Login / Signup

Predicting the Incidence of Pressure Ulcers in the Intensive Care Unit Using Machine Learning.

Eric M CramerMartin G SeneviratneHusham SharifiAlp OzturkTina Hernandez Boussard
Published in: EGEMS (Washington, DC) (2019)
We demonstrate that an EHR-based model can outperform the Braden score as a screening tool for PUs. This may be a useful tool for automatic risk stratification early in an admission, helping to guide quality protocols in the ICU, including the allocation and timing of prophylactic interventions.
Keyphrases
  • intensive care unit
  • emergency department
  • risk factors
  • deep learning
  • electronic health record
  • physical activity
  • machine learning
  • mechanical ventilation