An architecture for complex clinical question answering

Abstract

We present the software architecture for a coming commu­nity resource, the Multi-source Integrated Platform for An­swering Clinical Questions (MiPACQ). This system is de­signed to capitalize on state-of-the-art semantic annotation of text to answer complex clinical practice questions and to enable clinical investigators to perform pioneering data min­ing tasks. The architecture allows easy customization to fa­cilitate integration with different electronic medical records systems and data sources, to retrain machine learning (ML) classifiers to handle domain-specific details, to utilize new annotators and ML algorithms as they become available, and to enhance, replace or add new core system components.