The research team estimated that about 75 percent of online pharmacies are illicit. However, many consumers may not have the knowledge or medical literacy to flag these merchants as illegitimate, which could lead to risks such as purchasing opioids without a prescription or receiving the wrong dosage.
“It’s very challenging to develop these tools for two reasons,” Hui Zhao, PhD, a member of the research team, said in an Aug. 27 news release. “First is just the huge scale of the problem. There are at least 32,000 to 35,000 online pharmacies. Second, the nature of online channels because these online pharmacies are so dynamic. They come and go quickly — around 20 a day.”
To develop the algorithm, the Penn State team created a baseline of what a legitimate online pharmacy looks like, to which they compared all other online pharmacies they encountered. They also took referral websites into consideration, as online pharmacies that are referred by a site that links mostly to illicit pharmacies are likely to be illegitimate.
The researchers hope the algorithm can be used as a warning system, so consumers can be alerted that the pharmacy they are engaging with is illegitimate before they make a purchase. They also see potential for search engines, social media sites and online markets to use the algorithm to remove or filter the visibility of illicit pharmacies.
More articles on health IT:
Defense Health Agency launches AI project for cancer detection
Penn Medicine AI assists global consortium’s COVID-19 data model: 4 notes
AMA: IT experts must enlist medical ethicists, clinicians to strike potential biases in AI health tech
