Objective: Develop and validate a wearable-based solution for tracking motor function in Friedreich ataxia (FRDA).

Background: FRDA is an autosomal recessive neurodegenerative disorder causing progressive loss of coordination and mobility. Traditional clinical assessments for FRDA can be subjective and limited in detecting changes. Wearable sensors offer a solution by continuously monitoring physical activity and mobility in real-world settings, providing insights from daily experiences.

Method: We recruited 39 FRDA patients and remotely monitored their physical activity and upper extremity function using a set of wearable sensors for 7 consecutive days. We assessed the correlations of sensor-derived metrics from lower and upper extremity function as measured during activities of daily living with FDRA clinical measures (e.g., mFARS and FA-ADL) and biological biomarkers of disease severity (guanine-adenine-adenine (GAA) and frataxin (FXN) levels). Feature selection was performed using Spearman correlation analysis, and the machine learning model’s performance was evaluated using leave-one-out cross-validation.

Results: Significant correlations were observed, with moderate to high impact, between various metrics obtained from sensors and both the clinical and biological outcomes of FRDA. Additionally, we developed multiple machine learning models to forecast disease severity in FRDA, incorporating demographic, biological, and sensor-derived metrics. Upon inclusion of sensor-derived metrics, the model’s performance improved by 1.5 times and 2 times in terms of explained variance (R²) for predicting FRDA clinical measures and biological biomarkers of disease severity, respectively.

Conclusion: Our findings highlight the potential of wearable sensors in assessing disease severity and monitoring motor dysfunction in FRDA.

« Back to 2024 International Congress

MDS Abstracts - https://www.mdsabstracts.org/abstract/predicting-disease-severity-in-friedreichs-ataxia-through-wearable-monitoring-and-machine-learning/