Effect of a Sepsis Prediction Algorithm on Clinical Outcomes

Effect of a Sepsis Prediction Algorithm on Patient Mortality, Length of Stay, and Readmission

In this clinical outcomes analysis, the effect of a machine learning algorithm for severe sepsis prediction on in-hospital mortality, hospital length of stay, and 30-day readmission was evaluated.

Materials and Methods: Clinical outcomes evaluation performed on a multiyear, multicenter clinical data set of real-world data containing 75,147 patient encounters from nine hospitals. Mortality, hospital length of stay, and 30-day readmission analysis performed for 17,758 adult patients who met two or more Systemic Inflammatory Response Syndrome (SIRS) criteria at any point during their stay.

Inclusion Criteria:

• All patients over the age of 18 presenting to the emergency department or admitted to an inpatient unit at the participating facilities were automatically included for clinical outcomes analysis

Exclusion Criteria:

• Patients under the age of 18