Prediction of life satisfaction from resting-state functional connectome

Background Better life satisfaction (LS) is associated with better psychological and psychiatric outcomes. To the best of our knowledge, no studies have examined prediction models for LS. Methods Using resting-state functional magnetic resonance imaging (R-fMRI) data from the Human Connectome Project (HCP) Young Adult S1200 dataset, we examined whether LS is predictable from intrinsic functional connectivity (iFC). All the HCP data were subdivided into either discovery (n = 100) or validation (n = 766) datasets. Using R-fMRI data in the discovery dataset, we computed a matrix of iFCs between brain regions. Ridge regression, in combination with principal component analysis and 10-fold cross-validation, was used to predict LS. Prediction performance was evaluated by comparing actual and predicted LS scores. The generalizability of the prediction model obtained from the discovery dataset was evaluated by applying this model to the validation dataset. Results The model was able to successfully predict LS in the discovery dataset (r = 0.381, p < .001). The model was also able to successfully predict the degree of LS (r = 0.137, 5000-repetition permutation test p = .006) in the validation dataset, suggesting that our model is generalizable to the prediction of LS in young adults. iFCs stemming from visual, ventral attention, or limbic networks to other networks (such as the dorsal attention network and default mode network) were likely to contribute positively toward predicted LS scores. iFCs within ventral attention and limbic networks also positively contributed to predicting LS. On the other hand, iFCs stemming from the visual and cerebellar networks to other networks were likely to contribute negatively to the predicted LS scores. Conclusion The present findings suggest that LS is predictable from the iFCs. These results are an important step toward identifying the neural basis of life satisfaction.