JMIR Publications

ABSTRACT

Background:

The increased use of wearable sensor technology has highlighted the potential for remote telehealth services such as rehabilitation. Telehealth services incorporating wearable sensors are most likely to appeal to the elderly population in remote and rural areas who may struggle with long commutes to clinics. However, the usability of such systems can often discourage patients from adopting these services.

Objective:

This study aims to identify the usability factors which most influence whether an elder would decide to continually use a wearable device.

Methods:

Elders across four different regions (Northern Ireland, Ireland, Sweden, and Finland) wore an activity tracker for 7 days under a free-living environment protocol. Four surveys were administered and biometrics measured by researchers before the trial began. At the end of the trial period, researchers administered two further surveys to gain insights into the perceived usability of the wearable device. These were the standardized System Usability Scale as well as a custom usability questionnaire designed by the research team. Statistical analyses were performed to identify the key factors that affect continued wearable use, and Machine Learning classifiers were used to provide an early prediction on wearable device adoption.

Results:

The study consisted of healthy elders (N= 65, mean=70.52 years, SD=5.65) wearing a Xiaomi Mi Band 3 activity tracker for 7 days in a free-living environment. The results from the System Usability Scale survey show that there is no notable difference in perceived system usability regardless of region, gender, or age, eliminating the notion that usability perception differs based on geographical location, sex, or deviation in elders age. There was also no statistical difference in SUS score between elders who had previously owned a wearable device, or if they wore one or two devices during the trial. The bespoke usability questionnaire determined that the two most important factors that influenced continued device usage within an elderly cohort was device comfort (tau=0.34) and if the device was fit-for-purpose (tau=0.34). A computational model providing an early identifier of continued device use was developed using these two features. Random Forest classifiers were shown to provide the highest predictive performance (80% accuracy). By including the top eight ranked questions from the bespoke questionnaire as features to our model, the accuracy increased to 88%.

Conclusions:

This paper concludes that comfort and accuracy are the two main influencing factors in sustaining wearable device usage. This paper suggests that the reported factors influencing usability are transferable to other wearable sensor systems. Future work will aim to test this hypothesis by using the same methodology on a cohort using other wearable technology.