Serum and Cerebrospinal Fluid Cytokine Biomarkers for Diagnosis of Multiple Sclerosis

Figure 1

Steps of the data analysis. The study was organized into 5 stages: (1) Dataset collection. (2) Dataset managing and Feature Selection: the feature score (ANOVA) and score (Pearson coefficient correlation) were calculated between: (1) serum and CSF of MS vs. non-MS; (2) serum vs. CSF of MS and non-MS. (3) Model Training and Testing: the cytokines (features) having high feature score and were selected for developing machine learning model. (4) Model evaluation and Cross Validation: the data of the selected features was then given as input into the five (gNB, KNN, DT, XGB, and RF) machine learning models to predict the outcome of the disease. (5) Results analysis: the performance of each model was evaluated by calculating accuracy.