< Back to previous page


Assessing upper limb function in breast cancer survivors using wearable sensors and machine learning in a free-living environment.

Journal Contribution - Journal Article

(1)Background: Being able to objectively assess upper limb (UL) dysfunction in breast cancer survivors (BCS) is an emerging issue. This study aims to determine the accuracy of a pretrained lab-based machine learning model (MLM) to distinguish functional from non-functional arm movements in a home situation in BCS; (2)Methods: Participants performed four daily life activities while wearing two wrist accelerometers and being video recorded. To define UL functioning, video data was annotated and accelerometer data were analyzed using a counts threshold method and a MLM. Prediction accuracy, recall, sensitivity, f1-score, ‘total minutes functionally activity’ and ‘percentage functional active’ were considered; (3)Results: Nonetheless a good MLM accuracy (0.77-0.90), recall, and specificity, the f1-score is poor. An overestimation of the ‘total minutes functional activity’ and ‘percentage functional active’ is found by the MLM. Between the video annotated data and the functional activity determined by the MLM, mean differences are 0.14% and 0.10% for the left and right side, respectively. For the video-annotated data versus the counts threshold method, mean differences are 0.27% and 0.24%, respectively;(4) Conclusions: A MLM is a better alternative than the counts threshold method to distinguish functional from non-functional arm movements. However, the abovementioned wrist accelerometer-based assessment methods overestimated the UL functional activity.
Journal: Sensors
ISSN: 1424-8220
Issue: 13
Volume: 23
Publication year:2023