Fig. 2
From: Blood-based lipidomic signature of severe obstructive sleep apnoea in Alzheimer’s disease
Potential lipid signature for the diagnosis of severe OSA in AD patients. A Lipids included in the final model. Feature selection was based on a combination of random forest and automated model selection using the Akaike information criterion. B Receiver operating characteristic curves for predicting severe OSA using the lipid signature. The AUC (95% CI) for the model is shown. Definition of abbreviations: PC phosphatidylcholine, Cis-8,11,14,17-ETA Cis-8,11,14,17-eicosatetraenoic acid, OxTG oxidized triglyceride