Skip to main content
. Author manuscript; available in PMC: 2020 Feb 22.
Published in final edited form as: Menopause. 2019 Jul;26(7):771–780. doi: 10.1097/GME.0000000000001301

Table 2.

Prediction of variables by using random survival forest model

Variablea Predictive valueb VIMP
IRS1 rs1801278 1.2406 0.3030
AKT2 rs7247515 1.3628 0.2335
IRS1 rs1801123 2.0276 0.1741
AKT2 rs3730256 2.1780 0.0804
Age 2.8748 0.0009
Height 3.0972 –0.0002
% calories from SFA/day 3.2312 0.0004
% calories from MFA/day 3.6040 0.0015
% calories from PFA/day 3.7308 0.0004
Exogenous estrogen use (E + P use) 4.4596 0.0003
Physical activity 7.0142 0.0009

E+P, estrogen + progestin; MFA, monounsaturated fatty acids; PFA, polyunsaturated fatty acids; SFA, saturated fatty acids; VIMP, variable of importance.

a

Variables are ordered by predictive value.

b

The predictive value of variables was assessed via minimal depth method in the nested random survival forest models. A lower value is likely to have a greater influence on prediction.