Enhancing Prediction of Human Traits and Behaviors through Ensemble Learning of Traditional and Novel Resting-State fMRI Connectivity Analyses

Recent efforts in cognitive neuroscience have focused on leveraging resting-state functional connectivity (RSFC) data from fMRI to predict human traits and behaviors more accurately. Traditional methods typically analyze RSFC by correlating averaged time-series data between regions of interest (ROIs) or networks, a process that may overlook critical spatial signal patterns. To address this limitation, we introduced a novel linear regression technique that estimates RSFC by predicting spatial brain activity patterns in a target ROI from those in a seed ROI. We applied both traditional and our novel RSFC estimation methods to a large-scale dataset from the Human Connectome Project, analyzing resting-state fMRI data to predict sex, age, personality traits, and psychological task performance. Additionally, we developed an ensemble learner that integrates these methods using a weighted average approach to enhance prediction accuracy. Our findings revealed that hierarchical clustering of RSFC patterns using our novel method displays distinct whole-brain grouping patterns compared to the traditional approach. Importantly, the ensemble model outperformed the traditional RSFC method in predicting human traits and behaviors. Notably, the predictions from the traditional and novel methods showed relatively low similarity, indicating that our novel approach captures unique and previously undetected information about human traits and behaviors through fine-grained local spatial patterns of neural activation. These results highlight the potential of combining traditional and innovative RSFC analysis techniques to enrich our understanding of the neural basis of human traits and behaviors.