Table 3 Performance metrics of each AI model based on etiological groups

91.83

18.51

50.56

71.42

53.39

0.552 (0.451–0.650)

86.66

13.63

14.60

85.71

24.72

0.502 (0.401–0.602)

94.11

15.11

17.97

92.85

28.15

0.546 (0.445–0.645)

84.61

13.33

12.36

85.71

22.33

0.490 (0.390–0.590)

44.44

9.57

4.49

64.28

12.62

0.270 (0.187–0.367)

69.38

25.92

45.94

48.27

46.60

0.477 (0.377–0.577)

80.00

29.54

16.21

89.65

36.89

0.548 (0.447–0.646)

94.11

32.55

21.62

96.55

42.71

0.633 (0.533–0.726)

61.53

26.66

10.81

82.75

31.06

0.441 (0.343-0542)

44.44

25.53

5.40

82.75

27.18

0.350 (0.259–0.450)

81.63

29.63

51.28

64.00

54.36

0.556 (0.455–0.654)

80.00

25.00

15.38

88.00

33.01

0.525 (0.424–0.624)

82.35

25.58

17.94

88.00

34.95

0.540 (0.439-0649)

69.23

23.33

11.53

84.00

29.12

0.463 (0.364–0.564)

33.33

20.21

3.84

76.00

21.35

0.268 (0.185–0.364)

91.83

20.37

51.13

73.33

54.36

0.561 (0.460–0.659)

73.33

12.50

12.50

73.33

21.35

0.429 (0.332–0.530)

94.11

16.27

18.18

93.33

29.12

0.552 (0.451–2.568)

76.92

13.33

11.36

80.00

21.35

0.451 (0.353–0.552)

66.66

12.76

6.81

80.00

17.47

0.397 (0.302–0.492)