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

Abstract

IntroductionS100 calcium-binding protein B (S100B) is a neurotrophic factor that regulates neuronal growth and plasticity by activating astrocytes and microglia through the production of cytokines involved in Generalized Anxiety Disorder (GAD). However, few studies have combined S100B and cytokines to explore their role as neuro-inflammatory biomarkers in GAD.MethodsSerum 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 immunosorbent assay (ELISA), while Hamilton Anxiety Rating Scale (HAMA) scores and Hamilton Depression Rating Scale (HAMD) scores were measured to evaluate anxiety and depression severity. This was used to help physicians identify persons having GAD. Machine learning techniques were applied for feature ordering of cytokines and S100B and the classification of persons with GAD and HC.ResultsThe serum S100B, IL-1β, and IL-2 levels of GAD cases were significantly lower than HC (P < 0.001), and the IL-4 level in persons with GAD was significantly higher than HC (P < 0.001). At the same time, IL-10 had no significant difference between the two groups (P = 0.215). The feature ranking distinguishing GAD from HC using machine learning ranked the features in the following order: 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 distinguishing persons with GAD from HC was 94.47 ± 2.06% using an integrated back propagation neural network based on a bagging algorithm (BPNN-Bagging).ConclusionThe serum S-100B, IL-1β, and IL-2 levels in persons with GAD were down-regulated while IL-4 was up-regulated. The combination of S100B and cytokines had a good diagnosis value in determining GAD with an accuracy of 94.47%. Machine learning was a very effective method to study neuro-inflammatory biomarkers interacting with each other and mediated by plenty of factors.

Analysis of Risk Factors and Diagnosis for Anxiety Disorder in Older People with the Aid of Artificial Intelligence: Observational Study

“…The results in [24] showed that the stacking ensemble model that combines several models to reduce variance and improve predictions, could have a better performance than that of the single predictive ML models depending on how a base model and a meta model are combined. The results were consistent to previous studies [22][23], which showed that the stacking ensemble model had a lower root-mean-square error (RMSE) than the single machine learning model. In this study, we used the TUDA dataset that is different from what was used in [22][23][24], hence in our preliminary analysis, we applied single base models for our analysis.…”

“…In [23], an integrated back propagation neural network based on a bagging algorithm (BPNN-Bagging) was used for diagnosing GAD by combining S100 calcium-binding protein B (S100B) and Cytokines as Neuro-Inflammatory Biomarkers. S100B can regulate neuronal growth and plasticity, and astrocytes and microglia are activated through the production of GAD-related cytokines.…”

Biological Markers in Newly Diagnosed Generalized Anxiety Disorder Patients: 8-OHdG, S100B and Oxidative Stress

“…19 In a study investigating serum S100B levels in GAD patients, the serum S100B level was seen to be significantly down-regulated in GAD patients compared to the control group. 20 However, in the current study, the S100B levels were found to be higher in GAD patients than in the control group. It was reported in a previous study that this increase emerged as a response to acute environmental stimuli, and caused an increase in behavioral and neural plasticity.…”

“… 21 While S100B can be evaluated as a protective factor in the acute period of anxiety, the effect may decrease in the chronic period. 20 It has been concluded that serum S100B levels can show variability depending on disease duration and the level of exposure to chronic stress.…”

Development and validation of a nomogram based on lymphocyte subsets to distinguish bipolar depression from major depressive disorder

“…Typically, because of the interplay of variables among lymphocyte subsets, focusing on the significance of a single factor may overlook the highly correlated factors from a clinical standpoint. Henceforth, to avoid these deficiencies, a clinical decision-making approach currently widely used in affective disorders – based on machine learning techniques, may help deal with complex factors, and show high predictive power ( 35 , 36 ). Regretfully, it is rarely utilized to differentiate between BD and MDD disorders.…”