Novel algorithms deriving clinical performance measures from smartphone sensor data collected under a walking test

Abstract

The modern ubiquity of smartphones which incorporate sensors such as inertial measurement units (IMU) and global positioning system (GPS) receivers, raises the possibility that they might be used as inexpensive devices for clinical performance testing. Here, we report on the development and testing of an app and associated statistical signal processing algorithms, to measure the basic gait properties of step rate, walking speed and distance under an outside short walk test experimental protocol, from digital accelerometry and GPS. We provide extensive details on the assumptions underlying the development of the algorithms. A small set of experiments across a range of conditions and individuals, demonstrate the reliability of the combined app, protocol and algorithms. With reasonable adherence to the test protocol, these experiments show 2% error across all metrics. The emphasis in this paper is on illustrating the design principles which all such systems, aiming to re-purpose consumer smartphones as clinical gait measurement devices, must address.