I have a suspicion that this is exactly what’s going on here and may be why past studies found no differences. AI is much better at quickly synthesizing complex patterns into coherent categories than humans are.

Also, 90% is not that good all things considered. The brain is almost certainly a complex mix of features that defy black and white categorization.

Hopefully we will be wise enough to not require trans people to prove their trans-ness scientifically. People have a right to do what they wish with their bodies and express their gender in a way that feels right to them, and should not be required to match some artificial physical diagnosis of what it means to be trans. Even if it turns out that most trans people do share certain brain structures or patterns. There will always be exceptions and that doesn’t mean we get to label someone’s identity as inauthentic.

Someone else mentioned the iris test being more accurate but that it also includes the eye area around the iris, including eyelashes and eye shape. That would clearly bias the model.

I wonder if there’s anything else that’s might be giving clues to the machine or if it I limited to what they say it’s determining sex based on. As a trans-nonbinary person myself, I’m very skeptical and anxious about technologies like this leading to biases and prejudices being emboldened.

Just a guess but if they labeled training data either male or female then i believe its more likely that it detects biological sex..

But if i they would also label and train on lgbt brains then i bet machine learning can differentiate between all of those.

I bet you can do the same thing with neurodivergent people but you would need to make sure the training data is without error to make me trust it.

That's interesting. I and my father are both hyperlexic (as in, taught ourselves to read, in my case, before I could speak) but not trans or autistic.

I wonder how that mixes into the fold?

I mean the paper you quoted keeps saying "gender" ...Is it actually for affirming trans folks? Big if true but I obviously didn't read the source material.

More like a proof of concept, since they didn't significantly improve upon the accuracy of their predictions compared to prior models.

From a technical perspective yeah, but from a colloquial manner AI and ML have been used interchangeably for years. An issue only made worse by AI now frequently being used to describe GenAI which, while ML, behaves in a manner where it's somewhat misleading to use AI/ML/Gen AI interchangeably.

They can’t rule out the potential explanation that being raised male changes your brain in a different way than being raised female without having subjects that were raised differently than their birth sex. You would have to control for that variable in order to rule it out.

You can't point to a difference and say it's (directly) caused by chromosomes or the SRY gene or hormones, whatever. Brain differences increase with age, suggesting that they may be more to do with socialisation than genetics. Does this evidence prove that women should be treated differently or is it evidence that women are, in fact, treated differently?

It doesn't sound like they excluded trans or genderqueer people, they just ignored their gender. Or maybe I'm reading it wrong, but?

I think so. With a more diverse dataset and fewer binary assumptions baked into the analysis I think we'd start seeing the bimodal contours of a spectrum between the masculine and feminine peaks. The graphics included in the study seem to hint at this, showing nodes of similarity with a tapering tail toward the middle of the distribution for all three sets of data they analyzed:

IIRC Simon Baron Cohen's studies on his (IMHO poorly named) extreme male brain theory of autism found that only 70% of men had "male brains".