Skip to main content
. Author manuscript; available in PMC: 2022 Dec 20.
Published in final edited form as: Stat Med. 2021 Sep 22;40(29):6707–6722. doi: 10.1002/sim.9207

TABLE 4.

Model results for NYULH COVID-19 data application.

PLSI GMRL GMRL
Estimate 95% CI** Estimate 95% CI**
Baseline information (exponential of coefficient)
Age 1.12* 1.09 1.15 1.12* 1.09 1.15
Sex: Male 1.06* 1.01 1.12 1.05* 1.01 1.12
Race: White 1.02 0.97 1.07 1.02 0.97 1.07
logBMI 1.06 0.94 1.20 1.06 0.94 1.20
SpO2 0.91* 0.89 0.94 0.91* 0.89 0.94
Temperature 0.98 0.96 1.01 0.99 0.96 1.01
Smoking: current/former 1.00 0.94 1.06 1.00 0.95 1.06
History of cardiac disease 1.06* 1.02 1.12 1.06* 1.01 1.11
History of pulmonary disease 1.02 0.94 1.09 1.02 0.94 1.09
History of diabetes 1.03 0.98 1.08 1.04 0.98 1.08
History of malignancy 1.11* 1.02 1.21 1.11* 1.01 1.21
Single-index component (coefficient)
Procalcitonin 0.91* 0.43 0.98 0.75* 0.51 0.89
Troponin 0.27* 0.05 0.86 0.34* 0.11 0.56
D-dimer 0.32* 0.01 0.57 0.40* 0.16 0.60
Ferritin −0.01 −0.37 0.13 −0.02 −0.29 0.16
CRP 0.06 −0.16 0.39 0.40* 0.02 0.67
*

Estimated coefficient with p-value less than 0.05.

**

95% confidence intervals were estimated by 1000 simulations.

Pre-specified link function g(t) = exp(t) for both generalizedmean residual life model (GMRL) and partially linear single-index generalized mean residual life model (PLSI GMRL).

Biomarkers in single-index component were log-transformed and standardized.