Reading about a disease does not mean you have it.
You could be researching for a relative.
You could be writing an article.
You could be curious.
A tracking system may still find the visit valuable.
Browsing can reveal a probable concern without proving a condition
Health-related websites can expose unusually sensitive context simply through the pages a person visits.
A URL, page title, tracking event, search term, or advertising pixel may indicate that somebody viewed information about depression, fertility, cancer, addiction, medications, sexual health, or another medical subject.
The Federal Trade Commission’s technology staff has highlighted this problem directly. In a 2023 analysis of pixel tracking following the GoodRx and BetterHelp enforcement actions, the FTC explained that embedded tracking technologies can collect user activity and enable companies to analyze and infer information from it. See Lurking Beneath the Surface: Hidden Impacts of Pixel Tracking.
The signal is meaningful.
It is not necessarily true in the way a medical record is true.
That difference matters.
A visit can be commercially useful even when it is ambiguous
The FTC’s BetterHelp case alleged that the service shared personal information with advertising platforms for targeting and retargeting, including information connected to people who visited the service without necessarily becoming counseling customers. See the FTC’s BetterHelp enforcement announcement.
The GoodRx case went further into confirmed health information, with the FTC alleging that medication and health-condition data was shared with advertising companies and used to target users. See the FTC’s GoodRx case.
Those cases are not identical to merely reading a health article.
They show why the advertising value exists: health-related signals can be turned into targeting categories, audience lists, or assumptions about what a person might respond to.
Inference is where the danger becomes slippery
Suppose somebody reads three pages about insulin pumps.
An advertising system might infer diabetes-related interest.
That inference could be correct.
It could also describe a parent, nurse, student, journalist, investor, or person helping a friend.
Once an inferred label enters a profile, downstream systems may not preserve that uncertainty. A probabilistic guess can start behaving like a fact because a database field needs something to put in the row.
That is the important distinction for Dead Internet Theory research:
behavioral evidence is not the same thing as a confirmed personal attribute.
The Surveillance Economy does not need to know your diagnosis with clinical certainty.
It only needs to believe a health-related label is predictive enough to sell, target, rank, or segment.
A browser history can therefore become commercially valuable long before it becomes medically meaningful.