# Leveraging machine learning for digital gait analysis in ataxia using sensor-free motion capture

## TL;DR

Researchers used machine learning on video recordings to accurately assess walking problems in ataxia patients, detecting subtle changes that traditional methods miss.

## Contribution

The study introduces sensor-free motion capture with ML to improve gait assessment in ataxia, capturing longitudinal and pre-symptomatic changes.

## Key findings

- ML models accurately predicted clinical gait scores with an F1-score of 63.99%, slightly better than human ratings.
- The model detected subtle gait changes in pre-symptomatic patients with an F1-score of 75.96%.
- Longitudinal gait changes were captured with a Pearson’s correlation coefficient of −0.626, significantly better than human ratings.

## Abstract

Gait disturbances are the clinical hallmark of ataxia. Their severity is assessed within a well-established clinical scale, which only allows coarse scoring and does not reflect the complexity of individual gait deterioration. We investigated whether sensor-free motion capture enables to replicate clinical scoring and improve the assessment of gait disturbances.

The normal walking task during clinical assessment was videotaped in 91 ataxia patients and 28 healthy controls. A full-body pose estimation model (AlphaPose) was used to extract positions, distances, and angles over time while walking. The resulting time series were analyzed with four machine learning (ML) models, which were combinations of feature extraction (tsfresh, ROCKET) and prediction methods (XGBoost, Ridge). First, in a regression and classification approach, we trained the ML models on reconstructing the clinical score. Second, we used explainable AI (SHAP) to identify the most important time series. Third, we investigated time series features to study longitudinal changes.

Gait disturbances are assessed with high accuracy by ML models, slightly improving human rating (i) in the categorial prediction of the clinical score (F1-score best model: 63.99%, human: 60.57% F1-score), (ii) in the detection of subtle changes (pre-symptomatic patients, clinically rated unimpaired are differentiated from HC with a F1-score of 75.96%) and (iii) in the detection of longitudinal changes over time (Pearson’s correlation coefficient model: −0.626, p < 0.01; human: −0.060, not significant).

ML-based analysis shows improved sensitivity in assessing gait disturbances in ataxia. Subtle and longitudinal changes can be captured within this study. These findings suggest that such approaches may hold promise as potential outcome parameters for early interventions, therapy monitoring, and home-based assessments.

This study explored a way to measure walking problems in people with ataxia, a condition that affects balance and movement. Researchers used video recordings of patients and healthy participants while walking and analyzed them with a machine learning model that tracks body movements without needing sensors. The model was used to predict clinical scores of walking difficulties and to detect subtle changes over time. The results showed that this approach can capture walking problems accurately and may help detect early changes before symptoms appear, as well as track changes over time. This method could support earlier interventions, improved therapy monitoring, and even enable home-based assessments for people with ataxia.

Wegner et al. apply machine learning to video recordings of walking tasks in people with ataxia and healthy controls using sensor-free motion capture. Their models replicate clinical ratings and detect subtle longitudinal gait changes that are challenging to capture in standard assessments, supporting improved monitoring of disease progression.