Applying supervised machine learning to opioid risk scoring systems in healthcare reveals significant performance gaps, suggesting urgent AI regulatory needs.
Abstract NarxCare®, a proprietary opioid risk scoring system embedded in Prescription Drug Monitoring Programs (PDMPs), has generated significant patient complaints. We adhered to the published technical specifications and applied them to two large-scale real-world datasets: California’s PDMP and IQVIA PharMetrics® Plus claims. Despite reconstructing the documented feature set, adding socioeconomic covariates, and rigorously evaluating multiple supervised machine learning architectures, all models performed well below reported benchmarks.
No takes yet. Share an insight, caveat, or question.
Wang et al. (2025) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: