David PerlmutterPresident,, Perlmutter Health Center · Board-Certified Neurologist | Functional Medicine Pioneer | #1 New York Times Best-Selling Author | International Speaker | Host of The Empowering Neurologist Podcast

June 23, 2026

23 Jun 2026 · 1 min

Watch on YouTube

0:58

In this presentation, the speaker describes a real-world clinical case where a patient with worsening leg pain and sleep disturbances—initially attributed to restless‑leg syndrome—was evaluated by an AI diagnostic assistant. The AI recommended testing for arsenic, explaining that the patient is homozygous for a slow‑acting variant of the AS3MT gene, which impairs methylation and elimination of arsenic. The patient lives in a former mining town with known soil contamination of arsenic and cadmium. The AI also detected emerging insulin resistance despite the patient being lean and active, linking it to arsenic exposure. The physician, puzzled by the constellation of findings, was guided by the AI to consider environmental toxicology as the underlying cause.

Chapters

We have one real-world example of a patient who was suffering from increasing leg pain and sleep disturbances. His physician thought was just a worsening of his longstanding restless leg syndrome. And the AI came up and said, test for arsenic. And his physician was like, why for arsenic? And the AI is able to explain. This guy is homozygous for a slow-acting version of a gene called AS3MT that methylates arsenic, which is critical for its elimination from the body. And he lives in an area that's a former mining town where the soil is known to be contaminated with arsenic and cadmium. And the coolest thing was the AI noticed he was becoming insulin resistant despite being very trim and active. And his primary care physician was just scratching his head. And it's because elevated arsenic induces insulin resistance.