To develop the predictive model, a team of researchers from Denver Health Medical Center and various University of Colorado campuses analyzed EHR data from patients who were hospitalized at an urban safety-net hospital between 2008 and 2014. The team considered variables such as medical diagnoses, mental health diagnoses, smoking status, chronic pain, acute pain, surgical interventions and past year receipt of opioids when building its model.
The final model, which included 13 covariates, accurately predicted chronic opioid use in 79 percent of patients. It accurately predicted no chronic opioid use in 78 percent of patients.
“Application of such a predictive model within the EHR could identify patients at high risk for future chronic opioid use to allow clinicians to provide early patient education about pain management strategies and, when able, to wean opioids prior to discharge while incorporating alternative therapies for pain into discharge planning,” the study authors concluded.
More articles on data analytics & precision medicine:
NantHealth reports 300% increase in genetic analysis revenue since 2016: 4 things to know
IBM releases new cloud platform for data science, machine learning
IQVIA Institute for Human Data Science: 10 innovation, tech predictions on healthcare transformation
