Hybrid CDSS Flags Anticoagulant Prescribing Errors With No Misses
This development and external validation study tests whether a hybrid rule-based plus machine learning decision support tool can reliably surface anticoagulant orders warranting pharmacist review across multiple Korean tertiary hospitals.
Hybrid CDSS boosts anticoagulant prescription safety with smart alerts.
Anticoagulants carry a high risk of bleeding errors, making effective prescription review vital to patient safety. The hybrid CDSS generated clinically relevant alerts with strong discrimination (AUC 0.871 to 0.963), and up to 57.1% required pharmacist intervention. While promising, validation period and sample limitations suggest cautious interpretation of the CDSS's broader applicability. This hybrid CDSS might enhance pharmacist-led anticoagulant review by prioritizing clinically relevant alerts.
📊 Deep Analysis Available
Subscribers get the full breakdown: study design, outcomes, pharmacist implications, clinical pearls, GRADE evidence grade, and a downloadable PDF report. Cancel anytime.
Free account, no credit card. Includes 1 full deep analysis every month.
Authors:Jeong J, Heo KN, Kim AJ, Baek JH, Jo YH, Kim S, Jo M, Ah YM, Han JM, Choi SW, Song J, Min S, Lee JY
Citation:Jeong J, Heo KN, Kim AJ, et al. A Hybrid Rule-Based and Machine Learning-Based Clinical Decision Support System to Support Prescription Review: Development and External Validation Study. Journal of medical Internet research. 2026;28:e101202. doi:10.2196/101202