Poster presented June 4, 2026, at the Nursing Knowledge Big Data Science Conference held in Minneapolis.
Learning Objectives:
1. Describe the role of data harmonization strategies in unifying multi-modal pharmacogenomic and perioperative clinical data streams for analysis.
2. Explain how dynamic longitudinal modeling shifts perioperative risk assessment from static predictions to anticipatory risk stratification.
Introduction: Postoperative adverse events (PAEs) are dynamic, non-linear processes; however, current predictive models frequently treat them as static endpoints instead of evolving risk trajectories.1,2A significant barrier to precision anesthesia is the informatics silo between high-dimensional pharmacogenomic (PGx) variants (i.e., genetic influences on drug response) and dense, longitudinal electronic health record (EHR) time-series data. Analyzing these data in isolation limits the early identification of patients at high risk for complications, such as respiratory depression or delayed emergence from anesthesia.3 This conceptual framework, the Pharmacogenomic-Clinical Data Integration (PCDI), addresses this gap by employing multi-modal data streams, specifically PGx markers and EHR perioperative clinical records, creating a unique dataset that supports advanced longitudinal modeling of postoperative recovery and adverse events.
Full abstract available in the conference proceedings, available online and as a downloadable PDF. See link below.