# ordenar os desfechos 1 na frente dos 0
require(survminer)
## Loading required package: survminer
## Warning: package 'survminer' was built under R version 4.0.5
## Loading required package: ggplot2
## Loading required package: ggpubr
## Warning: package 'ggpubr' was built under R version 4.0.5
require(survival)
## Loading required package: survival
require(readxl)
## Loading required package: readxl
#Coinfectados
Cronicos_TB_IO_Janela_para_Lu_1_ <- read_excel("Cronicos_TB_IO Janela para Lu (1).xlsx",
sheet = "Coinfectados_TB")
#load("~/banco.Rdata")
#dataset<-banco
#require(survival)
#require(dplyr)
#require(XML)
#require(survminer)
load("C:/Users/edson/Downloads/luciane_novo/outrasvar.RData")
#load("C:/Users/edson/Downloads/luciane_novo/banco_desfecho.RData")
#load("C:/Users/edson/Downloads/luciane_novo/cv_baseFEV21.RData")
#banco_desfecho$Grupo6<-banco_desfecho$Grupo5
#ordenar os desfechos 1 na frente dos 0
#require(dplyr)
#banco_desfecho<-arrange(banco_desfecho,desc(banco_desfecho$desfecho))
#selecionar primeiro prontuario quando tiver mais de um
#banco_desfecho2<-distinct(banco_desfecho, banco_desfecho$Registro, .keep_all=T)
#tranformar dias em meses
#banco_desfecho2$tempomeses<-banco_desfecho2$tempocarini/30
#banco_desfecho2$tempomeses<-as.numeric(banco_desfecho2$tempomeses)
#transformar em NA quando grupo 5 == somente cronico sem cd4
#banco_desfecho2$Grupo5[banco_desfecho2$Grupo5=="Crônico"]<-NA
#banco_desfecho2$Grupo6[banco_desfecho2$Grupo6=="Crônico"]<-NA
#Reordenar fatores
#banco_desfecho2$Grupo5[banco_desfecho2$Grupo5=="Agudo"]<-"0Agudo"
#banco_desfecho2$Grupo5[banco_desfecho2$Grupo5=="Recente"]<-"1Recente"
#banco_desfecho2$Grupo5[banco_desfecho2$Grupo5=="Crônico<350"]<-"2Cronicomenor350"
#banco_desfecho2$Grupo5[banco_desfecho2$Grupo5=="Crônico>=350"]<-"3Cronico=>350"
#Kaplan
require(XML)
## Loading required package: XML
## Warning: package 'XML' was built under R version 4.0.5
require(dplyr)
## Loading required package: dplyr
## Warning: package 'dplyr' was built under R version 4.0.4
##
## 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
#Merge com cv
#banco<-merge(banco_desfecho2,cv_baseFEV21)
# Merge com banco Modelo4
#banco<-merge(banco, modelo4_enviadoEdu_1_)
#load("C:/Users/edson/Downloads/cd8_base.RData")
#banco<-merge(banco,cd8_base)
#Escolaridade
#banco$escola2[banco$escola=="mais de 12 anos"]<-"12 year or more of schooling"
#banco$escola2[banco$escola!="mais de 12 anos"]<-"less than 12 years of schooling"
#banco$escola2<-as.factor(banco$escola2)
#load("~/banco.Rdata")
#subset para fazer o table stack
#banco2<-subset(banco, select = c(gon, clam, sifilis,hbv_cronico.y.x, esquema2, CMV_pos_ARV,escola2, Registro))
#banco3<-banco2
#transformar desfecho em fator
#banco2$desfecho<-as.factor(banco2$desfecho)
#banco<-merge(banco_desfecho2, banco2,by="Registro")
#banco<-merge(banco,cd8_base)
#banco<-merge(banco,modelo4_enviadoEdu_1_)
#banco<-merge(banco,cd8_base)
#banco<-merge(banco,cv_baseFEV21)
#banco$idade[banco$Registro==34706]<-18.66593
#banco2<-banco
#banco3<-banco2
#transformar desfecho em fator
#banco2$desfecho<-as.factor(banco2$desfecho)
#banco$escola2[banco$escola=="mais de 12 anos"]<-"12 year or more of schooling"
#banco$escola2[banco$escola!="mais de 12 anos"]<-"less than 12 years of schooling"
#banco$escola2[banco$escola2=="até 8 anos"]<-"less than 12 years of schooling"
#banco$escola2[banco$escola==NA]<-NA
require(readxl)
require(utils)
banco<-read.csv2("C:/Users/edson/OneDrive/Documentos/IVAS_EDU.csv",header = T,sep=",")
banco$logcv<-as.numeric(banco$logcv)
banco$cv<-as.numeric(banco$cv)
banco$cd8_cd4<-as.numeric(banco$cd8_cd4)
banco<-full_join(banco,Cronicos_TB_IO_Janela_para_Lu_1_)
## Joining, by = "Registro"
banco$coinfec2<-"n"
banco$coinfec2[banco$coinfec=="s"]<-"s"
Cronicos_TB_IO_Janela_para_Lu_1_ <- read_excel("Cronicos_TB_IO Janela para Lu (1).xlsx",
sheet = "Doenças Relacionadas")
## New names:
## * `` -> ...7
como<-dplyr::distinct (Cronicos_TB_IO_Janela_para_Lu_1_,Cronicos_TB_IO_Janela_para_Lu_1_$Registro,.keep_all=T)
a<-dplyr::left_join(banco,como, by="Registro")
a$qualquerco<-0
a$qualquerco[is.na(a$I202_DOEN.y)==F]<-1
a$qualquerco<-as.factor(a$qualquerco)
banco<-a
#banco <- read_excel("C:/Users/edson/OneDrive/Documentos/IVAS_EDU.xlsx")
#banco_lu_update <- read_excel("C:/Users/edson/OneDrive/Documentos/banco_lu_update.xlsx")
#g<-subset(banco_lu_update,select = c(Registro, FIBIG2))
#banco<-dplyr::left_join(banco, g, by="Registro")
banco$tempomeses<-as.numeric(banco$tempomeses)
.Survfit <- survfit(Surv(tempomeses, desfecho) ~ Grupo5,
conf.type="log", conf.int=0.95, type="kaplan-meier", error="greenwood",
data=banco)
ggsurvplot(.Survfit, data = banco,
# Change legends: title & labels
ylab="Probability of CD4/CD8 ratio normalization",
legend.title = "Grupos",
legend.labs = c("Acute HIV infection", "Recent HIV Infection","Chronic HIV Infection, TCD4 <350","Chronic HIV Infection, TCD4>=350"),
# Add p-value and tervals
pval = TRUE,
conf.int = F,
conf.int.style="step"
)
.Survfit
## Call: survfit(formula = Surv(tempomeses, desfecho) ~ Grupo5, data = banco,
## error = "greenwood", conf.type = "log", conf.int = 0.95,
## type = "kaplan-meier")
##
## 55 observations deleted due to missingness
## n events median 0.95LCL 0.95UCL
## Grupo5=0Agudo 65 49 1.13e+14 1.03e+14 2.51e+14
## Grupo5=1Recente 35 25 1.20e+14 1.67e-01 4.39e+14
## Grupo5=2Cronicomenor350 193 33 8.73e+14 7.47e+14 NA
## Grupo5=3Cronico=>350 257 92 5.63e+14 4.62e+14 7.67e+14
summary(.Survfit)
## Call: survfit(formula = Surv(tempomeses, desfecho) ~ Grupo5, data = banco,
## error = "greenwood", conf.type = "log", conf.int = 0.95,
## type = "kaplan-meier")
##
## 55 observations deleted due to missingness
## Grupo5=0Agudo
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 1.67e-01 65 24 0.6308 0.0599 0.5237 0.760
## 1.03e+14 32 2 0.5913 0.0623 0.4811 0.727
## 1.04e+14 30 1 0.5716 0.0632 0.4602 0.710
## 1.07e+14 29 2 0.5322 0.0647 0.4193 0.675
## 1.13e+14 27 2 0.4928 0.0657 0.3795 0.640
## 1.17e+14 25 2 0.4534 0.0661 0.3407 0.603
## 1.27e+14 23 1 0.4337 0.0661 0.3217 0.585
## 1.63e+14 22 1 0.4139 0.0659 0.3029 0.566
## 2.33e+14 20 1 0.3932 0.0658 0.2833 0.546
## 2.43e+14 19 1 0.3725 0.0655 0.2639 0.526
## 2.47e+14 18 1 0.3519 0.0651 0.2449 0.506
## 2.51e+14 17 1 0.3312 0.0644 0.2261 0.485
## 2.93e+14 16 1 0.3105 0.0637 0.2077 0.464
## 2.97e+14 15 1 0.2898 0.0627 0.1896 0.443
## 3.23e+14 14 1 0.2691 0.0615 0.1719 0.421
## 3.63e+14 11 2 0.2201 0.0593 0.1299 0.373
## 5.73e+14 7 1 0.1887 0.0586 0.1027 0.347
## 5.77e+14 6 1 0.1572 0.0566 0.0776 0.318
## 5.97e+14 5 1 0.1258 0.0533 0.0548 0.289
## 6.13e+14 4 1 0.0943 0.0484 0.0345 0.258
## 6.17e+14 3 1 0.0629 0.0412 0.0174 0.227
##
## Grupo5=1Recente
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 1.67e-01 35 13 0.629 0.0817 0.4873 0.811
## 1.03e+14 18 1 0.594 0.0843 0.4495 0.784
## 1.12e+14 17 1 0.559 0.0862 0.4129 0.756
## 1.13e+14 16 1 0.524 0.0876 0.3774 0.727
## 1.20e+14 15 1 0.489 0.0885 0.3429 0.697
## 1.43e+14 14 1 0.454 0.0888 0.3094 0.666
## 1.87e+14 12 1 0.416 0.0891 0.2735 0.633
## 2.03e+14 11 1 0.378 0.0887 0.2390 0.599
## 2.93e+14 10 1 0.340 0.0875 0.2058 0.563
## 3.03e+14 9 1 0.303 0.0856 0.1739 0.527
## 4.39e+14 7 1 0.259 0.0835 0.1380 0.488
## 4.63e+14 6 1 0.216 0.0800 0.1046 0.447
## 6.47e+14 5 1 0.173 0.0748 0.0741 0.404
##
## Grupo5=2Cronicomenor350
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 1.67e-01 193 15 0.922 0.0193 0.8853 0.961
## 1.12e+14 116 1 0.914 0.0207 0.8747 0.956
## 1.38e+14 108 1 0.906 0.0222 0.8635 0.950
## 1.64e+14 98 1 0.897 0.0238 0.8512 0.944
## 1.73e+14 93 1 0.887 0.0254 0.8386 0.938
## 1.74e+14 91 1 0.877 0.0269 0.8260 0.932
## 1.77e+14 87 1 0.867 0.0284 0.8132 0.925
## 1.97e+14 85 1 0.857 0.0299 0.8003 0.918
## 2.31e+14 76 1 0.846 0.0315 0.7860 0.910
## 2.40e+14 73 1 0.834 0.0332 0.7715 0.902
## 2.77e+14 61 1 0.820 0.0353 0.7540 0.893
## 3.37e+14 45 1 0.802 0.0390 0.7293 0.882
## 3.68e+14 42 1 0.783 0.0425 0.7041 0.871
## 4.63e+14 29 1 0.756 0.0488 0.6662 0.858
## 4.78e+14 27 1 0.728 0.0545 0.6288 0.843
## 4.90e+14 26 1 0.700 0.0591 0.5933 0.826
## 7.47e+14 10 1 0.630 0.0851 0.4835 0.821
## 7.63e+14 8 1 0.551 0.1048 0.3799 0.800
## 8.73e+14 2 1 0.276 0.2018 0.0656 1.000
##
## Grupo5=3Cronico=>350
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 1.67e-01 257 27 0.8949 0.0191 0.8582 0.933
## 1.03e+14 186 1 0.8901 0.0196 0.8525 0.929
## 1.06e+14 185 1 0.8853 0.0201 0.8468 0.926
## 1.07e+14 184 1 0.8805 0.0206 0.8411 0.922
## 1.09e+14 183 1 0.8757 0.0210 0.8355 0.918
## 1.10e+14 182 1 0.8709 0.0214 0.8299 0.914
## 1.11e+14 181 1 0.8661 0.0218 0.8243 0.910
## 1.17e+14 180 1 0.8613 0.0222 0.8187 0.906
## 1.20e+14 179 1 0.8564 0.0226 0.8132 0.902
## 1.22e+14 177 1 0.8516 0.0230 0.8077 0.898
## 1.25e+14 176 1 0.8468 0.0234 0.8021 0.894
## 1.27e+14 174 1 0.8419 0.0238 0.7966 0.890
## 1.33e+14 170 1 0.8370 0.0241 0.7910 0.886
## 1.35e+14 169 1 0.8320 0.0245 0.7854 0.881
## 1.37e+14 167 1 0.8270 0.0248 0.7797 0.877
## 1.52e+14 158 1 0.8218 0.0252 0.7738 0.873
## 1.54e+14 157 2 0.8113 0.0260 0.7620 0.864
## 1.69e+14 148 1 0.8058 0.0264 0.7558 0.859
## 1.73e+14 145 1 0.8003 0.0268 0.7495 0.854
## 1.75e+14 144 1 0.7947 0.0272 0.7432 0.850
## 1.79e+14 141 1 0.7891 0.0275 0.7369 0.845
## 1.80e+14 140 1 0.7834 0.0279 0.7306 0.840
## 1.87e+14 137 1 0.7777 0.0283 0.7242 0.835
## 1.97e+14 133 1 0.7719 0.0287 0.7177 0.830
## 2.12e+14 125 1 0.7657 0.0291 0.7107 0.825
## 2.15e+14 124 1 0.7595 0.0295 0.7038 0.820
## 2.27e+14 120 1 0.7532 0.0299 0.6967 0.814
## 2.37e+14 118 1 0.7468 0.0304 0.6896 0.809
## 2.47e+14 116 1 0.7404 0.0308 0.6825 0.803
## 2.63e+14 112 1 0.7338 0.0312 0.6751 0.798
## 2.67e+14 111 1 0.7272 0.0316 0.6678 0.792
## 2.71e+14 108 1 0.7204 0.0320 0.6603 0.786
## 2.73e+14 107 1 0.7137 0.0324 0.6529 0.780
## 2.77e+14 106 1 0.7070 0.0328 0.6455 0.774
## 2.91e+14 94 1 0.6994 0.0333 0.6371 0.768
## 2.97e+14 93 1 0.6919 0.0338 0.6288 0.761
## 3.07e+14 86 1 0.6839 0.0343 0.6198 0.755
## 3.10e+14 85 1 0.6758 0.0349 0.6108 0.748
## 3.27e+14 80 1 0.6674 0.0354 0.6014 0.741
## 3.67e+14 70 1 0.6578 0.0362 0.5906 0.733
## 3.87e+14 63 1 0.6474 0.0371 0.5786 0.724
## 3.93e+14 62 1 0.6370 0.0379 0.5668 0.716
## 4.07e+14 61 1 0.6265 0.0387 0.5550 0.707
## 4.24e+14 58 1 0.6157 0.0395 0.5429 0.698
## 4.25e+14 56 1 0.6047 0.0403 0.5306 0.689
## 4.33e+14 55 1 0.5937 0.0411 0.5184 0.680
## 4.43e+14 54 1 0.5827 0.0418 0.5064 0.671
## 4.62e+14 52 1 0.5715 0.0424 0.4941 0.661
## 4.77e+14 50 1 0.5601 0.0431 0.4817 0.651
## 5.17e+14 48 3 0.5251 0.0449 0.4441 0.621
## 5.58e+14 40 1 0.5120 0.0456 0.4299 0.610
## 5.63e+14 38 1 0.4985 0.0464 0.4154 0.598
## 5.77e+14 37 1 0.4850 0.0471 0.4010 0.587
## 5.97e+14 33 1 0.4703 0.0479 0.3853 0.574
## 6.23e+14 28 1 0.4535 0.0490 0.3669 0.561
## 6.97e+14 19 1 0.4297 0.0519 0.3390 0.544
## 7.03e+14 17 1 0.4044 0.0547 0.3102 0.527
## 7.63e+14 11 1 0.3676 0.0608 0.2658 0.508
## 7.67e+14 9 1 0.3268 0.0664 0.2195 0.487
## 8.36e+14 4 1 0.2451 0.0865 0.1227 0.490
## 8.53e+14 3 1 0.1634 0.0882 0.0567 0.471
## 9.33e+14 2 1 0.0817 0.0727 0.0143 0.467
## 9.37e+14 1 1 0.0000 NaN NA NA
banco$desfecho<-as.factor(banco$desfecho)
#Escolaridade
htmlTable::htmlTable(epiDisplay::tableStack(c(gon, clam, sifilis,hbv_cronico.y.x, esquema2, CMV_pos_ARV,escola2,cd4,cd8,cd8_cd4,FIBIG2, tempomeses, desfecho, COR,GENERO, idade,coinfec2,qualquerco), by=Grupo5, percent= "column", simulate.p.value = T, dataFrame = banco, var.labels = F, decimal = 2, total.column = T))
|
|
0Agudo
|
1Recente
|
2Cronicomenor350
|
3Cronico=>350
|
Total
|
Test stat.
|
P value
|
|
Total
|
65
|
35
|
193
|
257
|
605
|
|
|
|
|
|
|
|
|
|
|
|
|
16 : gon
|
|
|
|
|
|
Fisher’s exact test
|
0.0925
|
|
Não
|
12 (70.59)
|
0 (0)
|
18 (85.71)
|
48 (87.27)
|
78 (82.98)
|
|
|
|
Sim
|
5 (29.41)
|
1 (100)
|
3 (14.29)
|
7 (12.73)
|
16 (17.02)
|
|
|
|
|
|
|
|
|
|
|
|
|
17 : clam
|
|
|
|
|
|
Fisher’s exact test
|
0.5152
|
|
Não
|
13 (76.47)
|
1 (100)
|
19 (90.48)
|
41 (74.55)
|
74 (78.72)
|
|
|
|
Sim
|
4 (23.53)
|
0 (0)
|
2 (9.52)
|
14 (25.45)
|
20 (21.28)
|
|
|
|
|
|
|
|
|
|
|
|
|
18 : sifilis
|
|
|
|
|
|
Chisq. (3 df) = 2.634
|
0.4516
|
|
Não
|
46 (82.14)
|
21 (84)
|
94 (74.02)
|
123 (74.1)
|
284 (75.94)
|
|
|
|
Sim
|
10 (17.86)
|
4 (16)
|
33 (25.98)
|
43 (25.9)
|
90 (24.06)
|
|
|
|
|
|
|
|
|
|
|
|
|
19 : hbv_cronico.y.x
|
|
|
|
|
|
Fisher’s exact test
|
0.0355
|
|
não
|
62 (100)
|
33 (100)
|
169 (96.02)
|
236 (99.58)
|
500 (98.43)
|
|
|
|
sim
|
0 (0)
|
0 (0)
|
7 (3.98)
|
1 (0.42)
|
8 (1.57)
|
|
|
|
|
|
|
|
|
|
|
|
|
20 : esquema2
|
|
|
|
|
|
Chisq. (6 df) = 57.719
|
< 0.001
|
|
INSTI
|
29 (44.62)
|
4 (11.43)
|
90 (46.63)
|
158 (61.48)
|
281 (51.09)
|
|
|
|
IP
|
17 (26.15)
|
3 (8.57)
|
35 (18.13)
|
19 (7.39)
|
74 (13.45)
|
|
|
|
NNRTI
|
19 (29.23)
|
28 (80)
|
68 (35.23)
|
80 (31.13)
|
195 (35.45)
|
|
|
|
|
|
|
|
|
|
|
|
|
21 : CMV_pos_ARV
|
|
|
|
|
|
Kruskal-Wallis test
|
0.5898
|
|
median(IQR)
|
1 (1,1)
|
1 (1,1)
|
1 (1,1)
|
1 (1,1)
|
1 (1,1)
|
|
|
|
|
|
|
|
|
|
|
|
|
22 : escola2
|
|
|
|
|
|
Chisq. (3 df) = 28.568
|
< 0.001
|
|
12 year or more of schooling
|
21 (32.31)
|
18 (51.43)
|
32 (16.93)
|
44 (17.19)
|
115 (21.1)
|
|
|
|
less than 12 years of schooling
|
44 (67.69)
|
17 (48.57)
|
157 (83.07)
|
212 (82.81)
|
430 (78.9)
|
|
|
|
|
|
|
|
|
|
|
|
|
5 : cd4
|
|
|
|
|
|
Kruskal-Wallis test
|
< 0.001
|
|
median(IQR)
|
582 (399.25,845.25)
|
588.5 (439,679)
|
160 (71,255)
|
553 (433,773)
|
424 (237,633)
|
|
|
|
|
|
|
|
|
|
|
|
|
4 : cd8
|
|
|
|
|
|
Kruskal-Wallis test
|
< 0.001
|
|
median(IQR)
|
940 (545.5,1609)
|
1243 (814,1651.25)
|
912.5 (545.5,1207.75)
|
1124.5 (895,1528.75)
|
1043 (696.5,1473)
|
|
|
|
|
|
|
|
|
|
|
|
|
6 : cd8_cd4
|
|
|
|
|
|
Kruskal-Wallis test
|
< 0.001
|
|
median(IQR)
|
0.7 (0.4,108250773559356)
|
0.53 (0.29,0.73)
|
0.18 (0.09,0.28)
|
0.52 (0.4,0.73)
|
0.41 (0.22,0.67)
|
|
|
|
|
|
|
|
|
|
|
|
|
39 : FIBIG2
|
|
|
|
|
|
Fisher’s exact test
|
< 0.001
|
|
Chronic
|
0 (0)
|
0 (0)
|
193 (100)
|
257 (100)
|
450 (81.82)
|
|
|
|
I
|
5 (7.69)
|
0 (0)
|
0 (0)
|
0 (0)
|
5 (0.91)
|
|
|
|
II
|
3 (4.62)
|
0 (0)
|
0 (0)
|
0 (0)
|
3 (0.55)
|
|
|
|
III
|
10 (15.38)
|
0 (0)
|
0 (0)
|
0 (0)
|
10 (1.82)
|
|
|
|
IV
|
13 (20)
|
0 (0)
|
0 (0)
|
0 (0)
|
13 (2.36)
|
|
|
|
V
|
34 (52.31)
|
0 (0)
|
0 (0)
|
0 (0)
|
34 (6.18)
|
|
|
|
VI
|
0 (0)
|
35 (100)
|
0 (0)
|
0 (0)
|
35 (6.36)
|
|
|
|
|
|
|
|
|
|
|
|
|
15 : tempomeses
|
|
|
|
|
|
Kruskal-Wallis test
|
< 0.001
|
|
median(IQR)
|
101333333333333 (6.3,250666666666667)
|
103333333333333 (9.5,298333333333333)
|
163666666666667 (33.4,321666666666667)
|
201666666666667 (54.1,383666666666667)
|
169833333333333 (34.88,356583333333334)
|
|
|
|
|
|
|
|
|
|
|
|
|
11 : desfecho
|
|
|
|
|
|
Chisq. (3 df) = 92.549
|
< 0.001
|
|
0
|
16 (24.62)
|
10 (28.57)
|
160 (82.9)
|
165 (64.2)
|
351 (63.82)
|
|
|
|
1
|
49 (75.38)
|
25 (71.43)
|
33 (17.1)
|
92 (35.8)
|
199 (36.18)
|
|
|
|
|
|
|
|
|
|
|
|
|
29 : COR
|
|
|
|
|
|
Chisq. (3 df) = 10.912
|
0.0122
|
|
Branca
|
27 (41.54)
|
12 (35.29)
|
65 (34.76)
|
61 (23.92)
|
165 (30.5)
|
|
|
|
Pardo/Negro
|
38 (58.46)
|
22 (64.71)
|
122 (65.24)
|
194 (76.08)
|
376 (69.5)
|
|
|
|
|
|
|
|
|
|
|
|
|
30 : GENERO
|
|
|
|
|
|
Chisq. (3 df) = 10.401
|
0.0154
|
|
FEMININO
|
10 (15.38)
|
2 (5.71)
|
36 (18.65)
|
66 (25.78)
|
114 (20.77)
|
|
|
|
MASCULINO
|
55 (84.62)
|
33 (94.29)
|
157 (81.35)
|
190 (74.22)
|
435 (79.23)
|
|
|
|
|
|
|
|
|
|
|
|
|
27 : idade
|
|
|
|
|
|
Kruskal-Wallis test
|
< 0.001
|
|
median(IQR)
|
2674718638 (2283283009,3230579193)
|
2671150151 (2497117760,3067389514.5)
|
2995333516 (2412846555,3787537744)
|
2473510843 (2094976668,3038429865)
|
2637112270 (2240255284.5,3329947845.25)
|
|
|
|
|
|
|
|
|
|
|
|
|
46 : coinfec2
|
|
|
|
|
|
Fisher’s exact test
|
< 0.001
|
|
n
|
65 (100)
|
35 (100)
|
168 (87.05)
|
252 (98.05)
|
520 (94.55)
|
|
|
|
s
|
0 (0)
|
0 (0)
|
25 (12.95)
|
5 (1.95)
|
30 (5.45)
|
|
|
|
|
|
|
|
|
|
|
|
|
54 : qualquerco
|
|
|
|
|
|
Chisq. (3 df) = 105.095
|
< 0.001
|
|
0
|
65 (100)
|
35 (100)
|
105 (54.4)
|
225 (87.55)
|
430 (78.18)
|
|
|
|
1
|
0 (0)
|
0 (0)
|
88 (45.6)
|
32 (12.45)
|
120 (21.82)
|
|
|
|
|
|
|
|
|
|
|
|
#Reordenar fatores
#banco$Grupo6[banco$Grupo6=="Agudo"]<-"3Agudo"
#banco$Grupo6[banco$Grupo6=="Recente"]<-"1Recente"
banco$Grupo6[banco$Grupo6=="2Cronicomenor350"]<-"0Cronicomenor350"
banco$Grupo6[banco$Grupo6=="0Cronico=>350"]<-"2Cronico=>350"
#modelo de cox univariado
a<-coxph(Surv(tempomeses, desfecho) ~ banco$FIBIG2 ,method='efron',id=Registro ,data=banco)
b<-coxph(Surv(tempomeses, desfecho) ~ Grupo6 ,method='efron',id=Registro ,data=banco)
c<-coxph(Surv(tempomeses, desfecho) ~ logcv ,method='efron',id=Registro ,data=banco)
d<-coxph(Surv(tempomeses, desfecho) ~ esquema2 ,method='efron',id=Registro ,data=banco)
aa<-coxph(Surv(tempomeses, desfecho) ~ COR ,method='efron',id=Registro ,data=banco)
bb<-coxph(Surv(tempomeses, desfecho) ~ idade ,method='efron',id=Registro ,data=banco)
cc<-coxph(Surv(tempomeses, desfecho) ~ escola2 ,method='efron',id=Registro ,data=banco)
dd<-coxph(Surv(tempomeses, desfecho) ~ GENERO ,method='efron',id=Registro ,data=banco)
e<-coxph(Surv(tempomeses, desfecho) ~ cd8_cd4 ,method='efron',id=Registro ,data=banco)
f<-coxph(Surv(tempomeses, desfecho) ~ gon ,method='efron',id=Registro ,data=banco)
g<-coxph(Surv(tempomeses, desfecho) ~ clam ,method='efron',id=Registro ,data=banco)
h<-coxph(Surv(tempomeses, desfecho) ~ sifilis ,method='efron',id=Registro ,data=banco)
i<-coxph(Surv(tempomeses, desfecho) ~ CMV_pos_ARV ,method='efron',id=Registro ,data=banco)
j<-coxph(Surv(tempomeses, desfecho) ~ coinfec2 ,method='efron',id=Registro ,data=banco)
k<-coxph(Surv(tempomeses, desfecho) ~ qualquerco ,method='efron',id=Registro ,data=banco)
# idade 10 anos uni
bb
## Call:
## coxph(formula = Surv(tempomeses, desfecho) ~ idade, data = banco,
## method = "efron", id = Registro)
##
##
## 1:2 coef exp(coef) se(coef) z p
## idade -4.251e-11 1.000e+00 5.458e-11 -0.779 0.436
##
## States: 1= (s0), 2= 1
##
## Likelihood ratio test=0.6 on 1 df, p=0.4372
## n= 604, number of events= 216
## (1 observation deleted due to missingness)
estimate<-exp(-0.021988 *10)
cihigh<-exp(-0.021988*10+ 20*0.008678)
cilow<-exp(-0.021988*10 - 20*0.008678)
estimate
## [1] 0.8026151
cihigh
## [1] 0.9547364
cilow
## [1] 0.6747318
#teste log rank
summary(b)
## Call:
## coxph(formula = Surv(tempomeses, desfecho) ~ Grupo6, data = banco,
## method = "efron", id = Registro)
##
## n= 550, number of events= 199
## (55 observations deleted due to missingness)
##
## coef exp(coef) se(coef) z Pr(>|z|)
## Grupo61Recente 1.5451 4.6887 0.2664 5.800 6.63e-09 ***
## Grupo62Cronico=>350 0.6299 1.8774 0.2031 3.101 0.00193 **
## Grupo63Agudo 1.8016 6.0595 0.2262 7.965 1.65e-15 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## Grupo61Recente 4.689 0.2133 2.782 7.903
## Grupo62Cronico=>350 1.877 0.5327 1.261 2.795
## Grupo63Agudo 6.060 0.1650 3.890 9.440
##
## Concordance= 0.677 (se = 0.022 )
## Likelihood ratio test= 76.68 on 3 df, p=<2e-16
## Wald test = 82.55 on 3 df, p=<2e-16
## Score (logrank) test = 96.96 on 3 df, p=<2e-16
#tab_model
a<-sjPlot::tab_model(a)
## Registered S3 methods overwritten by 'lme4':
## method from
## cooks.distance.influence.merMod car
## influence.merMod car
## dfbeta.influence.merMod car
## dfbetas.influence.merMod car
b<-sjPlot::tab_model(b)
c<-sjPlot::tab_model(c)
d<-sjPlot::tab_model(d)
aa<-sjPlot::tab_model(aa)
bb<-sjPlot::tab_model(bb)
cc<-sjPlot::tab_model(cc)
dd<-sjPlot::tab_model(dd)
e<-sjPlot::tab_model(e)
f<-sjPlot::tab_model(f)
g<-sjPlot::tab_model(g)
h<-sjPlot::tab_model(h)
i<-sjPlot::tab_model(i)
j<-sjPlot::tab_model(j)
k<-sjPlot::tab_model(k)
#fazer tabela compilada bonitinha
e<-c(a$page.content,b$page.content,c$page.content,d$page.content,aa$page.content,bb$page.content,cc$page.content,dd$page.content,e$page.content,f$page.content,g$page.content,h$page.content,i$page.content,j$page.content,k$page.content)
#e<- as.list(a$page.content,b$page.content,c$page.content,d$page.content,aa$page.content,bb$page.content,cc$page.content,dd$page.content,e$page.content,f$page.content,g$page.content,h$page.content,i$page.content,j$page.content)
e<-as.list(e)
e<- htmlTable::concatHtmlTables(e)
questions<-readHTMLTable(e, trim=T, as.data.frame=T, header=T)
data<-bind_rows(questions)
names(data)[c(1)] <- c("Variavel")
names(data)[c(2)] <- c("Estimates")
names(data)[c(3)]<- c("CI")
names(data)[c(4)]<- c("P")
data<-subset(data, data$Variavel!="Â")
data<-subset(data, data$Variavel!="Predictors")
data<-subset(data, data$Variavel!="R2 Nagelkerke")
data<-subset(data, data$Variavel!="Observations")
data$CI<-stringr::str_replace(data$CI, "â€","-")
data$CI<-stringr::str_replace(data$CI, "“Â","-")
data$CI<-stringr::str_replace(data$CI, "Â -","")
data$CI<-stringr::str_replace(data$CI, "Â","")
data$CI<-stringr::str_replace(data$CI, "--","-")
data$CI<-stringr::str_replace(data$CI, "Â","")
data<-unique(data)
#modelo uni
htmlTable::htmlTable(data)
|
|
Variavel
|
Estimates
|
CI
|
P
|
|
2
|
banco\(FIBIG2[banco\)FIBIG2I]
|
15.92
|
6.40 - 39.64
|
<0.001
|
|
3
|
banco\(FIBIG2[banco\)FIBIG2II]
|
3.94
|
0.97 - 15.95
|
0.055
|
|
4
|
banco\(FIBIG2[banco\)FIBIG2III]
|
3.68
|
1.72 - 7.88
|
0.001
|
|
5
|
banco\(FIBIG2[banco\)FIBIG2IV]
|
3.57
|
1.93 - 6.61
|
<0.001
|
|
6
|
banco\(FIBIG2[banco\)FIBIG2V]
|
3.73
|
2.41 - 5.75
|
<0.001
|
|
7
|
banco\(FIBIG2[banco\)FIBIG2VI]
|
3.05
|
1.99 - 4.68
|
<0.001
|
|
11
|
Grupo6 [1Recente]
|
4.69
|
2.78 - 7.90
|
<0.001
|
|
12
|
Grupo6 [2Cronico=>350]
|
1.88
|
1.26 - 2.80
|
0.002
|
|
13
|
Grupo6 [3Agudo]
|
6.06
|
3.89 - 9.44
|
<0.001
|
|
17
|
logcv
|
1.00
|
1.00 - 1.00
|
0.057
|
|
21
|
esquema2 [IP]
|
1.71
|
1.14 - 2.56
|
0.009
|
|
22
|
esquema2 [NNRTI]
|
1.60
|
1.17 - 2.17
|
0.003
|
|
26
|
COR [Pardo/Negro]
|
1.16
|
0.87 - 1.56
|
0.319
|
|
30
|
idade
|
1.00
|
1.00 - 1.00
|
0.436
|
|
34
|
escola2 [less than 12years of schooling]
|
1.01
|
0.73 - 1.39
|
0.966
|
|
38
|
GENERO [MASCULINO]
|
1.01
|
0.74 - 1.38
|
0.940
|
|
42
|
cd8_cd4
|
1.00
|
1.00 - 1.00
|
0.001
|
|
46
|
gon [Sim]
|
1.16
|
0.48 - 2.78
|
0.741
|
|
50
|
clam [Sim]
|
0.60
|
0.25 - 1.47
|
0.265
|
|
54
|
sifilis [Sim]
|
0.96
|
0.67 - 1.39
|
0.838
|
|
58
|
CMV_pos_ARV
|
2.63
|
0.36 - 19.01
|
0.338
|
|
62
|
coinfec2 [s]
|
0.54
|
0.27 - 1.10
|
0.088
|
|
66
|
qualquerco [1]
|
0.68
|
0.48 - 0.97
|
0.033
|
#Modelo Multivariado
f<-coxph(Surv(tempomeses, desfecho) ~ Grupo6 +idade + esquema2 ,method='efron',id=Registro ,data=banco)
sjPlot::tab_model(f)
|
|
Surv(tempomeses,
desfecho)
|
|
Predictors
|
Estimates
|
CI
|
p
|
|
Grupo6 [1Recente]
|
4.23
|
2.47 – 7.25
|
<0.001
|
|
Grupo6 [2Cronico=>350]
|
1.95
|
1.29 – 2.92
|
0.001
|
|
Grupo6 [3Agudo]
|
5.89
|
3.78 – 9.19
|
<0.001
|
|
idade
|
1.00
|
1.00 – 1.00
|
0.979
|
|
esquema2 [IP]
|
1.55
|
1.01 – 2.38
|
0.046
|
|
esquema2 [NNRTI]
|
1.40
|
1.01 – 1.96
|
0.046
|
|
Observations
|
550
|
|
R2 Nagelkerke
|
0.338
|
f
## Call:
## coxph(formula = Surv(tempomeses, desfecho) ~ Grupo6 + idade +
## esquema2, data = banco, method = "efron", id = Registro)
##
##
## 1:2 coef exp(coef) se(coef) z p
## Grupo61Recente 1.443e+00 4.234e+00 2.745e-01 5.258 1.46e-07
## Grupo62Cronico=>350 6.655e-01 1.946e+00 2.079e-01 3.201 0.00137
## Grupo63Agudo 1.773e+00 5.890e+00 2.268e-01 7.817 5.41e-15
## idade 1.575e-12 1.000e+00 5.851e-11 0.027 0.97852
## esquema2IP 4.381e-01 1.550e+00 2.196e-01 1.995 0.04604
## esquema2NNRTI 3.380e-01 1.402e+00 1.697e-01 1.992 0.04633
##
## States: 1= (s0), 2= 1
##
## Likelihood ratio test=82.06 on 6 df, p=1.337e-15
## n= 550, number of events= 199
## (55 observations deleted due to missingness)
estimate<-exp(-0.024319*10)
ciupper<-exp(-0.024319*10+ 0.009579*20)
cilow<-exp(-0.024319*10- 0.009579*20)
estimate
## [1] 0.7841225
cilow
## [1] 0.6474136
ciupper
## [1] 0.9496992
f<-coxph(Surv(tempomeses, desfecho) ~ Grupo6 +idade +esquema2 ,method='efron',id=Registro ,data=banco)
sjPlot::tab_model(f)
|
|
Surv(tempomeses,
desfecho)
|
|
Predictors
|
Estimates
|
CI
|
p
|
|
Grupo6 [1Recente]
|
4.23
|
2.47 – 7.25
|
<0.001
|
|
Grupo6 [2Cronico=>350]
|
1.95
|
1.29 – 2.92
|
0.001
|
|
Grupo6 [3Agudo]
|
5.89
|
3.78 – 9.19
|
<0.001
|
|
idade
|
1.00
|
1.00 – 1.00
|
0.979
|
|
esquema2 [IP]
|
1.55
|
1.01 – 2.38
|
0.046
|
|
esquema2 [NNRTI]
|
1.40
|
1.01 – 1.96
|
0.046
|
|
Observations
|
550
|
|
R2 Nagelkerke
|
0.338
|
f<-coxph(Surv(tempomeses, desfecho) ~ Grupo6 +cd8_cd4 +esquema2,method='efron',id=Registro ,data=banco)
sjPlot::tab_model(f)
|
|
Surv(tempomeses,
desfecho)
|
|
Predictors
|
Estimates
|
CI
|
p
|
|
Grupo6 [1Recente]
|
3.00
|
1.65 – 5.45
|
<0.001
|
|
Grupo6 [2Cronico=>350]
|
1.62
|
1.02 – 2.57
|
0.043
|
|
Grupo6 [3Agudo]
|
4.60
|
2.75 – 7.69
|
<0.001
|
|
cd8_cd4
|
1.00
|
1.00 – 1.00
|
0.029
|
|
esquema2 [IP]
|
1.50
|
0.92 – 2.45
|
0.101
|
|
esquema2 [NNRTI]
|
1.37
|
0.92 – 2.05
|
0.117
|
|
Observations
|
363
|
|
R2 Nagelkerke
|
0.302
|
f<-coxph(Surv(tempomeses, desfecho) ~ Grupo6 +idade ,method='efron',id=Registro ,data=banco)
sjPlot::tab_model(f)
|
|
Surv(tempomeses,
desfecho)
|
|
Predictors
|
Estimates
|
CI
|
p
|
|
Grupo6 [1Recente]
|
4.70
|
2.77 – 7.97
|
<0.001
|
|
Grupo6 [2Cronico=>350]
|
1.88
|
1.26 – 2.81
|
0.002
|
|
Grupo6 [3Agudo]
|
6.06
|
3.89 – 9.45
|
<0.001
|
|
idade
|
1.00
|
1.00 – 1.00
|
0.974
|
|
Observations
|
550
|
|
R2 Nagelkerke
|
0.320
|
f<-coxph(Surv(tempomeses, desfecho) ~ Grupo6 +cd8_cd4 ,method='efron',id=Registro ,data=banco)
sjPlot::tab_model(f)
|
|
Surv(tempomeses,
desfecho)
|
|
Predictors
|
Estimates
|
CI
|
p
|
|
Grupo6 [1Recente]
|
3.31
|
1.84 – 5.95
|
<0.001
|
|
Grupo6 [2Cronico=>350]
|
1.61
|
1.02 – 2.55
|
0.041
|
|
Grupo6 [3Agudo]
|
4.73
|
2.83 – 7.90
|
<0.001
|
|
cd8_cd4
|
1.00
|
1.00 – 1.00
|
0.049
|
|
Observations
|
363
|
|
R2 Nagelkerke
|
0.286
|
f<-coxph(Surv(tempomeses, desfecho) ~ Grupo6 +gon ,method='efron',id=Registro ,data=banco)
## Warning in fitter(X, Y, istrat, offset, init, control, weights = weights, :
## Loglik converged before variable 1 ; coefficient may be infinite.
sjPlot::tab_model(f)
|
|
Surv(tempomeses,
desfecho)
|
|
Predictors
|
Estimates
|
CI
|
p
|
|
Grupo6 [1Recente]
|
0.00
|
0.00 – Inf
|
0.998
|
|
Grupo6 [2Cronico=>350]
|
2.07
|
0.47 – 9.23
|
0.339
|
|
Grupo6 [3Agudo]
|
8.99
|
1.96 – 41.35
|
0.005
|
|
gon [Sim]
|
1.02
|
0.43 – 2.43
|
0.964
|
|
Observations
|
94
|
|
R2 Nagelkerke
|
0.369
|
f<-coxph(Surv(tempomeses, desfecho) ~ Grupo6 +idade +esquema2 ,method='efron',id=Registro ,data=banco)
sjPlot::tab_model(f)
|
|
Surv(tempomeses,
desfecho)
|
|
Predictors
|
Estimates
|
CI
|
p
|
|
Grupo6 [1Recente]
|
4.23
|
2.47 – 7.25
|
<0.001
|
|
Grupo6 [2Cronico=>350]
|
1.95
|
1.29 – 2.92
|
0.001
|
|
Grupo6 [3Agudo]
|
5.89
|
3.78 – 9.19
|
<0.001
|
|
idade
|
1.00
|
1.00 – 1.00
|
0.979
|
|
esquema2 [IP]
|
1.55
|
1.01 – 2.38
|
0.046
|
|
esquema2 [NNRTI]
|
1.40
|
1.01 – 1.96
|
0.046
|
|
Observations
|
550
|
|
R2 Nagelkerke
|
0.338
|
f<-coxph(Surv(tempomeses, desfecho) ~ Grupo6 +cd8_cd4 +qualquerco,method='efron',id=Registro ,data=banco)
sjPlot::tab_model(f)
|
|
Surv(tempomeses,
desfecho)
|
|
Predictors
|
Estimates
|
CI
|
p
|
|
Grupo6 [1Recente]
|
4.23
|
2.16 – 8.27
|
<0.001
|
|
Grupo6 [2Cronico=>350]
|
1.95
|
1.16 – 3.29
|
0.012
|
|
Grupo6 [3Agudo]
|
6.03
|
3.29 – 11.05
|
<0.001
|
|
cd8_cd4
|
1.00
|
1.00 – 1.00
|
0.046
|
|
qualquerco [1]
|
1.54
|
0.91 – 2.61
|
0.112
|
|
Observations
|
363
|
|
R2 Nagelkerke
|
0.297
|
f<-coxph(Surv(tempomeses, desfecho) ~ Grupo6 +idade+qualquerco ,method='efron',id=Registro ,data=banco)
sjPlot::tab_model(f)
|
|
Surv(tempomeses,
desfecho)
|
|
Predictors
|
Estimates
|
CI
|
p
|
|
Grupo6 [1Recente]
|
5.40
|
3.03 – 9.62
|
<0.001
|
|
Grupo6 [2Cronico=>350]
|
2.07
|
1.34 – 3.20
|
0.001
|
|
Grupo6 [3Agudo]
|
6.99
|
4.22 – 11.58
|
<0.001
|
|
idade
|
1.00
|
1.00 – 1.00
|
0.910
|
|
qualquerco [1]
|
1.32
|
0.85 – 2.05
|
0.214
|
|
Observations
|
550
|
|
R2 Nagelkerke
|
0.325
|
f<-coxph(Surv(tempomeses, desfecho) ~ Grupo6 +cd8_cd4+qualquerco ,method='efron',id=Registro ,data=banco)
sjPlot::tab_model(f)
|
|
Surv(tempomeses,
desfecho)
|
|
Predictors
|
Estimates
|
CI
|
p
|
|
Grupo6 [1Recente]
|
4.23
|
2.16 – 8.27
|
<0.001
|
|
Grupo6 [2Cronico=>350]
|
1.95
|
1.16 – 3.29
|
0.012
|
|
Grupo6 [3Agudo]
|
6.03
|
3.29 – 11.05
|
<0.001
|
|
cd8_cd4
|
1.00
|
1.00 – 1.00
|
0.046
|
|
qualquerco [1]
|
1.54
|
0.91 – 2.61
|
0.112
|
|
Observations
|
363
|
|
R2 Nagelkerke
|
0.297
|
f<-coxph(Surv(tempomeses, desfecho) ~ Grupo6 +gon ,method='efron',id=Registro ,data=banco)
## Warning in fitter(X, Y, istrat, offset, init, control, weights = weights, :
## Loglik converged before variable 1 ; coefficient may be infinite.
sjPlot::tab_model(f)
|
|
Surv(tempomeses,
desfecho)
|
|
Predictors
|
Estimates
|
CI
|
p
|
|
Grupo6 [1Recente]
|
0.00
|
0.00 – Inf
|
0.998
|
|
Grupo6 [2Cronico=>350]
|
2.07
|
0.47 – 9.23
|
0.339
|
|
Grupo6 [3Agudo]
|
8.99
|
1.96 – 41.35
|
0.005
|
|
gon [Sim]
|
1.02
|
0.43 – 2.43
|
0.964
|
|
Observations
|
94
|
|
R2 Nagelkerke
|
0.369
|