> ## Content Index
> Fetch the complete content index at: https://www.fdaweb.com/llms.txt
> Use this file to discover other available public pages before exploring further.

# FDA Uses Machine Learning to Identify Opioid CV Signals
- URL: https://www.fdaweb.com/fda-uses-machine-learning-to-identify-opioid-cv-signals/
- Published: 2026-10-13T20:41:22.000Z
- Updated: 2026-10-13T20:41:22.000Z
- Author: David McFarland
- Tags: Drugs

FDA researchers and academic collaborators identified nearly 80,000 prescription opioid-related cardiovascular adverse event signals in a large-scale analysis of the agency's Adverse Event Reporting System, suggesting that machine learning could improve postmarketing drug safety surveillance.

The [study](https://www.frontiersin.org/journals/drug-safety-and-regulation/articles/10.3389/fdsfr.2026.1898403/full?ref=fdaweb.com), published September 28 in *Frontiers in Drug Safety and Regulation*, analyzed about 18.4 million adverse event reports submitted between 2004 and the third quarter of 2024.

Researchers identified 79,620 opioid-cardiovascular adverse event pairs meeting their statistical signal criteria, involving 15 FDA-approved opioid groups and 291 distinct cardiovascular events. Fentanyl and oxycodone accounted for the largest numbers of reported cardiovascular events, while hypertension, hypotension, cardiac arrest, cardiorespiratory arrest and tachycardia were the most frequently reported event types.

Using empirical Bayesian signal detection, network analysis and machine learning-based clustering, the researchers say they identified similarities in cardiovascular adverse event reporting patterns among several opioids, including fentanyl, remifentanil, sufentanil and morphine.

The authors said combining traditional pharmacovigilance methods with machine learning could help FDA identify cardiovascular safety patterns that might otherwise be overlooked and support more targeted safety monitoring and labeling assessments.

The findings are based on spontaneous adverse event reports, which cannot establish causation or determine the incidence of cardiovascular complications among opioid users, they note.