Balance Deficits due to Cerebellar Ataxia: A Machine Learning and Cloud-Based Approach

Quantitative Gait and Balance Outcomes for Ataxia Trials: Consensus Recommendations by the Ataxia Global Initiative Working Group on Digital-Motor Biomarkers

With disease-modifying drugs on the horizon for degenerative ataxias, ecologically valid, finely granulated, digital health measures are highly warranted to augment clinical and patient-reported outcome measures. Gait and balance disturbances most often present as the first signs of degenerative cerebellar ataxia and are the most reported disabling features in disease progression. Thus, digital gait and balance measures constitute promising and relevant performance outcomes for clinical trials.This narrative review with embedded consensus will describe evidence for the sensitivity of digital gait and balance measures for evaluating ataxia severity and progression, propose a consensus protocol for establishing gait and balance metrics in natural history studies and clinical trials, and discuss relevant issues for their use as performance outcomes.

Machine learning to detect, stage and classify diseases and their symptoms based on inertial sensor data: a mapping review

This article presents a systematic review aimed at mapping the literature published in the last decade on the use of machine learning (ML) for clinical decision-making through wearable inertial sensors. The review aims to analyze the trends, perspectives, strengths, and limitations of current literature in integrating ML and inertial measurements for clinical applications. The review process involved defining four research questions and applying four relevance assessment indicators to filter the search results, providing insights into the pathologies studied, technologies and setups used, data processing schemes, ML techniques applied, and their clinical impact. When combined with ML techniques, inertial measurement units (IMUs) have primarily been utilized to detect and classify diseases and their associated motor symptoms. They have also been used to monitor changes in movement patterns associated with the presence, severity, and progression of pathology across a diverse range of clinical conditions. ML models trained with IMU data have shown potential in improving patient care by objectively classifying and predicting motor symptoms, often with a minimally encumbering setup. The findings contribute to understanding the current state of ML integration with wearable inertial sensors in clinical practice and identify future research directions. Despite the widespread adoption of these technologies and techniques in clinical applications, there is still a need to translate them into routine clinical practice. This underscores the importance of fostering a closer collaboration between technological experts and professionals in the medical field.

Modified Recurrence Quantification Analysis for Objective Assessment of Cerebellar Ataxia

Cerebellar Ataxia (CA) is a neurological condition that affects coordination, balance and speech. Assessing its severity is important for developing effective treatment and rehabilitation plans. Traditional assessment methods involve a clinician instructing a person with ataxia to perform tests and assigning a severity score based on their performance. However, this approach is subjective as it relies on the clinician's experience, and can vary between clinicians. To address this subjectivity, some researchers have developed automated assessment methods using signal processing and data-driven approaches, such as supervised machine learning. These methods still rely on subjective ground truth and can perform poorly in real-world scenarios. This research proposed an alternative approach that uses signal processing to modify recurrence plots and compare the severity of ataxia in a person with CA to a control cohort. The highest correlation score obtained was 0.782 on the back sensor with the feet-apart and eyes-open test. The contributions of the research include modifying the recurrence plot as a measurement tool for assessing CA severity, proposing a new approach to assess severity by comparing kinematic data between people with CA and a control reference group, and identifying the best subtest and sensor position for practical use in CA assessments.

Robust and language-independent acoustic features in Parkinson's disease

Introduction

The analysis of vocal samples from patients with Parkinson's disease (PDP) can be relevant in supporting early diagnosis and disease monitoring. Intriguingly, speech analysis embeds several complexities influenced by speaker characteristics (e.g., gender and language) and recording conditions (e.g., professional microphones or smartphones, supervised, or non-supervised data collection). Moreover, the set of vocal tasks performed, such as sustained phonation, reading text, or monologue, strongly affects the speech dimension investigated, the feature extracted, and, as a consequence, the performance of the overall algorithm.

Methods

We employed six datasets, including a cohort of 176 Healthy Control (HC) participants and 178 PDP from different nationalities (i.e., Italian, Spanish, Czech), recorded in variable scenarios through various devices (i.e., professional microphones and smartphones), and performing several speech exercises (i.e., vowel phonation, sentence repetition). Aiming to identify the effectiveness of different vocal tasks and the trustworthiness of features independent of external co-factors such as language, gender, and data collection modality, we performed several intra- and inter-corpora statistical analyses. In addition, we compared the performance of different feature selection and classification models to evaluate the most robust and performing pipeline.

Results

According to our results, the combined use of sustained phonation and sentence repetition should be preferred over a single exercise. As for the set of features, the Mel Frequency Cepstral Coefficients demonstrated to be among the most effective parameters in discriminating between HC and PDP, also in the presence of heterogeneous languages and acquisition techniques.

Conclusion

Even though preliminary, the results of this work can be exploited to define a speech protocol that can effectively capture vocal alterations while minimizing the effort required to the patient. Moreover, the statistical analysis identified a set of features minimally dependent on gender, language, and recording modalities. This discloses the feasibility of extensive cross-corpora tests to develop robust and reliable tools for disease monitoring and staging and PDP follow-up.

Automatic ML-based vestibular gait classification: examining the effects of IMU placement and gait task selection

BACKGROUND

Vestibular deficits can impair an individual's ability to maintain postural and/or gaze stability. Characterizing gait abnormalities among individuals affected by vestibular deficits could help identify patients at high risk of falling and inform rehabilitation programs. Commonly used gait assessment tools rely on simple measures such as timing and visual observations of path deviations by clinicians. These simple measures may not capture subtle changes in gait kinematics. Therefore, we investigated the use of wearable inertial measurement units (IMUs) and machine learning (ML) approaches to automatically discriminate between gait patterns of individuals with vestibular deficits and age-matched controls. The goal of this study was to examine the effects of IMU placement and gait task selection on the performance of automatic vestibular gait classifiers.

METHODS

Thirty study participants (15 with vestibular deficits and 15 age-matched controls) participated in a single-session gait study during which they performed seven gait tasks while donning a full-body set of IMUs. Classification performance was reported in terms of area under the receiver operating characteristic curve (AUROC) scores for Random Forest models trained on data from each IMU placement for each gait task.

RESULTS

Several models were able to classify vestibular gait better than random (AUROC > 0.5), but their performance varied according to IMU placement and gait task selection. Results indicated that a single IMU placed on the left arm when walking with eyes closed resulted in the highest AUROC score for a single IMU (AUROC = 0.88 [0.84, 0.89]). Feature permutation results indicated that participants with vestibular deficits reduced their arm swing compared to age-matched controls while they walked with eyes closed.

CONCLUSIONS

These findings highlighted differences in upper extremity kinematics during walking with eyes closed that were characteristic of vestibular deficits and showed evidence of the discriminative ability of IMU-based automated screening for vestibular deficits. Further research should explore the mechanisms driving arm swing differences in the vestibular population.

Prediction of the disease course in Friedreich ataxia

We explored whether disease severity of Friedreich ataxia can be predicted using data from clinical examinations. From the database of the European Friedreich Ataxia Consortium for Translational Studies (EFACTS) data from up to five examinations of 602 patients with genetically confirmed FRDA was included. Clinical instruments and important symptoms of FRDA were identified as targets for prediction, while variables such as genetics, age of disease onset and first symptom of the disease were used as predictors. We used modelling techniques including generalised linear models, support-vector-machines and decision trees. The scale for rating and assessment of ataxia (SARA) and the activities of daily living (ADL) could be predicted with predictive errors quantified by root-mean-squared-errors (RMSE) of 6.49 and 5.83, respectively. Also, we were able to achieve reasonable performance for loss of ambulation (ROC-AUC score of 0.83). However, predictions for the SCA functional assessment (SCAFI) and presence of cardiological symptoms were difficult. In conclusion, we demonstrate that some clinical features of FRDA can be predicted with reasonable error; being a first step towards future clinical applications of predictive modelling. In contrast, targets where predictions were difficult raise the question whether there are yet unknown variables driving the clinical phenotype of FRDA.

Blockchained Federated Learning for Privacy and Security Preservation: Practical Example of Diagnosing Cerebellar Ataxia

Cerebellar ataxia (CA) refers to the incoordination of movements of the eyes, speech, trunk, and limbs caused by cerebellar dysfunction. Conventional machine learning (ML) utilizes centralised databases to train a model of diagnosing CA. Despite the high accuracy, these approaches raise privacy concern as participants' data revealed in the data centre. Federated learning is an effective distributed solution to exchange only the ML model weight rather than the raw data. However, FL is also vulnerable to network attacks from malicious devices. In this study, we depict the concept of blockchained FL with individual's validators. We simulate the proposed approach with real-world dataset collected from kinematic sensors of CA individuals with four geographically separated clinics. Experimental results show the blockchained FL maintains competitive accuracy of 89.30%, while preserving both privacy and security.

IMU-Based Monitoring for Assistive Diagnosis and Management of IoHT: A Review

With the rapid development of Internet of Things (IoT) technologies, traditional disease diagnoses carried out in medical institutions can now be performed remotely at home or even ambient environments, yielding the concept of the Internet of Health Things (IoHT). Among the diverse IoHT applications, inertial measurement unit (IMU)-based systems play a significant role in the detection of diseases in many fields, such as neurological, musculoskeletal, and mental. However, traditional numerical interpretation methods have proven to be challenging to provide satisfying detection accuracies owing to the low quality of raw data, especially under strong electromagnetic interference (EMI). To address this issue, in recent years, machine learning (ML)-based techniques have been proposed to smartly map IMU-captured data on disease detection and progress. After a decade of development, the combination of IMUs and ML algorithms for assistive disease diagnosis has become a hot topic, with an increasing number of studies reported yearly. A systematic search was conducted in four databases covering the aforementioned topic for articles published in the past six years. Eighty-one articles were included and discussed concerning two aspects: different ML techniques and application scenarios. This review yielded the conclusion that, with the help of ML technology, IMUs can serve as a crucial element in disease diagnosis, severity assessment, characteristic estimation, and monitoring during the rehabilitation process. Furthermore, it summarizes the state-of-the-art, analyzes challenges, and provides foreseeable future trends for developing IMU-ML systems for IoHT.

Federated Deep Learning for the Diagnosis of Cerebellar Ataxia: Privacy Preservation and Auto-crafted Feature Extractor

Cerebellar ataxia (CA) is concerned with the incoordination of movement caused by cerebellar dysfunction. Movements of the eyes, speech, trunk, and limbs are affected. Conventional machine learning approaches utilizing centralised databases have been used to objectively diagnose and quantify the severity of CA. Although these approaches achieved high accuracy, large scale deployment will require large clinics and raises privacy concerns. In this study, we propose an image transformation-based approach to leverage the advantages of state-of-the-art deep learning with federated learning in diagnosing CA. We use motion capture sensors during the performance of a standard neurological balance test obtained from four geographically separated clinics. The recurrence plot, melspectrogram, and poincaré plot are three transformation techniques explored. Experimental results indicate that the recurrence plot yields the highest validation accuracy (86.69%) with MobileNetV2 model in diagnosing CA. The proposed scheme provides a practical solution with high diagnosis accuracy, removing the need for feature engineering and preserving data privacy for a large-scale deployment.