Fig 1.
Study design from data preprocessing through performance evaluation.
Fig 2.
A) ROC with AUC values, B) permutation test obtained from the OL set.
Table 1.
Selected metabolites as identified using CFS, PLS-DA, COR-LVQ and their common compounds.
Fig 3.
Performance evaluation in terms of sensitivity, specificity, and AUC for all metabolite panels obtained different variable selection algorithms.
Fig 4.
Bar graph: altered pathways in enrichment analysis showing top fifteen metabolic pathways perturbed upon IUGR.
Table 2.
Pathway analysis of intrauterine growth restriction.