BrainYears™ was developed in collaboration with the Buck Institute for Research on Aging. Our initial model was trained across the adult lifespan and tested on a held-out set of participants it never saw during training, reaching a Pearson correlation of 0.92 and a mean absolute error of 4.4 years: gold-standard MRI brain age accuracy, from a headset rather than a scanner. The full methodology, including the study cohorts, is in our pre-published paper on bioRxiv:
The model is currently being re-run on our substantially larger longitudinal dataset.
Was this article helpful?
That’s Great!
Thank you for your feedback
Sorry! We couldn't be helpful
Thank you for your feedback
Feedback sent
We appreciate your effort and will try to fix the article