Annals of emergency medicine
-
Multicenter Study
Early Prediction of Acute Kidney Injury in the Emergency Department With Machine-Learning Methods Applied to Electronic Health Record Data.
Acute kidney injury occurs commonly and is a leading cause of prolonged hospitalization, development and progression of chronic kidney disease, and death. Early acute kidney injury treatment can improve outcomes. However, current decision support is not able to detect patients at the highest risk of developing acute kidney injury. We analyzed routinely collected emergency department (ED) data and developed prediction models with capacity for early identification of ED patients at high risk for acute kidney injury. ⋯ Machine learning applied to routinely collected ED data identified ED patients at high risk for acute kidney injury up to 72 hours before they met diagnostic criteria. Further prospective evaluation is necessary.
-
Review Meta Analysis
Outcome of Immediate Versus Early Antibiotics in Severe Sepsis and Septic Shock: A Systematic Review and Meta-analysis.
Debate exists about the mortality benefit of administering antibiotics within either 1 or 3 hours of sepsis onset. We performed this meta-analysis to analyze the effect of immediate (0 to 1 hour after onset) versus early (1 to 3 hours after onset) antibiotics on mortality in patients with severe sepsis or septic shock. ⋯ We found no difference in mortality between immediate and early antibiotics across all patients. Although the quality of evidence across studies was low, these findings do not support a mortality benefit for immediate compared with early antibiotics across all patients with sepsis.