Using a clinical document importance estimator to optimize an agent-based clinical report retrieval system

Abstract

The OPTIM project aims to optimize the graphical user interface of an electronic health record (EHR) by predicting clinical documents' relevance and provide a ranked list of relevant documents for the given user at a certain time. In this paper we will describe part of the system architecture pertaining to report retrieval and relevance assignment, focusing on the optimization of an agent based report retrieval system (MAID) using the webservice layer of the OPTIM project. The prototype of MAID using the optimized retrieval was tested in a simulated environment. In the executed simulations the classifier was able to rate 10 reports per second. Including a report rating in the EHR interface based on clinical relevance calculated by mathematical models can potentially improve the usability of the EHR.