Skip to main content

Table 2 The training data and the test data of fat and energy of two milk analyzers (mean ± SD)

From: Comparing human milk macronutrients measured using analyzers based on mid-infrared spectroscopy and ultrasound and the application of machine learning in data fitting

 

Data set (n = 465)

MIR

P-valuea

Ultrasound

P-valuea

95% LOAb

Fat (g/dl)

Training data (n = 372)

3.14 ± 0.69

0.39

2.79 ± 1.14

0.13

-1.87 ~ 1.18

Test data (n = 93)

3.21 ± 0.84

2.99 ± 1.32

-1.76 ~ 1.34

Energy (kj/dl)

Training data (n = 372)

269.62 ± 29.81

0.89

258.50 ± 47.08

0.60

-76.88 ~ 54.64

Test data (n = 93)

270.07 ± 24.84

261.36 ± 43.64

-71.84 ~ 54.42

  1. a refers to the p-value of t-test between training dataset and test dataset; b refers to the result of Bland-Altman analysis between observed ultrasonic and MIR values