Publications by authors named "C Ertmer"

Introduction: Herpes simplex virus (HSV) is frequently detected in the respiratory tract of mechanically ventilated patients and is associated with a worse outcome. The aim of this study is to determine whether antiviral therapy in HSV-positive patients improves outcome.

Methods And Analysis: Prospective, multicentre, open-label, randomised, controlled trial in parallel-group design.

View Article and Find Full Text PDF
Article Synopsis
  • Scientists looked at health data from very sick patients with a condition called sepsis to see if machine learning can help predict who might survive better than using regular methods.
  • They tested two machine learning methods using data from a big group of patients and found that these methods were much better at predicting survival than the standard way of checking changes in scores.
  • The results showed that using daily scores from the first week could really help doctors know who might be in trouble, which could lead to better patient care in the future.
View Article and Find Full Text PDF

Background: Based on the Kidney Disease: Improving Global Outcomes (KDIGO) definitions, urine output, serum creatinine, and need for kidney replacement therapy are used for staging acute kidney injury (AKI). Currently, AKI staging correlates strongly with mortality and can be used as a predictive tool. However, factors associated with the development of AKI may affect its predictive ability.

View Article and Find Full Text PDF

Background: Sepsis is a life-threatening organ dysfunction caused by a dysregulated host response to infection. Mortality of patients with sepsis is high and largely unchanged throughout the past decades. Animal models have been widely used for the study of sepsis and septic shock, but translation into effective treatment regimes in the clinic have mostly failed.

View Article and Find Full Text PDF

Background: Intensive care unit (ICU) readmissions are associated with mortality and poor outcomes. To improve discharge decisions, machine learning (ML) could help to identify patients at risk of ICU readmission. However, as many models are black boxes, dangerous properties may remain unnoticed.

View Article and Find Full Text PDF