A unified algorithm framework for quality control of sensor data for behavioural clinimetric testing

The use of smartphone and wearable sensing technology for objective, non-invasive and remote clinimetric testing of symptoms has considerable potential. However, the clinimetric accuracy achievable with such technology is highly reliant on separating the useful from irrelevant or confounded sensor data. Monitoring patient symptoms using digital sensors outside of controlled, clinical lab settings creates a variety of practical challenges, such as unavoidable and unexpected user behaviours. These behaviours often violate the assumptions of clinimetric testing protocols, where these protocols are designed to probe for specific symptoms. Such violations are frequent outside the lab, and can affect the accuracy of the subsequent data analysis and scientific conclusions. At the same time, curating sensor data by hand after the collection process is inherently subjective, laborious and error-prone. To address these problems, we report on a unified algorithmic framework for automated sensor data quality control, which can identify those parts of the sensor data which are sufficiently reliable for further analysis. Algorithms which are special cases of this framework for different sensor data types (e.g. accelerometer, digital audio) detect the extent to which the sensor data adheres to the assumptions of the test protocol for a variety of clinimetric tests. The approach is general enough to be applied to a large set of clinimetric tests and we demonstrate its performance on walking, balance and voice smartphone-based tests, designed to monitor the symptoms of Parkinson's disease.