Oxy_COV_Description
MALLAH Siham
26/04/2023
Description de la population
ne pas prendre en compte le nombre de NA pour Rox H1, R24, R72
IOT/mortalité J28
library(tidyverse)
library(finalfit)## Warning: le package 'finalfit' a été compilé avec la version R 4.2.2dependent_1="IOT_mortalite_J28"
explanatory_A=c("CPAP.1","OHD_CPAP.1")
explanatory_B=c("Rox_H1","Rox_H24","Rox_H48","Rox_H72")
explanatory_C=c("Duree_Hospit","Duree_SI_Rea")
explanatory_E=c("var_RoxH24_H1", "var_RoxH48_H1","var_RoxH72_H1")Relation IOT/mortalité J28 avec CPAP/OHD
res_glm_uni_A <- Oxy_cov%>%
glmuni(dependent_1, explanatory_A) %>%
fit2df(estimate_suffix=" (univarié)")
kable(res_glm_uni_A,row.names=FALSE, align=c("l", "l", "r", "r", "r", "r"))| explanatory | OR (univarié) |
|---|---|
| CPAP.1Oui | 1.43 (0.44-6.44, p=0.591) |
| OHD_CPAP.1OHD_CPAP | 1.43 (0.44-6.44, p=0.591) |
Relation IOT/mortalité J28 avec ROX
res_glm_uni_B<- Oxy_cov%>%
glmuni(dependent_1, explanatory_B) %>%
fit2df(estimate_suffix=" (univarié)")
kable(res_glm_uni_B,row.names=FALSE, align=c("l", "l", "r", "r", "r", "r"))| explanatory | OR (univarié) |
|---|---|
| Rox_H1 | 0.89 (0.76-1.03, p=0.146) |
| Rox_H24 | 0.51 (0.38-0.65, p<0.001) |
| Rox_H48 | 0.69 (0.56-0.83, p<0.001) |
| Rox_H72 | 0.72 (0.55-0.92, p=0.012) |
Relation IOT/mortalité J28 avec durée d’hospitalisation et de séjour
res_glm_uni_C <- Oxy_cov%>%
glmuni(dependent_1, explanatory_C) %>%
fit2df(estimate_suffix=" (univarié)")
kable(res_glm_uni_C,row.names=FALSE, align=c("l", "l", "r", "r", "r", "r"))| explanatory | OR (univarié) |
|---|---|
| Duree_Hospit | 1.10 (1.06-1.16, p<0.001) |
| Duree_SI_Rea | 1.19 (1.12-1.28, p<0.001) |
Relation IOT/mortalité J28 avec la variation de l’evolution Rox dans le temps
res_glm_uni_E <- Oxy_cov%>%
glmuni(dependent_1, explanatory_E) %>%
fit2df(estimate_suffix=" (univarié)")
kable(res_glm_uni_E,row.names=FALSE, align=c("l", "l", "r", "r", "r", "r"))| explanatory | OR (univarié) |
|---|---|
| var_RoxH24_H1 | 0.77 (0.66-0.89, p=0.001) |
| var_RoxH48_H1 | 0.80 (0.67-0.94, p=0.011) |
| var_RoxH72_H1 | 0.79 (0.60-1.01, p=0.076) |
IOT mortalité J90
library(tidyverse)
library(finalfit)
dependent_2="IOT_mortalite_J90"
explanatory_A=c("CPAP.1","OHD_CPAP.1")
explanatory_B=c("Rox_H1","Rox_H24","Rox_H48","Rox_H72")
explanatory_C=c("Duree_Hospit","Duree_SI_Rea")
explanatory_E=c("var_RoxH24_H1", "var_RoxH48_H1","var_RoxH72_H1")Relation IOT/mortalité J90 avec CPAP/OHD
res_glm_uni_A1 <- Oxy_cov%>%
glmuni(dependent_2, explanatory_A) %>%
fit2df(estimate_suffix=" (univarié)")
kable(res_glm_uni_A1,row.names=FALSE, align=c("l", "l", "r", "r", "r", "r"))| explanatory | OR (univarié) |
|---|---|
| CPAP.1Oui | 1.49 (0.46-6.70, p=0.550) |
| OHD_CPAP.1OHD_CPAP | 1.49 (0.46-6.70, p=0.550) |
Relation IOT/mortalité J28 avec ROX
res_glm_uni_B1<- Oxy_cov%>%
glmuni(dependent_2, explanatory_B) %>%
fit2df(estimate_suffix=" (univarié)")
kable(res_glm_uni_B1,row.names=FALSE, align=c("l", "l", "r", "r", "r", "r"))| explanatory | OR (univarié) |
|---|---|
| Rox_H1 | 0.90 (0.77-1.04, p=0.153) |
| Rox_H24 | 0.55 (0.42-0.69, p<0.001) |
| Rox_H48 | 0.68 (0.56-0.82, p<0.001) |
| Rox_H72 | 0.73 (0.56-0.93, p=0.015) |
Relation IOT/mortalité J28 avec durée d’hospitalisation et de séjour
res_glm_uni_C1 <- Oxy_cov%>%
glmuni(dependent_2, explanatory_C) %>%
fit2df(estimate_suffix=" (univarié)")
kable(res_glm_uni_C,row.names=FALSE, align=c("l", "l", "r", "r", "r", "r"))| explanatory | OR (univarié) |
|---|---|
| Duree_Hospit | 1.10 (1.06-1.16, p<0.001) |
| Duree_SI_Rea | 1.19 (1.12-1.28, p<0.001) |
Relation IOT/mortalité J90 avec variation Rox dans le temps
res_glm_uni_E1 <- Oxy_cov%>%
glmuni(dependent_2, explanatory_E) %>%
fit2df(estimate_suffix=" (univarié)")
kable(res_glm_uni_E1,row.names=FALSE, align=c("l", "l", "r", "r", "r", "r"))| explanatory | OR (univarié) |
|---|---|
| var_RoxH24_H1 | 0.79 (0.67-0.91, p=0.002) |
| var_RoxH48_H1 | 0.80 (0.67-0.93, p=0.009) |
| var_RoxH72_H1 | 0.81 (0.62-1.02, p=0.094) |
impact des criteres secondaire sur l’IOT/mortalité à J28
dependent_1="IOT_mortalite_J28"
explanatory_AT=c("Age","sexe","Poids","IMC","Vaccination","ATCD_Diabète","ATCD_HTA","ATCD_ID","ATCD_Path_respi","ATCD_Cardiopathie","ATCD_IR_Dialyse","J_symptome_hospit","TDM_severité","TA_Tocilizumab","TA_plasma_conv","var_RoxH72_H1","var_RoxH48_H1","var_RoxH24_H1")Analyse univariées
res_glm_uni_AT <- Oxy_cov%>%
glmuni(dependent_1, explanatory_AT) %>%
fit2df(estimate_suffix=" (univarié)")
kable(res_glm_uni_AT,row.names=FALSE, align=c("l", "l", "r", "r", "r", "r"))| explanatory | OR (univarié) |
|---|---|
| Age | 1.02 (1.00-1.06, p=0.115) |
| sexeM | 0.78 (0.36-1.73, p=0.529) |
| Poids | 1.00 (0.98-1.02, p=0.841) |
| IMCIMC<30 | 0.79 (0.11-16.00, p=0.838) |
| IMCIMC>30 | 1.71 (0.23-34.79, p=0.640) |
| VaccinationOui | 0.90 (0.13-3.81, p=0.899) |
| ATCD_DiabèteOui | 1.41 (0.59-3.23, p=0.421) |
| ATCD_HTAOui | 1.61 (0.76-3.44, p=0.218) |
| ATCD_IDOui | 3.15 (0.74-12.59, p=0.101) |
| ATCD_Path_respiOui | 2.42 (0.97-5.82, p=0.051) |
| ATCD_CardiopathieOui | 1.18 (0.40-3.07, p=0.752) |
| ATCD_IR_DialyseOui | 1.22 (0.06-9.84, p=0.868) |
| J_symptome_hospit | 0.96 (0.85-1.04, p=0.423) |
| TDM_severitéminime | 0.13 (0.02-0.75, p=0.028) |
| TDM_severitémodérée | 0.13 (0.02-0.58, p=0.009) |
| TDM_severitésévère | 0.18 (0.03-0.84, p=0.032) |
| TA_TocilizumabOui | 1.19 (0.50-2.68, p=0.687) |
| TA_plasma_convOui | 1.22 (0.06-9.84, p=0.868) |
| var_RoxH72_H1 | 0.79 (0.60-1.01, p=0.076) |
| var_RoxH48_H1 | 0.80 (0.67-0.94, p=0.011) |
| var_RoxH24_H1 | 0.77 (0.66-0.89, p=0.001) |
Analyse multivariées
res_glm_uni_multi_AT <- Oxy_cov %>%
finalfit(dependent_1, explanatory_AT)
kable(res_glm_uni_multi_AT,row.names=FALSE, align=c("l", "l", "r", "r", "r", "r"))| Dependent: IOT_mortalite_J28 | Non | Oui | OR (univariable) | OR (multivariable) | |
|---|---|---|---|---|---|
| Age | Mean (SD) | 59.4 (13.7) | 63.5 (11.9) | 1.02 (1.00-1.06, p=0.115) | 1.03 (0.88-1.22, p=0.722) |
| sexe | F | 40 (75.5) | 13 (24.5) | - | - |
| M | 87 (79.8) | 22 (20.2) | 0.78 (0.36-1.73, p=0.529) | 0.56 (0.03-15.43, p=0.700) | |
| Poids | Mean (SD) | 85.6 (19.1) | 86.3 (19.3) | 1.00 (0.98-1.02, p=0.841) | 0.99 (0.89-1.12, p=0.906) |
| IMC | 4 (80.0) | 1 (20.0) | - | - | |
| IMC<30 | 81 (83.5) | 16 (16.5) | 0.79 (0.11-16.00, p=0.838) | - | |
| IMC>30 | 42 (70.0) | 18 (30.0) | 1.71 (0.23-34.79, p=0.640) | 4.33 (0.15-367.64, p=0.436) | |
| Vaccination | Non | 119 (78.3) | 33 (21.7) | - | - |
| Oui | 8 (80.0) | 2 (20.0) | 0.90 (0.13-3.81, p=0.899) | 0.00 (NA-48714314526816672236800088282668802042468264446422620086886040286800446068000068226868860008622208408260442608226022.00, p=0.997) | |
| ATCD_Diabète | Non | 99 (79.8) | 25 (20.2) | - | - |
| Oui | 28 (73.7) | 10 (26.3) | 1.41 (0.59-3.23, p=0.421) | 0.53 (0.01-8.70, p=0.682) | |
| ATCD_HTA | Non | 73 (82.0) | 16 (18.0) | - | - |
| Oui | 54 (74.0) | 19 (26.0) | 1.61 (0.76-3.44, p=0.218) | 0.16 (0.00-2.69, p=0.243) | |
| ATCD_ID | Non | 122 (79.7) | 31 (20.3) | - | - |
| Oui | 5 (55.6) | 4 (44.4) | 3.15 (0.74-12.59, p=0.101) | 22.78 (0.06-54506.73, p=0.330) | |
| ATCD_Path_respi | Non | 109 (81.3) | 25 (18.7) | - | - |
| Oui | 18 (64.3) | 10 (35.7) | 2.42 (0.97-5.82, p=0.051) | 77.61 (4.05-23686.37, p=0.028) | |
| ATCD_Cardiopathie | Non | 108 (78.8) | 29 (21.2) | - | - |
| Oui | 19 (76.0) | 6 (24.0) | 1.18 (0.40-3.07, p=0.752) | 1.03 (0.02-26.06, p=0.985) | |
| ATCD_IR_Dialyse | Non | 124 (78.5) | 34 (21.5) | - | - |
| Oui | 3 (75.0) | 1 (25.0) | 1.22 (0.06-9.84, p=0.868) | 0.00 (NA-7432908025791255637606082884460060228046808028628040640688204648404264404220408668024026044626804686244246428204666206882406808066682068804260424.00, p=0.997) | |
| J_symptome_hospit | Mean (SD) | 8.2 (5.2) | 7.4 (3.7) | 0.96 (0.85-1.04, p=0.423) | 1.03 (0.79-1.26, p=0.788) |
| TDM_severité | majeur | 3 (37.5) | 5 (62.5) | - | - |
| minime | 18 (81.8) | 4 (18.2) | 0.13 (0.02-0.75, p=0.028) | 5.98 (0.03-4331.26, p=0.527) | |
| modérée | 66 (82.5) | 14 (17.5) | 0.13 (0.02-0.58, p=0.009) | 0.16 (0.00-14.41, p=0.430) | |
| sévère | 40 (76.9) | 12 (23.1) | 0.18 (0.03-0.84, p=0.032) | 0.40 (0.00-35.54, p=0.681) | |
| TA_Tocilizumab | Non | 95 (79.2) | 25 (20.8) | - | - |
| Oui | 32 (76.2) | 10 (23.8) | 1.19 (0.50-2.68, p=0.687) | 2.48 (0.03-378.92, p=0.671) | |
| TA_plasma_conv | Non | 124 (78.5) | 34 (21.5) | - | - |
| Oui | 3 (75.0) | 1 (25.0) | 1.22 (0.06-9.84, p=0.868) | 0.00 (NA-3644767661526009483204064840020004864448220626002202626882004462446468222244068266082468422246688684602246060464420208684200460006.00, p=0.995) | |
| var_RoxH72_H1 | Mean (SD) | -0.4 (2.9) | -2.1 (1.9) | 0.79 (0.60-1.01, p=0.076) | 0.83 (0.44-1.46, p=0.511) |
| var_RoxH48_H1 | Mean (SD) | 0.1 (3.4) | -2.2 (3.3) | 0.80 (0.67-0.94, p=0.011) | 1.30 (0.73-2.63, p=0.381) |
| var_RoxH24_H1 | Mean (SD) | 0.0 (3.0) | -2.2 (2.8) | 0.77 (0.66-0.89, p=0.001) | 0.46 (0.15-0.90, p=0.071) |
odds ratio de tous les modèles
Il s’agit ici d’obtenir et de présenter les odds ratio :
des modèles de régression univariés, du modèle de régression multivarié complet, d’un modèle de régression multicarié restreint (obtenu par sélection des variables)
dependent_1="IOT_mortalite_J28"
explanatory_full=c("Age","sexe","Poids","IMC","Vaccination","ATCD_Diabète","ATCD_HTA","ATCD_ID","ATCD_Path_respi","ATCD_Cardiopathie","ATCD_IR_Dialyse","J_symptome_hospit","TDM_severité","TA_Tocilizumab","TA_plasma_conv","var_RoxH72_H1","var_RoxH48_H1","var_RoxH24_H1")
explanatory_final = c("IMC","TDM_severité","ATCD_Path_respi","var_RoxH72_H1","var_RoxH48_H1")res_summary <- Oxy_cov %>%
summary_factorlist(dependent_1, explanatory_full, fit_id=TRUE)
res_uni <- Oxy_cov%>%
glmuni(dependent_1, explanatory_full) %>%
fit2df(estimate_suffix="(univarié)")
res_multi_full <- Oxy_cov%>%
glmmulti(dependent_1, explanatory_full) %>%
fit2df(estimate_suffix="(ajustés - modèle complet)")
res_multi_final <- Oxy_cov%>%
glmmulti(dependent_1, explanatory_final) %>%
fit2df(estimate_suffix="(ajustés - modèle final)")
tab_res <- res_summary %>%
finalfit_merge(res_uni) %>%
finalfit_merge(res_multi_full) %>%
finalfit_merge(res_multi_final) %>%
dplyr::select(-levels, fit_id, -index)
tab_res## fit_id label Non Oui
## 1 Age Age 59.4 (13.7) 63.5 (11.9)
## 19 sexeF sexe 40 (31.5) 13 (37.1)
## 20 sexeM 87 (68.5) 22 (62.9)
## 18 Poids Poids 85.6 (19.1) 86.3 (19.3)
## 14 IMC IMC 4 (3.1) 1 (2.9)
## 15 IMCIMC<30 81 (63.8) 16 (45.7)
## 16 IMCIMC>30 42 (33.1) 18 (51.4)
## 29 VaccinationNon Vaccination 119 (93.7) 33 (94.3)
## 30 VaccinationOui 8 (6.3) 2 (5.7)
## 4 ATCD_DiabèteNon ATCD_Diabète 99 (78.0) 25 (71.4)
## 5 ATCD_DiabèteOui 28 (22.0) 10 (28.6)
## 6 ATCD_HTANon ATCD_HTA 73 (57.5) 16 (45.7)
## 7 ATCD_HTAOui 54 (42.5) 19 (54.3)
## 8 ATCD_IDNon ATCD_ID 122 (96.1) 31 (88.6)
## 9 ATCD_IDOui 5 (3.9) 4 (11.4)
## 12 ATCD_Path_respiNon ATCD_Path_respi 109 (85.8) 25 (71.4)
## 13 ATCD_Path_respiOui 18 (14.2) 10 (28.6)
## 2 ATCD_CardiopathieNon ATCD_Cardiopathie 108 (85.0) 29 (82.9)
## 3 ATCD_CardiopathieOui 19 (15.0) 6 (17.1)
## 10 ATCD_IR_DialyseNon ATCD_IR_Dialyse 124 (97.6) 34 (97.1)
## 11 ATCD_IR_DialyseOui 3 (2.4) 1 (2.9)
## 17 J_symptome_hospit J_symptome_hospit 8.2 (5.2) 7.4 (3.7)
## 25 TDM_severitémajeur TDM_severité 3 (2.4) 5 (14.3)
## 26 TDM_severitéminime 18 (14.2) 4 (11.4)
## 27 TDM_severitémodérée 66 (52.0) 14 (40.0)
## 28 TDM_severitésévère 40 (31.5) 12 (34.3)
## 23 TA_TocilizumabNon TA_Tocilizumab 95 (74.8) 25 (71.4)
## 24 TA_TocilizumabOui 32 (25.2) 10 (28.6)
## 21 TA_plasma_convNon TA_plasma_conv 124 (97.6) 34 (97.1)
## 22 TA_plasma_convOui 3 (2.4) 1 (2.9)
## 33 var_RoxH72_H1 var_RoxH72_H1 -0.4 (2.9) -2.1 (1.9)
## 32 var_RoxH48_H1 var_RoxH48_H1 0.1 (3.4) -2.2 (3.3)
## 31 var_RoxH24_H1 var_RoxH24_H1 0.0 (3.0) -2.2 (2.8)
## OR(univarié)
## 1 1.02 (1.00-1.06, p=0.115)
## 19 -
## 20 0.78 (0.36-1.73, p=0.529)
## 18 1.00 (0.98-1.02, p=0.841)
## 14 -
## 15 0.79 (0.11-16.00, p=0.838)
## 16 1.71 (0.23-34.79, p=0.640)
## 29 -
## 30 0.90 (0.13-3.81, p=0.899)
## 4 -
## 5 1.41 (0.59-3.23, p=0.421)
## 6 -
## 7 1.61 (0.76-3.44, p=0.218)
## 8 -
## 9 3.15 (0.74-12.59, p=0.101)
## 12 -
## 13 2.42 (0.97-5.82, p=0.051)
## 2 -
## 3 1.18 (0.40-3.07, p=0.752)
## 10 -
## 11 1.22 (0.06-9.84, p=0.868)
## 17 0.96 (0.85-1.04, p=0.423)
## 25 -
## 26 0.13 (0.02-0.75, p=0.028)
## 27 0.13 (0.02-0.58, p=0.009)
## 28 0.18 (0.03-0.84, p=0.032)
## 23 -
## 24 1.19 (0.50-2.68, p=0.687)
## 21 -
## 22 1.22 (0.06-9.84, p=0.868)
## 33 0.79 (0.60-1.01, p=0.076)
## 32 0.80 (0.67-0.94, p=0.011)
## 31 0.77 (0.66-0.89, p=0.001)
## OR(ajustés - modèle complet)
## 1 1.03 (0.88-1.22, p=0.722)
## 19 -
## 20 0.56 (0.03-15.43, p=0.700)
## 18 0.99 (0.89-1.12, p=0.906)
## 14 -
## 15 -
## 16 4.33 (0.15-367.64, p=0.436)
## 29 -
## 30 0.00 (NA-48714314526816672236800088282668802042468264446422620086886040286800446068000068226868860008622208408260442608226022.00, p=0.997)
## 4 -
## 5 0.53 (0.01-8.70, p=0.682)
## 6 -
## 7 0.16 (0.00-2.69, p=0.243)
## 8 -
## 9 22.78 (0.06-54506.73, p=0.330)
## 12 -
## 13 77.61 (4.05-23686.37, p=0.028)
## 2 -
## 3 1.03 (0.02-26.06, p=0.985)
## 10 -
## 11 0.00 (NA-7432908025791255637606082884460060228046808028628040640688204648404264404220408668024026044626804686244246428204666206882406808066682068804260424.00, p=0.997)
## 17 1.03 (0.79-1.26, p=0.788)
## 25 -
## 26 5.98 (0.03-4331.26, p=0.527)
## 27 0.16 (0.00-14.41, p=0.430)
## 28 0.40 (0.00-35.54, p=0.681)
## 23 -
## 24 2.48 (0.03-378.92, p=0.671)
## 21 -
## 22 0.00 (NA-3644767661526009483204064840020004864448220626002202626882004462446468222244068266082468422246688684602246060464420208684200460006.00, p=0.995)
## 33 0.83 (0.44-1.46, p=0.511)
## 32 1.30 (0.73-2.63, p=0.381)
## 31 0.46 (0.15-0.90, p=0.071)
## OR(ajustés - modèle final)
## 1 -
## 19 -
## 20 -
## 18 -
## 14 -
## 15 0.26 (0.01-8.88, p=0.380)
## 16 0.41 (0.02-14.30, p=0.566)
## 29 -
## 30 -
## 4 -
## 5 -
## 6 -
## 7 -
## 8 -
## 9 -
## 12 -
## 13 6.54 (1.54-30.50, p=0.012)
## 2 -
## 3 -
## 10 -
## 11 -
## 17 -
## 25 -
## 26 0.15 (0.00-6.76, p=0.303)
## 27 0.09 (0.00-2.99, p=0.136)
## 28 0.20 (0.01-6.61, p=0.316)
## 23 -
## 24 -
## 21 -
## 22 -
## 33 0.78 (0.51-1.14, p=0.223)
## 32 0.93 (0.63-1.29, p=0.669)
## 31 -tab_res## fit_id label Non Oui
## 1 Age Age 59.4 (13.7) 63.5 (11.9)
## 19 sexeF sexe 40 (31.5) 13 (37.1)
## 20 sexeM 87 (68.5) 22 (62.9)
## 18 Poids Poids 85.6 (19.1) 86.3 (19.3)
## 14 IMC IMC 4 (3.1) 1 (2.9)
## 15 IMCIMC<30 81 (63.8) 16 (45.7)
## 16 IMCIMC>30 42 (33.1) 18 (51.4)
## 29 VaccinationNon Vaccination 119 (93.7) 33 (94.3)
## 30 VaccinationOui 8 (6.3) 2 (5.7)
## 4 ATCD_DiabèteNon ATCD_Diabète 99 (78.0) 25 (71.4)
## 5 ATCD_DiabèteOui 28 (22.0) 10 (28.6)
## 6 ATCD_HTANon ATCD_HTA 73 (57.5) 16 (45.7)
## 7 ATCD_HTAOui 54 (42.5) 19 (54.3)
## 8 ATCD_IDNon ATCD_ID 122 (96.1) 31 (88.6)
## 9 ATCD_IDOui 5 (3.9) 4 (11.4)
## 12 ATCD_Path_respiNon ATCD_Path_respi 109 (85.8) 25 (71.4)
## 13 ATCD_Path_respiOui 18 (14.2) 10 (28.6)
## 2 ATCD_CardiopathieNon ATCD_Cardiopathie 108 (85.0) 29 (82.9)
## 3 ATCD_CardiopathieOui 19 (15.0) 6 (17.1)
## 10 ATCD_IR_DialyseNon ATCD_IR_Dialyse 124 (97.6) 34 (97.1)
## 11 ATCD_IR_DialyseOui 3 (2.4) 1 (2.9)
## 17 J_symptome_hospit J_symptome_hospit 8.2 (5.2) 7.4 (3.7)
## 25 TDM_severitémajeur TDM_severité 3 (2.4) 5 (14.3)
## 26 TDM_severitéminime 18 (14.2) 4 (11.4)
## 27 TDM_severitémodérée 66 (52.0) 14 (40.0)
## 28 TDM_severitésévère 40 (31.5) 12 (34.3)
## 23 TA_TocilizumabNon TA_Tocilizumab 95 (74.8) 25 (71.4)
## 24 TA_TocilizumabOui 32 (25.2) 10 (28.6)
## 21 TA_plasma_convNon TA_plasma_conv 124 (97.6) 34 (97.1)
## 22 TA_plasma_convOui 3 (2.4) 1 (2.9)
## 33 var_RoxH72_H1 var_RoxH72_H1 -0.4 (2.9) -2.1 (1.9)
## 32 var_RoxH48_H1 var_RoxH48_H1 0.1 (3.4) -2.2 (3.3)
## 31 var_RoxH24_H1 var_RoxH24_H1 0.0 (3.0) -2.2 (2.8)
## OR(univarié)
## 1 1.02 (1.00-1.06, p=0.115)
## 19 -
## 20 0.78 (0.36-1.73, p=0.529)
## 18 1.00 (0.98-1.02, p=0.841)
## 14 -
## 15 0.79 (0.11-16.00, p=0.838)
## 16 1.71 (0.23-34.79, p=0.640)
## 29 -
## 30 0.90 (0.13-3.81, p=0.899)
## 4 -
## 5 1.41 (0.59-3.23, p=0.421)
## 6 -
## 7 1.61 (0.76-3.44, p=0.218)
## 8 -
## 9 3.15 (0.74-12.59, p=0.101)
## 12 -
## 13 2.42 (0.97-5.82, p=0.051)
## 2 -
## 3 1.18 (0.40-3.07, p=0.752)
## 10 -
## 11 1.22 (0.06-9.84, p=0.868)
## 17 0.96 (0.85-1.04, p=0.423)
## 25 -
## 26 0.13 (0.02-0.75, p=0.028)
## 27 0.13 (0.02-0.58, p=0.009)
## 28 0.18 (0.03-0.84, p=0.032)
## 23 -
## 24 1.19 (0.50-2.68, p=0.687)
## 21 -
## 22 1.22 (0.06-9.84, p=0.868)
## 33 0.79 (0.60-1.01, p=0.076)
## 32 0.80 (0.67-0.94, p=0.011)
## 31 0.77 (0.66-0.89, p=0.001)
## OR(ajustés - modèle complet)
## 1 1.03 (0.88-1.22, p=0.722)
## 19 -
## 20 0.56 (0.03-15.43, p=0.700)
## 18 0.99 (0.89-1.12, p=0.906)
## 14 -
## 15 -
## 16 4.33 (0.15-367.64, p=0.436)
## 29 -
## 30 0.00 (NA-48714314526816672236800088282668802042468264446422620086886040286800446068000068226868860008622208408260442608226022.00, p=0.997)
## 4 -
## 5 0.53 (0.01-8.70, p=0.682)
## 6 -
## 7 0.16 (0.00-2.69, p=0.243)
## 8 -
## 9 22.78 (0.06-54506.73, p=0.330)
## 12 -
## 13 77.61 (4.05-23686.37, p=0.028)
## 2 -
## 3 1.03 (0.02-26.06, p=0.985)
## 10 -
## 11 0.00 (NA-7432908025791255637606082884460060228046808028628040640688204648404264404220408668024026044626804686244246428204666206882406808066682068804260424.00, p=0.997)
## 17 1.03 (0.79-1.26, p=0.788)
## 25 -
## 26 5.98 (0.03-4331.26, p=0.527)
## 27 0.16 (0.00-14.41, p=0.430)
## 28 0.40 (0.00-35.54, p=0.681)
## 23 -
## 24 2.48 (0.03-378.92, p=0.671)
## 21 -
## 22 0.00 (NA-3644767661526009483204064840020004864448220626002202626882004462446468222244068266082468422246688684602246060464420208684200460006.00, p=0.995)
## 33 0.83 (0.44-1.46, p=0.511)
## 32 1.30 (0.73-2.63, p=0.381)
## 31 0.46 (0.15-0.90, p=0.071)
## OR(ajustés - modèle final)
## 1 -
## 19 -
## 20 -
## 18 -
## 14 -
## 15 0.26 (0.01-8.88, p=0.380)
## 16 0.41 (0.02-14.30, p=0.566)
## 29 -
## 30 -
## 4 -
## 5 -
## 6 -
## 7 -
## 8 -
## 9 -
## 12 -
## 13 6.54 (1.54-30.50, p=0.012)
## 2 -
## 3 -
## 10 -
## 11 -
## 17 -
## 25 -
## 26 0.15 (0.00-6.76, p=0.303)
## 27 0.09 (0.00-2.99, p=0.136)
## 28 0.20 (0.01-6.61, p=0.316)
## 23 -
## 24 -
## 21 -
## 22 -
## 33 0.78 (0.51-1.14, p=0.223)
## 32 0.93 (0.63-1.29, p=0.669)
## 31 -knitr::kable(tab_res, row.names=FALSE, align=c("l", "l", "r", "r", "r", "r", "r")) | fit_id | label | Non | Oui | OR(univarié) | OR(ajustés - modèle complet) | OR(ajustés - modèle final) |
|---|---|---|---|---|---|---|
| Age | Age | 59.4 (13.7) | 63.5 (11.9) | 1.02 (1.00-1.06, p=0.115) | 1.03 (0.88-1.22, p=0.722) | - |
| sexeF | sexe | 40 (31.5) | 13 (37.1) | - | - | - |
| sexeM | 87 (68.5) | 22 (62.9) | 0.78 (0.36-1.73, p=0.529) | 0.56 (0.03-15.43, p=0.700) | - | |
| Poids | Poids | 85.6 (19.1) | 86.3 (19.3) | 1.00 (0.98-1.02, p=0.841) | 0.99 (0.89-1.12, p=0.906) | - |
| IMC | IMC | 4 (3.1) | 1 (2.9) | - | - | - |
| IMCIMC<30 | 81 (63.8) | 16 (45.7) | 0.79 (0.11-16.00, p=0.838) | - | 0.26 (0.01-8.88, p=0.380) | |
| IMCIMC>30 | 42 (33.1) | 18 (51.4) | 1.71 (0.23-34.79, p=0.640) | 4.33 (0.15-367.64, p=0.436) | 0.41 (0.02-14.30, p=0.566) | |
| VaccinationNon | Vaccination | 119 (93.7) | 33 (94.3) | - | - | - |
| VaccinationOui | 8 (6.3) | 2 (5.7) | 0.90 (0.13-3.81, p=0.899) | 0.00 (NA-48714314526816672236800088282668802042468264446422620086886040286800446068000068226868860008622208408260442608226022.00, p=0.997) | - | |
| ATCD_DiabèteNon | ATCD_Diabète | 99 (78.0) | 25 (71.4) | - | - | - |
| ATCD_DiabèteOui | 28 (22.0) | 10 (28.6) | 1.41 (0.59-3.23, p=0.421) | 0.53 (0.01-8.70, p=0.682) | - | |
| ATCD_HTANon | ATCD_HTA | 73 (57.5) | 16 (45.7) | - | - | - |
| ATCD_HTAOui | 54 (42.5) | 19 (54.3) | 1.61 (0.76-3.44, p=0.218) | 0.16 (0.00-2.69, p=0.243) | - | |
| ATCD_IDNon | ATCD_ID | 122 (96.1) | 31 (88.6) | - | - | - |
| ATCD_IDOui | 5 (3.9) | 4 (11.4) | 3.15 (0.74-12.59, p=0.101) | 22.78 (0.06-54506.73, p=0.330) | - | |
| ATCD_Path_respiNon | ATCD_Path_respi | 109 (85.8) | 25 (71.4) | - | - | - |
| ATCD_Path_respiOui | 18 (14.2) | 10 (28.6) | 2.42 (0.97-5.82, p=0.051) | 77.61 (4.05-23686.37, p=0.028) | 6.54 (1.54-30.50, p=0.012) | |
| ATCD_CardiopathieNon | ATCD_Cardiopathie | 108 (85.0) | 29 (82.9) | - | - | - |
| ATCD_CardiopathieOui | 19 (15.0) | 6 (17.1) | 1.18 (0.40-3.07, p=0.752) | 1.03 (0.02-26.06, p=0.985) | - | |
| ATCD_IR_DialyseNon | ATCD_IR_Dialyse | 124 (97.6) | 34 (97.1) | - | - | - |
| ATCD_IR_DialyseOui | 3 (2.4) | 1 (2.9) | 1.22 (0.06-9.84, p=0.868) | 0.00 (NA-7432908025791255637606082884460060228046808028628040640688204648404264404220408668024026044626804686244246428204666206882406808066682068804260424.00, p=0.997) | - | |
| J_symptome_hospit | J_symptome_hospit | 8.2 (5.2) | 7.4 (3.7) | 0.96 (0.85-1.04, p=0.423) | 1.03 (0.79-1.26, p=0.788) | - |
| TDM_severitémajeur | TDM_severité | 3 (2.4) | 5 (14.3) | - | - | - |
| TDM_severitéminime | 18 (14.2) | 4 (11.4) | 0.13 (0.02-0.75, p=0.028) | 5.98 (0.03-4331.26, p=0.527) | 0.15 (0.00-6.76, p=0.303) | |
| TDM_severitémodérée | 66 (52.0) | 14 (40.0) | 0.13 (0.02-0.58, p=0.009) | 0.16 (0.00-14.41, p=0.430) | 0.09 (0.00-2.99, p=0.136) | |
| TDM_severitésévère | 40 (31.5) | 12 (34.3) | 0.18 (0.03-0.84, p=0.032) | 0.40 (0.00-35.54, p=0.681) | 0.20 (0.01-6.61, p=0.316) | |
| TA_TocilizumabNon | TA_Tocilizumab | 95 (74.8) | 25 (71.4) | - | - | - |
| TA_TocilizumabOui | 32 (25.2) | 10 (28.6) | 1.19 (0.50-2.68, p=0.687) | 2.48 (0.03-378.92, p=0.671) | - | |
| TA_plasma_convNon | TA_plasma_conv | 124 (97.6) | 34 (97.1) | - | - | - |
| TA_plasma_convOui | 3 (2.4) | 1 (2.9) | 1.22 (0.06-9.84, p=0.868) | 0.00 (NA-3644767661526009483204064840020004864448220626002202626882004462446468222244068266082468422246688684602246060464420208684200460006.00, p=0.995) | - | |
| var_RoxH72_H1 | var_RoxH72_H1 | -0.4 (2.9) | -2.1 (1.9) | 0.79 (0.60-1.01, p=0.076) | 0.83 (0.44-1.46, p=0.511) | 0.78 (0.51-1.14, p=0.223) |
| var_RoxH48_H1 | var_RoxH48_H1 | 0.1 (3.4) | -2.2 (3.3) | 0.80 (0.67-0.94, p=0.011) | 1.30 (0.73-2.63, p=0.381) | 0.93 (0.63-1.29, p=0.669) |
| var_RoxH24_H1 | var_RoxH24_H1 | 0.0 (3.0) | -2.2 (2.8) | 0.77 (0.66-0.89, p=0.001) | 0.46 (0.15-0.90, p=0.071) | - |
le graphique d’explanatory full (avec tous les critere secondaire est tres chargé, il faudra choisir les criteres à faire apparaitre dessus)
Oxy_cov %>%
or_plot(dependent_1, explanatory_full)
Oxy_cov %>%
or_plot(dependent_1, explanatory_final)
Courbe de survie ( DC/IOT à J28) selon durée de maladie
La durée de la maladie a été calculée en additionnant le nombre de jour de sympatome à l’arrivée + le nombre de jour d’hospitalisation Les données sont comptabilisées en jours sont noté oui les données de décès et ou IOT à J28
library(rmarkdown)
library(markdown)
library(tidyverse)
library(finalfit)
library(survival)
library(survminer)
library(ggplot2)Surv_J28<-survfit(Surv(Survie_J,DC_IOT )~1,data=Oxy_cov)
Surv_J28## Call: survfit(formula = Surv(Survie_J, DC_IOT) ~ 1, data = Oxy_cov)
##
## n events median 0.95LCL 0.95UCL
## [1,] 162 36 50 39 68ggsurvplot(Surv_J28,xlab="Time(Days)")
Courbe de survie OHD CPAP
S_OHD_CPAP<-survfit(Surv(Survie_J,DC_IOT)~OHD_CPAP.1, data=Oxy_cov)
S_OHD_CPAP## Call: survfit(formula = Surv(Survie_J, DC_IOT) ~ OHD_CPAP.1, data = Oxy_cov)
##
## n events median 0.95LCL 0.95UCL
## OHD_CPAP.1=OHD seule 18 3 90 38 NA
## OHD_CPAP.1=OHD_CPAP 144 33 45 39 68le test du logrank est utilisé ici afin de comparer des courbes de survie. La mortalité ches les patients diffère-t-elle significativement selon OHT /CPAP ?
survdiff(Surv(Survie_J,DC_IOT)~OHD_CPAP.1, data=Oxy_cov)## Call:
## survdiff(formula = Surv(Survie_J, DC_IOT) ~ OHD_CPAP.1, data = Oxy_cov)
##
## N Observed Expected (O-E)^2/E (O-E)^2/V
## OHD_CPAP.1=OHD seule 18 3 6.13 1.597 2.32
## OHD_CPAP.1=OHD_CPAP 144 33 29.87 0.328 2.32
##
## Chisq= 2.3 on 1 degrees of freedom, p= 0.1ggsurvplot(S_OHD_CPAP, conf.int = TRUE, risk.table = TRUE, pval = TRUE, data = Oxy_cov)
Courbe de survie OHD DV
S_OHD_DV<-survfit(Surv(Survie_J,DC_IOT)~OHD_DV, data=Oxy_cov)
S_OHD_DV## Call: survfit(formula = Surv(Survie_J, DC_IOT) ~ OHD_DV, data = Oxy_cov)
##
## n events median 0.95LCL 0.95UCL
## OHD_DV=OHD seule 50 14 64 29 NA
## OHD_DV=OHD_DV 112 22 45 39 86le test du logrank est utilisé ici afin de comparer des courbes de survie. La mortalité ches les patients diffère-t-elle significativement selon OHT /CPAP ?
survdiff(Surv(Survie_J,DC_IOT)~OHD_DV, data=Oxy_cov)## Call:
## survdiff(formula = Surv(Survie_J, DC_IOT) ~ OHD_DV, data = Oxy_cov)
##
## N Observed Expected (O-E)^2/E (O-E)^2/V
## OHD_DV=OHD seule 50 14 12.4 0.217 0.368
## OHD_DV=OHD_DV 112 22 23.6 0.113 0.368
##
## Chisq= 0.4 on 1 degrees of freedom, p= 0.5ggsurvplot(S_OHD_DV, conf.int = TRUE, risk.table = TRUE, pval = TRUE, data = Oxy_cov)
Courbe de survie DV
S_DV_DL<-survfit(Surv(Survie_J,DC_IOT)~X.DV_DL, data=Oxy_cov)
S_DV_DL## Call: survfit(formula = Surv(Survie_J, DC_IOT) ~ X.DV_DL, data = Oxy_cov)
##
## n events median 0.95LCL 0.95UCL
## X.DV_DL=Fait 112 22 45 39 86
## X.DV_DL=Non fait 50 14 64 29 NAle test du logrank est utilisé ici afin de comparer des courbes de survie. La mortalité ches les patients diffère-t-elle significativement selon OHT /CPAP ?
survdiff(Surv(Survie_J,DC_IOT)~X.DV_DL, data=Oxy_cov)## Call:
## survdiff(formula = Surv(Survie_J, DC_IOT) ~ X.DV_DL, data = Oxy_cov)
##
## N Observed Expected (O-E)^2/E (O-E)^2/V
## X.DV_DL=Fait 112 22 23.6 0.113 0.368
## X.DV_DL=Non fait 50 14 12.4 0.217 0.368
##
## Chisq= 0.4 on 1 degrees of freedom, p= 0.5ggsurvplot(S_DV_DL, conf.int = TRUE, risk.table = TRUE, pval = TRUE, data = Oxy_cov)
Rcherche significativité Rox
Rox H72_H1
Rox_H72 <- read.csv2("C:/Users/mallah.s/Desktop/Stats et Theses/OxyCov/Rox_H72.csv", stringsAsFactors=TRUE)qqPlot(Rox_H72$var_RoxH72_H1)
## [1] 16 69la normalité est satisfaisante
shapiro.test(Rox_H72$var_RoxH72_H1)##
## Shapiro-Wilk normality test
##
## data: Rox_H72$var_RoxH72_H1
## W = 0.97979, p-value = 0.2437tLe te de Shapiro-Wilk ne rejette pas l’hypothèse de normalité. Au final, nous acceptons cette hypothèse. Nous allons donc pouvoir comparer les moyennes de Rox H1et H72
t.test(Rox_H72$Rox_H1,Rox_H72$Rox_H72, paired=TRUE)##
## Paired t-test
##
## data: Rox_H72$Rox_H1 and Rox_H72$Rox_H72
## t = 2.1045, df = 78, p-value = 0.03856
## alternative hypothesis: true mean difference is not equal to 0
## 95 percent confidence interval:
## 0.03628853 1.30801526
## sample estimates:
## mean difference
## 0.6721519Rox H48_H1
Rox_H48 <- read.csv2("C:/Users/mallah.s/Desktop/Stats et Theses/OxyCov/Rox_H48.csv", stringsAsFactors=TRUE)qqPlot(Rox_H48$var_RoxH48_H1)
## [1] 90 67la normalité n’est pas parfaite mais satisfaisante
shapiro.test(Rox_H48$var_RoxH48_H1)##
## Shapiro-Wilk normality test
##
## data: Rox_H48$var_RoxH48_H1
## W = 0.97691, p-value = 0.05701tLe te de Shapiro-Wilk ne rejette pas l’hypothèse de normalité. Au final, nous acceptons cette hypothèse. Nous allons donc pouvoir comparer les moyennes de Rox H1et H72
t.test(Rox_H48$Rox_H1,Rox_H48$Rox_H48, paired=TRUE)##
## Paired t-test
##
## data: Rox_H48$Rox_H1 and Rox_H48$Rox_H48
## t = 0.9546, df = 107, p-value = 0.3419
## alternative hypothesis: true mean difference is not equal to 0
## 95 percent confidence interval:
## -0.3479240 0.9942203
## sample estimates:
## mean difference
## 0.3231481la diffrence moyenne de Rox entre H48 et h1 est de 0.323, la p-value du t-test est >0.05, ainsi les résultats nous indiquent que Les Rox à H48 n’est pas significativement different de H1
Rox H24_H1
Rox_H24 <- read.csv2("C:/Users/mallah.s/Desktop/Stats et Theses/OxyCov/Rox_H24.csv", stringsAsFactors=TRUE)qqPlot(Rox_H24$var_RoxH24_H1)
## [1] 95 87la normalité est satisfaisante
shapiro.test(Rox_H24$var_RoxH24_H1)##
## Shapiro-Wilk normality test
##
## data: Rox_H24$var_RoxH24_H1
## W = 0.99072, p-value = 0.5064tLe te de Shapiro-Wilk ne rejette pas l’hypothèse de normalité. Au final, nous acceptons cette hypothèse. Nous allons donc pouvoir comparer les moyennes de Rox H1et H24
t.test(Rox_H24$Rox_H1,Rox_H24$Rox_H24, paired=TRUE)##
## Paired t-test
##
## data: Rox_H24$Rox_H1 and Rox_H24$Rox_H24
## t = 1.822, df = 135, p-value = 0.07067
## alternative hypothesis: true mean difference is not equal to 0
## 95 percent confidence interval:
## -0.04179095 1.01973212
## sample estimates:
## mean difference
## 0.4889706