Automated Topographic Prominence based quantitative assessment of speech timing in Cerebellar Ataxia

Artificial Intelligence in the Diagnosis and Quantitative Phenotyping of Hyperkinetic Movement Disorders: A Systematic Review

Background: Hyperkinetic movement disorders involve excessive, involuntary movements such as ataxia, chorea, dystonia, myoclonus, tics, and tremor. Recent advances in artificial intelligence (AI) allow investigators to integrate multimodal instrumented movement measurements and imaging techniques and to analyze these data together at scale. In this systematic review, we aim to characterize AI's performance in diagnosing and quantitatively phenotyping these disorders. Methods: We searched PubMed and Embase using a semi-automated article-screening pipeline. Results: Fifty-five studies met the inclusion criteria (n = 11,946 subjects). Thirty-five studies used machine learning, sixteen used deep learning, and four used both. Thirty-eight studies reported disease diagnosis, twenty-three reported quantitative phenotyping, and six reported both. Diagnostic accuracy was reported in 36 of 38 and correlation coefficients in 10 of 23 studies. Kinematics (e.g., accelerometers and inertial measurement units) were the most used dataset. Diagnostic accuracy was reported in 36 studies and ranged from 56 to 100% compared to clinical diagnoses to differentiate them from healthy controls. The correlation coefficient was reported in 10 studies and ranged from 0.54 to 0.99 compared to clinical ratings for quantitative phenotyping. Five studies had an overall judgment of "low risk of bias" and three had external validation. Conclusion: There is a need to adopt AI-based research guidelines to minimize reporting heterogeneity and bolster clinical interpretability.

Sensitive Quantification of Cerebellar Speech Abnormalities Using Deep Learning Models

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. This work aims to develop models that can accurately identify and quantify clinical signs of ataxic speech. We use convolutional neural networks to capture the motor speech phenotype of cerebellar ataxia based on time and frequency partial derivatives of log-mel spectrogram representations of speech. We train classification models to distinguish patients with ataxia from healthy controls as well as regression models to estimate disease severity. Classification models were able to accurately distinguish healthy controls from individuals with ataxia, including ataxia participants who clinicians rated as having no detectable clinical deficits in speech. Regression models produced accurate estimates of disease severity, were able to measure subclinical signs of ataxia, and captured disease progression over time. Convolutional networks 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. Learned speech analysis models have the potential to aid early detection of disease signs in ataxias and provide sensitive, low-burden assessment tools in support of clinical trials and neurological care.

Machine Learning-Based Scoring System to Predict the Risk and Severity of Ataxic Speech Using Different Speech Tasks

The assessment of speech in Cerebellar Ataxia (CA) is time-consuming and requires clinical interpretation. In this study, we introduce a fully automated objective algorithm that uses significant acoustic features from time, spectral, cepstral, and non-linear dynamics present in microphone data obtained from different repeated Consonant-Vowel (C-V) syllable paradigms. The algorithm builds machine-learning models to support a 3-tier diagnostic categorisation for distinguishing Ataxic Speech from healthy speech, rating the severity of Ataxic Speech, and nomogram-based supporting scoring charts for Ataxic Speech diagnosis and severity prediction. The selection of features was accomplished using a combination of mass univariate analysis and elastic net regularization for the binary outcome, while for the ordinal outcome, Spearman's rank-order correlation criterion was employed. The algorithm was developed and evaluated using recordings from 126 participants: 65 individuals with CA and 61 controls (i.e., individuals without ataxia or neurotypical). For Ataxic Speech diagnosis, the reduced feature set yielded an area under the curve (AUC) of 0.97 (95% CI 0.90-1), the sensitivity of 97.43%, specificity of 85.29%, and balanced accuracy of 91.2% in the test dataset. The mean AUC for severity estimation was 0.74 for the test set. The high C-indexes of the prediction nomograms for identifying the presence of Ataxic Speech (0.96) and estimating its severity (0.81) in the test set indicates the efficacy of this algorithm. Decision curve analysis demonstrated the value of incorporating acoustic features from two repeated C-V syllable paradigms. The strong classification ability of the specified speech features supports the framework's usefulness for identifying and monitoring Ataxic Speech.

Stable Decoding from a Speech BCI Enables Control for an Individual with ALS without Recalibration for 3 Months

Brain-computer interfaces (BCIs) can be used to control assistive devices by patients with neurological disorders like amyotrophic lateral sclerosis (ALS) that limit speech and movement. For assistive control, it is desirable for BCI systems to be accurate and reliable, preferably with minimal setup time. In this study, a participant with severe dysarthria due to ALS operates computer applications with six intuitive speech commands via a chronic electrocorticographic (ECoG) implant over the ventral sensorimotor cortex. Speech commands are accurately detected and decoded (median accuracy: 90.59%) throughout a 3-month study period without model retraining or recalibration. Use of the BCI does not require exogenous timing cues, enabling the participant to issue self-paced commands at will. These results demonstrate that a chronically implanted ECoG-based speech BCI can reliably control assistive devices over long time periods with only initial model training and calibration, supporting the feasibility of unassisted home use.

Multi-focus autofocusing circular hyperbolic umbilic beams

We propose and demonstrate a type of multi-focus autofocusing beams, circular hyperbolic umbilic beams (CHUBs), based on the double-active variable caustics in catastrophe theory. The mathematical form is more general compared to circular Airy, Pearcey and swallowtail beams. The CHUBs can generate multi-focus at its optical axis, while the on-axis intensity fluctuates up to two orders of magnitude that of the maximum intensity in the initial plane. Using the concept of topographic prominence, we quantify the autofocusing ability. We construct the criteria for selecting the effective foci, and then explore the influence of related parameters. Our findings suggest that the CHUBs could be a suitable tool for multi-particle manipulation, optical tweezers, optical lattices and related applications.

Detection and differentiation of ataxic and hypokinetic dysarthria in cerebellar ataxia and parkinsonian disorders via wave splitting and integrating neural networks

Dysarthria may present during the natural course of many degenerative neurological conditions. Hypokinetic and ataxic dysarthria are common in movement disorders and represent the underlying neuropathology. We developed an artificial intelligence (AI) model to distinguish ataxic dysarthria and hypokinetic dysarthria from normal speech and differentiate ataxic and hypokinetic speech in parkinsonian diseases and cerebellar ataxia. We screened 804 perceptual speech analyses performed in the Samsung Medical Center Neurology Department between January 2017 and December 2020. The data of patients diagnosed with parkinsonian disorders or cerebellar ataxia were included. Two speech tasks (numbering from 1 to 50 and reading nine sentences) were analyzed. We adopted convolutional neural networks and developed a patch-wise wave splitting and integrating AI system for audio classification (PWSI-AI-AC) to differentiate between ataxic and hypokinetic speech. Of the 395 speech recordings for the reading task, 76, 112, and 207 were from normal, ataxic dysarthria, and hypokinetic dysarthria subjects, respectively. Of the 409 recordings of the numbering task, 82, 111, and 216 were from normal, ataxic dysarthria, and hypokinetic dysarthria subjects, respectively. The reading and numbering task recordings were classified with 5-fold cross-validation using PWSI-AI-AC as follows: hypokinetic dysarthria vs. others (area under the curve: 0.92 ± 0.01 and 0.92 ± 0.02), ataxia vs. others (0.93 ± 0.04 and 0.89 ± 0.02), hypokinetic dysarthria vs. ataxia (0.96 ± 0.02 and 0.95 ± 0.01), hypokinetic dysarthria vs. none (0.86 ± 0.03 and 0.87 ± 0.05), and ataxia vs. none (0.87 ± 0.07 and 0.87 ± 0.09), respectively. PWSI-AI-AC showed reliable performance in differentiating ataxic and hypokinetic dysarthria and effectively augmented data to classify the types even with limited training samples. The proposed fully automatic AI system outperforms neurology residents. Our model can provide effective guidelines for screening related diseases and differential diagnosis of neurodegenerative diseases.

Oral and Laryngeal Diadochokinesis Across the Life Span: A Scoping Review of Methods, Reference Data, and Clinical Applications

PURPOSE

The aim of this study was to conduct a scoping review of research on oral and laryngeal diadochokinesis (DDK) in children and adults, either typically developing/developed or with a clinical diagnosis.

METHOD

Searches were conducted with PubMed/MEDLINE, Google Scholar, CINAHL, and legacy sources in retrieved articles. Search terms included the following: DDK, alternating motion rate, maximum repetition rate, sequential motion rate, and syllable repetition rate.

RESULTS

Three hundred sixty articles were retrieved and included in the review. Data source tables for children and adults list the number and ages of study participants, DDK task, and language(s) spoken. Cross-sectional data for typically developing children and typically developed adults are compiled for the monosyllables /pʌ/, /tʌ/, and /kʌ/; the trisyllable /pʌtʌkʌ/; and laryngeal DDK. In addition, DDK results are summarized for 26 disorders or conditions.

DISCUSSION

A growing number of multidisciplinary reports on DDK affirm its role in clinical practice and research across the world. Atypical DDK is not a well-defined singular entity but rather a label for a collection of disturbances associated with diverse etiologies, including motoric, structural, sensory, and cognitive. The clinical value of DDK can be optimized by consideration of task parameters, analysis method, and population of interest.

Multi-domain Data Capture and Cloud Buffered Multimodal Evaluation Platform for Clinical Assessment of Cerebellar Ataxia

Cerebellar Ataxia is a neurological disorder without an approved treatment. Patients will have impaired and uncoordinated motor functionality making them unable to complete their day-to-day activities. Ataxia clinics are established around the world to facilitate research and rehabilitate patients. However, the patients are generally evaluated by human - observation. Therefore, machine learning based data analysis is popular on motion captured via sensors. There are many neurological tests designed to analyse the motor impairments in different domains (such as upper limb, lower limb, gait, balance and speech). Clinicians follow scoring protocols to record the severity of patients for each domain test. This paper delivers a clinical assessment platform combining 12 neurological tests in 5 domains. It captures motion (from BioKin sensors), haptic and audio data (from the tablet or laptop screen). A data analysis system is hosted in a remote server which evaluates data to produce a severity score via different models built for each neurological test. The assessment platform clients and server communicate via a cloud buffer system. The scores input by the clinicians and predicted by the machine learning models are logged in the cloud database. This enables clinicians and doctors to view and compare the history of patient diagnosis. The server system is structured for automated score model upgrades via prompted approval. Thus, the most viable scoring model could be accommodated for each test based on longitudinal studies.

A Sensor-Based Comprehensive Objective Assessment of Motor Symptoms in Cerebellar Ataxia

Human observer-based assessments of Cerebellar Ataxia (CA) are subjective and are often inadequate to track mild motor symptoms. This study examines the potential use of a comprehensive sensor-based approach for objective evaluation of CA in five domains (speech, upper limb, lower limb, gait and balance) through the instrumented versions of nine bedside neurological tests. A total of twenty-three participants diagnosed with CA to varying degrees and eleven healthy controls were recruited. Data was collected using wearable inertial sensors and Kinect camera. In our study, an optimal feature subset based on feature importance in the Random Forest classifier model demonstrated an impressive performance accuracy of 97% (F1 score = 95.2%) for CA-control discrimination. Our experimental findings also indicate that the Romberg test contributed most, followed by the peripheral tests, while the Gait test contributed least to the classification. Sensor-based approaches, therefore, have the potential to complement existing clinical assessment techniques, offering advantages in terms of consistency, objectivity and informed clinical decision-making.

Objective Assessment of Cerebellar Ataxia: A Comprehensive and Refined Approach

Parametric analysis of Cerebellar Ataxia (CA) could be of immense value compared to its subjective clinical assessments. This study focuses on a comprehensive scheme for objective assessment of CA through the instrumented versions of 9 commonly used neurological tests in 5 domains- speech, upper limb, lower limb, gait and balance. Twenty-three individuals diagnosed with CA to varying degrees and eleven age-matched healthy controls were recruited. Wearable inertial sensors and Kinect camera were utilised for data acquisition. Binary and multilabel discrimination power and intra-domain relationships of the features extracted from the sensor measures and the clinical scores were compared using Graph Theory, Centrality Measures, Random Forest binary and multilabel classification approaches. An optimal subset of 13 most important Principal Component (PC) features were selected for CA-control classification. This classification model resulted in an impressive performance accuracy of 97% (F1 score = 95.2%) with Holmesian dimensions distributed as 47.7% Stability, 6.3% Timing, 38.75% Accuracy and 7.24% Rhythmicity. Another optimal subset of 11 PC features demonstrated an F1 score of 84.2% in mapping the total 27 PC across 5 domains during CA multilabel discrimination. In both cases, the balance (Romberg) test contributed the most (31.1% and 42% respectively), followed by the peripheral tests whereas gait (Walking) test contributed the least. These findings paved the way for a better understanding of the feasibility of an instrumented system to assist informed clinical decision-making.