Table 7 Random forest prediction results using structured data features

From: CARE-AD: a multi-agent large language model framework for Alzheimer’s disease prediction using longitudinal clinical notes

Prediction year

AD cases

Controls

Accuracy

Precision

Recall

F1 score

Precision

Recall

F1 score

−1 day

0.45

(0.42, 0.48)

0.65

(0.62, 0.68)

0.53

(0.50, 0.56)

0.89

(0.87, 0.91)

0.78

(0.75, 0.81)

0.83

(0.81, 0.85)

0.75

(0.72, 0.78)

−1 year

0.37

(0.34, 0.40)

0.57

(0.54, 0.60)

0.45

(0.42, 0.48)

0.86

(0.84, 0.88)

0.73

(0.70, 0.76)

0.79

(0.76, 0.82)

0.70

(0.67, 0.73)

−2 year

0.31

(0.28, 0.34)

0.51

(0.48, 0.54)

0.39

(0.36, 0.42)

0.84

(0.82, 0.86)

0.69

(0.66, 0.72)

0.76

(0.73, 0.79)

0.65

(0.62, 0.68)

−3 year

0.20

(0.18, 0.22)

0.38

(0.35, 0.41)

0.26

(0.23, 0.29)

0.77

(0.74, 0.80)

0.58

(0.55, 0.61)

0.66

(0.63, 0.69)

0.53

(0.50, 0.56)

−5 year

0.18

(0.16, 0.20)

0.35

(0.32, 0.38)

0.24

(0.21, 0.27)

0.76

(0.73, 0.79)

0.55

(0.52, 0.58)

0.64

(0.61, 0.67)

0.51

(0.48, 0.54)

−7 year

0.14

(0.12, 0.16)

0.31

(0.28, 0.34)

0.20

(0.18, 0.22)

0.72

(0.69, 0.75)

0.49

(0.46, 0.52)

0.58

(0.55, 0.61)

0.45

(0.42, 0.48)

−10 year

0.11

(0.09, 0.13)

0.26

(0.23, 0.29)

0.16

(0.14, 0.18)

0.68

(0.65, 0.71)

0.44

(0.41, 0.47)

0.53

(0.50, 0.56)

0.40

(0.37, 0.43)