MORPHER - A Platform to Support Modeling of Outcome and Risk Prediction in Health Research

Abstract

Machine learning is rapidly becoming a mainstay in research and industry. Particularly for clinical predictive modeling, these approaches are being increasingly applied, as evidenced by the growth in the number of related publications. While different computer tools exist that support rapid prototyping, we observe that the state of the art is lacking in the extent to which the needs of research clinicians are addressed. This leads to an increase in the time needed for development and validation of such models. In this paper, we outline the requirements and challenges inherent to this domain and present a platform for rapid prototyping tailored to the specific needs of clinical modeling for outcome and risk prediction. We argue that a move towards hybrid solutions, i.e., a mix of cloud and on-premise infrastructure, constitutes a viable way to reduce the time needed to develop and validate clinical predictive models in a standardized, reproducible fashion.