EHRs help detect inpatients at imminent risk of dying

Electronic health records can help identify hospitalized patients at risk of death, according to a new study in The American Journal of Medicine.

Inpatients' conditions can deteriorate quickly; the faster the intervention, the better the patient's chances of survival. The researchers, from Arizona based Banner Health, created an algorithm that looked for at least two out of four systemic inflammatory response syndrome (SIRS) criteria, plus at least one of 14 acute organ dysfunction parameters. The algorithm continually sampled the EHR data in real time of 312,214 patients in 24 Banner Health hospitals, and contained an alert to notify the physician of the risk of death when a patient triggered it.

The alert identified a majority of the high risk patients within 48 hours of admission and enabled early and targeted medical intervention. The patients who triggered the alert had a "significantly high" chance of dying in that hospital stay compared to patients who didn't trigger the alarm.

"This study highlights our experience at Banner Health in using EMR to successfully identify patients with potential for clinical deterioration," lead author Hargobind Khurana, M.D., of Banner Health, said in an announcement. "This has also helped in the early identification and appropriate treatment of life-threatening conditions like sepsis.

"Clearly there are many impressive benefits that an EMR can bring to a health system that has significantly invested in this technology," Khurana added. "EMR-based alerts bring these benefits directly to a patient's bedside where they are needed the most. Predictive analytics used in a systematic manner, are no longer just inert computerized algorithms, but are invaluable tools in the hands of an organized healthcare system that has learned how to apply them consistently."

To learn more:
- read the abstract
- here's the announcement