AUTHOR=Shen Zhongxia , Cui Lijun , Mou Shaoqi , Ren Lie , Yuan Yonggui , Shen Xinhua , Li Gang 

TITLE=Combining S100B and Cytokines as Neuro-Inflammatory Biomarkers for Diagnosing Generalized Anxiety Disorder: A Proof-of-Concept Study Based on Machine Learning

JOURNAL=Frontiers in Psychiatry

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/psychiatry/articles/10.3389/fpsyt.2022.881241

DOI=10.3389/fpsyt.2022.881241

ISSN=1664-0640

ABSTRACT=Introduction: S100B is a neurotrophic factor regulates neuronal growth and plasticity via activating astrocytes and microglia through production of cytokines involved in Generalized Anxiety Disorder (GAD), but few studies have combined S100B and cytokines to explore their roles as neuro-inflammatory biomarkers in GAD. Methods: Serum S100B and cytokines (IL-1β, IL-2, IL-4 and IL-10) of 108 untreated GAD cases and 123 healthy controls (HC) were determined by enzyme linked-immuno-sorbent assay (ELISA), while Hamilton Anxiety Rating Scale (HAMA) scores and Hamilton Depression Rating Scale (HAMD) scores were measured to evaluate anxiety and depression severity, which were used to help physicians select the involved patients only with GAD. Machine learning techniques were applied for feature ordering of cytokines and S100B and for classification of GAD and HC. Results: The serum S100B and IL-1β, IL-2 levels of GAD cases were significantly lower than HC (P<0.001), the IL-4 level of GAD were significantly higher than HC (P<0.001), while IL-10 had no significant difference between two groups (P=0.215). The feature ranking in distinguishing GAD from HC using machine learning were IL-2, IL-1β，IL-4，S100B and IL-10. The accuracy of S100B combined with IL-1β, IL-2, IL-4 and IL-10 in classifying GAD from HC was 94.47±2.06% using integrated back propagation neural network based on bagging algorithm (BPNN_Bagging). Conclusion: The serum S-100B, IL-1β, IL-2 levels of GAD were down-regulated while IL-4 was up-regulated. The combination of S100B and cytokines had a better diagnosis value with the accuracy of 94.47%. S100B, IL-1β, IL-2, and IL-4 are very effective neuro-inflammatory biomarkers of GAD according to the clinical characteristics ranking and statistic results.