Objective: Electronic medical records (EMR) typically contain both structured attributes as well as narrative text. The usefulness of EMR for research and administration is hampered by the difficulty in automatically analyzing their narrative portions. Accordingly, this paper proposes SPIRE, a strategy for prioritizing EMR, using natural language processing in combination with analysis of structured data, in order to identify and rank EMR that match specific queries from clinical researchers and health administrators.
Materials and Methods: The resulting software tool was evaluated technically and validated with three cases (heart failure, pulmonary hypertension and diabetes mellitus) compared against expert obtained results.
Results and Discussion: Our preliminary results show high sensitivity (70%, 82% and 87% respectively) and specificity (85%, 73.7% and 87.5%) in the resulting set of records. The AUC was between 0.84 and 0.9.
Conclusions: SPIRE was successfully implemented and used in the context of a university hospital information system, enabling clinical researchers to obtain prioritized EMR to solve their information needs through collaborative search templates with faster and more accurate results than other existing methods.
Development of IT-based services to support decision-making in healthcare should be guided by the following considerations: rigor, relevance, user-centered participation and inclusion of the best practices for IT-based service systems. In this paper, the balance between rigor and relevance is achieved by following the design science research methodology; user-centered participation is tackled from the socio-technical tradition in information systems; best practices considered in the planning, design and implementation of the services are informed by the MOF framework. Moreover, and considering the premise that these pillars should holistically converge, this research has been approached from a systemic stance where iterative, participative, socio-technical activities have allowed the effective collaboration between information systems researchers, clinical researchers, medical staff and administrative hospital personnel. This paper argues for a move towards enhancing systemic, participative, design-centered service systems engineering by reporting a case which applies these concepts for providing decision-support services, enabled by data and text mining techniques, to contribute to clinical research and administration by being able to search electronic health records where narrative text hides meaningful information that would otherwise require a time-consuming human revision of these records.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.