Back

Stanford Screenomics: An Open-source Platform for Unobtrusive Multimodal Digital Trace Data Collection from Android Smartphones

Kim, I.; Boffa, J.; Cho, M.; Conroy, D. E.; Kline, N.; Haber, N.; Robinson, T. N.; Reeves, B.; Ram, N.

2025-06-26 health informatics
10.1101/2025.06.24.25329707 medRxiv
Show abstract

Smartphone-based digital trace data can offer powerful insights for identifying behavioral patterns and health risks. However, existing tools for comprehensive data collection lack scalability, customizability, transparency, and accessibility. To address these gaps, we developed an open-source platform that enables in-situ capture of multimodal digital traces from smartphones (e.g., moment-by-moment capture of screenshots, application usage logs, interaction histories, and phone sensor readings). The Stanford Screenomics Data Collection application allows researchers to tailor data types and quality, data transfer methods, and upload cadence. The Dashboard application supports real-time monitoring of participants data provision, identification of data issues, and automated reactive communications to participants. The platforms back-end employs a NoSQL database for secure, and HIPAA-compliant storage. Using illustrative 24-hour digital trace data we demonstrate how the platform expands the range of possible digital phenotyping studies. Date of Submission: [06] 2025 This article has not been published before and is not currently being considered for publication.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.