Development and external validation of a delirium prediction model for hospitalized patients with COVID-19
Abstract
The coronavirus disease 2019 pandemic has placed unprecedented stress on health systems and has been associated with elevated risk for delirium. The convergence of pandemic resource limitation and clinical demand associated with delirium requires careful risk stratification for targeted prevention efforts.
BOSTON – CIDH is proud to announce the publication into the Journal of the Academy of Consultation-Liaison Psychiatry by Dr. Thomas McCoy and his team. The team’s objective was to develop a predictive model for incident delirium among patients with the 2019 coronavirus disease. When applying supervised machine learning to develop the incident delirium predictive model across 6 hospitals, they found that 16.8% (488 out of 2907 COVID-19 patients) developed delirium.
The team found that the use of their predictive model when applied to hospitalized patients with COVID-19 can be effectively used to assess the risk to develop incident delirium.
