(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 pre-trained 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 were annotated and accelerometer data were analyzed using a counts threshold method and an MLM. Prediction accuracy, recall, sensitivity, f1-score, ‘total minutes functional activity’ and ‘percentage functionally active’ were considered. (3) Results: Despite a good MLM accuracy (0.77–0.90), recall, and specificity, the f1-score was poor. An overestimation of the ‘total minutes functional activity’ and ‘percentage functionally active’ was found by the MLM. Between the video-annotated data and the functional activity determined by the MLM, the mean differences were 0.14% and 0.10% for the left and right side, respectively. For the video-annotated data versus the counts threshold method, the mean differences were 0.27% and 0.24%, respectively. (4) Conclusions: An MLM is a better alternative than the counts threshold method for distinguishing functional from non-functional arm movements. However, the abovementioned wrist accelerometer-based assessment methods overestimate UL functional activity.
Background/Objectives: Post-radiation fibrosis is a common complication in patients with head and neck cancer (HNC), characterised by increased tissue stiffness and functional limitations. Shear wave elastography (SWE) enables objective assessment of tissue stiffness, while self-reported outcome measures provide insight into symptom burden. However, the longitudinal evolution of these outcomes and their relationship remains insufficiently described. This study aimed to characterise post-radiation fibrosis over time using objective SWE measurements of sternocleidomastoid (SCM) muscle stiffness and self-reported fibrosis-related symptoms, and to examine their longitudinal association. Methods: This prospective longitudinal study included 56 patients with HNC undergoing primary or postoperative (chemo)radiotherapy. Muscle stiffness was measured using SWE, and fibrosis-related symptoms were assessed with the Lymphoedema Symptom Intensity and Distress Survey-Head and Neck (LSIDS-H&N) at 1 week, 6 weeks, 12 weeks, 6 months, and 12 months after the start of radiotherapy. Longitudinal analyses were performed using mixed-effects models adjusted for surgery and radiation dose, and within-subject associations were evaluated using repeated measures correlation. Results: Muscle stiffness increased over time, with estimated mean stiffness values rising from 4.12 m/s at baseline to 4.76 m/s at 6 months and 4.92 m/s at 12 months. Significant increases were observed at 6 months (p = 0.007) and 12 months (p = 0.012) compared with baseline. In contrast, self-reported fibrosis-related symptoms remained stable, with no significant differences between time points. No significant within-subject association was found between muscle stiffness and self-reported fibrosis-related symptoms (r = −0.13, p = 0.498). Conclusions: Muscle stiffness measured with SWE increased over time following radiotherapy, whereas self-reported fibrosis-related symptoms remained stable. No significant longitudinal association was found between these outcomes, suggesting they may capture different aspects of fibrosis.