived from movement trajectories mouse cursor then generates estimate impairment dominant arm using component Brief Ataxia Rating Scale (BARS). The severity score estimates generated by single sessions deviated clinician-assigned BARS scores more than researcher However, taking median few 2 consecutive produced that were better supervised sessions. Further, aggregating resulted good reliability (ICC = 0.81 A-T participants). This work demonstrated feasibility performing reliable individual through tasks at home without supervision researchers. Further needed, however, assess how broadly these results generalize.

Language: Английский

---

Reliability and Discriminative Validity of Wearable Sensors for the Quantification of Upper Limb Movement Disorders in Individuals with Dyskinetic Cerebral Palsy

Sensors, Journal Year: 2023, Volume and Issue: 23(3), P. 1574 - 1574

Published: Feb. 1, 2023

Background-Movement patterns in dyskinetic cerebral palsy (DCP) are characterized by abnormal postures and involuntary movements. Current evaluation tools DCP subjective time-consuming. Sensors could yield objective information on pathological DCP, but their reliability has not yet been evaluated. The objectives of this study were to evaluate (i) (ii) discriminative ability sensor parameters. Methods-Inertial measurement units placed the arm, forearm, hand individuals with without while performing reach-forward, reach-and-grasp-vertical, reach-sideways tasks. Intra-class correlation coefficients (ICC) calculated for reliability, Mann-Whitney U-tests between-group differences. Results-Twenty-two extremities (mean age 16.7 y) twenty 17.2 ICC values all parameters except jerk sample entropy ranged from 0.50 0.98 during reach forwards/sideways 0.40 0.95 reach-and-grasp vertical. Jerk maximal acceleration/angular velocity significantly higher group comparison peers. Conclusions-This was first assess reporting high between- within-session majority These findings suggest that movements can be reliably captured using a selection

Language: Английский

---

At-home wearables and machine learning capture motor impairment and progression in adult ataxias

medRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 29, 2024

A significant barrier to developing disease-modifying therapies for spinocerebellar ataxias (SCAs) and multiple system atrophy of the cerebellar type (MSA-C) is scarcity tools sensitively measure disease progression in clinical trials. Wearable sensors worn continuously during natural behavior at home have potential produce ecologically valid precise measures motor function by leveraging frequent numerous high-resolution samples behavior. Here we test whether movement-building block characteristics (i.e., submovements), obtained from wrist ankle home, can capture SCAs MSA-C, as recently shown amyotrophic lateral sclerosis (ALS) ataxia telangiectasia (A-T). Remotely collected cross-sectional (

Language: Английский

---

The effect of different interfaces during virtual game practice on motor performance of individuals with genetic ataxia: A cross-sectional study

PLoS ONE, Journal Year: 2024, Volume and Issue: 19(11), P. e0312705 - e0312705

Published: Nov. 1, 2024

Reaching and coordination tasks are widely used in traditional physical rehabilitation programs for individuals with Ataxia. Virtual reality interventions could optimize the motor performance of these individuals; however, type virtual interface may influence during practice. We aimed to estimate extent effect different interfaces (webcam touchscreen) on various types genetic ataxia, compared a control group, computer game tasks.

Language: Английский

---

Wearable systems in movement disorders

International review of movement disorders, Journal Year: 2023, Volume and Issue: unknown, P. 93 - 113

Published: Jan. 1, 2023

Language: Английский

---

Consumer-grade wearables and machine learning sensitively capture disease progression in amyotrophic lateral sclerosis

medRxiv (Cold Spring Harbor Laboratory), Journal Year: 2023, Volume and Issue: unknown

Published: March 30, 2023

Abstract ALS causes degeneration of motor neurons, resulting in progressive muscle weakness and impairment fine motor, gross bulbar, respiratory function. Promising drug development efforts have accelerated ALS, but are constrained by a lack objective, sensitive, accessible outcome measures. Here we investigate the use consumer-grade wearable sensors, worn on four limbs at home during natural behavior, to quantify function disease progression 376 individuals with over several year period. We utilized an analysis approach that automatically detects characterizes submovements from passively collected accelerometer data produces machine-learned severity score for each limb is independent clinical ratings. The produced interpretable highly reliable scores progressed faster than gold standard Functional Rating Scale-Revised (−0.70 SD/year versus -0.48 SD/year), supporting its as ecologically valid, scalable measure trials care.

Language: Английский

---

Sensitive quantification of cerebellar speech abnormalities using deep learning models

medRxiv (Cold Spring Harbor Laboratory), Journal Year: 2023, Volume and Issue: unknown

Published: April 4, 2023

Objective, sensitive, and meaningful disease assessments are critical to support clinical trials care. Speech changes one of the earliest most evident manifestations cerebellar ataxias. The purpose this work is develop models that can accurately identify quantify these abnormalities.We use deep learning such as ResNet 18 , take time frequency partial derivatives log-mel spectrogram representations speech input, learn capture motor phenotype ataxia. We train classification separate patients with ataxia from healthy controls well regression estimate severity.Our model was able distinguish individuals ataxia, including participants no detectable deficits in speech. Furthermore produced accurate estimates severity, were measure subclinical signs captured progression over ataxia.Deep models, trained on signal, detect sub-clinical ataxias sensitively change time.Such have potential assist early detection provide sensitive low-burden assessment tools neurological

Language: Английский

---

Estimation of ataxia severity in children with ataxia-telangiectasia using ankle-worn sensors

Journal of Neurology, Journal Year: 2023, Volume and Issue: 270(10), P. 5097 - 5101

Published: June 27, 2023

Language: Английский

---

Encouraging Arm Use in Stroke Survivors: The Impact of Smart Reminders during a Home-Based Intervention

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 18, 2024

Background Upper limb impairment post-stroke often leads to a predominant use of the unaffected arm and consequent learned disuse affected side, hindering upper outcome. Wearable sensors such as accelerometers, combined with smart reminders (i.e., based on amount activity), offer potential approach promote increased improve during daily life. This study aimed evaluate efficacy wrist vibratory six-week home-based intervention in chronic stroke survivors. Methods We evaluated impact primary outcome, Motor Activity Log-14 Item Version scores Amount Use (MAL-14 AOU), secondary outcomes MAL-14 Quality Movement (QOM) sensor-derived activity metrics from arm. A randomized controlled trial design was used for study: group received personalized individualized goals, while control did not receive any feedback. Mixed linear models assessed influence group, week period, initial level metrics. Results Forty-two participants were enrolled study. Overall, exhibited modest but clinically relevant increases AOU (+ 0.2 points) QOM after no statistically significant differences between group. Feasibility challenges noted, adherence wearing trackers sensor data quality. However, sufficiently available (n = 23), extracted significantly higher (p < 0.05). The strongly influenced both 0.01). Conclusions investigated effectiveness incorporating increase among survivors While results regarding at home are promising, patient-reported remained below meaningful thresholds showed differences. Further, it is essential acknowledge feasibility issues missing data. Trial registration: NCT03294187

Language: Английский

---

The use of digital devices to monitor physical behaviour in motor neuron disease: a systematic review (Preprint)

Published: Nov. 6, 2024

Motor neuron disease (MND) is a progressive and incurable neurodegenerative disease. There an urgent need for sensitive measures of progression that can be used to robustly evaluate new treatments. Measures physical function, derived from digital devices, are beginning assess progression. Given MND relatively rare, there value in establishing consensus approach standardizing use such devices. This systematic review explored how devices being quantify free-living behaviour people living with (plwMND). We evaluated the feasibility using assessed implications monitoring future design clinical trials. Systematic searches four databases were performed October 2023 June 2024. Peer-reviewed articles (including pre-prints) written English language plwMND included. Twelve met inclusion criteria data extraction. Studies traditional endpoints focusing on duration, intensity, frequency activity or non-traditional features individual’s movement patterns. Greater frequencies improved endpoint sensitivity was shown provide smaller sample size requirements shorter durations hypothetical PlwMND found acceptable reported low burden. The perspectives other end-users practice not explored. Remote its infancy but has exciting potential function MND. It essential develop statement within community, working towards agreed standardised methods collection, analysis reporting.

Language: Английский

---