Fig. 4
Machine learning analysis and expression of candidate biomarkers. (A, B) Lasso regression analysis of 12 candidate genes with threefold cross-validation was performed to select optimal biomarkers, with Lambda.min and Lambda.1se values identified for feature selection. (C, D) Box plots showing expression levels of selected biomarkers in PMOP vs Control and PD vs Control groups, with significant differences indicated (* p < 0.05, ** p < 0.01, *** p < 0.001, **** p < 0.0001). (E, F) Box plots showing expression levels of selected biomarkers in PMOP evaluation dataset and PD evaluation dataset (* p < 0.05, ** p < 0.01, *** p < 0.001, **** p < 0.0001).
