Semantic driven data migration for predictive treatment of major depressive disorder

Abstract

SEMMDD is a collection of researchers working to improve treatment for Major Depressive Disorder. Specifically, focus is put on accurately modeling patient response to various depression therapies. This paper contributes to this ongoing research through two main bodies of work. First, a process is described that migrates traditional tabular datasets into a decentralized web of knowledge known as the Semantic Web. Data migration is achieved by employing World Wide Web Consortium open standards and best practices. Datasets altered in this way benefit by increasing their exposure to like-minded content creators and lowering the learning curve for others to become involved. Additionally, I explain how this process fulfills the need for a data migration system that facilitates effective data proliferation along with exhaustive provenance capture. The second body of work tasked Machine Learning algorithms to make predictions for a patient's ultimate response to therapy based on their initial depressive state. As a result, I make recommendations concerning which algorithm configurations best fit the depression data and where future modeling efforts can best be focused. Machine Learning algorithms were utilized to give an alternate perspective to modeling patient treatment response in comparison to a historical use of neural network modeling. This recent body of work contributes to a larger initiative working to empower clinicians with the tools necessary to prescribe medical treatment. Armed with this knowledge, clinicians can make treatment decisions based more on historical trends seen in data and less on anecdotal experience.