We have seen many examples of digital health innovation failing to gain traction in the real world setting. Often is it because the sensor or app at the heart of it all just wasn't right for the job. Could we approach this in a better way, such that we can enhance the chances of success?

In spite of significant recent advances in molecular genetics and neuroscience, behavioral ratings based on clinical visual observations are still the gold standard for screening, diagnosing, and assessing outcomes in mental health disorders.