JMIR Publications

ABSTRACT

The US National Institute of Mental Health (NIMH) declared the final decade of the XXth century to be “the Decade of the Brain.” However, thirty years later, the former NIMH Director acknowledged that this initiative had not produced any substantial increase in rates of recovery from mental disorders. Some of the challenges contributing to this include that day-to-day clinical interactions in psychiatry are fundamentally the same as they were 50 years ago. Similarly, despite extraordinary empirical advances in psychopharmacology, all psychotropic medications work for a subset but not for most patients. We do not yet understand the pathogenesis of mental disorders and the mechanisms of their treatment. Thus, we still have to follow a “trial and error” approach and optimizing the medication regime of patients with complex mental disorders can take an inordinate amount of time. Over the past decade, new tools have allowed us to continuously assess objective measures (e.g., hours of sleep) and to densely-sample subjective measures (e.g., mood, motivation). Almost a decade ago, the promise of this approach, referred to as “digital phenotyping” was recognized, comparing its potential impact on psychiatry to the impact of the microscope on biological sciences. In this Viewpoint, we describe the steps needed to fully unlock the potential of digital phenotyping to improve clinical outcomes in Psychiatry and to translate this information into clinically actionable predictions.