In the U.S., more than one in five drug prescriptions are for off-label indications. Better tracking of these unapproved uses could help medical researchers identify potentially dangerous uses and prioritize promising ones for further study and eventual approval.
Prescription records don’t usually indicate the condition a drug is intended to treat, but physicians’ clinical notes are likely to include this information. Researchers at Stanford developed a new method to extract off-label uses from 9.5 million de-identified clinical records collected at Stanford since 1994. Their study was published online today in PLOS ONE.
To prioritize these uses for further study, the researchers took into account the cost of each drug and its risk of causing adverse reactions. They used these two parameters to rank each drug use. “Then we placed them into good and bad buckets,” Shah said. The “bad bucket” of high-cost, high-risk uses should raise red flags that prompt re-evaluation by physicians and regulators.
Lead author Kenneth Jung, a graduate student in biomedical informatics, was surprised by how many of the novel uses were predictable based on prior knowledge.
“A lot of it actually made sense,” he said. “We should have known about some of these uses already. This gives us confidence that the method we developed works.”
Among the low-risk prescriptions, folic acid was used to treat a wide range of conditions, while several immunosuppressants and anti-tumor agents were classified as especially high-risk. To test the robustness of their findings, the researchers plan to apply the same method to electronic medical records from other hospitals and compare their results.
Previously: Clinical informatics gains recognition as new medical sub-specialty, Stanford researchers use data mining to show safety of peripheral artery disease treatment and Studies document risky use of powerful clotting drug
Photo by Erin DeMay