Current methods to assess depression and select appropriate treatments have many limitations and need improvement. Diagnosis is usually based on having a clinician interview the patient, a method developed in the 1960s. The main drawbacks of most assessment methods today are lack of objectivity, being symptom-based and not preventative, and requiring accurate communication of lengthy information in a short amount of time. This work explores new technology to assess depression, including its increase or decrease in symptoms, in an automatic, more objective, pre- and post-symptomatic, and cost-effective way using wearable sensors and smart phones. These can provide up to 24/7 monitoring of different personal parameters such as physiological data, voice characteristics, sleep, and social interaction, "seeing" things that may not usually be visible, which may enable earlier detection and prevention. We aim to enable more accurate subtyping of depression, prevention of depression, assessment of depression for people who cannot communicate, better assignment of an efficacious treatment, early detection of treatment remission and response, and anticipation of post-treatment relapse or recovery.