AI and Decision-Theoretic Methods for Medication Safety Management
OVERVIEWA scoping review of analytical approaches for medication management and patient safety identified 64 unique studies, over half published since 2020. Among these, 49% addressed adverse drug event detection or prediction, 24% focused on medication error detection, and 13% examined medication reconciliation or review. Despite widespread application of AI methods, only 7 studies used decision-theoretic frameworks and just 5 combined both approaches, revealing a significant methodological gap. The review found a predominant focus on single-drug event detection with limited research on managing incomplete or inaccurate medication lists across patient encounters—a common real-world challenge. The literature reflects the need for future work combining predictive, prescriptive, and generative analytics, integrating traditional machine learning, generative AI, and decision-theoretic methods for more comprehensive medication safety management. A complementary study using ensemble learning for adverse drug combination prediction achieved 93.6% accuracy, 97.9% recall, and a ROC-AUC of 97.5% using data from the FDA Adverse Event Reporting System (FAERS), demonstrating that ensemble approaches combining logistic regression, random forest, and CatBoost algorithms can effectively identify high-risk drug combinations. The model also generates confidence scores representing risk levels for specific drug combinations, supporting its use as a clinical decision support tool for polypharmacy…
Subscribe to read full wiki analysis
Full wiki content — including source provenance, contradiction tracking, related pages, and analyst notes — is available to Subscriber members.
View Plans & SubscribeNew users get a 7-day trial — no credit card required.