Sepsis is an inflammatory response to infection that can overwhelm the body and damage tissues and organs. Each year, there are over one million cases of sepsis and 258,000 deaths from it in the US, and people who survive sepsis are often left with permanent damage (CDC, 2015).
A new study raises hope that electronic medical records can identify hospitalized patients at a high risk of death from sepsis (Khurana et al., 2016). The study, published in The American Journal of Medicine, reviewed an automated alert system which scoured data from electronic medical records of 312,214 patients in 24 Banner Health hospitals over a time frame of two years. The system was designed to continuously sample electronic medical record data and trigger an alert upon the occurrence of three medical events suggestive of systemic inflammatory response syndrome and organ dysfunction: two symptoms of systemic inflammatory response syndrome occurring within six hours of each other (e.g., respiratory rate > 20 breaths per minute, heart rate > 90 beats per minute, temperature < 36.0°C or > 38.3°C, white blood cell count < 4,000 or > 12,000 cells per mcL, band count > 10%); any symptom of acute organ dysfunction; and the occurrence of the first two criteria within eight hours of each other. When triggered, the alert is visible to any medical provider who accesses the chart and, in turn, promotes early detection of a patient’s high mortality risk.
The researchers found that patients who triggered the alert had a much higher rate of in-hospital death compared to patients who did not trigger the alert.
Moreover, of the patients who died after triggering the alert, on average, 5.3 days passed from the time the alert was triggered to when the patient died.
The use of electronic medical records raises innumerable issues concerning access, privacy, and misuse. However, with the advancement of technology in medicine comes the ability to improve electronic medical record systems to make them more advantageous and valuable to physicians and patients. Systems such as this have the potential to serve as an “effective early warning tool” that can save lives that would otherwise be lost to sepsis.
CDC, Centers for Disease Control and Prevention. (2015, November 30). Sepsis.
Elsevier. (2016, May 17). Electronic medical record automated alerts notify physicians when patients at risk of death.
Khurana, H. S., Groves, R. H., Simons, M. P., Martin, M., Stoffer, B., Kou, S., . . . Parthasarathy, S. (2016). Real-time automated sampling of electronic medical records predicts hospital mortality. American Journal of Medicine, 129, 688–698. doi:10.1016/j.amjmed.2016.02.037