Leading dietary determinants identified using machine learning techniques and a healthy diet score for changes in cardiometabolic risk factors in children: a longitudinal analysis

Shang, Xianwen; Li, Yanping; Xu, Haiquan; Zhang, Qian; Liu, Ailing; Du, Songming; Guo, Hongwei; Ma, Guansheng

doi:10.1186/s12937-020-00611-2

Table 2 Changes in cardiometabolic risk score during follow-up associated with dietary intakes at baseline

From: Leading dietary determinants identified using machine learning techniques and a healthy diet score for changes in cardiometabolic risk factors in children: a longitudinal analysis

	Low intake (gram/100 kcal/day)	High intake (gram/100 kcal/day)	P-value*
Refined grains	0	> 0
Participants	1453	3361
CMRS^†, Model 1^‡	−0.24 ± 0.12^§	− 0.03 ± 0.12	0.0024
CMRS, Model 2	− 0.12 ± 0.12	0.07 ± 0.11	0.0074
CMRS, Model 3	0.01 ± 0.14	0.21 ± 0.14	0.0058
Seafood	0	> 0
Participants	2571	2243
CMRS, Model 1	0.09 ± 0.11	− 0.37 ± 0.12	< 0.0001
CMRS, Model 2	0.22 ± 0.11	− 0.25 ± 0.11	< 0.0001
CMRS, Model 3	0.32 ± 0.14	− 0.14 ± 0.14	< 0.0001
Fried wheat/rice	0	> 0
Participants	3892	922
CMRS, Model 1	−0.22 ± 0.12	0.34 ± 0.13	< 0.0001
CMRS, Model 2	− 0.09 ± 0.11	0.34 ± 0.13	< 0.0001
CMRS, Model 3	0.04 ± 0.14	0.45 ± 0.15	< 0.0001
SSBs	0	> 0
Participants	3472	1342
CMRS, Model 1	−0.17 ± 0.12	0.07 ± 0.13	0.0008
CMRS, Model 2	−0.05 ± 0.11	0.18 ± 0.12	0.0007
CMRS, Model 3	0.08 ± 0.14	0.33 ± 0.15	0.0004
Wheat	≦4.66	> 4.66
Participants	3048	1766
CMRS, Model 1	−0.21 ± 0.12	0.07 ± 0.12	< 0.0001
CMRS, Model 2	− 0.05 ± 0.11	0.10 ± 0.12	0.0182
CMRS, Model 3	0.08 ± 0.14	0.22 ± 0.14	0.0433
Red meat other than pork	≦0.01	> 0.01
Participants	3394	1420
CMRS, Model 1	−0.03 ± 0.12	− 0.28 ± 0.12	0.0005
CMRS, Model 2	0.10 ± 0.11	− 0.19 ± 0.12	< 0.0001
CMRS, Model 3	0.23 ± 0.14	− 0.05 ± 0.14	< 0.0001
Rice	≦5.99	> 5.99
Participants	1109	3705
CMRS, Model 1	0.33 ± 0.13	− 0.25 ± 0.12	< 0.0001
CMRS, Model 2	0.46 ± 0.13	− 0.12 ± 0.11	< 0.0001
CMRS, Model 3	0.54 ± 0.15	− 0.01 ± 0.14	< 0.0001
Root and tuber	≦2.29	> 2.29
Participants	2711	2103
CMRS, Model 1	−0.14 ± 0.12	0.00 ± 0.13	0.0635
CMRS, Model 2	−0.00 ± 0.11	0.05 ± 0.12	0.41
CMRS, Model 3	0.14 ± 0.14	0.17 ± 0.14	0.63
Fungi and mushroom	0	> 0
Participants	3244	1570
CMRS, Model 1	−0.16 ± 0.12	0.03 ± 0.12	0.0058
CMRS, Model 2	−0.04 ± 0.11	0.12 ± 0.12	0.0195
CMRS, Model 3	0.10 ± 0.14	0.25 ± 0.14	0.0212
Nuts and legumes	0	> 0
Participants	1946	2868
CMRS, Model 1	−0.16 ± 0.12	− 0.07 ± 0.12	0.17
CMRS, Model 2	− 0.00 ± 0.11	0.02 ± 0.11	0.79
CMRS, Model 3	0.13 ± 0.14	0.15 ± 0.14	0.78

^*The change in CMRS was calculated by subtracting the result at baseline from that at follow-up
^†GLM was used to estimate multivariable-adjusted means and standard errors of cardiometabolic risk factors between quintiles. Benjamin-Hochberg’s procedure was used to control the false discovery rate at level 5% for multiple comparisons with the P-value cut-off point of significance was 0.0233 for change in CMRS (Model 3)
^‡Model 1 was adjusted for classes in school as clustering effects and characteristics of individuals including age, sex, and corresponding CMR factor at baseline as fixed effects; Model 2 was adjusted for Model 1 plus puberty, grade, intervention, BMI, physical activity, and energy intake at baseline as fixed effects; Model 3 was adjusted for Model 2 plus birthweight, household income, mother’s education, father’s education, mother’s BMI, and father’s BMI as fixed effects
^§All these data are means ± standard errors of change in CMRS

Back to article page

ISSN: 1475-2891

Contact us

General enquiries: journalsubmissions@springernature.com

Nutrition Journal

Contact us