In this study, we will use various machine learning methods to predict the outcomes of non-operative management of small bowel obstructions.
An analysis of all patients at UPMC Presbyterian Shadyside over the past 10 years to develop a demographic profile of patients with Clostridium difficile infection, as well as to identify predictors of a complicated disease course. The study will also include the development of computable phenotypes of disease (phekb.org) for both routine and complicated Clostridium difficile infection.
Venous thromboembolic disease (VTE), which encompasses deep vein thrombosis (DVT) and pulmonary embolism (PE), is a common and preventable source of post-operative morbidity and mortality. The high incidence of VTE reflects both underutilization of standard thromboprophylactic regimens and also an incomplete understanding of how surgery and critical illness affect the risk of post-operative VTE over time.