The hidden math of behavioral health — and why it's harder than it looks

A 2024 paper in JAMA Psychiatry looked at 160,000 patient records and found something most of us in the community have known for years: behavioral health outcomes are much more variable than the rest of medicine. Depression treatment doesn't have one right answer. Neither does anxiety, ADHD, or autism. The same treatment can work great for one person and do nothing for another — even when they look the same on paper.

This is why the usual playbook for AI in health doesn't automatically apply here. In medicine, the variance is small and the signals are strong: X-rays, lab results, vitals. In behavioral health, the variance is high and the signals are soft. The math is harder. The models need more data, and the data is messier. This is also why the people who build tools for this space — therapists, clinicians, educators who actually do the work — are the ones who get it. The ones who write the rules from a desk don't.

The piece is worth reading because it makes a case for why behavioral health AI needs to be built differently, not just bolted on. It's not about a better chatbot. It's about understanding the variance, the community, and the people who live with it every day.

Why this matters for us: la gente is the ones living with behavioral health — our tías, our primos, our kids in special ed — and if the tools are built for a different variance than the one they actually face, they'll work great in the lab and fail at the kitchen table.