Depression is the leading cause of disability worldwide. Despite the existence of best-practice guidelines which recommend that patients be treated using measurement-based care (MBC), few clinicians employ this effective practice due to a lack of effective MBC tools. In addition, data derived from patients being treated using MBC can be used to produce computational models that can improve the personalization of depression treatment, but necessitates systematic and longitudinal collection of digital data, which is rarely collected in clinical practice. Our project has two major aims: the first is to support the implementation of a digital mental health tool that facilitates the practice of MBC at two McGill-affiliated sites. We use this experience to work with patients, clinicians and family members to optimize the experience and ensure adherence. The second goal will be to further develop an existing machine learning model of treatment selection which will be incorporated into the tool at a later date. Positive results on this project are likely to lead to a wider rollout of Aifred’s tool in the RUIS McGill networks.