Early Prediction of Sepsis in Intensive Care Patients Using the Machine Learning Algorithm NAVOY® Sepsis, a Prospective Randomized Clinical Validation Study

Background: The objective of this study was to prospectively validate, in an ICU setting, the prognostic accuracy of the machine learning sepsis prediction algorithm NAVOY® Sepsis. The algorithm uses, on an hourly basis, 4 hours of input for up to 20 routinely collected vital parameters, blood gas values, and lab values, to predict the development of sepsis in the coming hours. Methods Patients aged 18 years or older admitted to the ICU at Skåne University Hospital Malmö from December 2020 to September 2021 were recruited in the study, with all available ICU beds monitored with the algorithm NAVOY® Sepsis. A total of 304 patients were randomized into one of two groups: Algorithm group with active sepsis alerts, or Standard of care. NAVOY® Sepsis made silent predictions in the Standard of care group, in order to evaluate its performance without disturbing the outcome. The study was blinded, i.e., study personnel did not know to which group patients were randomized. The healthcare provider followed standard practices in assessing possible development of sepsis and intervening accordingly. The patients were followed-up in the study until ICU discharge. Results In this study, NAVOY® Sepsis could predict the development of sepsis, according to the Sepsis-3 criteria, three hours before sepsis onset with high performance: accuracy 0.79; sensitivity 0.80; and specificity 0.78. The primary analysis was performed on all patients from the Standard of care group that had enough data for the algorithm to make a prediction 3 hours before sepsis onset (n = 85). Conclusions The accuracy, sensitivity, and specificity were all high, validating the prognostic accuracy of NAVOY® Sepsis in an ICU setting, including Covid-19 patients. Trial registration Registered at ClinicalTrials.gov September 30, 2020; NCT04570618.