##chargement des packages----
library(questionr)
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.1 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ ggplot2 3.4.2 ✔ tibble 3.2.1
## ✔ lubridate 1.9.2 ✔ tidyr 1.3.0
## ✔ purrr 1.0.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(tableone)
library(labelled)
library(gtsummary)
library(GGally)
## Registered S3 method overwritten by 'GGally':
## method from
## +.gg ggplot2
library(readxl)
library(effects)
## Le chargement a nécessité le package : carData
## lattice theme set by effectsTheme()
## See ?effectsTheme for details.
library(survival)
library(survminer)
## Le chargement a nécessité le package : ggpubr
##
## Attachement du package : 'survminer'
##
## L'objet suivant est masqué depuis 'package:survival':
##
## myeloma
library(ggplot2)
library(dplyr)
library(knitr)
library(cowplot)
##
## Attachement du package : 'cowplot'
##
## L'objet suivant est masqué depuis 'package:ggpubr':
##
## get_legend
##
## L'objet suivant est masqué depuis 'package:lubridate':
##
## stamp
##chargement des données
data_leila <- read_excel("~/FAC/2024-2025/theses/leila/data_leila.xlsx")
## New names:
## • `tgp` -> `tgp...56`
## • `tgp` -> `tgp...57`
data_beam<-filter(data_leila, c(patientcohorte==1))
##recodage des variables et bases de données le cas échéant----
data_beam$surpoids<-ifelse(data_beam$imc>25, 1, 0)
data_beam$old65<-ifelse(data_beam$age>65, 1, 0)
data_beam$ligne_cat2<-ifelse(data_beam$nombre_de_ligne_antérieur>1, 1, 0)
data_beam$ligne_cat3<-ifelse(data_beam$nombre_de_ligne_antérieur>2, 1, 0)
data_beam$ligne_cat4<-ifelse(data_beam$nombre_de_ligne_antérieur>3, 1, 0)
data_beam$sexe.cat<-ifelse(data_beam$sexe=="F", 1, 0)
data_beam$sc.max<-ifelse(data_beam$sc_utilisee_si_capee==2, 1, 0)
data_beam$alteration_foie<-ifelse(data_beam$foie_sans_anomalie==1, 0, 1)
data_beam$alteration_rein<-ifelse(data_beam$rein_sans_anomalie==1, 0, 1)
##renommer des variables pour présentation dans les tableaux de résultats
library(labelled)
var_label(data_beam$old65) <- "Patients de + de 65 ans"
var_label(data_beam$surpoids) <- "Patients avec IMC >25"
var_label(data_beam$obesite) <- "Patients avec IMC >30"
var_label(data_beam$poids_chimio_avant_conditionnement) <- "Poids"
var_label(data_beam$surface_corporelle) <- "Surface corporelle calculée"
var_label(data_beam$sc_utilisee_si_capee) <- "Surface corporelle utilisée pour calcul des doses"
var_label(data_beam$oms.cat) <- "Score OMS 0 vs 1 et +"
var_label(data_beam$pathologie) <- "Type d'hémopathie"
var_label(data_beam$nombre_de_ligne_antérieur) <- "Nombre de lignes antérieures"
var_label(data_beam$ligne_cat2) <- "1 ligne anterieure et +"
var_label(data_beam$ligne_cat3) <- "2 lignes anterieures et +"
var_label(data_beam$ligne_cat4) <- "3 lignes anterieures et +"
var_label(data_beam$reponse_maladie_avant_beam) <- "Statut réponse avant autogreffe"
var_label(data_beam$conditionnement_utilise) <- "Protocole intensification"
var_label(data_beam$hb) <- "Hb avant BEAM (g/dl)"
var_label(data_beam$plaquettes) <- "Taux de plaquettes avant BEAM (G/l)"
var_label(data_beam$leucocyte) <- "GB avant BEAM (g/dl)"
var_label(data_beam$pnn) <- "PNN avant BEAM (G/l)"
var_label(data_beam$foie_sans_anomalie) <- "Bilan hépatique sans anomalie"
var_label(data_beam$rein_sans_anomalie) <- "Bilan rénal sans anomalie"
var_label(data_beam$transfusion_cg) <- "Patients avec trasnfusion CG"
var_label(data_beam$transfusion_cp) <- "Patients avec trasnfusion CP"
var_label(data_beam$gcsf) <- "Patients avec G_CSF"
var_label(data_beam$duree_leucopenie_grade3) <- "Durée de Leucopénie Grade_3 postBEAM"
var_label(data_beam$duree_leucopenie_grade4) <- "Durée de Leucopénie Grade_4 postBEAM"
##création de variables à plusieurs catégorie selon valeurs variable continue
#na
##tableau descriptif patients selon obesite ----
tbl_summary(
data_beam, include = c("age",
"old65",
"sexe",
"poids_chimio_avant_conditionnement",
"surpoids",
"surface_corporelle",
"sc_utilisee_si_capee",
"oms.cat",
"pathologie"
),
by="obesite",
digits=all_categorical()~ c(0,1)
)%>%
add_p(
pvalue_fun = scales::label_pvalue(accuracy = .001)
)%>%
add_overall(last = TRUE)
## Warning for variable 'poids_chimio_avant_conditionnement':
## simpleWarning in wilcox.test.default(x = DATA[[1L]], y = DATA[[2L]], ...): impossible de calculer la p-value exacte avec des ex-aequos
## Warning for variable 'surface_corporelle':
## simpleWarning in wilcox.test.default(x = DATA[[1L]], y = DATA[[2L]], ...): impossible de calculer la p-value exacte avec des ex-aequos
## Warning for variable 'sc_utilisee_si_capee':
## simpleWarning in wilcox.test.default(x = DATA[[1L]], y = DATA[[2L]], ...): impossible de calculer la p-value exacte avec des ex-aequos
| Characteristic |
0, N = 33 |
1, N = 33 |
p-value |
Overall, N = 66 |
| age |
56 (38, 64) |
56 (45, 58) |
0.868 |
56 (42, 63) |
| Patients de + de 65 ans |
6 (18.2%) |
5 (15.2%) |
0.741 |
11 (16.7%) |
| sexe |
|
|
0.800 |
|
| F |
13 (39.4%) |
12 (36.4%) |
|
25 (37.9%) |
| M |
20 (60.6%) |
21 (63.6%) |
|
41 (62.1%) |
| Poids |
70 (63, 77) |
96 (89, 105) |
<0.001 |
84 (70, 96) |
| Patients avec IMC >25 |
12 (36.4%) |
33 (100.0%) |
<0.001 |
45 (68.2%) |
| Surface corporelle calculée |
1.83 (1.76, 1.92) |
2.10 (1.98, 2.30) |
<0.001 |
1.95 (1.82, 2.10) |
| Surface corporelle utilisée pour calcul des doses |
1.83 (1.76, 1.92) |
2.00 (1.98, 2.00) |
<0.001 |
1.95 (1.82, 2.00) |
| Score OMS 0 vs 1 et + |
11 (34.4%) |
16 (51.6%) |
0.167 |
27 (42.9%) |
| Unknown |
1 |
2 |
|
3 |
| Type d'hémopathie |
|
|
0.131 |
|
| L hodgkin |
14 (42.4%) |
8 (24.2%) |
|
22 (33.3%) |
| L_plasmablastique |
1 (3.0%) |
0 (0.0%) |
|
1 (1.5%) |
| LBDGC |
7 (21.2%) |
12 (36.4%) |
|
19 (28.8%) |
| LF |
1 (3.0%) |
2 (6.1%) |
|
3 (4.5%) |
| lnh manteau |
6 (18.2%) |
10 (30.3%) |
|
16 (24.2%) |
| LT anaplasique |
2 (6.1%) |
0 (0.0%) |
|
2 (3.0%) |
| LTAI |
2 (6.1%) |
0 (0.0%) |
|
2 (3.0%) |
| Poppema |
0 (0.0%) |
1 (3.0%) |
|
1 (1.5%) |
##tableau descriptif traitements selon obesite ----
tbl_summary(
data_beam, include = c("conditionnement_utilise",
"nombre_de_ligne_antérieur",
"ligne_cat2",
"ligne_cat3",
"ligne_cat4",
"reponse_maladie_avant_beam",
"gcsf",
),
by="obesite",
digits=all_categorical()~ c(0,1)
)%>%
add_p(
pvalue_fun = scales::label_pvalue(accuracy = .001)
)%>%
add_overall(last = TRUE)
## There was an error in 'add_p()/add_difference()' for variable 'gcsf', p-value omitted:
## Error in stats::chisq.test(x = structure(c(1, 1, 1, NA, 1, 1, 1, 1, 1, : 'x' et 'y' doivent avoir au moins 2 niveaux
| Characteristic |
0, N = 33 |
1, N = 33 |
p-value |
Overall, N = 66 |
| Protocole intensification |
|
|
0.159 |
|
| BEAM 5 jours |
11 (33.3%) |
6 (18.2%) |
|
17 (25.8%) |
| BEAM 6 jours |
22 (66.7%) |
27 (81.8%) |
|
49 (74.2%) |
| Nombre de lignes antérieures |
|
|
0.507 |
|
| 1 |
8 (24.2%) |
11 (33.3%) |
|
19 (28.8%) |
| 2 |
18 (54.5%) |
11 (33.3%) |
|
29 (43.9%) |
| 3 |
5 (15.2%) |
6 (18.2%) |
|
11 (16.7%) |
| 4 |
1 (3.0%) |
3 (9.1%) |
|
4 (6.1%) |
| 5 |
1 (3.0%) |
2 (6.1%) |
|
3 (4.5%) |
| 1 ligne anterieure et + |
25 (75.8%) |
22 (66.7%) |
0.415 |
47 (71.2%) |
| 2 lignes anterieures et + |
7 (21.2%) |
11 (33.3%) |
0.269 |
18 (27.3%) |
| 3 lignes anterieures et + |
2 (6.1%) |
5 (15.2%) |
0.427 |
7 (10.6%) |
| Statut réponse avant autogreffe |
|
|
0.641 |
|
| NR |
5 (15.2%) |
1 (3.0%) |
|
6 (9.1%) |
| RC |
4 (12.1%) |
5 (15.2%) |
|
9 (13.6%) |
| RC1 |
7 (21.2%) |
5 (15.2%) |
|
12 (18.2%) |
| RC2 |
12 (36.4%) |
13 (39.4%) |
|
25 (37.9%) |
| RC3 |
4 (12.1%) |
6 (18.2%) |
|
10 (15.2%) |
| RP |
0 (0.0%) |
1 (3.0%) |
|
1 (1.5%) |
| RP4 |
1 (3.0%) |
1 (3.0%) |
|
2 (3.0%) |
| RP5 |
0 (0.0%) |
1 (3.0%) |
|
1 (1.5%) |
| Patients avec G_CSF |
32 (100.0%) |
28 (100.0%) |
|
60 (100.0%) |
| Unknown |
1 |
5 |
|
6 |
##tableau descriptif bilans bio selon obesite ----
tbl_summary(
data_beam, include = c("foie_sans_anomalie",
"rein_sans_anomalie",
"hb",
"plaquettes",
"leucocyte",
"pnn",
),
by="obesite",
digits=all_categorical()~ c(0,1)
)%>%
add_p(
pvalue_fun = scales::label_pvalue(accuracy = .001)
)%>%
add_overall(last = TRUE)
## Warning for variable 'hb':
## simpleWarning in wilcox.test.default(x = DATA[[1L]], y = DATA[[2L]], ...): impossible de calculer la p-value exacte avec des ex-aequos
## Warning for variable 'plaquettes':
## simpleWarning in wilcox.test.default(x = DATA[[1L]], y = DATA[[2L]], ...): impossible de calculer la p-value exacte avec des ex-aequos
## Warning for variable 'leucocyte':
## simpleWarning in wilcox.test.default(x = DATA[[1L]], y = DATA[[2L]], ...): impossible de calculer la p-value exacte avec des ex-aequos
## Warning for variable 'pnn':
## simpleWarning in wilcox.test.default(x = DATA[[1L]], y = DATA[[2L]], ...): impossible de calculer la p-value exacte avec des ex-aequos
| Characteristic |
0, N = 33 |
1, N = 33 |
p-value |
Overall, N = 66 |
| Bilan hépatique sans anomalie |
12 (36.4%) |
7 (21.9%) |
0.199 |
19 (29.2%) |
| Unknown |
0 |
1 |
|
1 |
| Bilan rénal sans anomalie |
24 (72.7%) |
23 (69.7%) |
0.786 |
47 (71.2%) |
| Hb avant BEAM (g/dl) |
11.10 (10.20, 12.20) |
11.60 (10.40, 12.80) |
0.308 |
11.35 (10.40, 12.50) |
| Taux de plaquettes avant BEAM (G/l) |
199 (160, 261) |
212 (180, 265) |
0.870 |
212 (161, 262) |
| Unknown |
0 |
1 |
|
1 |
| GB avant BEAM (g/dl) |
5.39 (4.66, 6.84) |
6.55 (5.09, 7.78) |
0.168 |
5.91 (4.69, 7.32) |
| PNN avant BEAM (G/l) |
3.40 (2.70, 4.30) |
4.50 (3.40, 5.50) |
0.047 |
4.05 (2.80, 5.38) |
##tableau descriptif toxicités selon obesite ----
tbl_summary(
data_beam, include = c("transfusion_cg",
"transfusion_cp",
"duree_leucopenie_grade3",
"duree_leucopenie_grade4",
),
by="obesite",
digits=all_categorical()~ c(0,1)
)%>%
add_p(
pvalue_fun = scales::label_pvalue(accuracy = .001)
)%>%
add_overall(last = TRUE)
## Warning for variable 'transfusion_cg':
## simpleWarning in stats::chisq.test(x = structure(c(1, 1, 1, 1, 1, 1, 1, 1, 1, : L’approximation du Chi-2 est peut-être incorrecte
## Warning for variable 'duree_leucopenie_grade3':
## simpleWarning in wilcox.test.default(x = DATA[[1L]], y = DATA[[2L]], ...): impossible de calculer la p-value exacte avec des ex-aequos
## Warning for variable 'duree_leucopenie_grade4':
## simpleWarning in wilcox.test.default(x = DATA[[1L]], y = DATA[[2L]], ...): impossible de calculer la p-value exacte avec des ex-aequos
| Characteristic |
0, N = 33 |
1, N = 33 |
p-value |
Overall, N = 66 |
| Patients avec trasnfusion CG |
27 (84.4%) |
26 (83.9%) |
0.956 |
53 (84.1%) |
| Unknown |
1 |
2 |
|
3 |
| Patients avec trasnfusion CP |
31 (93.9%) |
32 (100.0%) |
0.492 |
63 (96.9%) |
| Unknown |
0 |
1 |
|
1 |
| Durée de Leucopénie Grade_3 postBEAM |
11.0 (9.0, 13.0) |
10.0 (8.0, 12.0) |
0.548 |
10.0 (8.2, 12.0) |
| Durée de Leucopénie Grade_4 postBEAM |
8.00 (7.00, 9.00) |
8.00 (7.00, 9.00) |
0.902 |
8.00 (7.00, 9.00) |
##Analyse des facteurs de risques de neutropénie grade 3
#Analyse univariée
data_beam |>
tbl_uvregression(
y = duree_leucopenie_grade3,
include = c(sexe.cat, age, old65, ligne_cat2, ligne_cat3, ligne_cat4, obesite, surpoids,
sc_utilisee_si_capee, gcsf, oms.cat, alteration_foie, alteration_rein,
sc.max, pnn),
method = glm,
pvalue_fun = scales::label_pvalue(accuracy = .001),
exponentiate = FALSE
) |>
bold_labels()
| Characteristic |
N |
Beta |
95% CI |
p-value |
| age |
66 |
0.00 |
-0.06, 0.05 |
0.889 |
| Patients avec IMC >30 |
66 |
-0.27 |
-1.8, 1.3 |
0.732 |
| Surface corporelle utilisée pour calcul des doses |
66 |
-5.1 |
-11, 0.73 |
0.091 |
| Score OMS 0 vs 1 et + |
63 |
1.4 |
-0.17, 3.0 |
0.085 |
| PNN avant BEAM (G/l) |
66 |
-0.37 |
-0.66, -0.07 |
0.017 |
| Patients avec G_CSF |
60 |
|
|
|
| Patients avec IMC >25 |
66 |
0.73 |
-0.93, 2.4 |
0.394 |
| Patients de + de 65 ans |
66 |
0.85 |
-1.2, 2.9 |
0.423 |
| 1 ligne anterieure et + |
66 |
0.78 |
-0.93, 2.5 |
0.373 |
| 2 lignes anterieures et + |
66 |
0.64 |
-1.1, 2.4 |
0.474 |
| 3 lignes anterieures et + |
66 |
1.2 |
-1.3, 3.7 |
0.350 |
| sexe.cat |
66 |
1.9 |
0.39, 3.5 |
0.016 |
| sc.max |
66 |
-1.5 |
-3.0, 0.06 |
0.064 |
| alteration_foie |
65 |
1.7 |
0.04, 3.4 |
0.049 |
| alteration_rein |
66 |
0.85 |
-0.86, 2.6 |
0.335 |
#Analyse mutlivariée
##analyse avec obesite et variables sélectionnée
mod1 <- lm(
duree_leucopenie_grade3 ~ obesite +sexe.cat + oms.cat+pnn+alteration_foie,
pvalue_fun = scales::label_pvalue(accuracy = .001),
data = data_beam
)
## Warning: Dans lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## l'argument supplémentaire 'pvalue_fun' sera ignoré
summary(mod1)
##
## Call:
## lm(formula = duree_leucopenie_grade3 ~ obesite + sexe.cat + oms.cat +
## pnn + alteration_foie, data = data_beam, pvalue_fun = scales::label_pvalue(accuracy = 0.001))
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.480 -1.650 -0.426 1.622 7.267
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 10.6165 0.9832 10.798 2.63e-15 ***
## obesite -0.5760 0.7639 -0.754 0.4540
## sexe.cat 1.2525 0.7707 1.625 0.1098
## oms.cat 1.5554 0.7665 2.029 0.0472 *
## pnn -0.3835 0.1448 -2.648 0.0105 *
## alteration_foie 1.6101 0.8558 1.881 0.0651 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.915 on 56 degrees of freedom
## (4 observations effacées parce que manquantes)
## Multiple R-squared: 0.25, Adjusted R-squared: 0.1831
## F-statistic: 3.734 on 5 and 56 DF, p-value: 0.005485
exp(coefficients(mod1))
## (Intercept) obesite sexe.cat oms.cat pnn
## 4.080334e+04 5.621214e-01 3.499037e+00 4.737087e+00 6.814840e-01
## alteration_foie
## 5.003231e+00
exp(confint(mod1, level=0.95))
## 2.5 % 97.5 %
## (Intercept) 5692.8510203 2.924568e+05
## obesite 0.1216863 2.596680e+00
## sexe.cat 0.7471456 1.638671e+01
## oms.cat 1.0200564 2.199877e+01
## pnn 0.5098485 9.108990e-01
## alteration_foie 0.9009557 2.778419e+01
mod1%>%tbl_regression(intercept = TRUE)
| Characteristic |
Beta |
95% CI |
p-value |
| (Intercept) |
11 |
8.6, 13 |
<0.001 |
| Patients avec IMC >30 |
-0.58 |
-2.1, 0.95 |
0.5 |
| sexe.cat |
1.3 |
-0.29, 2.8 |
0.11 |
| Score OMS 0 vs 1 et + |
1.6 |
0.02, 3.1 |
0.047 |
| PNN avant BEAM (G/l) |
-0.38 |
-0.67, -0.09 |
0.011 |
| alteration_foie |
1.6 |
-0.10, 3.3 |
0.065 |
##analyse avec obesite et variables sélectionnée sans sexe
mod1 <- lm(
duree_leucopenie_grade3 ~ obesite + oms.cat+pnn+alteration_foie,
pvalue_fun = scales::label_pvalue(accuracy = .001),
data = data_beam
)
## Warning: Dans lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## l'argument supplémentaire 'pvalue_fun' sera ignoré
summary(mod1)
##
## Call:
## lm(formula = duree_leucopenie_grade3 ~ obesite + oms.cat + pnn +
## alteration_foie, data = data_beam, pvalue_fun = scales::label_pvalue(accuracy = 0.001))
##
## Residuals:
## Min 1Q Median 3Q Max
## -5.0282 -1.6049 -0.5528 1.8306 7.9718
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 11.1202 0.9464 11.750 <2e-16 ***
## obesite -0.6025 0.7746 -0.778 0.4399
## oms.cat 1.5718 0.7774 2.022 0.0479 *
## pnn -0.4184 0.1453 -2.880 0.0056 **
## alteration_foie 1.8213 0.8580 2.123 0.0381 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.957 on 57 degrees of freedom
## (4 observations effacées parce que manquantes)
## Multiple R-squared: 0.2147, Adjusted R-squared: 0.1596
## F-statistic: 3.895 on 4 and 57 DF, p-value: 0.007268
exp(coefficients(mod1))
## (Intercept) obesite oms.cat pnn alteration_foie
## 6.752457e+04 5.474542e-01 4.815351e+00 6.581101e-01 6.180057e+00
exp(confint(mod1, level=0.95))
## 2.5 % 97.5 %
## (Intercept) 1.014937e+04 4.492461e+05
## obesite 1.160582e-01 2.582377e+00
## oms.cat 1.015152e+00 2.284152e+01
## pnn 4.919772e-01 8.803435e-01
## alteration_foie 1.108810e+00 3.444514e+01
mod1%>%tbl_regression(intercept = TRUE)
| Characteristic |
Beta |
95% CI |
p-value |
| (Intercept) |
11 |
9.2, 13 |
<0.001 |
| Patients avec IMC >30 |
-0.60 |
-2.2, 0.95 |
0.4 |
| Score OMS 0 vs 1 et + |
1.6 |
0.02, 3.1 |
0.048 |
| PNN avant BEAM (G/l) |
-0.42 |
-0.71, -0.13 |
0.006 |
| alteration_foie |
1.8 |
0.10, 3.5 |
0.038 |
#REcherche facteurs explicatifs durée neutropénie
mod1 <- lm(
duree_leucopenie_grade3 ~ sc_utilisee_si_capee +sexe.cat + oms.cat+pnn+alteration_foie,
pvalue_fun = scales::label_pvalue(accuracy = .001),
data = data_beam
)
## Warning: Dans lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## l'argument supplémentaire 'pvalue_fun' sera ignoré
summary(mod1)
##
## Call:
## lm(formula = duree_leucopenie_grade3 ~ sc_utilisee_si_capee +
## sexe.cat + oms.cat + pnn + alteration_foie, data = data_beam,
## pvalue_fun = scales::label_pvalue(accuracy = 0.001))
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.6015 -1.6467 -0.4798 1.7223 7.1263
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 14.7819 6.3279 2.336 0.0231 *
## sc_utilisee_si_capee -2.2664 3.2822 -0.691 0.4927
## sexe.cat 0.9536 0.8932 1.068 0.2903
## oms.cat 1.4886 0.7572 1.966 0.0543 .
## pnn -0.3804 0.1453 -2.618 0.0113 *
## alteration_foie 1.5756 0.8519 1.850 0.0696 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.918 on 56 degrees of freedom
## (4 observations effacées parce que manquantes)
## Multiple R-squared: 0.2488, Adjusted R-squared: 0.1817
## F-statistic: 3.71 on 5 and 56 DF, p-value: 0.005703
exp(coefficients(mod1))
## (Intercept) sc_utilisee_si_capee sexe.cat
## 2.628335e+06 1.036847e-01 2.595143e+00
## oms.cat pnn alteration_foie
## 4.430758e+00 6.835940e-01 4.833720e+00
exp(confint(mod1, level=0.95))
## 2.5 % 97.5 %
## (Intercept) 8.211535980 8.412730e+11
## sc_utilisee_si_capee 0.000144606 7.434350e+01
## sexe.cat 0.433551241 1.553395e+01
## oms.cat 0.972154558 2.019393e+01
## pnn 0.510982421 9.145143e-01
## alteration_foie 0.877345747 2.663129e+01
mod1%>%tbl_regression(intercept = TRUE)
| Characteristic |
Beta |
95% CI |
p-value |
| (Intercept) |
15 |
2.1, 27 |
0.023 |
| Surface corporelle utilisée pour calcul des doses |
-2.3 |
-8.8, 4.3 |
0.5 |
| sexe.cat |
0.95 |
-0.84, 2.7 |
0.3 |
| Score OMS 0 vs 1 et + |
1.5 |
-0.03, 3.0 |
0.054 |
| PNN avant BEAM (G/l) |
-0.38 |
-0.67, -0.09 |
0.011 |
| alteration_foie |
1.6 |
-0.13, 3.3 |
0.070 |
#recherche sans sc
mod1 <- lm(
duree_leucopenie_grade3 ~ sexe.cat + oms.cat+pnn+alteration_foie,
pvalue_fun = scales::label_pvalue(accuracy = .001),
data = data_beam
)
## Warning: Dans lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## l'argument supplémentaire 'pvalue_fun' sera ignoré
summary(mod1)
##
## Call:
## lm(formula = duree_leucopenie_grade3 ~ sexe.cat + oms.cat + pnn +
## alteration_foie, data = data_beam, pvalue_fun = scales::label_pvalue(accuracy = 0.001))
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.690 -1.656 -0.581 1.367 7.045
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 10.4633 0.9583 10.919 1.36e-15 ***
## sexe.cat 1.2649 0.7676 1.648 0.10491
## oms.cat 1.4558 0.7522 1.935 0.05791 .
## pnn -0.3884 0.1441 -2.694 0.00925 **
## alteration_foie 1.5185 0.8439 1.799 0.07727 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.904 on 57 degrees of freedom
## (4 observations effacées parce que manquantes)
## Multiple R-squared: 0.2424, Adjusted R-squared: 0.1893
## F-statistic: 4.56 on 4 and 57 DF, p-value: 0.002897
exp(coefficients(mod1))
## (Intercept) sexe.cat oms.cat pnn alteration_foie
## 3.500570e+04 3.542619e+00 4.288113e+00 6.781447e-01 4.565178e+00
exp(confint(mod1, level=0.95))
## 2.5 % 97.5 %
## (Intercept) 5137.3842551 2.385259e+05
## sexe.cat 0.7616111 1.647842e+01
## oms.cat 0.9508074 1.933926e+01
## pnn 0.5081139 9.050730e-01
## alteration_foie 0.8424256 2.473910e+01
mod1%>%tbl_regression(intercept = TRUE)
| Characteristic |
Beta |
95% CI |
p-value |
| (Intercept) |
10 |
8.5, 12 |
<0.001 |
| sexe.cat |
1.3 |
-0.27, 2.8 |
0.10 |
| Score OMS 0 vs 1 et + |
1.5 |
-0.05, 3.0 |
0.058 |
| PNN avant BEAM (G/l) |
-0.39 |
-0.68, -0.10 |
0.009 |
| alteration_foie |
1.5 |
-0.17, 3.2 |
0.077 |
#recherche sans sc ni sexe
mod1 <- lm(
duree_leucopenie_grade3 ~ oms.cat+pnn+alteration_foie,
pvalue_fun = scales::label_pvalue(accuracy = .001),
data = data_beam
)
## Warning: Dans lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## l'argument supplémentaire 'pvalue_fun' sera ignoré
summary(mod1)
##
## Call:
## lm(formula = duree_leucopenie_grade3 ~ oms.cat + pnn + alteration_foie,
## data = data_beam, pvalue_fun = scales::label_pvalue(accuracy = 0.001))
##
## Residuals:
## Min 1Q Median 3Q Max
## -5.253 -1.810 -0.476 1.646 7.747
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 10.9651 0.9220 11.893 < 2e-16 ***
## oms.cat 1.4678 0.7632 1.923 0.05938 .
## pnn -0.4239 0.1446 -2.931 0.00483 **
## alteration_foie 1.7276 0.8466 2.041 0.04583 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.947 on 58 degrees of freedom
## (4 observations effacées parce que manquantes)
## Multiple R-squared: 0.2063, Adjusted R-squared: 0.1653
## F-statistic: 5.026 on 3 and 58 DF, p-value: 0.003644
exp(coefficients(mod1))
## (Intercept) oms.cat pnn alteration_foie
## 5.782036e+04 4.339613e+00 6.544999e-01 5.627339e+00
exp(confint(mod1, level=0.95))
## 2.5 % 97.5 %
## (Intercept) 9132.6089614 3.660722e+05
## oms.cat 0.9417921 1.999618e+01
## pnn 0.4899856 8.742503e-01
## alteration_foie 1.0336046 3.063739e+01
mod1%>%tbl_regression(intercept = TRUE)
| Characteristic |
Beta |
95% CI |
p-value |
| (Intercept) |
11 |
9.1, 13 |
<0.001 |
| Score OMS 0 vs 1 et + |
1.5 |
-0.06, 3.0 |
0.059 |
| PNN avant BEAM (G/l) |
-0.42 |
-0.71, -0.13 |
0.005 |
| alteration_foie |
1.7 |
0.03, 3.4 |
0.046 |
#recherche sans sc ni sexe ni oms
mod1 <- lm(
duree_leucopenie_grade3 ~ pnn+alteration_foie,
pvalue_fun = scales::label_pvalue(accuracy = .001),
data = data_beam
)
## Warning: Dans lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
## l'argument supplémentaire 'pvalue_fun' sera ignoré
summary(mod1)
##
## Call:
## lm(formula = duree_leucopenie_grade3 ~ pnn + alteration_foie,
## data = data_beam, pvalue_fun = scales::label_pvalue(accuracy = 0.001))
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.4869 -2.1247 -0.5354 1.6673 8.5929
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 11.2496 0.8805 12.777 < 2e-16 ***
## pnn -0.3986 0.1455 -2.739 0.00803 **
## alteration_foie 1.9514 0.8196 2.381 0.02035 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.989 on 62 degrees of freedom
## (1 observation effacée parce que manquante)
## Multiple R-squared: 0.1616, Adjusted R-squared: 0.1346
## F-statistic: 5.977 on 2 and 62 DF, p-value: 0.004229
exp(coefficients(mod1))
## (Intercept) pnn alteration_foie
## 7.684787e+04 6.712311e-01 7.038747e+00
exp(confint(mod1, level=0.95))
## 2.5 % 97.5 %
## (Intercept) 1.322046e+04 4.467014e+05
## pnn 5.018115e-01 8.978493e-01
## alteration_foie 1.367631e+00 3.622611e+01
mod1%>%tbl_regression(intercept = TRUE)
| Characteristic |
Beta |
95% CI |
p-value |
| (Intercept) |
11 |
9.5, 13 |
<0.001 |
| PNN avant BEAM (G/l) |
-0.40 |
-0.69, -0.11 |
0.008 |
| alteration_foie |
2.0 |
0.31, 3.6 |
0.020 |