Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: Mood disorders are common and associated with significant morbidity and mortality. Better tools are needed for their diagnosis and treatment. Deeper phenotypic understanding of these disorders is integral to development of these tools. This study is the first effort to use passively collected, mobile phone keyboard activity to build deep digital phenotypes. Objective: To demonstrate the feasibility of using passively collected keyboard dynamic metadata to infer mood states Methods: Within subject design of eight weeks, subjects were provided a mobile phone loaded with a customized keyboard which passively collected keystroke metadata. Subjects were administered the Hamilton Depression Rating Scale (HDRS) and Young Mania Rating Scale (YMRS) weekly. Linear mixed-effects models were created to predict HDRS and YMRS scores (total keystrokes n= 626,641, weekly average 9,791 ± 7,861; total accelerometer readings n= 6,660,890, weekly average 104,076 ± 68,912). Results: A statistically significant mixed-effects regression model for the prediction of HDRS-17 item scores was created: conditional R²=0.63, P=0.014. A mixed-effects regression model for YMRS scores showed the variance accounted for by random effect was zero, and so a simple linear regression model was created: R²=0.34, P=0.0011. Multiple significant variables were demonstrated for each measure. Conclusions: Mood states in bipolar disorder are correlated with specific changes in mobile phone usage. The creation of these models provides evidence for the feasibility of using passively collected keyboard metadata to detect and monitor mood disturbances.