How Smarter Data Could Transform Opioid Safety: A New Model for Pharmacists

Pharmacists and health care providers have numerous means to monitor and evaluate prescribing effectiveness for patients who need opioids. Currently, the FDA mandates the use of Risk Evaluation and Mitigation Strategies (REMS) and Prescription Drug Monitoring Programs (PDMPs) to help practitioners prescribe and dispense these high-risk drugs more safely. Although these programs provide important information, illicit use, overdoses, and deaths still occur.

In the past 15 years, the US has experienced a drastic increase in the number of opioid-related deaths. From 1 death per 100,000 individuals in 2013 to 9.9 per 100,000 in 2018, rates have continued to rise. This is largely due to the decrease in legitimate opioid prescriptions and the illegal manufacture of fentanyl and fentanyl-like drugs. In 2022, US overdose deaths numbered more than 80,000, with almost 90% of them attributable to synthetic opioids. In addition to the tragic loss of life, the health care costs associated with this crisis are enormous—more than $1 trillion in 2017.^1,2

Although both REMS and PDMPs are valuable tools in the fight against inappropriate drug use or misuse, they have limitations and often do not include real-world data (RWD). REMS, while effective in focusing on provider education and patient observation, tend to ignore the social determinants of health (SDOH) factors associated with opioid misuse. Some examples of SDOH include access to pharmacies or medical treatment facilities, employment status, and poverty. State-run PDMPs provide data to medical personnel and those in law enforcement on the prescribing and dispensing of opioids, but only 13 states can share this information in real time.¹

A proposal was recently printed in Therapeutic Innovation and Regulatory Science identifying a method integrating these 2 programs and RWD to improve predictions of prescription opioid misuse. The paper proposed a 4-part model aimed at providing better information to diminish opioid misuse and is summarized in Table 1.¹

In the first pillar, the researchers would develop an artificial intelligence (AI) and machine learning (ML) process to incorporate all RWD gathered from regulatory systems and SDOH to better predict which individuals are at a higher risk of overdose. As data from some studies have shown that socioeconomic factors and the existence of pharmacy deserts correlate with higher rates of opioid misuse, this pillar is intended to eliminate further biases.

The second pillar involves adaptive licensing with evolving labels, which uses the FDA’s current strategy for drug labeling that requires manufacturers of opioid medications to collect RWD on opioid misuse, addiction, overdose, mortality, and safety. Under this pillar, the FDA would authorize swift labeling changes (dynamic label modifications) to reflect the risks of opioid use. Legal protections for manufacturers who embrace this concept would also be established in this second pillar.

The third pillar recommends leveraging pharmacists’ expertise with new technologies to help identify patterns of misuse. They propose using blockchain technology, coupled with state-run PDMPs, to provide real-time and Health Insurance Portability and Accountability Act (HIPAA)–compliant data transmission and sharing to detect inappropriate opioid use. With additional support and certification training, pharmacists and pharmacist-led teams can be integral to the solution.

In the fourth pillar, local agencies would partner with regulators to test illicit drugs, identify their components, and provide feedback to local health providers, thereby minimizing patient harm. The widespread availability of naloxone and additional patient interventions has been shown to decrease emergency department use in this population and reduce overdose deaths.

The researchers designed a simulated experiment of 8000 hypothetical patients to test the proposed model’s efficacy. The results showed that this AI-driven program, accompanied by ML, was able to forecast potential overdoses earlier and more effectively than current methods and warrants further exploration and implementation.

REFERENCES

1. Rana A, Ram K. Beyond REMS & PDMPs: a proposed framework for next-generation opioid regulation. Ther Innov Regul Sci. 2026;60(1):63-74. doi:10.1007/s43441-025-00882-z

2. Understanding the opioid overdose epidemic. CDC. June 9, 2025. Accessed February 25, 2026. https://www.cdc.gov/overdose-prevention/about/understanding-the-opioid-overdose-epidemic.html