Table 3 Random forest variable importance of prediction model.

From: Machine learning analysis with population data for prepregnancy and perinatal risk factors for the neurodevelopmental delay of offspring

Rank

MDD

Importance

CDD

Importance

NDD

Importance

1

SES

0.4115

SES

0.3771

Age

0.3999

2

Age

0.3859

Age

0.3219

SES

0.3902

3

Cesarean delivery

0.0409

Sex

0.1044

Sex

0.0441

4

Antidepressant

0.022

Cesarean delivery

0.0351

Cesarean delivery

0.0239

5

Pregestational depression

0.018

Pregestational anxiety

0.029

Antidepressant

0.0181

6

Pregestational anxiety

0.0157

Antidepressant

0.023

Pregestational anxiety

0.0172

7

Sex

0.0154

Pregestational DM

0.0139

Pregestational DM

0.0147

8

Pregestational DM

0.0149

Pregestational depression

0.0113

Pregestational depression

0.0117

9

Pregestational HTN

0.0123

Pregestational HTN

0.0095

Pregestational HTN

0.009

10

Postpartum Depression

0.0101

PIH

0.0082

PIH

0.0088

11

PIH

0.0098

Postpartum Depression

0.0081

Postpartum Depression

0.0086

12

GDM

0.0056

GDM

0.0072

GDM

0.0054

13

Thyroid disease

0.0055

FGR

0.0062

FGR

0.0047

14

FGR

0.0045

PTB

0.0044

PTB

0.0038

15

PTB

0.0039

Placenta abruptio

0.0037

Thyroid disease

0.0031

16

SGA

0.003

PPROM

0.0035

Placenta abruptio

0.003

17

Placenta abruptio

0.0028

SGA

0.0033

PROM

0.003

18

PPROM

0.0027

Thyroid disease

0.0027

SGA

0.0028

19

LGA

0.0026

LGA

0.0019

LGA

0.0022

  1. SES, social economic status; HTN, hypertension; DM. diabetes; PTB, preterm birth; LGA, large for gestational age; SGA, small for gestational age; FGR, fetal growth restriction; PROM, premature rupture of membrane; GDM, gestational diabetes; PIH, pregnancy induced hypertension.