AI Assists VAERS Analysis for Vaccine Injury Insights

Because these claims are not verified, VAERS data alone can't be used to determine if a vaccine caused an adverse event. "VAERS, at best, was always a hypothesis-generating mechanism," says Paul Offit, a pediatrician and director of the Vaccine Education Center at Children's Hospital of Philadelphia who was previously a member of the CDC's Advisory Council on Immunization Practices. Anybody can report, and there's no control group." Offit says the system only shows adverse events that happened at some point following immunization; it doesn't prove that a vaccine caused those reactions.

CDC's own website says that a report to VAERS does not mean that a vaccine caused an adverse event. Despite this, anti-vaccine activists have misused VAERS data over the years to argue that vaccines are not safe. Leslie Lenert, previously the founding director of the CDC's National Center for Public Health Informatics, says government scientists have been using traditional natural language processing AI models to look for patterns in VAERS data for several years, so it's not surprising that HHS would move toward the adoption of more advanced large language models.

One major limitation of VAERS is that it doesn't include data on how many people received a vaccine, which can make events logged in the database seem more common than they actually are.