Skip to main content

Table 2 Prediction outcomes of the BUII, EVO 2.0, Kane, Pearl-DGS, RBF 3.0 and Zhu-Lu formulas in highly myopic eyes

From: The Zhu-Lu formula: a machine learning-based intraocular lens power calculation formula for highly myopic eyes

Parameters

BUII

EVO 2.0

Kane

Pearl-DGS

RBF 3.0

Zhu-Lu

P value

Internal test dataset (n = 361)

 

PE (D)

       

 Mean

 − 0.11

 − 0.14

 − 0.31

0.14

 − 0.10

0.005

 

 SD

0.54

0.56

0.55

0.71

0.51

0.46

 

MAE ± SD (D)

0.46 ± 0.30

0.46 ± 0.34

0.49 ± 0.39

0.55 ± 0.47

0.38 ± 0.35

0.34 ± 0.31

 

MedAE (D)

0.43*

0.40*

0.40*

0.45*

0.29

0.26

 < 0.001

IOL formula performance index

0.048

0.048

0.056

0.040

0.065

0.071

 

External test dataset (n = 150)

 

PE (D)

       

 Mean

 − 0.01

 − 0.02

 − 0.21

0.20

 − 0.06

0.05

 

 SD

0.57

0.53

0.52

0.53

0.57

0.50

 

MAE ± SD (D)

0.43 ± 0.38

0.40 ± 0.35

0.45 ± 0.34

0.45 ± 0.34

0.44 ± 0.37

0.38 ± 0.34

 

MedAE (D)

0.34

0.32

0.37*

0.40*

0.36*

0.30

0.001

IOL formula performance index

0.063

0.063

0.052

0.050

0.056

0.063

 
  1. BUII = Barrett Universal II; EVO = Emmetropia Verifying Optical; RBF = Radial Basis Function; PE = prediction error; SD = standard deviation; D = diopters; MAE = mean absolute error; MedAE = median absolute error; IOL = intraocular lens
  2. *P < 0.05 when compared with the Zhu-Lu formula using the Friedman test with Bonferroni post hoc analysis