Search alternatives:
latest decrease » largest decrease (Expand Search), greatest decrease (Expand Search), largest decreases (Expand Search)
larger decrease » marked decrease (Expand Search)
shap decrease » small decrease (Expand Search), mean decrease (Expand Search), a decrease (Expand Search)
step decrease » sizes decrease (Expand Search), teer decrease (Expand Search), we decrease (Expand Search)
latest decrease » largest decrease (Expand Search), greatest decrease (Expand Search), largest decreases (Expand Search)
larger decrease » marked decrease (Expand Search)
shap decrease » small decrease (Expand Search), mean decrease (Expand Search), a decrease (Expand Search)
step decrease » sizes decrease (Expand Search), teer decrease (Expand Search), we decrease (Expand Search)
-
1
-
2
-
3
-
4
-
5
SHAP waterfall plot.
Published 2025“…Across 10 models, CatBoost performed best on the test set (AUC = 0.970, accuracy = 0.920, F1 = 0.918), with robust calibration and decision-curve net benefit. SHAP interpretation ranked eGDR among the most influential predictors: SHAP summary and dependence plots indicated that higher eGDR decreased the model’s predicted probability of frailty. …”
-
6
SHAP decision plot.
Published 2025“…Across 10 models, CatBoost performed best on the test set (AUC = 0.970, accuracy = 0.920, F1 = 0.918), with robust calibration and decision-curve net benefit. SHAP interpretation ranked eGDR among the most influential predictors: SHAP summary and dependence plots indicated that higher eGDR decreased the model’s predicted probability of frailty. …”
-
7
SHAP dependence plots.
Published 2025“…Across 10 models, CatBoost performed best on the test set (AUC = 0.970, accuracy = 0.920, F1 = 0.918), with robust calibration and decision-curve net benefit. SHAP interpretation ranked eGDR among the most influential predictors: SHAP summary and dependence plots indicated that higher eGDR decreased the model’s predicted probability of frailty. …”
-
8
Biases in larger populations.
Published 2025“…<p>(<b>A</b>) Maximum absolute bias vs the number of neurons in the population for the Bayesian decoder. …”
-
9
-
10
-
11
-
12
-
13
-
14
-
15
-
16
-
17
SHAP dependence plots with interaction coloring.
Published 2025“…Across 10 models, CatBoost performed best on the test set (AUC = 0.970, accuracy = 0.920, F1 = 0.918), with robust calibration and decision-curve net benefit. SHAP interpretation ranked eGDR among the most influential predictors: SHAP summary and dependence plots indicated that higher eGDR decreased the model’s predicted probability of frailty. …”
-
18
-
19
-
20