New Algorithm Predicts IQ Scores Using fMRI Brain Scans

A team of researchers from the California Institute of Technology (Pasadena, CA, USA), Cedars-Sinai Medical Center (Los Angeles, CA, USA), and the University of Salerno (Fisciano SA, Italy) have developed a machine-learning algorithm that can predict a person's intelligence by analyzing functional magnetic resonance imaging (fMRI) scans of their resting state brain activity.

Functional MRI develops a map of brain activity by detecting changes in blood flow in specific brain regions. By analyzing patterns of activity in their brain, an individual's intelligence can be gleaned when the mind is idle and not doing anything in particular. In order to train the algorithm on the complex patterns of activity in the human brain, the researchers used data collected by the Human Connectome Project (HCP), a scientific endeavor funded by the National Institutes of Health (NIH) that seeks to improve understanding of the various connections in the human brain. The researchers downloaded the brain scans and intelligence scores of about 900 individuals who had participated in the HCP, fed these into their algorithm, and set it to work.


After processing the data, the algorithm was able to predict intelligence at statistically significant levels across the 900 subjects. However, there is still significant room for improvement, as the scans are coarse and noisy measures of what is actually taking place in the brain, and considerable amount of potentially useful information is still being discarded. The researchers hope that in the near future, the MRIs could also be used for diagnosing conditions such as autism, schizophrenia, and anxiety as they are currently used for detecting tumors, aneurisms, or liver disease.

"If trained properly, these algorithms can answer questions as complex as the one we are trying to answer here. They are very powerful, but if you actually ask, 'How do they learn? How do they do these things?' These are difficult questions to answer," said the study’s co-author Paola Galdi.

Related Links:
California Institute of Technology
Cedars-Sinai Medical Center
University of Salerno