Wearable sensors represent a valuable means for monitoring motion signs and symptoms of Parkinson’s disease (PD). In this paper, we explore the potential of a single inertial sensor to yield information correlated to the patient’s subjective perception of axial motion impairment during daily activities. This latter is expressed using as a relevant metric the sum of MDS-UPDRS items 2.11-2.13. Methods: thirty-one patients with PD were enrolled in this study, and asked to perform a timed-up-and-go test while wearing an inertial sensor on their thigh. Several time- and frequency-domain features were extracted from the inertial signals. They were fed to a random forest regression model for the prediction of the axial impairment metric. The model was optimized using 10-fold cross-validation and performance were assessed using leave-one-subject-out test. Results: Pearson correlation coefficient with the addressed metric of 0.76 (0.86) and mean absolute error of 1.70 (1.52) were obtained in patients under (not under) dopaminergic therapy. Moreover, moderate to strong correlations were found between the predicted score and some important disease progression, axial impairment, and motor performance metrics. Conclusion: a single wearable inertial sensor may be used for assessing motor disabilities of patients with PD.


    Access

    Download


    Export, share and cite



    Title :

    Correlation between wearable inertial sensor data and standardised Parkinson's disease axial impairment measures using machine learning


    Contributors:

    Publication date :

    2022-01-01



    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Classification :

    DDC:    629



    Predicting axial impairment in parkinson’s disease through a single inertial sensor

    Borzi L. / Mazzetta I. / Zampogna A. et al. | BASE | 2022

    Free access

    Gait Parameters Change Prior to Freezing in Parkinson's Disease: A Data-Driven Study with Wearable Inertial Units

    Maria Laura Ferster / Sinziana Mazilu / Gerhard Tröster | DOAJ | 2015

    Free access

    A Single Wearable Sensor for Gait Analysis in Parkinson’s Disease: A Preliminary Study

    Pierleoni P. / Raggiunto S. / Belli A. et al. | BASE | 2022

    Free access

    Standardised controls

    Engineering Index Backfile | 1942


    Standardised controls

    Engineering Index Backfile | 1928