JMIR Publications

ABSTRACT

Background:

Online pharmacies have grown tremendously in recent years, from $29.35 Billion in 2014 to an expected $128 Billion in 2023 globally. Although licit online pharmacies (LOPs) provide a channel of convenience and potentially lower costs for patients, illicit online pharmacies (IOPs) open the doors to unfettered access to prescription drugs, controlled substances (e.g., opioid), and potentially counterfeits, posing dramatic risk in drug supply chain and patient health. Unfortunately, we know very little about IOPs and even identifying and monitoring IOPs is challenging due to the scale of the problem (30,000-35,000 online pharmacies in total) and the dynamic nature of the online channel (online pharmacies come and go easily).

Objective:

This paper aims to increase our understanding of IOPs through web data and also proposes a framework to identify and track IOPs, the first step to fight IOPs.

Methods:

We first collect online traffic and engagement data to study and compare how consumers access and engage with LOPs and IOPs. We then propose a simple but novel framework for predicting online pharmacies’ status (licit or illicit) through the referral links between the websites. Under this framework, we develop two prediction models, the Reference Rating Prediction Method (RRPM) and the Reference-based K Nearest Neighbor (RKNN).

Results:

We find that Direct (typing URL), Search, and Referral are the three major traffic sources, representing more than 95% traffic to both LOPs and IOPs. It is alarming to see that Direct represents the second highest traffic source (34.32%) to IOPs. When tested on a dataset with 763 online pharmacies, both RRPM and R2NN perform very well, achieving an accuracy above 95% in their predictions of the status of the OPs. When we implement the two models on Google search results for three popular drugs, two of which directly related to opioid, they produced an error rate of only 7.96% and 6.20%, respectively.

Conclusions:

Our model has many potential applications for search engines, social media, payment companies, policy makers/government agencies, and drug manufacturers, to help fight IOPs. With scarce work in this area, we hope to help address the current opioid crisis from this perspective and also inspire future research in the critical area of drug safety.