NutriSighT: Interpretable Transformer Model for Dynamic Prediction of Hypocaloric Enteral Nutrition in Mechanically Ventilated Patients.

Achieving adequate enteral nutrition among mechanically ventilated patients is challenging, yet critical. We developed NutriSighT, a transformer model using learnable positional coding to predict which patients would achieve hypocaloric nutrition between days 3-7 of mechanical ventilation. Using retrospective data from two large ICU databases (3,284 patients from AmsterdamUMCdb - development set, and 6,456 from MIMIC-IV - external validation set), we included adult patients intubated for at least 72 hours.

The epidemiology of midline-associated bloodstream infections in an urban health care system.

This study sought to determine the incidence and characteristics of midline-associated bloodstream infections (MABSI) at an urban health system during the COVID-19 pandemic. A MABSI rate similar to the central line-associated bloodstream infection rate was found. A large number of MABSI were caused by Staphylococcus spp and Enterococcus spp, as has previously been reported for central line-associated bloodstream infection.