Assessing Cerebellar Disorders With Wearable Inertial Sensor Data Using Time-Frequency and Autoregressive Hidden Markov Model Approaches

Knudson, Karin; Gupta, Anoopum S.

doi:10.48550/arxiv.2108.08975

Cited by 1 publication

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The severity estimation task was modeled as described in Methods (II-D). For this task, the combination of ResNet18 total , the agreement between predicted and clinical scores was MAE = 3.5 and R 2 = 0.61, which is comparable with other approaches using wearable inertial measurement unit data [6].…”

Section: B Severity Estimationsupporting

confidence: 75%

“…A variety of other techniques and technologies have been used and proposed in the past, including inertial measurement units (IMUs) that record accelerometer and gyroscope data to quantify gait or limb movement [6], [7], computer mouse tasks that assess arm motor control [12], and eye tracking devices to quantify eye movement abnormalities [13]. Our approach complements prior work, by using convolutional neural networks with mel spectrogram time and frequency gradient inputs to probe the effects of ataxia on vocal motor impairments in an unbiased fashion.…”

Section: Discussionmentioning

confidence: 99%

“…The field of quantitative phenotyping attempts to fill this gap by using sensors and devices to quantify aspects of motor and cognitive behavior that are important in cerebellar ataxias [5]. There has been increasing interest in the use of inertial measurement units (IMUs) that record accelerometer and gyroscope data to quantify gait or limb movement [6]- [11] features, computer mouse tasks that assess arm motor control [12], and eye tracking devices to quantify eye movement abnormalities [13], [14]. Such data can be used to generate granular descriptions of disease phenotypes and severity, and can be extended to the home setting for accessible and frequent assessments.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Sensitive quantification of cerebellar speech abnormalities using deep learning models

Vattis¹,

Luddy²,

Ouillon³

et al. 2023

Preprint

View full text Add to dashboard Cite

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

show abstract

Section: B Severity Estimationsupporting

confidence: 75%