Stanford researchers have developed a new AI model that can identify different brain functional connectivities depending on sex.

The study, published in PNAS on February 20, helps resolve whether sex-related differences exist in the human brain and suggests that understanding these differences may be critical to addressing neuropsychiatric conditions that affect women and men differently.

Vinod Menon, director of the Stanford Cognitive and Systems Neuroscience Laboratory and lead author of the work, said that “a key motivation for this study is that sex plays a crucial role in human brain development, in aging, and in the manifestation of psychiatric and neurological disorders”. And that “identifying consistent and replicable sex differences in the healthy adult brain is a critical step toward a deeper understanding of sex-specific vulnerabilities in psychiatric and neurological disorders.”

The systems that most helped the model distinguish between male and female brains were the default mode network, which is a brain system that helps us process self-referential information, and the striatum and limbic network, which are involved in learning and responding to rewards.

For years there has been debate about whether a person’s sex affects the way his or her brain is organized and functions. Brain structures are similar in men and women and some previous research examining how brain organization differs between men and women was inconclusive.

In the PNAS study, Dr. Menon’s team used both artificial intelligence and to multiple large datasets to perform a more exhaustive analysis than those that had been previously developed.

First, they created a deep neural network model, which learned to classify data from brain scans. Thus, the researchers recorded a large amount of data from these scans, assigning them to the patient’s sex, so that the model began to distinguish patterns that showed sex-associated differences.

Furthermore, this approach manages to capture the interaction between different brain regions. The researchers tested the model on 1,500 scans.

Subsequently, the computational model was able to elucidate with 90% reliability whether a certain image obtained through brain scanning techniques corresponded to a woman or a man, depending on its activation and connectivity characteristics.

The success of the model confirms the existence of objective sexual differences in the brain, now detected using a novel technique. As Menon stated “this is a very strong piece of evidence that sex is a robust determinant of human brain organization.”

Using a tool called “explainable IA”, Menon and his team identified the most important networks that made the model distinguish between a male and female brain. They found that the model most frequently searched for the default mode network, the striatum, and the limbic network.

“These models worked really well because we successfully separated brain patterns between sexes,” Menon said. “That tells me that overlooking sex differences in brain organization could lead us to miss key factors underlying neuropsychiatric disorders.”

Bioethical assessment

The confirmation in this study of the existence of objective functional differences between the male and female brains represents new evidence of the need for a differentiated clinical approach to the diagnosis and treatment of neuropsychiatric pathologies.

It also involves a questioning of gender transition processes, which seem to ignore that the characteristics of brain functioning associated with sex remain after gender transition procedures, both pharmacological and surgical.

Complications in the psychological evolution of patients undergoing gender transition processes could be related to the sex-dependent imprints, genetic coding and hormonal regulation that our brains show. This is not modified by the aforementioned treatments and can trigger significant disorders after transition processes.

Julio Tudela and Ester Bosch

Bioethics Observatory – Institute of Life Sciences

Catholic University of Valencia

Subscribe

Subscribe to our newsletter:

We don’t spam! Read our privacy policy for more info.