JMIR Publications

ABSTRACT

Background:

The elderly are at an increased risk of falls with the consequent impacts on the health of the individual and health expenditure for the population. Smartwatch apps have been developed to detect a fall, but their sensitivity and specificity have not been subjected to blinded assessment; nor have the factors that influence the efficacy of falls detection been fully identified.

Objective:

Assess accuracy metrics for a novel fall detection smartwatch algorithm.

Methods:

We performed a cross-sectional study of 22 healthy adults comparing the detection of induced forward, side (left and right), and backwards falls and near falls provided by a smartwatch threshold-based algorithm with a video record of induced falls serving as the gold standard; a blinded assessor compared the two. Three different smartwatches with two different operating systems were used. There were 226 falls, 64 were backward, 51 forward, 55 left sided, and 56 were right sided.

Results:

The overall smartwatch app sensitivity for falls was 77%, specificity 99%, false positive rate 1.7%, and false negative rate 16.4%. The positive and negative predictive values were 98% and 84% respectively, while the accuracy was 89%. There were 249 near falls: sensitivity 89%, specificity 100%, no false positives, 11% false negatives, positive predictive value 100%, false negative predictive value 83%, and accuracy of 93%.

Conclusions:

Falls were more likely to be detected if the fall was on the same side as the wrist with the smartwatch. There was a trend towards some smartwatches and operating systems having superior sensitivity. The efficacy data and modifying factors pertaining to this smartwatch app can serve as a reference point for other similar smartwatch apps.