The objective of this self-contained health information technology (IT) pilot is to refine and prospectively evaluate a novel, outcomes-based emergency department (ED) triage tool. The tool, HopScore' (developed at Johns Hopkins) aims to support objective triage decisions and improve patient differentiation based on time- sensitive and critical patient outcomes. HopScore uses easily obtained patient demographic and clinical information commonly collected at ED triage to predict patients risk for critical outcomes (i.e., i-hospital mortality, intensive care unit admission, emergent surgery or cardiac catheterization) and general inpatient admission. HopScore addresses deficiencies in the current standard, Emergency Severity Index (ESI) triage tool used by 72% of EDs across the United States (US). Deficiencies of ESI include: (1) no link to critical patient outcomes, (2) a strong reliance on trige evaluator's subjective judgment which results in variable application, (3) poor distribution (i.e., discrimination) of patients across the 5-level index; almost half of all patients nationally are undifferentiated, classified as acuity level 3. At our urban and community ED study sites, the proportion level 3 is 57% and 64%, respectively. Evidence from previous retrospective studies conducted by or team suggest that compared to ESI, HopScore will improve patient safety and drive more efficient distribution of limited ED resources. To evaluate these hypotheses, the specific aims of the application are to: (1) refine the HopScore decision tree algorithm for implementation using separate urban, community, and nationally representative ED populations, (2) design and develop HopScore as a software application that provides swift and interpretable triage decision-support, (3) execute a phased implementation toward consistent use in clinical practice at Johns Hopkins (urban) and Howard County General (community) EDs, (4) prospectively evaluate the HopScore application's usability and impact on patient and operational outcomes compared to ESI (i.e., pre- and post- intervention) in these same settings. The overarching goal of the proposed health IT project is to develop a usable triage tool implemented in clinical practice that has a positive impact on both patient and operational outcomes for a crowded inner-city and community ED. The Johns Hopkins ED provides care to a predominantly low income (64% uninsured or underinsured) and minority (71% African-American) population responsive to AHRQ's mission to support priority populations. Overall, the application is in-line with AHRQ's general IT portfolio goals to anticipate future needs and disseminate evidence on the effectiveness of health IT toward improving the quality, safety, and efficiency of healthcare delivery.
The objective of this health information technology (IT) pilot is to develop and evaluate a novel, outcomes- based emergency department (ED) triage tool (`HopScore'). HopScore uses patient demographic and clinical information commonly collected at triage to predict patients risk for time-sensitive outcomes. The application aims to implement HopScore and demonstrate positive impact on both patient and operation outcomes for an urban and community ED.
| Levin, Scott; Toerper, Matthew; Hamrock, Eric et al. (2018) Machine-Learning-Based Electronic Triage More Accurately Differentiates Patients With Respect to Clinical Outcomes Compared With the Emergency Severity Index. Ann Emerg Med 71:565-574.e2 |
| Hinson, Jeremiah S; Martinez, Diego A; Schmitz, Paulo S K et al. (2018) Accuracy of emergency department triage using the Emergency Severity Index and independent predictors of under-triage and over-triage in Brazil: a retrospective cohort analysis. Int J Emerg Med 11:3 |
| Dugas, Andrea Freyer; Kirsch, Thomas D; Toerper, Matthew et al. (2016) An Electronic Emergency Triage System to Improve Patient Distribution by Critical Outcomes. J Emerg Med 50:910-8 |
