Deep brain stimulation (DBS) technology has made an impressive impact on clinical medicine, but after ~25 year of experience and ~125,000 cases, variability in clinical outcomes remains an issue of concern. While this probably isn't surprising for emerging indications such as depression, it is unfortunate (bordering on unacceptable) for established applications such as Parkinson's disease. One possible explanation for this outcome variability is the lack of DBS-specific informatics toolboxes and/or database systems that could be used to identify patterns and define best practices. The concept is to integrate data like pre-operative clinical assessments and surgical targeting images with post-operative clinical outcome metrics and stimulation parameter settings. While a comprehensive DBS informatics system doesn't currently exist, components are available and their integration is underway. Such an assembly will facilitate application of machine learning algorithms to help the DBS community improve patient selection and optimize clinical outcomes.