Table 4 AD prediction performance of our proposed CARE-AD approach

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

Prediction Y ear

AD cases

Controls

Accuracy

Precision

Recall

F1 score

Precision

Recall

F1 score

−1 day

0.59

(0.57, 0.61)

0.73

(0.70, 0.76)

0.65

(0.63, 0.67)

0.92

(0.91, 0.93)

0.86

(0.85, 0.87)

0.89

(0.88, 0.90)

0.83

(0.82, 0.84)

−1 year

0.47

(0.45, 0.49)

0.66

(0.63, 0.69)

0.55

(0.53, 0.57)

0.89

(0.89, 0.90)

0.79

(0.78, 0.80)

0.84

(0.83, 0.85)

0.76

(0.75, 0.78)

−2 year

0.39

(0.37, 0.41)

0.59

(0.56, 0.62)

0.47

(0.45, 0.49)

0.87

(0.86, 0.88)

0.75

(0.73, 0.76)

0.80

(0.79, 0.81)

0.71

(0.70, 0.73)

−3 year

0.34

(0.32, 0.35)

0.54

(0.51, 0.57)

0.41

(0.39, 0.43)

0.85

(0.84, 0.87)

0.71

(0.69, 0.72)

0.77

(0.76, 0.79)

0.67

(0.66, 0.68)

−5 year

0.26

(0.25, 0.28)

0.46

(0.43, 0.49)

0.33

(0.31, 0.35)

0.81

(0.80, 0.82)

0.65

(0.64, 0.67)

0.72

(0.71, 0.73)

0.61

(0.59, 0.62)

−7 year

0.24

(0.23, 0.26)

0.43

(0.40, 0.46)

0.31

(0.29, 0.33)

0.80

(0.79, 0.81)

0.62

(0.61, 0.64)

0.70

(0.69, 0.71)

0.58

(0.57, 0.60)

−10 year

0.20

(0.18, 0.21)

0.38

(0.35, 0.41)

0.26

(0.24, 0.28)

0.77

(0.76, 0.78)

0.57

(0.55, 0.59)

0.65

(0.64, 0.67)

0.53

(0.51, 0.54)

Back to article page