Table 2 Model evaluation results.

From: Personalized medication recommendations for Parkinson’s disease patients using gated recurrent units and SHAP interpretability

 

Personalized GRU

Nonpersonalized GRU

Logistic regression

Random forest

Average MR (95% CI)

0.92 (0.78, 1.05)

0.68 (0.64, 0.73)

0.67 (0.63, 0.72)

0.67 (0.63, 0.71)

Average precision (95% CI)

0.94 (0.86, 1.02)

0.84 (0.81, 0.87)

0.84 (0.80, 0.87)

0.82 (0.79, 0.85)

Average recall (95% CI)

0.94 (0.87, 1.01)

0.84 (0.81, 0.87)

0.82 (0.79, 0.85)

0.79 (0.76, 0.82)

Average F1-score (95% CI)

0.94 (0.86, 1.01)

0.83 (0.80, 0.85)

0.81 (0.78, 0.84)

0.79 (0.76, 0.82)

Average hamming loss (95% CI)

0.03 (-0.02. 0.08)

0.14 (0.12, 0.16)

0.15 (0.12, 0.17)

0.15 (0.13, 0.17)

Back to article page