A strategy for prioritizing electronic medical records using structured analysis and natural language processing

Abstract

Objective: Electronic medical records (EMRs) typically contain both structured attributes and narrative text. The usefulness of EMRs for research and administration is hampered by the difficulty in automatically analyzing their narrative portions. Accordingly, this paper proposes a strategy for prioritizing EMRs (SPIRE), using natural language processing in combination with the analysis of structured data to identify and rank EMRs that match queries intended to find patients with a specific disease posed by 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) and compared against expert-obtained results. Results and Discussion: Our preliminary results show high sensitivity (70%, 82% and 87%) 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 EMRs to solve their information needs through collaborative search templates with faster and more accurate results than other existing methods.