Table 2.
GLMnet results of lipid models in the classification of AD versus control.
| Lipid models | Sensitivity | Specificity | AUC |
|---|---|---|---|
| All_lipids | 0.66 | 0.73 | 0.78 |
| Cer | 0.7 | 0.79 | 0.79 |
| ChE | 0.78 | 0.75 | 0.82 |
| DG | 0.72 | 0.69 | 0.76 |
| LPC | 0.49 | 0.62 | 0.58 |
| PC | 0.69 | 0.76 | 0.78 |
| PE | 0.58 | 0.5 | 0.57 |
| PI | 0.7 | 0.76 | 0.79 |
| SM | 0.71 | 0.78 | 0.83 |
| TG | 0.65 | 0.82 | 0.83 |
| SM_TG | 0.69 | 0.75 | 0.81 |
| ChE_SM | 0.7 | 0.81 | 0.79 |
| ChE_TG | 0.71 | 0.78 | 0.82 |
| ChE_SM_TG | 0.67 | 0.77 | 0.79 |
Cer ceramides, SM sphingomyelins, ChE cholesteryl esters, DG diglycerides, TG triglycerides, PC phosphatidylcholines, LPC lyso-phosphatidylcholines, PE phosphatidylethanolamines, PI phosphatidylinositols, GLMnet elastic net penalization for the generalized linear model.