RAPIDS: Reproducible Analysis Pipeline for Data Streams Collected with Mobile Devices (Preprint)

BACKGROUND Smartphone and wearable devices are widely used in behavioral and clinical research to collect longitudinal data that, along with ground truth data, are used to create models of human behavior. Mobile sensing researchers often program analysis code from scratch even though many research teams collect data from similar mobile sensors, platforms and devices. As a result, the quality of code varies, code is often not shared alongside publications, and when it is, it might not be stored on a version control system and most of the time there is no guarantee the development environment can be replicated. This makes it difficult for other scientists to read, reuse, audit, and reproduce a publication’s code and its results. OBJECTIVE We present RAPIDS, a reproducible pipeline to standardize the preprocessing, feature extraction, analysis, visualization, and reporting of data streams coming from mobile sensors. METHODS RAPIDS is formed by a group of R and Python scripts that are executed on top of reproducible virtual environments, orchestrated by Snakemake and organized following the cookiecutter data science project. Its development has been and will be informed by public discussions with the mobile sensing research community. RESULTS We share open source, documented, extensible and tested code to preprocess and extract behavioral features from data collected with the AWARE Framework in Android and iOS smartphones as well as Fitbit devices. We also provide a file structure and development environment that other researchers can follow to publish their own models, visualizations, and reports. CONCLUSIONS RAPIDS allows researchers to process mobile sensor data in a rigorous and reproducible way. This saves time and effort during the data analysis phase of a project and makes it easier to share an analysis workflow alongside publications.