A data-driven approach to detect upper limb functional use during daily life in breast cancer survivors using wrist-worn sensors

Abstract

To gain insights into the impact of upper limb (UL) dysfunctions after breast cancer treatment, this study aimed to develop a temporal convolutional neural network (TCN) to detect functional daily UL use in breast cancer survivors using data from a wrist-worn accelerometer. A pre-existing dataset of 10 breast cancer survivors was used that contained raw 3-axis acceleration data and simultaneously recorded video data, captured during four daily life activities. The input of our TCN consists of a 3-axis acceleration sequence with a receptive field of 243 samples. The 4 ResNet TCN blocks perform dilated temporal convolutions with a kernel of size 3 and a dilation rate that increases by a factor of 3 after each iteration. Outcomes of interest were functional UL use (minutes) and percentage UL use. We found strong agreement between the video and predicted data for functional UL use (ICC = 0.975) and moderately strong agreement for %UL use (ICC = 0.794). The TCN model overestimated the functional UL use by 0.71 min and 3.06%. Model performance showed good accuracy, f1, and AUPRC scores (0.875, 0.909, 0.954, respectively). In conclusion, using wrist-worn accelerometer data, the TCN model effectively identified functional UL use in daily life among breast cancer survivors.The upper limbs (ULs) are essential to our everyday life. To clean our houses, to complete work tasks, to drink, to eat, to scratch, to help or touch other people, etc. Usually, we are unaware of how much we use our ULs until we are unable to properly use them. Life events such as surgery or treatment for breast cancer are moments that might suddenly affect UL function.After breast cancer treatment, an estimated 30-50% of women suffer from persistent UL dysfunction 1 . This persistent dysfunction goes beyond the natural healing time of tissue after surgery or radiotherapy, and it is considered one of the most troublesome long-term complications after breast cancer treatment 1-3 . Women suffering from UL dysfunction are less able to perform their daily tasks, have an increased risk for chronic pain, and suffer from participation difficulties, which lead to a decrease in their quality of life 1,3 . This impact on everyday life is currently only assessed using questionnaires. While questionnaires are easily administered and provide valuable information on a person's perception of UL function, they have important drawbacks such as recall bias and self-presentation bias (i.e. disclose only what the person wants to or is consciously aware of). Next to questionnaires, clinic-based assessments of body function, e.g. UL range of motion and activity or functional task performance, can measure the capability of a patient but might be poor indicators of actual UL use in daily life 4-6 . Thus, assessment of behaviour in a natural setting is vital, to assess the real-world impact of surgery on UL use and to evaluate UL recovery 7 .To assess UL function, a few definitions need to be addressed. UL function is previously defined by the functional arm activity behavioura...