LABS & RESEARCH
Applied neurodevelopmental AI research.
Labs is where we work on the hard parts of the problem before they become products — the model, the measurement, and the long arc of a child's development. Our studies and publications live here too, listed as they happen.
ND-LLM
A neurodevelopment-specific language model.
A model trained on longitudinal neurodevelopmental records rather than the open internet, built to make a decade of fragmented history legible in the minutes before an appointment.
Read the work
Screening Battery Calibration
Turning subjective observation into comparable data.
Work on making the FitQuest screening battery score consistently across different assessors, sites and sessions — so two assessments can actually be compared.
Read the work
Developmental Trajectory Modelling
Reading the shape of change, not the snapshot.
Early research into modelling a child's developmental path over years — detecting when a trajectory bends, and when a bend is worth a clinician's attention.
Read the work
Cross-Linguistic Screening
Screening that survives the language it's given in.
Exploratory work on developmental screening across the many languages and dialects families actually speak, where a translated instrument is not the same instrument.
Read the workA neurodevelopmental data moat, and the ND-LLM built on top of it.
Deep Connection is built around a proprietary, longitudinal neurodevelopmental dataset that compounds with every child screened, consulted and monitored, the foundation for our ND-LLM, a neurodevelopment-specific model no one else can replicate.
proprietary, longitudinal dataset
Researchers and institutions interested in our methods, or in running a study with us, are welcome to get in touch.
Collaborate with usSee what Deep Connection is really building.
Whichever side of this you're on, there's a way in.