Scientists Use AI to Detect Adhd Through Unique Visual Rhythms
Posted3 months agoActive3 months ago
psypost.orgResearchstory
calmpositive
Debate
10/100
AI in HealthcareAdhd DiagnosisMachine Learning
Key topics
AI in Healthcare
Adhd Diagnosis
Machine Learning
Researchers have used AI to detect ADHD through unique visual rhythms, achieving a groundbreaking result that sparks interest in the potential applications of AI in medical diagnosis.
Snapshot generated from the HN discussion
Discussion Activity
Light discussionFirst comment
2h
Peak period
2
2-3h
Avg / period
2
Key moments
- 01Story posted
Oct 13, 2025 at 4:34 AM EDT
3 months ago
Step 01 - 02First comment
Oct 13, 2025 at 7:04 AM EDT
2h after posting
Step 02 - 03Peak activity
2 comments in 2-3h
Hottest window of the conversation
Step 03 - 04Latest activity
Oct 13, 2025 at 7:21 AM EDT
3 months ago
Step 04
Generating AI Summary...
Analyzing up to 500 comments to identify key contributors and discussion patterns
ID: 45566131Type: storyLast synced: 11/20/2025, 4:38:28 PM
Want the full context?
Jump to the original sources
Read the primary article or dive into the live Hacker News thread when you're ready.
Their control group almost certainly has some people with undiagnosed ADHD, and although they don’t describe their recruitment methods, I suspect they (unintentionally but knowingly—the participants are all college students) excluded a lot of folks through how they identified potential participants.
They fact that three quarters of their ADHD participants were on stimulant medication already indicates they’ve oversampled on those folks, and honestly I’m guessing their stats reflect more the effect of Adderall and Ritalin on visual processing than they do the effects of ADHD.
But one of the things that’s often misunderstood about ADHD is that whatever the physical underpinnings of the sorts of neurodivergence that get classified as “ADHD symptoms”, a key aspect of whether or not someone “has ADHD” is not whether their brain functions in a different way that “typical” people, but instead whether or not those symptoms cause regular distress in their daily lives.
In other words, you may exhibit many of the physical and behavioral markers of ADHD but if those traits aren’t making you struggle, then you don’t “have ADHD”. And so any physical test is going to be unable to ever be entirely reliable, because there are lots of folks living their lives who would flag on the test but who don’t “have ADHD”. The study results even hints at that with a much worse rate of identifying neurotypicals successfully.