Publication date: Jul 06, 2025
PFI and SHAP analyses indicated that DAP metabolites were of significant contribution weights in AMD risk prediction, higher than most of the sociodemographic covariates. Shapley values and waterfall plots of randomly selected AMD individuals emphasized the predictive capacity of ML with high accuracy and sensitivity in each case. For example, several researchers have emphasized the impacts of heavy metals,3 air pollutants,4 and radiation5 exposure on the development of AMD. Receiver operating characteristic curve analysis evaluated Random Forests as the best ML model with its optimal predictive performance among 11 models.
Semantics
| Type | Source | Name |
|---|---|---|
| drug | DRUGBANK | Methyldopa |
| disease | MESH | age-related macular degeneration |
| drug | DRUGBANK | Phosphate ion |
| drug | DRUGBANK | Amifampridine |
| disease | MESH | Eye Diseases |
| disease | MESH | lifestyle |
| disease | MESH | pathogenesis |
| disease | MESH | complications |
| drug | DRUGBANK | Water |
| disease | MESH | cancer |
| disease | MESH | central nervous system disorders |
| disease | MESH | depression |
| disease | MESH | hypertension |
Original Article
(Visited 6 times, 1 visits today)