A recent study conducted by researchers at Stanford Medicine has revealed a new artificial intelligence model that was able to determine with over 90% accuracy whether brain activity scans belonged to a male or female.
The findings, set to be published on February 19 in the Proceedings of the National Academy of Sciences, help address the ongoing debate surrounding sex-based differences in the human brain. The study suggests that understanding these differences is crucial for addressing neuropsychiatric conditions that affect men and women differently.
“This study is motivated by the significant role that sex plays in human brain development, aging, and the presentation of psychiatric and neurological disorders,” explained Vinod Menon, PhD, who is a professor of psychiatry and behavioral sciences and the director of the Stanford Cognitive and Systems Neuroscience Laboratory. “Identifying consistent sex differences in the healthy adult brain is a vital step towards a deeper understanding of sex-specific vulnerabilities in psychiatric and neurological disorders.”
Menon is the senior author of the study, with senior research scientist Srikanth Ryali, PhD, and academic staff researcher Yuan Zhang, PhD, serving as lead authors.
The model was able to identify “hotspots” in the brain that helped distinguish between male and female brains, such as the default mode network and the striatum and limbic network.
The study does not provide insight into whether sex-related differences in the brain emerge early in life or are influenced by hormonal factors or societal circumstances.
The study utilized recent advances in artificial intelligence and analyzed multiple large datasets to create a deep neural network model. This model demonstrated superior performance compared to previous studies, showcasing detectable sex differences in the brain.
Menon and his team used explainable AI to identify the brain networks that were crucial in the model’s determination of whether a brain scan belonged to a man or woman.
The researchers also developed sex-specific models of cognitive abilities, highlighting the behavioral implications of functional brain differences between sexes.
The research was funded by the National Institutes of Health and other organizations.
