Disease Progression Modeling Workbench 360

Disease Progression Modeling (DPM)1 aims to characterize the progression of a disease and its comorbidities over time using a wide range of analytics models including disease staging2, patient trajectory analytics3, prediction4, and time-to-event estimations5 for key disease-related events. DPM has applications throughout the healthcare ecosystem, from providers (e.g., decision support for patient staging), to payers (e.g., care management), and pharmaceutical companies (e.g., clinical trial enrichment). But the complexity of building effective DPM models can be a roadblock for their rapid experimentation and adoption. Some of this is addressed by standardization of data model and tooling for data analysis and cohort selection6. However, there are still unmet needs to facilitate the development of advanced machine learning techniques such as deep learning with additional requirements such as experiment tracking and reproducibility7. Furthermore, to accelerate DPM research, a data scientist’s available tools should include a framework for deploying models as cloud-ready microservices for rapid prototyping and dissemination8.