Fig. 1.

Validation of metabolic signature for cognitive impairment. a Scores plot for sparse-partial least squared discriminant analysis (sPLS-DA), with each score representing a sample. b Loadings plot for selected metabolites representing their mean importance for sample grouping reflected in the scores plot. The colour-coding of the bars indicates their importance for the corresponding group. c Receiver operating characteristics (ROC) curve indicates the ability of the model to distinguish the groups. Together with the ROC curve is the area under the curve (AUC) with the presented 95% CI, accuracy, PPV, and NPV. d ROC curve of selected metabolites combined with significantly altered markers of neurodegeneration (Aβ₄₀, GFAP, Nf-L, p-tau181) showing an improved diagnostic efficacy, also presented with AUC and the 95% CI, accuracy, PPV, and NPV. Abbreviations; AD – Alzheimer’s Disease, AUC – Area under the curve, CI – Confidence interval, Con – Healthy controls, LV – Latent variable, NPV – Negative predictive value, PPV – Positive predictive value.