Applying natural language processing techniques to develop a task-specific EMR interface for timely stroke thrombolysis: A feasibility study. (April 2018)

• Record Type: Journal Article
• Authors: Sung, Sheng-Feng; Chen, Kuanchin; Wu, Darren Philbert; Hung, Ling-Chien; Su, Yu-Hsiang; Hu, Ya-Han
• Is Part Of: International journal of medical informatics. Volume 112(2018)
• Page Start: 149
• Page End: 157
• Publication Date: 2018-04
• Subjects: AIS acute ischemic stroke -- CUI concept unique identifier -- ED emergency department -- EMR electronic medical record -- IVT intravenous thrombolytic therapy -- NLP natural language processing -- SICH symptomatic intracranial hemorrhage -- SUS System Usability Scale -- UMLS Unified Medical Language System; Acute ischemic stroke -- Electronic medical record -- Intravenous thrombolysis -- Natural language processing; Medical informatics -- Periodicals; Information science -- Periodicals; Computers -- Periodicals; Medical technology -- Periodicals; Medical Informatics -- Periodicals; Technology, Medical -- Periodicals; Computers; Information science; Medical informatics; Medical technology; Electronic journals; Periodicals; Electronic journals; 610.285
• DOI: 10.1016/j.ijmedinf.2018.02.005
• Languages: English
• ISSNs: 1386-5056

Abstract

Highlights: We developed a task-specific EMR interface to help clinicians determine eligibility for intravenous thrombolysis (IVT). The proposed algorithm extracted medical concepts related to IVT eligibility criteria from clinical notes. Both the algorithm performance and the user performance with the interface were evaluated. The algorithm showed a high level of overall classification accuracy. The user experiment indicated that the developed interface could help reduce errors in assessing contraindications to IVT. Abstract: Objective: To reduce errors in determining eligibility for intravenous thrombolytic therapy (IVT) in stroke patients through use of an enhanced task-specific electronic medical record (EMR) interface powered by natural language processing (NLP) techniques. Materials and methods: The information processing algorithm utilized MetaMap to extract medical concepts from IVT eligibility criteria and expanded the concepts using the Unified Medical Language System Metathesaurus. Concepts identified from clinical notes by MetaMap were compared to those from IVT eligibility criteria. The task-specific EMR interface displays IVT-relevant information by highlighting phrases that contain matched concepts. Clinical usability was assessed with clinicians staffing the acute stroke team by comparing user performance while using the task-specific and the current EMR interfaces. Results: The algorithm identified IVT-relevant concepts with micro-averaged precisions, recalls, and F1 measures of 0.998, 0.812, and 0.895 at the phrase level and of 1, 0.972, and 0.986 at the document level. Users using the task-specific interface achieved a higher accuracy score than those using the current interface (91% versus 80%, p = 0.016) in assessing the IVT eligibility criteria. The completion time between the interfaces was statistically similar (2.46 min versus 1.70 min, p = 0.754). Discussion: Although the information processing algorithm had room for improvement, the task-specific EMR interface significantly reduced errors in assessing IVT eligibility criteria. Conclusion: The study findings provide evidence to support an NLP enhanced EMR system to facilitate IVT decision-making by presenting meaningful and timely information to clinicians, thereby offering a new avenue for improvements in acute stroke care.