AI can help us figure out what psychedelic drugs are hitting our brains by analyzing words used in trip reports

Randomized clinical trials, which involve giving some participants the drug and others a placebo and comparing the effects of the two, are considered the gold standard in such studies.

But such trials are slow and expensive, and tend to involve only a small number of participants. “[It takes] years, costing a seven-figure sum, [and] Bzdok said.

Instead, his team used natural language processing to evaluate 6,850 written accounts of hallucinogenic drug use. Each account was written by someone who took one of 27 drugs — including ketamine, MDMA, LSD, and psilocin — in a real-world setting rather than as part of a lab test. Accounts accessed from ‘s website Erowida member-supported drug information organization.

Bzdok’s team then integrated this data with a profile of the receptors in the brain that each drug is known to interact with. Together, these steps allowed the team to determine which neurotransmitter receptors were associated with words associated with specific drug experiences.

For example, words associated with mystical experiences, such as “space,” “universe,” “consciousness,” “dimensionality,” and “breakthrough” are associated with drugs that link with specific dopamine, serotonin, and opioid receptors.

Bzdok says this approach could provide new starting points for drug development. In theory, drugs designed to target these receptors should elicit specific aspects of the hallucinogenic drug experience, says Bzdok, whose work is published today in the journal Psychiatry. said. Scientific advance.

Frederick Barrett, a psychedelic neuroscientist at Johns Hopkins University in Baltimore, is not entirely convinced. “People don’t always know [what drug they’re taking],” he says. “Dosage isn’t always calibrated well in the real world, and there’s a lot of variation that comes into the real-world experience that might even be fully realized.”