Developing Neuroimaging Biomarker for Brain Diseases with a Machine Learning Framework and the Brainnetome Atlas

Putative Risk Biomarkers of Bipolar Disorder in At-risk Youth

Bipolar disorder is a highly heritable and functionally impairing disease. The recognition and intervention of BD especially that characterized by early onset remains challenging. Risk biomarkers for predicting BD transition among at-risk youth may improve disease prognosis. We reviewed the more recent clinical studies to find possible pre-diagnostic biomarkers in youth at familial or (and) clinical risk of BD. Here we found that putative biomarkers for predicting conversion to BD include findings from multiple sample sources based on different hypotheses. Putative risk biomarkers shown by perspective studies are higher bipolar polygenetic risk scores, epigenetic alterations, elevated immune parameters, front-limbic system deficits, and brain circuit dysfunction associated with emotion and reward processing. Future studies need to enhance machine learning integration, make clinical detection methods more objective, and improve the quality of cohort studies.

Individual prediction of hemispheric similarity of functional connectivity during normal aging

In the aging process of normal people, the functional activity pattern of brain is in constant change, and the change of brain runs through the whole life cycle, which plays a crucial role in the track of individual development. In recent years, some studies had been carried out on the brain functional activity pattern during individual aging process from different perspectives, which provided an opportunity for the problem we want to study. In this study, we used the resting-state functional magnetic resonance imaging (rs-fMRI) data from Cambridge Center for Aging and Neuroscience (Cam-CAN) database with large sample and long lifespan, and computed the functional connectivity (FC) values for each individual. Based on these values, the hemispheric similarity of functional connectivity (HSFC) obtained by Pearson correlation was used as the starting point of this study. We evaluated the ability of individual recognition of HSFC in the process of aging, as well as the variation trend with aging process. The results showed that HSFC could be used to identify individuals effectively, and it could reflect the change rule in the process of aging. In addition, we observed a series of results at the sub-module level and find that the recognition rate in the sub-module was different from each other, as well as the trend with age. Finally, as a validation, we repeated the main results by human brainnetome atlas (BNA) template and without global signal regression, found that had a good robustness. This also provides a new clue to hemispherical change patterns during normal aging.