Journal of the American Medical Informatics Association (JAMIA)

Artificial intelligence predicts opioid overdose in Tennessee

Researchers at Vanderbilt and the Tennessee Department of Health have developed 30-day predictive models for fatal and non-fatal opioid-related overdose among patients receiving opioid prescriptions in the state.

Interventions such as daily spontaneous waking trials can help patients avoid injuries associated with intensive care.

AI predicts next-day delirium or coma in ICU patients

A team at Vanderbilt University Medical Center used machine learning to predict the likelihood of next-day brain function status changes in critical care patients.

Strength in numbers

Voluntary data sharing across a region’s health systems and ambulatory care practices is important for measuring and improving health care quality and safety, Vanderbilt researchers report.

Building a cohort, the easy way

An automated system using keyword searches can help identify candidates for clinical trials on adverse drug reactions.

Model students: improving clinical decision-making

Vanderbilt investigators have devised a system to alert health IT teams to deteriorating performance in clinical prediction models.

New tool rapidly identifies health records for studies

Electronic health records (EHR) are increasingly a resource for biomedical discovery, and automated searches for records that reflect a phenotype of interest, typically a disease, are a common starting point.

1 2 3