Piloting electronic medical record-based early detection of inpatient deterioration in community hospitals

Abstract

Patients who deteriorate in the hospital outside the intensive care unit (ICU) have higher mortality and morbidity than those admitted directly to the ICU. As more hospitals deploy comprehensive inpatient electronic medical records (EMRs), attempts to support rapid response teams with automated early detection systems are becoming more frequent. We aimed to describe some of the technical and operational challenges involved in the deployment of an early detection system. This 2-hospital pilot, set within an integrated healthcare delivery system with 21 hospitals, had 2 objectives. First, it aimed to demonstrate that severity scores and probability estimates could be provided to hospitalists in real time. Second, it aimed to surface issues that would need to be addressed so that deployment of the early warning system could occur in all remaining hospitals. To achieve these objectives, we first established a rationale for the development of an early detection system through the analysis of risk-adjusted outcomes. We then demonstrated that EMR data could be employed to predict deteriorations. After addressing specific organizational mandates (eg, defining the clinical response to a probability estimate), we instantiated a set of equations into a Java application that transmits scores and probability estimates so that they are visible in a commercially available EMR every 6 hours. The pilot has been successful and deployment to the remaining hospitals has begun. Journal of Hospital Medicine 2016;11:S18-S24. © 2016 Society of Hospital Medicine.

FIG. 1

Time intervals involved in real-time capture and reporting of data from an inpatient electronic medical record. T₀ refers to the time when data extraction occurs and the system’s Java application issues a probability estimate. The figure shows that, because of charting and server delays, data may be delayed up to 2 hours. Similarly, because ~2 hours may be required to mount a coherent clinical response, a total time period of ~4 hours (uncertainty window) exists for a given probability estimate.

FIG. 2

Overall system architecture. Raw data are extracted directly from the inpatient electronic medical record (EMR) as well as other servers. In our case, the longitudinal comorbidity score is generated monthly outside the EMR by a department known as Decision Support (DS) which then stores the data in the Integrated Data Repository (IDR). Abbreviations: COPS2, Comorbidity Point Score, version 2; KPNC, Kaiser Permanente Northern California.

FIG. 3

Screen shot showing how early warning system outputs are displayed in clinicians’ inpatient dashboard. ADV ALERT SCORE (AAM score) indicates the probability that a patient will require unplanned transfer to intensive care within the next 12 hours. COPS shows the Comorbidity Point Score, version 2 (see Escobar et al. for details). LAPS shows the Laboratory-based Acute Physiology Score, version 2 (see Escobar et al. for details).