Choosing explanation over performance: Insights from machine learning-based prediction of human intelligence from brain connectivity
Abstract
A growing body of research predicts individual cognitive ability levels from brain characteristics including functional brain connectivity. The majority of this research achieves statistically significant prediction performance but provides limited insight into neurobiological processes underlying the predicted concepts. The insufficient identification of predictive brain characteristics may present an important factor critically contributing to this constraint. Here, we encourage to design predictive modeling studies with an emphasis on interpretability to enhance our conceptual understanding of human cognition. As an example, we investigated in a preregistered study which functional brain connections successfully predict general, crystallized, and fluid intelligence in a sample of 806 healthy adults (replication: N = 322). The choice of the predicted intelligence component as well as the task during which connectivity was measured proved crucial for better understanding intelligence at the neural level. Further, intelligence could be predicted not solely from one specific set of brain connections, but from various combinations of connections with system-wide locations. Such partially redundant, brain-wide functional connectivity characteristics complement intelligence-relevant connectivity of brain regions proposed by established intelligence theories. In sum, our study showcases how future prediction studies on human cognition can enhance explanatory value by prioritizing a systematic evaluation of predictive brain characteristics over maximizing prediction performance (emphasis added).