Abstract
BackgroundSevere sepsis and septic shock are among the leading causes of death in the United States and sepsis remains one of the most expensive conditions to diagnose and treat. Accurate early diagnosis and treatment can reduce the risk of adverse patient outcomes, but the efficacy of traditional rule-based screening methods is limited. The purpose of this study was to develop and validate a machine learning algorithm (MLA) for severe sepsis prediction up to 48 h before onset using a diverse patient dataset.MethodsRetrospective analysis was performed on datasets composed of de-identified electronic health records collected between 2001 and 2017, including 510,497 inpatient and emergency encounters from 461 health centers collected between 2001 and 2015, and 20,647 inpatient and emergency encounters collected in 2017 from a community hospital. MLA performance was compared to commonly used disease severity scoring systems and was evaluated at 0, 4, 6, 12, 24, and 48 h prior to severe sepsis onset.Results270,438 patients were included in analysis. At time of onset, the MLA demonstrated an AUROC of 0.931 (95% CI 0.914, 0.948) and a diagnostic odds ratio (DOR) of 53.105 on a testing dataset, exceeding MEWS (0.725, P < .001; DOR 4.358), SOFA (0.716; P < .001; DOR 3.720), and SIRS (0.655; P < .001; DOR 3.290). For prediction 48 h prior to onset, the MLA achieved an AUROC of 0.827 (95% CI 0.806, 0.848) on a testing dataset. On an external validation dataset, the MLA achieved an AUROC of 0.948 (95% CI 0.942, 0.954) at the time of onset, and 0.752 at 48 h prior to onset.ConclusionsThe MLA accurately predicts severe sepsis onset up to 48 h in advance using only readily available vital signs extracted from the existing patient electronic health records. Relevant implications for clinical practice include improved patient outcomes from early severe sepsis detection and treatment.
Highlights
Severe sepsis and septic shock are among the leading causes of death in the United States and sepsis remains one of the most expensive conditions to diagnose and treat
In response to the need for externally validated machine learning-based sepsis screening methods, this study evaluates the performance of our machine learning algorithm (MLA) which predicts and detects severe sepsis using data extracted from patient Electronic Health Records
To determine the onset time of severe sepsis, we identified the first time at which “organ dysfunction caused by sepsis,” with sepsis defined as “the presence of two or more Systemic Inflammatory Response Syndrome (SIRS) criteria paired with a suspicion of infection” [3] was present in the patient chart
Summary
Severe sepsis and septic shock are among the leading causes of death in the United States and sepsis remains one of the most expensive conditions to diagnose and treat. Accurate early diagnosis and treatment can reduce the risk of adverse patient outcomes, but the efficacy of traditional rule-based screening methods is limited. Severe sepsis and septic shock are a dysregulated response to infection, and they are among the leading causes of death in the United States. Multiple studies have shown that accurate early diagnosis and treatment, including sepsis bundle compliance, can reduce the risk of adverse patient outcomes from severe sepsis and septic shock [4,5,6]. Earlier detection and more accurate recognition of patients at high risk of developing severe sepsis or septic shock provide a valuable window for effective sepsis treatments. Oncology patients are nearly ten times more likely to develop sepsis when compared to patients with no cancer history [8], and patients with sepsis that developed during hospitalization experience a 23% higher mortality rate than patients with community-acquired sepsis [9, 10]
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call