Imperial College digital sepsis alert system saves lives and improves outcomes

  • J Am Med Inform Assoc

  • curated by Dawn O'Shea
  • UK Medical News
Access to the full content of this site is available only to registered healthcare professionals. Access to the full content of this site is available only to registered healthcare professionals.

The introduction of a digital alert system to monitor patients with sepsis has led to a reduction in deaths and hospital stays at Imperial College Healthcare NHS Trust.

A study published this week reports that the introduction of the system has resulted in lower odds of death, shorter hospital stays and increased odds of receiving timely antibiotics.

The system monitors a range of changes in patients such as temperature, heart rate and glucose levels and alerts doctors and nurses if they fall outside safe parameters. Clinicians are notified of patients who have triggered the alert either through a pop-up warning on their electronic health records and/or on a dashboard, which highlights any patient with an active alert when they open a patient’s record.

In addition to the alert, Imperial College Healthcare NHS Trust designed a multidisciplinary care plan which is launched in the electronic patient record system when a diagnosis of sepsis in confirmed. This prompts the clinical team to determine the best treatment options and ensure these are administered within one hour, as per national targets.

The study is the first evaluation of a digital sepsis alert system in a British hospital trust and the largest undertaken anywhere to date. It analysed data for patients who alerted in the emergency department from the introduction of the system in October 2016 up to May 2018.

The odds ratios for in-hospital 30-day mortality, prolonged hospital stay (≥7 days) and receipt of antibiotics within one hour were 0.76 (95% CI, 0.70-0.84; n=21,732), 0.93 (95% CI, 0.88-0.99; n=9988) and 1.71 (95% CI, 1.57-1.87; n=4622), respectively.

The findings are published in the Journal of the American Medical Informatics Association.