What are the Key Challenges Faced by Spinocerebellar Degeneration and Multiple System Atrophy Patients in Daily Life?: Insights from a Comprehensive Questionnaire Survey in Japan

The Cerebellum, Год журнала: 2025, Номер 24(3)

Опубликована: Апрель 1, 2025

Язык: Английский

---

Mobile Spatiotemporal Gait Segmentation Using an Ear-Worn Motion Sensor and Deep Learning

Опубликована: Авг. 22, 2024

Mobile health technologies enable continuous, quantitative assessment of mobility and gait in real-world environments, facilitating early diagnosis disorders, disease progression monitoring, prediction adverse events like falls. Traditionally, mobile predominantly relied on body-fixed sensors positioned at the feet or lower trunk. Here, we investigate potential an algorithm utilizing ear-worn motion sensor for spatiotemporal segmentation patterns. We collected 3D acceleration profiles from during varied walking speeds 53 healthy adults. Temporal convolutional networks were trained to detect stepping sequences predict spatial relations between steps. The resulting algorithm, mEar, accurately detects initial final ground contacts (F1 score 99% 91%, respectively). It enables determination temporal cycle characteristics (among others stride time length) with good excellent validity a precision sufficient monitor clinically relevant changes speed, stride-to-stride variability, side asymmetry. This study highlights ear as viable site monitoring proposes its integration in-ear vital sign monitoring. Such offers practical approach comprehensive telemedical applications, by integrating multiple single anatomical location.

Язык: Английский

---

The use of digital tools in rare neurological diseases towards a new care model: a narrative review

Neurological Sciences, Год журнала: 2024, Номер unknown

Опубликована: Июнь 10, 2024

Язык: Английский

---

Mobile Spatiotemporal Gait Segmentation Using an Ear-Worn Motion Sensor and Deep Learning

Sensors, Год журнала: 2024, Номер 24(19), С. 6442 - 6442

Опубликована: Окт. 4, 2024

Mobile health technologies enable continuous, quantitative assessment of mobility and gait in real-world environments, facilitating early diagnoses disorders, disease progression monitoring, prediction adverse events like falls. Traditionally, mobile predominantly relied on body-fixed sensors positioned at the feet or lower trunk. Here, we investigate potential an algorithm utilizing ear-worn motion sensor for spatiotemporal segmentation patterns. We collected 3D acceleration profiles from during varied walking speeds 53 healthy adults. Temporal convolutional networks were trained to detect stepping sequences predict spatial relations between steps. The resulting algorithm, mEar, accurately detects initial final ground contacts (F1 score 99% 91%, respectively). It enables determination temporal cycle characteristics (among others, stride time length) with good excellent validity a precision sufficient monitor clinically relevant changes speed, stride-to-stride variability, side asymmetry. This study highlights ear as viable site monitoring proposes its integration in-ear vital-sign monitoring. Such offers practical approach comprehensive telemedical applications, by integrating multiple single anatomical location.

Язык: Английский

---

Digital gait measures capture 1-year progression in early-stage spinocerebellar ataxia type 2

medRxiv (Cold Spring Harbor Laboratory), Год журнала: 2023, Номер unknown

Опубликована: Окт. 9, 2023

Abstract BACKGROUND With disease-modifying drugs in reach for cerebellar ataxias, fine-grained digital health measures are highly warranted to complement clinical and patient-reported outcome upcoming treatment trials monitoring. These need demonstrate sensitivity capture change, particular the early stages of disease. OBJECTIVE To unravel gait sensitive longitudinal change - particularly trial-relevant- stage spinocerebellar ataxia type 2 (SCA2). METHODS Multi-center study with combined cross-sectional 1-year interval analysis early-stage SCA2 participants (n=23, including 9 pre-ataxic expansion carriers; median ATXN2 CAG repeat 38±2; SARA [Scale Assessment Rating Ataxia] score 4.83±4.31). Gait was assessed using three wearable motion sensors during a 2-minute walk, analyses focusing on spatiotemporal variability shown severity, e.g. lateral step deviation. RESULTS We found significant changes between baseline follow-up large effect sizes (lateral deviation p=0.0001, size r prb =0.78), whereas showed no (p=0.67). Sample estimation indicates required cohort n=43 detect 50% reduction natural progression. Test-retest reliability Minimal Detectable Change confirm accuracy detecting identified change. CONCLUSIONS by can progression within just one year – contrast outcome. Lateral thus represents promising measure multi-centre interventional trials, ataxia.

Язык: Английский

---

Visual perceptive deep learning for smartphone video-based tremor analysis: VIPER-Tremor

Research Square (Research Square), Год журнала: 2023, Номер unknown

Опубликована: Дек. 2, 2023

Abstract Background: Tremor is one of the most common neurological symptoms. Its clinical and neurobiological complexity necessitates novel approaches for deep granular phenotyping. Instrumented neurophysiological analyses have proven useful management, but are highly resource-intensive lack broad accessibility. Simplified bedside scores, on other hand, granularity to capture subtle relevant tremor features. Addressing this gap, we develop a learning framework quantitative assessment limb utilizing only standard videos. Methods: We engineer visual perceptive analysis tool based Mediapipe, convolutional neural network architecture marker-less hand tracking: VIPER-Tremor. validate it against gold methods, including marker-based motion capture, wrist-worn accelerometery, scoring across two independent cohorts encompassing total 66 patients diagnosed with essential recorded in different therapeutic states brain stimulation. Results: Computer vision-derived metrics exhibit high convergent validity scores (Spearman’s rho= 0.55 – 0.86, p≤ .01) as well an accuracy up 2.60mm ≤0.21Hz amplitude frequency measurements, matching gold-standard equipment. VIPER-Tremor capable extracting advanced features differential diagnosis enables outcome prediction, dimension which conventional were unable provide. Conclusion: accurate, unbiased accessible solution smartphone video-based yields comparable results recordings. presents significant advancement analysis, combining accessibility, promises be pivotal emerging field precision neurology, enhancing diagnostic approaches.

Язык: Английский

---

Multifeature quantitative motor assessment of upper limb ataxia including drawing and reaching

Annals of Clinical and Translational Neurology, Год журнала: 2024, Номер 11(5), С. 1097 - 1109

Опубликована: Апрель 8, 2024

Abstract Objective Voluntary upper limb movements are an ecologically important yet insufficiently explored digital‐motor outcome domain for trials in degenerative ataxia. We extended and validated the trial‐ready quantitative motor assessment battery “Q‐Motor” with clinician‐reported, patient‐focused, performance outcomes of Methods Exploratory single‐center cross‐sectional 94 subjects (46 cross‐genotype ataxia patients; 48 matched controls), comprising five tasks measured by force transducer and/or position field: Finger Tapping, diadochokinesia, grip‐lift, and—as novel implementations—Spiral Drawing, Target Reaching. Digital‐motor measures were selected if they discriminated from controls (AUC >0.7) correlated—with at least one strong correlation (rho ≥0.6)—to Scale Assessment Rating Ataxia (SARA), activities daily living (FARS‐ADL), Nine‐Hole Peg Test (9HPT). Results Six movement features 69 met selection criteria, including speed variability all tasks, stability efficiency The drawing/reaching best captured impairment dexterity (|rho 9HPT | ≤0.81) FARS‐ADL items ADLul ≤0.64), particularly kinematic analysis smoothness (SPARC). hit rate , a composite endpoint precision almost perfectly (AUC: 0.97). Selected between mild, moderate, severe (SARA composite: 0–2/>2–4/>4–6) correlated severity trial‐relevant mild stage ≤10, n = 20). Interpretation Q‐Motor captures multiple impaired Validation key clinical domains provides basis evaluation longitudinal studies trial settings.

Язык: Английский

---

Spatiotemporal gait analysis of patients with spinocerebellar ataxia types 3 and 10 using Inertial Measurement Units: a comparative study

Research Square (Research Square), Год журнала: 2024, Номер unknown

Опубликована: Апрель 25, 2024

Given the high morbidity related to progression of gait deficits in spinocerebellar ataxias (SCA), there is a growing interest identifying biomarkers that can guide early diagnosis and rehabilitation. Spatiotemporal parameter (STP) analysis using inertial measurement units (IMUs) has been increasingly studied this context. This study evaluated STP profiles SCA types 3 10, compared them controls, correlated with clinical scales. IMU portable sensors were used measure STPs under four conditions: self-selected pace (SSP), fast (FP), checking-boxes (FPCB), serial seven subtractions (FPS7). Compared healthy subjects, both groups had higher values for step time, variability, swing lower speed, cadence, length. We also found reduction speed gain capacity controls an increase dual-task cost SCA10 group. However, no significant differences between groups. Swing mean length disease severity, risk falling functionality In SCA3 group, fear was cadence. results Montreal cognitive assessment test These show individuals present highly variable, short-stepped, slow pattern their quality worsened pace, mainly dual task involvement.

Язык: Английский

---

Spatiotemporal Gait Analysis of Patients with Spinocerebellar Ataxia Types 3 and 10 Using Inertial Measurement Units: A Comparative Study

The Cerebellum, Год журнала: 2024, Номер unknown

Опубликована: Июнь 13, 2024

Язык: Английский

---

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

medRxiv (Cold Spring Harbor Laboratory), Год журнала: 2024, Номер unknown

Опубликована: Окт. 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 (

Язык: Английский

---