Depression (DP) and schizophrenia (SCZ) are both highly prevalent psychiatric disorders, and their diagnosis depends on the examination of symptoms and clinical tests, which can be subjective. As a measure of real-time neural activity, Electroencephalographic (EEG) has shown its usability to classify people either as normal or as having DP or SCZ, but automatic classification between the three categories (DP, SCZ and the normal) was rarely reported. Here, we propose an automatic diagnostic framework based on a convolutional neural network called the Multi-Channel Frequency Network (MUCHf-Net), which automatically learns feature representations of EEGs that characterize them as normal, DP, or SCZ. Two EEG databases were used in this study, the first one contains EEGs from 300 individuals (DP: 100, SCZ: 100, normal: 100) collecting from our hospital, and the second contains EEGs from 30 individuals (DP: 10, SCZ: 10, normal: 10) from public available datasets, and the spectrum matrices from these multi-channel EEGs were feed into MUCHf-Net. The results showed that: (1) MUCHf-Net accurately distinguished normal EEGs from DP or SCZ EEGs (accuracy: 91.12%; F1 score: 0.8947); (2) low-frequency bands (delta, theta, alpha) contributed the most important information to the classification model; (3) features located in the frontal and parietal lobes contributed more than other regions did; (4) MUCHf-Net fine-tuned on public datasets also had high classification accuracy: 87.71% (triple: normal, SCZ or DP) and 79.27% (binary: psychiatric disorders (DP or SCZ) or normal). Our study shows that deep leaning has the potential to become an important tool for assisting in the diagnosis of psychiatric disorders.
BackgroundThere is an urgent need to identify differentiating and disease-monitoring biomarkers of schizophrenia, bipolar disorders (BD), and major depressive disorders (MDD) to improve treatment and management.MethodsWe recruited 54 first-episode schizophrenia (FES) patients, 52 BD patients, 35 MDD patients, and 54 healthy controls from inpatient and outpatient clinics. α-Melanocyte Stimulating Hormone (α-MSH), β-endorphin, neurotensin, orexin-A, oxytocin, and substance P were investigated using quantitative multiplex assay method. Psychotic symptoms were measured using the Brief Psychiatric Rating Scale (BPRS) and Positive and Negative Syndrome Scale (PANSS), manic symptoms using the Young Mania Rating Scale (YMRS), and depressive symptoms using 17 item-Hamilton Depression Rating Scale (HAMD). We additionally measured cognitive function by using a battery of tests given to all participants.Resultsα-MSH, neurotensin, orexin-A, oxytocin, and substance P were decreased in the three patient groups compared with controls. Neurotensin outperformed all biomarkers in differentiating patient groups from controls. There were no significant differences for 6 neuropeptides in their ability to differentiate between the three patient groups. Higher neurotensin was associated with better executive function across the entire sample. Lower oxytocin and higher substance p were associated with more psychotic symptoms in FES and BD groups. β-endorphin was associated with early morning wakening symptom in all three patient groups.ConclusionOur research shows decreased circulating neuropeptides have the potential to differentiate severe mental illnesses from controls. These neuropeptides are promising treatment targets for improving clinical symptoms and cognitive function in FES, BD, and MDD.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.