TABLE 3.
NTK biomarkers | N * | Base model r2 | Metabolite model r2 | Number of input metabolites | Number of elastic net selected metabolites | Elastic net selected metabolites model r2 |
P-tau | 295 | 0.11 | 0.71 | 40 | 14 | 0.67 |
T-tau | 296 | 0.10 | 0.72 | 44 | 19 | 0.70 |
Aβ42 | 296 | 0.01 | 0.52 | 54 | 47 | 0.52 |
Aβ40 | 293 | 0.04 | 0.80 | 73 | 71 | 0.80 |
NfL | 297 | 0.10 | 0.24 | 23 | 15 | 0.21 |
Neurogranin | 297 | 0.07 | 0.77 | 51 | 32 | 0.76 |
YKL-40 | 297 | 0.25 | 0.56 | 15 | 10 | 0.56 |
S100 | 296 | 0.05 | 0.23 | 20 | 4 | 0.19 |
GFAP | 297 | 0.17 | 0.35 | 6 | 5 | 0.35 |
sTREM2 | 297 | 0.05 | 0.53 | 27 | 14 | 0.52 |
α-synuclein | 297 | 0.03 | 0.74 | 90 | 30 | 0.67 |
Variables included in the base model were age, sex, years of education and cohort.
Variables included in the metabolite model were age, sex, years of education, cohort and all replicated significant metabolites for each biomarker.
Variables included in the metabolite model were age, sex, years of education, cohort and elastic net-selected metabolites.
*The sample sizes were different because of the missingness of metabolites.