Bio Age
2023-05-15
# install.packages("devtools")
# library(express)
# library(flexsurv)
# library(devtools)
# devtools::install_github("dayoonkwon/BioAge")
# library(Matrix)
library(BioAge) #topic of example
library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union###Step 1: train algorithms in NHANES III and project biological aging measures in NHANES IV I train in the NHANES III and project biological aging measures into the NHANES IV by using the hd_nhanes, kdm_nhanes, and phenoage_nhanes function of the BioAge package.
#HD using NHANES (separate training for men and women)
hd = hd_nhanes(biomarkers=c("albumin","alp","lncrp","totchol","lncreat","hba1c","sbp","bun","uap","lymph","mcv","wbc"))
#KDM bioage using NHANES (separate training for men and women)
kdm = kdm_nhanes(biomarkers=c("albumin","alp","lncrp","totchol","lncreat","hba1c","sbp","bun","uap","lymph","mcv","wbc"))
#phenoage uinsg NHANES
phenoage = phenoage_nhanes(biomarkers=c("albumin_gL","alp","lncrp","totchol","lncreat_umol","hba1c","sbp","bun","uap","lymph","mcv","wbc"))###Step 2: compare original KDM bioage and phenoage algorithms with algorithms composed with new biomarker set The projected data and estimated models are saved as part of the list structure. The dataset can be drawn by typing data. The model can be drawn by typing fit.
#assemble NHANES IV dataset with projected biological aging measures for analysis
data = merge(hd$data, kdm$data) %>% merge(., phenoage$data)###Figure1. Association of biological aging measures with chronological age in NAHNES IV dataset In the figure below, the graphs titled “KDM Biological Age” and “Levine Phenotypic Age” show measures based on the original biomarker sets published in Levine 2013 J Geron A and Levine et al. 2018 AGING. The remaining graphs shows the new measures computed with the biomarker set specified within this code.
#select biological age variables
agevar = c("kdm0","phenoage0","kdm","phenoage","hd","hd_log")
label = c("KDM\nBiological Age",
"Levine\nPhenotypic Age",
"Modified-KDM\nBiological Age",
"Modified-Levine\nPhenotypic Age",
"Homeostatic\nDysregulation",
"Log\nHomeostatic\nDysregulation")
#plot age vs bioage
plot_ba(data, agevar, label)## `geom_smooth()` using formula = 'y ~ x'## Warning: Removed 140840 rows containing non-finite values (`stat_smooth()`).## Warning: Removed 140840 rows containing missing values (`geom_point()`).
###Figure2. Correlations among biological aging measures The figure plots associations among the different biological aging measures. Cells below the diagonal show scatter plots of the measures listed above the cell (x-axis) and to the right (y-axis). Cells above the diagonal show the Pearson correlations for the measures listed below the cell and to the left. For this analysis, KDM Biological Age and Levine Phenotypic Age measures are differenced from chronological age (i.e. plotted values = BA-CA).
#select biological age variables
agevar = c("kdm_advance0","phenoage_advance0","kdm_advance","phenoage_advance","hd","hd_log")
#prepare lables
#values should be formatted for displaying along diagonal of the plot
#names should be used to match variables and order is preserved
label = c(
"kdm_advance0"="KDM\nBiological Age\nAdvancement",
"phenoage_advance0"="Levine\nPhenotypic Age\nAdvancement",
"kdm_advance"="Modified-KDM\nBiological Age\nAdvancement",
"phenoage_advance"="Modified-Levine\nPhenotypic Age\nAdvancement",
"hd" = "Homeostatic\nDysregulation",
"hd_log" = "Log\nHomeostatic\nDysregulation")
#use variable name to define the axis type ("int" or "float")
axis_type = c(
"kdm_advance0"="float",
"phenoage_advance0"="float",
"kdm_advance"="float",
"phenoage_advance"="flot",
"hd"="flot",
"hd_log"="float")
#plot BAA corplot
plot_baa(data,agevar,label,axis_type)
###Table 1. Associations of biological aging measures with mortality
table_surv(data, agevar, label)| Table 1. Associations of biological aging measures with mortality. BioAge coefficients in the table are hazard ratios estimated from Cox proportional hazard regressions. KDM Biological Age and Levine Phenotypic Age measures were differenced from chronological age for analysis (i.e. values = BA-CA). These differenced values were then standardized to have M=0, SD=1 separately for men and women within the analysis sample so that effect-sizes are denominated in terms of a sex-specific 1 SD unit increase in biological age advancement. Models included covariates for chronological age and sex. The original KDM Biological Age algorithm (left-most column) was projected onto data from NHANES 2007-2010 only because other NHANES IV waves did not include spirometry measurements. The original Levine Phenotypic Age algorithm (second column from left) was projected onto data from NHANES 1999-2010 and 2015-2018 only because the intervening waves did not include CRP measurements. | ||||||
| KDM Biological Age Advancement | Levine Phenotypic Age Advancement | Modified-KDM Biological Age Advancement | Modified-Levine Phenotypic Age Advancement | Homeostatic Dysregulation | Log Homeostatic Dysregulation | |
|---|---|---|---|---|---|---|
| Hazard Ratio (95% CI) | ||||||
| Full Sample | ||||||
| n | 8234 | 27837 | 26580 | 26580 | 26580 | 26580 |
| BioAge | 1.36 (1.2, 1.55) | 1.47 (1.42, 1.51) | 1.26 (1.22, 1.31) | 1.43 (1.37, 1.49) | 1.35 (1.3, 1.4) | 1.44 (1.38, 1.51) |
| Stratified by Gender | ||||||
| Men | ||||||
| n | 4114 | 13421 | 12879 | 12879 | 12879 | 12879 |
| BioAge | 1.44 (1.23, 1.69) | 1.44 (1.38, 1.5) | 1.28 (1.22, 1.34) | 1.41 (1.34, 1.49) | 1.32 (1.26, 1.38) | 1.4 (1.32, 1.49) |
| Women | ||||||
| n | 4120 | 14416 | 13701 | 13701 | 13701 | 13701 |
| BioAge | 1.23 (0.98, 1.54) | 1.52 (1.45, 1.6) | 1.24 (1.18, 1.31) | 1.46 (1.37, 1.55) | 1.39 (1.32, 1.48) | 1.53 (1.41, 1.66) |
| Stratified by Race | ||||||
| White | ||||||
| n | 3937 | 13958 | 13447 | 13447 | 13447 | 13447 |
| BioAge | 1.44 (1.21, 1.72) | 1.54 (1.47, 1.6) | 1.28 (1.22, 1.34) | 1.49 (1.42, 1.58) | 1.42 (1.35, 1.49) | 1.52 (1.43, 1.63) |
| Black | ||||||
| n | 1467 | 5176 | 4851 | 4851 | 4851 | 4851 |
| BioAge | 1.51 (1.15, 1.99) | 1.37 (1.28, 1.47) | 1.26 (1.17, 1.35) | 1.36 (1.26, 1.48) | 1.33 (1.23, 1.43) | 1.47 (1.31, 1.64) |
| Other | ||||||
| n | 2830 | 8703 | 8282 | 8282 | 8282 | 8282 |
| BioAge | 1.21 (0.89, 1.65) | 1.37 (1.28, 1.48) | 1.19 (1.1, 1.29) | 1.3 (1.19, 1.42) | 1.23 (1.14, 1.33) | 1.27 (1.15, 1.4) |
| People Aged 65 and Younger | ||||||
| Aged 65 and Younger | ||||||
| n | 6915 | 21252 | 20344 | 20344 | 20344 | 20344 |
| BioAge | 1.27 (1.06, 1.53) | 1.61 (1.52, 1.7) | 1.34 (1.25, 1.44) | 1.51 (1.41, 1.61) | 1.45 (1.36, 1.54) | 1.54 (1.42, 1.67) |
###Table 2. Associations of biological aging measures with healthspan-related characteristics The linear regression models and sample sizes in “Table 2” and “Table 3” below are saved as part of the list structure. Regression model can be drawn by typing table. Sample size can be drawn by typing n.
table2 = table_health(data,agevar,outcome = c("health","adl","lnwalk","grip_scaled"), label)
#pull table
table2$table| Table 2. Associations of biological aging measures with healthspan-related characteristics. Coefficients are from linear regressions of healthspan-related characteristics on biological aging measures. Outcome variables were standardized to have M=0, SD=1 for analysis. Standardization was performed separately for men and women in the case of grip strength. Walk speed was log transformed prior to standardization to reduce skew. KDM Biological Age and Levine Phenotypic Age measures were differenced from chronological age for analysis (i.e. values = BA-CA). These differenced values were then standardized to have M=0, SD=1 separately for men and women within the analysis sample so that effect-sizes are denominated in terms of a sex-specific 1 SD unit increase in biological age advancement. Models included covariates for chronological age and sex. The original KDM Biological Age algorithm (left-most column) was projected onto data from NHANES 2007-2010 only because other NHANES IV waves did not include spirometry measurements. The original Levine Phenotypic Age algorithm (second column from left) was projected onto data from NHANES 1999-2010 and 2015-2018 only because the intervening waves did not include CRP measurements. Walk speed was measured only in NHANES 1999-2002 and is available only for participants aged 50 and older. Grip strength was measured only in NHANES 2011-2014. | ||||||
| KDM Biological Age Advancement | Levine Phenotypic Age Advancement | Modified-KDM Biological Age Advancement | Modified-Levine Phenotypic Age Advancement | Homeostatic Dysregulation | Log Homeostatic Dysregulation | |
|---|---|---|---|---|---|---|
| b (95% CI) | ||||||
| Full Sample | ||||||
| health | 0.25 (0.23, 0.27) | 0.21 (0.2, 0.22) | 0.15 (0.14, 0.16) | 0.18 (0.17, 0.19) | 0.23 (0.21, 0.24) | 0.23 (0.22, 0.24) |
| adl | 0.13 (0.1, 0.16) | 0.17 (0.15, 0.19) | 0.09 (0.08, 0.11) | 0.14 (0.13, 0.16) | 0.11 (0.1, 0.13) | 0.12 (0.11, 0.14) |
| lnwalk | - | 0.21 (0.18, 0.24) | 0.1 (0.07, 0.12) | 0.15 (0.12, 0.18) | 0.15 (0.12, 0.18) | 0.17 (0.14, 0.2) |
| grip_scaled | - | - | - | - | - | - |
| Stratified by Gender | ||||||
| Men | ||||||
| health | 0.23 (0.2, 0.26) | 0.22 (0.2, 0.23) | 0.17 (0.15, 0.18) | 0.18 (0.17, 0.2) | 0.21 (0.2, 0.23) | 0.22 (0.2, 0.24) |
| adl | 0.12 (0.08, 0.15) | 0.15 (0.13, 0.17) | 0.1 (0.08, 0.12) | 0.12 (0.1, 0.14) | 0.09 (0.07, 0.11) | 0.1 (0.08, 0.13) |
| lnwalk | - | 0.16 (0.12, 0.2) | 0.08 (0.05, 0.12) | 0.11 (0.07, 0.14) | 0.12 (0.08, 0.15) | 0.14 (0.1, 0.18) |
| grip_scaled | - | - | - | - | - | - |
| Women | ||||||
| health | 0.28 (0.25, 0.31) | 0.22 (0.2, 0.23) | 0.14 (0.12, 0.15) | 0.17 (0.15, 0.19) | 0.24 (0.22, 0.26) | 0.24 (0.23, 0.26) |
| adl | 0.14 (0.09, 0.19) | 0.19 (0.17, 0.22) | 0.08 (0.06, 0.11) | 0.16 (0.14, 0.19) | 0.14 (0.12, 0.17) | 0.16 (0.13, 0.19) |
| lnwalk | - | 0.27 (0.22, 0.31) | 0.11 (0.07, 0.15) | 0.19 (0.14, 0.23) | 0.18 (0.13, 0.22) | 0.21 (0.16, 0.26) |
| grip_scaled | - | - | - | - | - | - |
| Stratified by Race | ||||||
| White | ||||||
| health | 0.3 (0.27, 0.33) | 0.27 (0.25, 0.28) | 0.17 (0.15, 0.18) | 0.25 (0.23, 0.26) | 0.24 (0.23, 0.26) | 0.24 (0.23, 0.26) |
| adl | 0.15 (0.11, 0.19) | 0.2 (0.18, 0.22) | 0.1 (0.08, 0.12) | 0.17 (0.15, 0.19) | 0.13 (0.11, 0.15) | 0.13 (0.11, 0.16) |
| lnwalk | - | 0.25 (0.21, 0.28) | 0.12 (0.09, 0.15) | 0.18 (0.15, 0.22) | 0.15 (0.11, 0.19) | 0.16 (0.12, 0.2) |
| grip_scaled | - | - | - | - | - | - |
| Black | ||||||
| health | 0.18 (0.13, 0.22) | 0.17 (0.14, 0.19) | 0.15 (0.13, 0.18) | 0.16 (0.14, 0.18) | 0.2 (0.17, 0.22) | 0.21 (0.18, 0.24) |
| adl | 0.08 (0, 0.16) | 0.13 (0.1, 0.17) | 0.08 (0.05, 0.12) | 0.11 (0.08, 0.15) | 0.11 (0.07, 0.15) | 0.12 (0.07, 0.17) |
| lnwalk | - | 0.14 (0.07, 0.21) | 0.03 (-0.03, 0.1) | 0.1 (0.03, 0.17) | 0.08 (0.01, 0.15) | 0.11 (0.02, 0.2) |
| grip_scaled | - | - | - | - | - | - |
| Other | ||||||
| health | 0.15 (0.11, 0.19) | 0.15 (0.13, 0.17) | 0.11 (0.09, 0.13) | 0.13 (0.11, 0.15) | 0.17 (0.15, 0.19) | 0.17 (0.15, 0.19) |
| adl | 0.15 (0.09, 0.21) | 0.15 (0.12, 0.18) | 0.09 (0.06, 0.12) | 0.12 (0.09, 0.15) | 0.1 (0.07, 0.13) | 0.12 (0.08, 0.15) |
| lnwalk | - | 0.15 (0.09, 0.21) | 0.01 (-0.04, 0.07) | 0.08 (0.03, 0.14) | 0.06 (0.01, 0.11) | 0.07 (0.01, 0.14) |
| grip_scaled | - | - | - | - | - | - |
| Stratified by Age | ||||||
| Age 20-40 | ||||||
| health | 0.21 (0.17, 0.25) | 0.19 (0.17, 0.21) | 0.15 (0.12, 0.17) | 0.12 (0.1, 0.14) | 0.19 (0.16, 0.22) | 0.15 (0.13, 0.18) |
| adl | 0.02 (-0.08, 0.13) | 0.11 (0.06, 0.17) | 0.04 (-0.02, 0.1) | 0.07 (0.02, 0.12) | 0.06 (0, 0.13) | 0.06 (0, 0.12) |
| lnwalk | - | - | - | - | - | - |
| grip_scaled | - | - | - | - | - | - |
| Age 40-60 | ||||||
| health | 0.28 (0.25, 0.32) | 0.26 (0.24, 0.28) | 0.19 (0.17, 0.21) | 0.22 (0.2, 0.24) | 0.28 (0.26, 0.3) | 0.28 (0.26, 0.3) |
| adl | 0.18 (0.09, 0.27) | 0.17 (0.12, 0.21) | 0.09 (0.05, 0.14) | 0.12 (0.08, 0.17) | 0.15 (0.1, 0.2) | 0.17 (0.12, 0.22) |
| lnwalk | - | 0.22 (0.17, 0.27) | 0.15 (0.1, 0.19) | 0.17 (0.13, 0.22) | 0.21 (0.17, 0.26) | 0.22 (0.17, 0.26) |
| grip_scaled | - | - | - | - | - | - |
| Age 60-80 | ||||||
| health | 0.26 (0.22, 0.3) | 0.21 (0.19, 0.23) | 0.14 (0.12, 0.15) | 0.2 (0.18, 0.22) | 0.22 (0.2, 0.24) | 0.26 (0.24, 0.28) |
| adl | 0.11 (0.08, 0.15) | 0.16 (0.14, 0.17) | 0.09 (0.07, 0.11) | 0.14 (0.12, 0.16) | 0.11 (0.1, 0.13) | 0.12 (0.1, 0.15) |
| lnwalk | - | 0.21 (0.17, 0.25) | 0.09 (0.06, 0.13) | 0.14 (0.1, 0.18) | 0.14 (0.1, 0.17) | 0.16 (0.12, 0.2) |
| grip_scaled | - | - | - | - | - | - |
#pull sample sizes
table2$n| Table 2.1. Sample sizes for regression in Table 2. Coefficients are from linear regressions of healthspan-related characteristics on biological aging measures. | ||||||
| KDM Biological Age Advancement | Levine Phenotypic Age Advancement | Modified-KDM Biological Age Advancement | Modified-Levine Phenotypic Age Advancement | Homeostatic Dysregulation | Log Homeostatic Dysregulation | |
|---|---|---|---|---|---|---|
| n | ||||||
| Full Sample | ||||||
| health | 7886 | 31077 | 30235 | 30235 | 30235 | 30235 |
| adl | 2812 | 14005 | 13512 | 13512 | 13512 | 13512 |
| lnwalk | - | 3607 | 3531 | 3531 | 3531 | 3531 |
| grip_scaled | - | - | - | - | - | - |
| Stratified by Gender | ||||||
| Men | ||||||
| health | 3974 | 15213 | 14849 | 14849 | 14849 | 14849 |
| adl | 1407 | 6921 | 6715 | 6715 | 6715 | 6715 |
| lnwalk | - | 1795 | 1768 | 1768 | 1768 | 1768 |
| grip_scaled | - | - | - | - | - | - |
| Women | ||||||
| health | 3912 | 15864 | 15386 | 15386 | 15386 | 15386 |
| adl | 1405 | 7084 | 6797 | 6797 | 6797 | 6797 |
| lnwalk | - | 1812 | 1763 | 1763 | 1763 | 1763 |
| grip_scaled | - | - | - | - | - | - |
| Stratified by Race | ||||||
| White | ||||||
| health | 3802 | 14634 | 14305 | 14305 | 14305 | 14305 |
| adl | 1537 | 7464 | 7256 | 7256 | 7256 | 7256 |
| lnwalk | - | 2122 | 2098 | 2098 | 2098 | 2098 |
| grip_scaled | - | - | - | - | - | - |
| Black | ||||||
| health | 1397 | 5938 | 5732 | 5732 | 5732 | 5732 |
| adl | 501 | 2486 | 2356 | 2356 | 2356 | 2356 |
| lnwalk | - | 547 | 525 | 525 | 525 | 525 |
| grip_scaled | - | - | - | - | - | - |
| Other | ||||||
| health | 2687 | 10505 | 10198 | 10198 | 10198 | 10198 |
| adl | 774 | 4055 | 3900 | 3900 | 3900 | 3900 |
| lnwalk | - | 938 | 908 | 908 | 908 | 908 |
| grip_scaled | - | - | - | - | - | - |
| Stratified by Age | ||||||
| Age 20-40 | ||||||
| health | 2864 | 10445 | 10161 | 10161 | 10161 | 10161 |
| adl | 298 | 1337 | 1286 | 1286 | 1286 | 1286 |
| lnwalk | - | - | - | - | - | - |
| grip_scaled | - | - | - | - | - | - |
| Age 40-60 | ||||||
| health | 2830 | 9866 | 9630 | 9630 | 9630 | 9630 |
| adl | 497 | 2180 | 2092 | 2092 | 2092 | 2092 |
| lnwalk | - | 1017 | 991 | 991 | 991 | 991 |
| grip_scaled | - | - | - | - | - | - |
| Age 60-80 | ||||||
| health | 2192 | 9916 | 9661 | 9661 | 9661 | 9661 |
| adl | 2017 | 9622 | 9321 | 9321 | 9321 | 9321 |
| lnwalk | - | 2133 | 2092 | 2092 | 2092 | 2092 |
| grip_scaled | - | - | - | - | - | - |
Table 3. Associations of socioeconomic circumstances measures with measures of biological aging
table3 = table_ses(data,agevar,exposure = c("edu","annual_income","poverty_ratio"), label)
#pull table
table3$table| Table 3. Associations of socioeconomic circumstances measures with measures of biological aging. Coefficients are from linear regressions of biological aging measures on measures of socioeconomic circumstances. KDM Biological Age and Levine Phenotypic Age measures were differenced from chronological age for analysis (i.e. values = BA-CA). These differenced values were then standardized to have M=0, SD=1 separately for men and women within the analysis sample. Socioeconomic circumstances measures were standardized to M=0, SD=1 for analysis so that effect-sizes are denominated in terms of a 1 SD unit improvement in socioeconomic circumstances. Models included covariates for chronological age and sex. The original KDM Biological Age algorithm (left-most column) was projected onto data from NHANES 2007-2010 only because other NHANES IV waves did not include spirometry measurements. The original Levine Phenotypic Age algorithm (second column from left) was projected onto data from NHANES 1999-2010 and 2015-2018 only because the intervening waves did not include CRP measurements. | ||||||
| KDM Biological Age Advancement | Levine Phenotypic Age Advancement | Modified-KDM Biological Age Advancement | Modified-Levine Phenotypic Age Advancement | Homeostatic Dysregulation | Log Homeostatic Dysregulation | |
|---|---|---|---|---|---|---|
| b (95% CI) | ||||||
| Full Sample | ||||||
| edu | -0.19 (-0.22, -0.17) | -0.07 (-0.08, -0.06) | -0.07 (-0.08, -0.06) | -0.09 (-0.1, -0.07) | -0.11 (-0.12, -0.1) | -0.11 (-0.12, -0.1) |
| annual_income | -0.17 (-0.19, -0.15) | -0.11 (-0.12, -0.1) | -0.08 (-0.09, -0.07) | -0.12 (-0.13, -0.11) | -0.12 (-0.13, -0.11) | -0.11 (-0.12, -0.11) |
| poverty_ratio | -0.18 (-0.21, -0.16) | -0.14 (-0.15, -0.13) | -0.07 (-0.08, -0.06) | -0.11 (-0.12, -0.1) | -0.12 (-0.13, -0.11) | -0.12 (-0.13, -0.11) |
| Stratified by Gender | ||||||
| Men | ||||||
| edu | -0.21 (-0.24, -0.18) | -0.08 (-0.09, -0.06) | -0.08 (-0.09, -0.06) | -0.09 (-0.11, -0.08) | -0.1 (-0.11, -0.09) | -0.1 (-0.11, -0.09) |
| annual_income | -0.16 (-0.19, -0.13) | -0.1 (-0.11, -0.08) | -0.06 (-0.08, -0.05) | -0.11 (-0.13, -0.1) | -0.11 (-0.12, -0.09) | -0.1 (-0.12, -0.09) |
| poverty_ratio | -0.18 (-0.21, -0.15) | -0.12 (-0.13, -0.1) | -0.07 (-0.08, -0.05) | -0.11 (-0.12, -0.09) | -0.11 (-0.13, -0.1) | -0.11 (-0.12, -0.1) |
| Women | ||||||
| edu | -0.18 (-0.21, -0.15) | -0.08 (-0.1, -0.07) | -0.06 (-0.08, -0.05) | -0.08 (-0.1, -0.07) | -0.12 (-0.13, -0.1) | -0.12 (-0.13, -0.1) |
| annual_income | -0.18 (-0.21, -0.15) | -0.12 (-0.13, -0.11) | -0.09 (-0.1, -0.07) | -0.13 (-0.15, -0.12) | -0.13 (-0.14, -0.12) | -0.12 (-0.14, -0.11) |
| poverty_ratio | -0.19 (-0.22, -0.16) | -0.15 (-0.17, -0.14) | -0.07 (-0.08, -0.05) | -0.11 (-0.13, -0.1) | -0.13 (-0.14, -0.12) | -0.12 (-0.13, -0.11) |
| Stratified by Race | ||||||
| White | ||||||
| edu | -0.24 (-0.27, -0.21) | -0.14 (-0.15, -0.12) | -0.1 (-0.11, -0.08) | -0.17 (-0.19, -0.16) | -0.11 (-0.13, -0.1) | -0.12 (-0.13, -0.1) |
| annual_income | -0.18 (-0.21, -0.15) | -0.14 (-0.16, -0.13) | -0.09 (-0.1, -0.07) | -0.17 (-0.18, -0.15) | -0.12 (-0.14, -0.11) | -0.12 (-0.13, -0.11) |
| poverty_ratio | -0.19 (-0.21, -0.16) | -0.17 (-0.19, -0.16) | -0.08 (-0.1, -0.07) | -0.17 (-0.18, -0.15) | -0.11 (-0.13, -0.1) | -0.11 (-0.13, -0.1) |
| Black | ||||||
| edu | -0.11 (-0.17, -0.06) | -0.04 (-0.06, -0.01) | -0.05 (-0.08, -0.02) | -0.08 (-0.11, -0.05) | -0.08 (-0.11, -0.06) | -0.06 (-0.08, -0.04) |
| annual_income | -0.12 (-0.18, -0.07) | -0.1 (-0.12, -0.07) | -0.1 (-0.13, -0.08) | -0.11 (-0.14, -0.09) | -0.1 (-0.12, -0.08) | -0.08 (-0.1, -0.06) |
| poverty_ratio | -0.12 (-0.17, -0.06) | -0.14 (-0.16, -0.11) | -0.1 (-0.12, -0.07) | -0.11 (-0.14, -0.09) | -0.11 (-0.13, -0.09) | -0.09 (-0.11, -0.07) |
| Other | ||||||
| edu | -0.1 (-0.13, -0.07) | -0.02 (-0.03, 0) | -0.04 (-0.06, -0.03) | -0.05 (-0.07, -0.03) | -0.08 (-0.1, -0.07) | -0.08 (-0.1, -0.07) |
| annual_income | -0.09 (-0.13, -0.05) | -0.03 (-0.05, -0.02) | -0.03 (-0.05, -0.02) | -0.09 (-0.1, -0.07) | -0.08 (-0.1, -0.07) | -0.08 (-0.1, -0.06) |
| poverty_ratio | -0.11 (-0.15, -0.08) | -0.06 (-0.08, -0.05) | -0.02 (-0.04, -0.01) | -0.07 (-0.09, -0.05) | -0.08 (-0.1, -0.07) | -0.08 (-0.1, -0.06) |
| Stratified by Age | ||||||
| Age 20-40 | ||||||
| edu | -0.14 (-0.18, -0.11) | -0.08 (-0.09, -0.06) | -0.02 (-0.04, -0.01) | -0.06 (-0.08, -0.04) | -0.06 (-0.07, -0.04) | -0.07 (-0.09, -0.06) |
| annual_income | -0.09 (-0.12, -0.06) | -0.06 (-0.08, -0.05) | 0 (-0.02, 0.01) | -0.05 (-0.07, -0.03) | -0.03 (-0.05, -0.02) | -0.05 (-0.06, -0.03) |
| poverty_ratio | -0.13 (-0.16, -0.1) | -0.1 (-0.11, -0.08) | -0.01 (-0.02, 0.01) | -0.04 (-0.05, -0.02) | -0.04 (-0.05, -0.03) | -0.05 (-0.07, -0.04) |
| Age 40-60 | ||||||
| edu | -0.2 (-0.24, -0.17) | -0.09 (-0.1, -0.07) | -0.08 (-0.1, -0.07) | -0.09 (-0.11, -0.07) | -0.12 (-0.14, -0.11) | -0.13 (-0.14, -0.11) |
| annual_income | -0.19 (-0.23, -0.16) | -0.15 (-0.17, -0.13) | -0.09 (-0.11, -0.08) | -0.16 (-0.18, -0.14) | -0.14 (-0.16, -0.13) | -0.15 (-0.17, -0.13) |
| poverty_ratio | -0.2 (-0.23, -0.16) | -0.17 (-0.18, -0.15) | -0.08 (-0.09, -0.06) | -0.13 (-0.15, -0.11) | -0.14 (-0.16, -0.12) | -0.14 (-0.16, -0.13) |
| Age 60-80 | ||||||
| edu | -0.24 (-0.28, -0.2) | -0.07 (-0.09, -0.05) | -0.09 (-0.11, -0.07) | -0.09 (-0.11, -0.07) | -0.14 (-0.16, -0.12) | -0.12 (-0.14, -0.1) |
| annual_income | -0.24 (-0.29, -0.19) | -0.1 (-0.12, -0.08) | -0.11 (-0.14, -0.09) | -0.13 (-0.15, -0.11) | -0.16 (-0.18, -0.14) | -0.14 (-0.16, -0.12) |
| poverty_ratio | -0.25 (-0.3, -0.21) | -0.14 (-0.16, -0.12) | -0.12 (-0.14, -0.09) | -0.14 (-0.16, -0.11) | -0.18 (-0.2, -0.16) | -0.16 (-0.18, -0.14) |
#pull sample sizes
table3$n| Table 3.1: Sample sizes for regression in Table 3. Coefficients are from linear regressions of biological aging measures on measures of socioeconomic circumstances. | ||||||
| KDM Biological Age Advancement | Levine Phenotypic Age Advancement | Modified-KDM Biological Age Advancement | Modified-Levine Phenotypic Age Advancement | Homeostatic Dysregulation | Log Homeostatic Dysregulation | |
|---|---|---|---|---|---|---|
| n | ||||||
| Full Sample | ||||||
| edu | 8234 | 37526 | 35910 | 35910 | 35910 | 35910 |
| annual_income | 7553 | 34245 | 32818 | 32818 | 32818 | 32818 |
| poverty_ratio | 7553 | 34245 | 32818 | 32818 | 32818 | 32818 |
| Stratified by Gender | ||||||
| Men | ||||||
| edu | 4116 | 18072 | 17384 | 17384 | 17384 | 17384 |
| annual_income | 3785 | 16563 | 15948 | 15948 | 15948 | 15948 |
| poverty_ratio | 3785 | 16563 | 15948 | 15948 | 15948 | 15948 |
| Women | ||||||
| edu | 4118 | 19454 | 18526 | 18526 | 18526 | 18526 |
| annual_income | 3768 | 17682 | 16870 | 16870 | 16870 | 16870 |
| poverty_ratio | 3768 | 17682 | 16870 | 16870 | 16870 | 16870 |
| Stratified by Race | ||||||
| White | ||||||
| edu | 3937 | 17297 | 16682 | 16682 | 16682 | 16682 |
| annual_income | 3728 | 16194 | 15642 | 15642 | 15642 | 15642 |
| poverty_ratio | 3728 | 16194 | 15642 | 15642 | 15642 | 15642 |
| Black | ||||||
| edu | 1468 | 7218 | 6820 | 6820 | 6820 | 6820 |
| annual_income | 1336 | 6525 | 6167 | 6167 | 6167 | 6167 |
| poverty_ratio | 1336 | 6525 | 6167 | 6167 | 6167 | 6167 |
| Other | ||||||
| edu | 2829 | 13011 | 12408 | 12408 | 12408 | 12408 |
| annual_income | 2489 | 11526 | 11009 | 11009 | 11009 | 11009 |
| poverty_ratio | 2489 | 11526 | 11009 | 11009 | 11009 | 11009 |
| Stratified by Age | ||||||
| Age 20-40 | ||||||
| edu | 3014 | 12944 | 12350 | 12350 | 12350 | 12350 |
| annual_income | 2791 | 11947 | 11426 | 11426 | 11426 | 11426 |
| poverty_ratio | 2791 | 11947 | 11426 | 11426 | 11426 | 11426 |
| Age 40-60 | ||||||
| edu | 2961 | 11798 | 11323 | 11323 | 11323 | 11323 |
| annual_income | 2714 | 10827 | 10402 | 10402 | 10402 | 10402 |
| poverty_ratio | 2714 | 10827 | 10402 | 10402 | 10402 | 10402 |
| Age 60-80 | ||||||
| edu | 2259 | 11641 | 11193 | 11193 | 11193 | 11193 |
| annual_income | 2048 | 10447 | 10049 | 10049 | 10049 | 10049 |
| poverty_ratio | 2048 | 10447 | 10049 | 10049 | 10049 | 10049 |
###Step 3: Project biological aging measures onto new data In this example, the projection dataset is from the CALERIE randomized controlled trial (data are not included in the package). For this analysis, CALERIE data were previously cleaned and units of measure and variable names were harmonized to match the NHANES data included with the package. All algorithms were trained using the NHANES III data and projected into the CALERIE using the hd_calc, kdm_calc, and phenoage_calc functions of the BioAge package.
##Projecting HD into the CALERIE using NHANES III For HD, the constructed variable is based on a malhanobis distance statistic, which is theoretically the distance between observations and a hypothetically healthy, young cohort. In this example, I train separately for men and women who are between the ages of 20 and 30 and not pregnant, and have observe biomarker data within clinically acceptable distributions. For clinical guidelines, I relied upon the ranges reported by the Mayo Clinic website.
#The CALERIE dataset is loaded from my local drive that has previously been downloaded and cleaned
#projecting HD into the CALERIE using NHANES III (seperate training for gender)
# hd_fem = hd_calc(data = CALERIE %>%
# filter(gender == 2)%>%
# mutate(lncrp = log(crp)),
# reference = NHANES3_CLEAN %>%
# filter(gender == 2)%>%
# mutate(lncrp = log(crp)),
# biomarkers=c("albumin","alp","lncrp","totchol","lncreat","hba1c","sbp","bun","uap","lymph","mcv","wbc"))
#
# hd_male = hd_calc(data = CALERIE %>%
# filter(gender == 1)%>%
# mutate(lncrp = log(crp)),
# reference = NHANES3_CLEAN %>%
# filter(gender == 1)%>%
# mutate(lncrp = log(crp)),
# biomarkers=c("albumin","alp","lncrp","totchol","lncreat","hba1c","sbp","bun","uap","lymph","mcv","wbc"))
#
# #pull the HD dataset
# hd_data = rbind(hd_fem$data, hd_male$data)###Projecting KDM bioage into the CALERIE using NHANES III Having estimated biological aging models using NHANES III in “Step 1”, I can project KDM bioage and phenoage into the CALERIE data by running kdm_calc and phenoage_calc and supplying a fit argument.
#projecting KDM bioage into the CALERIE using NHANES III (seperate training for gender)
# kdm_fem = kdm_calc(data = CALERIE %>%
# filter (gender ==2),
# biomarkers=c("albumin","alp","lncrp","totchol","lncreat","hba1c","sbp","bun","uap","lymph","mcv","wbc"),
# fit = kdm$fit$female,
# s_ba2 = kdm$fit$female$s_b2)
#
# kdm_male = kdm_calc(data = CALERIE %>%
# filter (gender ==1),
# biomarkers=c("albumin","alp","lncrp","totchol","lncreat","hba1c","sbp","bun","uap","lymph","mcv","wbc"),
# fit = kdm$fit$male,
# s_ba2 = kdm$fit$male$s_b2)
#pull the KDM dataset
# kdm_data = rbind(kdm_fem$data, kdm_male$data)###Projecting phenoage into the CALERIE using NHANES III
# phenoage_CALERIE = phenoage_calc(data = CALERIE,
# biomarkers = c("albumin_gL","alp","lncrp","totchol","lncreat_umol","hba1c","sbp","bun","uap","lymph","mcv","wbc"),
# fit = phenoage$fit)
#
# phenoage_data = phenoage_CALERIE$data
#
# #pull the full dataset
# newdata = left_join(CALERIE, hd_data[, c("sampleID", "hd", "hd_log")], by = "sampleID") %>%
# left_join(., kdm_data[, c("sampleID", "kdm", "kdm_advance")], by = "sampleID") %>%
# left_join(., phenoage_data[, c("sampleID","phenoage","phenoage_advance")], by = "sampleID") ###Summary statistics of calculated biological aging measures for the CALERIE at pre-intervention baseline
# summary(newdata %>% filter(fu==0) %>% select(kdm, phenoage, hd, hd_log))
#> kdm phenoage hd hd_log
#> Min. :22.37 Min. :11.97 Min. :0.8641 Min. :2.097
#> 1st Qu.:31.79 1st Qu.:27.41 1st Qu.:2.2555 1st Qu.:4.695
#> Median :38.70 Median :32.99 Median :2.7147 Median :5.229
#> Mean :37.43 Mean :32.64 Mean :2.9256 Mean :5.324
#> 3rd Qu.:42.84 3rd Qu.:38.14 3rd Qu.:3.4509 3rd Qu.:6.023
#> Max. :50.60 Max. :50.58 Max. :7.9852 Max. :8.797
#> NA's :13 NA's :13 NA's :13 NA's :13Note that the echo = FALSE parameter was added to the
code chunk to prevent printing of the R code that generated the
plot.