Mental Health Digital Biomarkers: Moving from Research to Practice
Mental health "digital biomarkers" purport to measure mental health and well-being using data collected from mobile devices and technology platforms (eg, location, usage patterns). Translating digital biomarkers into clinical practice raises multiple sociotechnical questions that need to be addressed if these computational tools intend to improve care. How do we assess whether digital biomarkers will be reliable in clinical settings, and even in cases where measurement is reliable, will digital biomarkers improve mental health?
In this talk, I will highlight some of our recent work answering these questions. I will explore how traditional ideas of measurement reliability can be adapted to the context of mental health digital biomarkers, to assess the readiness of digital measures for clinical use. In addition, I will highlight sociotechnical tensions that arise within a proposed implementation of digital biomarkers, called the "quantified workplace", creating opportunities for collaborative research - between computer and information scientists, clinical researchers, ethicists, and privacy scholars - to ensure that digital biomarkers truly support mental health.
Dan Adler is a PhD Candidate in Information Science at Cornell University. His work focuses on the implementation of data-driven measurement solutions in healthcare, focusing specifically on mental and behavioral healthcare. Dan has conducted quantitative work, developing and validating machine learning models to measure symptoms of depression and schizophrenia, as well as qualitative work, thinking about tensions surrounding the implementation of these tools, and how we can improve evidence generation in data-driven mental health measurement research. At Cornell, Dan is advised by Tanzeem Choudhury, and receives supervisory support from Deborah Estrin and Fei Wang.