Neumarker and Cortica signed a strategic collaboration on October 15 to test whether a large-scale EEG foundation model can predict which autism therapies work for which children.
Neumarker builds an AI-native brain intelligence platform around EEG foundation models. Cortica runs a physician-led, whole-child care model for children with autism and other developmental differences, employing more than 2,300 clinicians and serving over 20,000 patients a year. It also holds one of the larger longitudinal datasets in neurodevelopmental care.
The arrangement pairs de-identified clinical data with the brain wave model, with patient privacy and research requirements written into the terms.
The clinical problem is heterogeneity. Children with autism can respond very differently to identical interventions, and clinicians have few objective tools for guessing in advance.
“We hope to identify biomarkers that can support a more personalized approach to care,” said Ken Wang, Neumarker’s co-founder and CEO.
Neil Hattangadi, Cortica’s co-founder and CEO, described the goal as matching the right interventions to the right children at the right time.
Neumarker’s lead application, NMK-001, is in development for epilepsy. Extending the same platform into autism would test whether EEG signals generalize across neurological conditions or stay bound to seizure detection.
Kevin Shapiro, co-director of the Cortica Innovation Network, said the aim is to find measurable patterns of brain activity that explain variability and predict treatment response.
For payers and health plans already funding value-based autism contracts, the promise is a biomarker that could eventually justify which children get which intensity of care. No timeline or commercial terms were disclosed.
