The novel coronavirus (COVID-19) pandemic has led to a surge in mental distress and fear-related disorders, including posttraumatic stress disorder (PTSD). Fear-related disorders are characterized by dysregulations in fear and the associated neural pathways. In the present study, we examined whether individual variations in the fear neural connectome can predict fear-related symptoms during the COVID-19 pandemic. Using machine learning algorithms and back-propagation artificial neural network (BP-ANN) deep learning algorithms, we demonstrated that the intrinsic neural connectome before the COVID-19 pandemic could predict who would develop high fear-related symptoms at the peak of the COVID-19 pandemic in China (Accuracy rate = 75.00%, Sensitivity rate = 65.83%, Specificity rate = 84.17%). More importantly, prediction models could accurately predict the level of fear-related symptoms during the COVID-19 pandemic by using the prepandemic connectome state, in which the functional connectivity of lvmPFC (left ventromedial prefrontal cortex)-rdlPFC (right dorsolateral), rdACC (right dorsal anterior cingulate cortex)-left insula, lAMY (left amygdala)-lHip (left hippocampus) and lAMY-lsgACC (left subgenual cingulate cortex) was contributed to the robust prediction. The current study capitalized on prepandemic data of the neural connectome of fear to predict participants who would develop high fear-related symptoms in COVID-19 pandemic, suggesting that individual variations in the intrinsic organization of the fear circuits represent a neurofunctional marker that renders subjects vulnerable to experience high levels of fear during the COVID-19 pandemic.