What does this research mean for the field?

The NarxCare® opioid risk scoring system exhibits significantly low precision and F1 scores, indicating poor predictive performance despite the inclusion of socioeconomic covariates. Novelty: ClaimNovelty.NOVEL_FINDING. Consensus alignment: ConsensusAlignment.CHALLENGES_CONSENSUS.

What question did this study set out to answer?

The study aims to evaluate the effectiveness of the NarxCare opioid risk scoring system and identify issues related to algorithmic opacity.

February 26, 2026npj Digital Medicine0 citationsOpen Access

Algorithmic opacity in opioid risk scoring and the need for transparent AI regulation

SWSichao Wang RSRyan Stofer ZCZhouzhou Chu

Key Points

The study aims to evaluate the effectiveness of the NarxCare opioid risk scoring system and identify issues related to algorithmic opacity.
Applied NarxCare specifications to PDMP and IQVIA PharMetrics® Plus Closed Health Plan claims data.
Included socioeconomic covariates in the analysis.
Assessed precision and F1 scores of reconstructed models.
Precision scores ranged from 0.01 to 0.32, significantly below the benchmark of 0.75.
F1 scores ranged from 0.02 to 0.39, falling short of the benchmark value of 0.65.
Model performance remained low, suggesting substantial inadequacies in risk scoring.

Abstract

Abstract NarxCare®, a proprietary opioid risk scoring system embedded in Prescription Drug Monitoring Programs (PDMPs), has generated significant patient complaints. We adhered to the technical specifications and applied them to PDMP and IQVIA PharMetrics® Plus Closed Health Plan claims database. Despite adding socioeconomic covariates, precision (0.01–0.32) was far below the reported benchmark of 0.75, and F1 scores (0.02–0.39) were also substantially lower than the benchmark value of 0.65, across all our reconstructed models.

AI에게 질문

Bookmark

View Full Paper