Early warning for human mental sub-health based on fMRI data analysis: an example from a seafarers' resting-data study

Abstract

Effective mental sub-health early warning mechanism is of great significance in the protection of individual mental health. The traditional mental health assessment method is mainly based on questionnaire surveys, which may have some uncertainties. In this study, based on the relationship between the default mode network (DMN) and the mental health status, we proposed a human mental sub-health early warning method by utilizing two-fold support vector machine (SVM) model, where seafarers' fMRI data analysis was utilized as an example. The method firstly constructed a structural-functional DMN template by combining the anatomical automatic labeling template with the functional DMN extracted by independent component analysis. Then, it put forward a two-fold SVM-based classifier, with one-class SVM utilized for the training of the initial classifier and two-class SVM utilized to refine the classification performance, to identify seafarers' mental health status by utilizing the correlation coefficients (CCs) among the areas of structural-functional DMN as the features. The experimental results showed that the proposed model could discriminate the seafarers with DMN function alteration from the healthy control (HC) effectively, and further the results demonstrated that when compared with the HC group, the brain functional disorders of the mental sub-healthy seafarers mainly manifested as follows: the functional connectivity of DMN had obvious alteration; the CCs among the different DMN regions were significant lower; the regional homogeneity decreased in parts of the prefrontal cortex and increased in multi-regions of the parietal, temporal and occipital cortices; the fractional amplitude of low-frequency fluctuation decreased in parts of the prefrontal cortex and increased in parts of the parietal cortex. All of the results showed that fMRI-based analysis of brain functional activities could be effectively used to distinguish the mental health and sub-health status.