More than just an app, the Beiwe Research Platform consists of three cloud-based components for collecting data, managing studies and performing data analysis. Beiwe is currently being used in numerous studies, primarily at the Harvard Medical School teaching hospitals involving patients with psychiatric and neurological disorders, surgical patients, and patients with cancer.
Unlike the large majority of commercially available smartphone applications, Beiwe is intended for biomedical research. Our research platform collects and analyzes raw sensor and phone use data. Our initial application areas of digital phenotyping are in psychiatric, neurological, and surgical patients, where we aim to generate new outcome measures and social and behavioral biomarkers.
- Open-source under the 3-clause BSD license
- Infinitely scalable AWS cloud-based architecture
- Smartphone app available on iOS and Android
- Fully configurable data collection settings
- Easy study management
- Collects raw smartphone sensor and usage log data
- Configuration files ensure easy and transparent reproducibility
- Integrated data analysis pipeline
Investigators worldwide have three different ways of using Beiwe in their studies.
Direct CollaborationThe lab currently has limited bandwidth for new collaborations, but in this model, we create the new study on our production version of Beiwe, which we run on our lab’s AWS account, and we cover all platform costs, such as server uptime, data storage, and network traffic. These collaborations are usually funded by a joint grant.
Beiwe as a ServiceIn this model, we run the Beiwe study on AWS using our latest versions of the front-end, back-end, and data analysis software. This model is not a scientific collaboration between the Onnela Lab and the other group, but makes Beiwe data collection and analysis capabilities available for others. Fees are used to cover immediate costs of running the Beiwe instances and to partially cover the cost of maintenance and development.
Beiwe Open SourceThe Beiwe research platform is available, under an open-source license, to investigators worldwide for free. Under this model, individuals or institutions interested in using Beiwe will use the Beiwe AMI (Amazon Machine Image) to create their own instance of Beiwe on AWS. In this model, the investigators using the open source version are responsible for all expenses. Software is provided as is.
We receive a large number of inquiries about our approach and the research platform, and we attempt to address some of the most frequently asked questions here. Regarding the most frequently asked question, Beiwe is a transliteration of a Nordic goddess of sunlight and mental health. We pronounce it bee-we.
What is digital phenotyping?
Who developed Beiwe?
What is the difference between a smartphone app and a research platform?
Why does Beiwe collect raw data?
What about reproducibility and replicability of Beiwe studies?
Want to find out more about Beiwe or our work in Digital Phenotyping? Detailed information is available on the Onnela Lab Website.