Abstract Background: Natural Language Processing (NLP) is widely used to extract clinical
insights from Electronic Health Records (EHRs). However, the lack of annotated data …

Objective Social determinants of health (SDoH) are nonclinical dispositions that impact
patient health risks and clinical outcomes. Leveraging SDoH in clinical decision-making can …

Objectives To assess fairness and bias of a previously validated machine learning opioid
misuse classifier. Materials & Methods Two experiments were conducted with the classifier's …

Background Topic modeling approaches allow researchers to analyze and represent written
texts. One of the commonly used approaches in psychology is latent Dirichlet allocation …

Opioid use disorders (OUDs) are diseases of the brain with behavioral, psychological,
neurobiological, and medical manifestations. Vulnerability to OUDs can be affected by …

Background A mounting body of evidence suggests that polysubstance use (PSU) is
common among people who use opioids (PWUO). Measuring PSU, however, is statistically …

Objective Accurate and rapid phenotyping is a prerequisite to leveraging electronic health
records for biomedical research. While early phenotyping relied on rule-based algorithms …

Identification of patient subtypes from retrospective Electronic Health Record (EHR) data is
fraught with inherent modeling issues, such as missing data and variable length time …

Persons with drug use disorders are an underserved and stigmatized population, and the
COVID-19 pandemic could exacerbate these issues. The discussion around those with drug …

PURPOSE There is an unmet need to empirically explore and understand drivers of cancer
disparities, particularly social determinants of health. We explored natural language …