Exploring secondary healthcare data to evaluate opioid prescriptions and identify opioid use disorder (OUD) in high-risk patients
No Thumbnail Available
Authors
Meeting name
Sponsors
Date
Journal Title
Format
Thesis
Subject
Abstract
[EMBARGOED UNTIL 12/01/2025] Over the past two decades, the United States has faced a surge in dose- dependent adverse events from prescription opioids, resulting in increased morbidity and mortality. Despite the documented risks and limited analgesic benefits, high-dose opioid prescriptions persist, particularly among vulnerable populations. This study leverages real-world electronic health records (EHR) and Medicaid administrative claims data to analyze and address the complex dynamics of opioid prescriptions and Opioid Use Disorder (OUD) using advanced artificial intelligence (AI) techniques. This dissertation is organized around three primary aims. First, AI models were developed to uncover sociodemographic and socioeconomic factors linked to high- dose opioid prescriptions, surpassing traditional statistical methods. Second, time- aware deep learning models, including Long Short-Term Memory (LSTM) networks, were deployed to analyze clinical characteristics and temporal patterns in patients prescribed medium to high-dose opioids who later developed OUD. Third, the Project Extension for Community Healthcare Outcomes (ECHO) telemonitoring program was evaluated for its effectiveness in improving prescribing patterns and reducing inappropriate opioid use. The findings demonstrate the potential of AI-based approaches in early identification of OUD risk, with the LSTM model capturing critical temporal dependencies and providing actionable insights into clinical encounters and risk factors associated with OUD. This research highlights the role of AI in facilitating targeted interventions to reduce high-risk opioid prescribing, identify at-risk patients earlier, and manage complex clinical cases. By integrating AI into healthcare, this research contributes significantly to public health, clinical practice, and policymaking. It enhances understanding of OUD risk factors in vulnerable populations, improves patient monitoring, and promotes safer opioid prescribing practices.
Table of Contents
DOI
PubMed ID
Degree
Ph. D.