High-Throughput Digital Phenotyping

Data collection and analysis platforms for Android and iOS devices

From Data to Analytics to Insights


Our open-source data collection platform for Android and iOS devices, developed under an NIH Director’s New Innovator Award to Dr. JP Onnela in 2013. It consists of two native smartphone applications and an AWS-based back-end system.


Our open-source data analysis platform for Beiwe data. This Python library can be run locally, but also integrates directly with the Beiwe back-end on AWS to provide scalable on-demand analytics. Its Tableau API supports customizable workbooks and dashboards.


Our research is focused on the development of mathematical and statistical methods for analyzing intensive high-dimensional data. We also participate in applied digital phenotyping studies in medicine and public health with an emphasis on central nervous system disorders.

Our Approach

Social, behavioral, and cognitive phenotypes are difficult to study due to their temporal and contextual dependence. The standard approach to learning about something as complex as human behavior is to use surveys, which are cross-sectional, subjective, and often burdensome.

The ubiquity and capability of smartphones—when coupled with appropriate data analytic techniques—can be part of the solution. We coined the term Digital Phenotyping to refer to the “moment-by-moment quantification of the individual-level human phenotype in situ using data from personal digital devices, in particular smartphones.” We developed Beiwe and Forest specifically for use in smartphone-based digital phenotyping research.

Most commercially available smartphone applications use software development kits (SDKs) made by Apple and Google that generate unvalidated behavioral summary measures using closed proprietary algorithms. These apps don’t meet the high standards of reproducible science, and often require researchers to modify their scientific questions based on what data happens to be available. Beiwe collects raw sensor and phone use data for analysis by Forest. That means that data collection and data analysis can be customized to address specific scientific questions of interest.

Meet Beiwe

Commitment to Reproducible Science

We create tools that help researchers conduct studies that are truly reproducible. Both Beiwe and Forest are open-source software, published under the permissive 3-clause BSD (BSD-3) license. Every single Beiwe data collection setting is captured as a JSON-formatted study configuration file that can be easily imported or exported. Public sharing of study configuration files makes it easy for anyone to reproduce a Beiwe platform-based study.

Using Beiwe and Forest


The Onnela Lab offers a few opportunities for direct research collaborations using Beiwe. We provide the platform and work directly with you to advance the research project. These collaborations are usually funded by a joint grant or industry partner.

Beiwe Service Center

This option makes Beiwe available to any academic or commercial entity under the software-as-a-service model. As a formal service core of Harvard University, its pricing is based on the extent of platform use. This is an easy option for others to use Beiwe in their research, but it is not a scientific collaboration with the Onnela Lab.

Open Source

As open-source software, Beiwe and Forest are available at no cost to investigators worldwide under the BSD-3 license. Individuals or institutions can deploy their own instance of Beiwe and Forest on AWS. The software is provided as-is, and investigators are responsible for all expenses.

Get Started with Beiwe

Beiwe Service Center

Beiwe is available to any academic or commercial entity under a software-as-a-service model, delivered through a formal service core of Harvard University. Pricing is based on the extent of platform use—just let us know the number of participants, study duration, and average length of follow-up per participant. Once we have a copy of your study IRB, we can usually create your study within 48 hours.