R Notebook
0.0.1 Libraries
0.0.2 Data (training and validation set)
data <- read.csv("/Users/carolinaferreiraatuesta/Documents/UCL/Reserach Project/Datasets/derivationtrain_test.csv")cat <-
c('id',
'auras',
'withdraw1',
'sex',
'childconvul',
'neuro_insult',
'status_epilepticus',
'family_history',
'non_epileptic',
'gtcs',
'gtcs6',
'MRI_normal',
'MRI_side',
'MRI_lobar',
'MRI_temp',
'EEG_ictal_side',
'EEG_ictal_temp',
'EEG_ictal_focal',
'EEG_interictal_normal',
'icEEG',
'PET',
'PET_side',
'learning_disability',
'psychiatric_pre_any',
'opside',
'optemp',
'opextent',
'op_incomplete',
'pathology_HS',
'pathology_FCD',
'pathology_DNT',
'pathology_CAV',
'pathology_GL',
'pathology_dual',
'pathology_other',
'pathology_normal',
'acutepostszauras',
'sz',
'szaurafree1st',
'aura',
'szaura',
'began_wd',
'wd_all',
'aeds'
)
cont <- c('numsz6',
'age_onset',
'duration',
'age_at_surgery',
'sz_time',
'aura_time',
'szaura_time',
'began_wd_time',
'age_began_wd',
'wd_all_time',
'years_follow_up')
tab1 <-
CreateTableOne(data = data,
testApprox = chisq.test,
testExact = fisher.test,
strata = 'train')
tab_all <-
CreateCatTable(vars = cat,
data=data)
tab1## Stratified by train
## 0 1 p
## n 119 231
## Column_1 (mean (SD)) 60.00 (34.50) 116.00 (66.83) <0.001
## id (mean (SD)) 1.00 (0.00) 1.00 (0.00) NaN
## auras (mean (SD)) 0.07 (0.25) 0.06 (0.24) 0.810
## withdraw1 (mean (SD)) 0.76 (0.43) 0.69 (0.46) 0.157
## sex (mean (SD)) 0.57 (0.50) 0.51 (0.50) 0.283
## childconvul (mean (SD)) 0.58 (0.50) 0.51 (0.50) 0.194
## neuro_insult (mean (SD)) 0.55 (0.50) 0.55 (0.50) 0.950
## status_epilepticus (mean (SD)) 0.16 (0.37) 0.10 (0.29) 0.076
## family_history (mean (SD)) 0.34 (0.47) 0.25 (0.43) 0.077
## non_epileptic (mean (SD)) 0.06 (0.24) 0.03 (0.17) 0.198
## age_onset (mean (SD)) 12.23 (10.21) 12.44 (10.16) 0.855
## gtcs (mean (SD)) 0.72 (0.45) 0.65 (0.48) 0.166
## gtcs6 (mean (SD)) 0.33 (0.47) 0.36 (0.48) 0.506
## numsz6 (mean (SD)) 21.25 (37.25) 25.44 (60.15) 0.488
## MRI_normal (mean (SD)) 0.03 (0.18) 0.05 (0.21) 0.541
## MRI_side (mean (SD)) 0.71 (0.69) 0.67 (0.74) 0.669
## MRI_lobar (mean (SD)) 0.99 (0.46) 0.97 (0.57) 0.663
## MRI_temp (mean (SD)) 0.50 (0.67) 0.58 (0.73) 0.373
## EEG_ictal_side (mean (SD)) 0.67 (0.70) 0.76 (0.79) 0.298
## EEG_ictal_temp (mean (SD)) 0.76 (0.43) 0.83 (0.55) 0.194
## EEG_ictal_focal (mean (SD)) 0.75 (0.44) 0.71 (0.45) 0.506
## EEG_interictal_normal (mean (SD)) 0.15 (0.36) 0.20 (0.40) 0.235
## icEEG (mean (SD)) 0.00 (0.00) 0.00 (0.00) NaN
## PET (mean (SD)) 0.06 (0.24) 0.08 (0.28) 0.430
## PET_side (mean (SD)) 2.86 (0.59) 2.79 (0.74) 0.376
## learning_disability (mean (SD)) 0.08 (0.27) 0.03 (0.18) 0.091
## psychiatric_pre_any (mean (SD)) 0.46 (0.50) 0.42 (0.49) 0.451
## duration (mean (SD)) 21.43 (12.19) 23.08 (12.04) 0.226
## age_at_surgery (mean (SD)) 33.66 (10.50) 35.52 (10.62) 0.119
## opside (mean (SD)) 0.60 (0.49) 0.50 (0.50) 0.094
## optemp (mean (SD)) 0.92 (0.28) 0.88 (0.32) 0.345
## opextent (mean (SD)) 0.94 (0.33) 0.88 (0.37) 0.151
## op_incomplete (mean (SD)) 0.00 (0.00) 0.00 (0.00) NaN
## pathology_HS (mean (SD)) 0.72 (0.45) 0.70 (0.46) 0.618
## pathology_FCD (mean (SD)) 0.02 (0.13) 0.04 (0.19) 0.262
## pathology_DNT (mean (SD)) 0.12 (0.32) 0.11 (0.31) 0.791
## pathology_CAV (mean (SD)) 0.08 (0.27) 0.08 (0.27) 0.940
## pathology_GL (mean (SD)) 0.03 (0.16) 0.03 (0.17) 0.787
## pathology_dual (mean (SD)) 0.02 (0.13) 0.03 (0.18) 0.344
## pathology_other (mean (SD)) 0.04 (0.20) 0.08 (0.27) 0.200
## pathology_normal (mean (SD)) 0.00 (0.00) 0.00 (0.00) NaN
## acutepostszauras (mean (SD)) 0.04 (0.20) 0.08 (0.28) 0.159
## sz (mean (SD)) 0.29 (0.45) 0.29 (0.45) 1.000
## sz_time (mean (SD)) 9.35 (6.35) 8.88 (6.21) 0.504
## szaurafree1st (mean (SD)) 0.99 (0.09) 0.99 (0.11) 0.703
## aura (mean (SD)) 0.11 (0.31) 0.07 (0.26) 0.260
## aura_time (mean (SD)) 10.81 (6.42) 10.42 (6.20) 0.578
## szaura (mean (SD)) 0.34 (0.47) 0.33 (0.47) 0.894
## szaura_time (mean (SD)) 8.82 (6.42) 8.49 (6.04) 0.636
## began_wd (mean (SD)) 0.93 (0.25) 0.88 (0.33) 0.116
## began_wd_time (mean (SD)) 2.50 (2.78) 3.03 (4.05) 0.202
## age_began_wd (mean (SD)) 35.77 (10.61) 38.20 (11.44) 0.055
## wd_all (mean (SD)) 0.69 (0.46) 0.52 (0.50) 0.002
## wd_all_time (mean (SD)) 6.11 (4.80) 6.65 (5.57) 0.367
## aeds (mean (SD)) 2.48 (0.82) 2.32 (0.84) 0.101
## years_follow_up (mean (SD)) 11.86 (6.22) 11.00 (6.16) 0.218
## train (mean (SD)) 0.00 (0.00) 1.00 (0.00) <0.001
## Stratified by train
## test
## n
## Column_1 (mean (SD))
## id (mean (SD))
## auras (mean (SD))
## withdraw1 (mean (SD))
## sex (mean (SD))
## childconvul (mean (SD))
## neuro_insult (mean (SD))
## status_epilepticus (mean (SD))
## family_history (mean (SD))
## non_epileptic (mean (SD))
## age_onset (mean (SD))
## gtcs (mean (SD))
## gtcs6 (mean (SD))
## numsz6 (mean (SD))
## MRI_normal (mean (SD))
## MRI_side (mean (SD))
## MRI_lobar (mean (SD))
## MRI_temp (mean (SD))
## EEG_ictal_side (mean (SD))
## EEG_ictal_temp (mean (SD))
## EEG_ictal_focal (mean (SD))
## EEG_interictal_normal (mean (SD))
## icEEG (mean (SD))
## PET (mean (SD))
## PET_side (mean (SD))
## learning_disability (mean (SD))
## psychiatric_pre_any (mean (SD))
## duration (mean (SD))
## age_at_surgery (mean (SD))
## opside (mean (SD))
## optemp (mean (SD))
## opextent (mean (SD))
## op_incomplete (mean (SD))
## pathology_HS (mean (SD))
## pathology_FCD (mean (SD))
## pathology_DNT (mean (SD))
## pathology_CAV (mean (SD))
## pathology_GL (mean (SD))
## pathology_dual (mean (SD))
## pathology_other (mean (SD))
## pathology_normal (mean (SD))
## acutepostszauras (mean (SD))
## sz (mean (SD))
## sz_time (mean (SD))
## szaurafree1st (mean (SD))
## aura (mean (SD))
## aura_time (mean (SD))
## szaura (mean (SD))
## szaura_time (mean (SD))
## began_wd (mean (SD))
## began_wd_time (mean (SD))
## age_began_wd (mean (SD))
## wd_all (mean (SD))
## wd_all_time (mean (SD))
## aeds (mean (SD))
## years_follow_up (mean (SD))
## train (mean (SD))tab_all##
## Overall
## n 350
## id = 1 (%) 350 (100.0)
## auras = 1 (%) 22 ( 6.3)
## withdraw1 = 1 (%) 251 ( 71.7)
## sex = 1 (%) 186 ( 53.1)
## childconvul = 1 (%) 186 ( 53.1)
## neuro_insult = 1 (%) 192 ( 54.9)
## status_epilepticus = 1 (%) 41 ( 11.7)
## family_history = 1 (%) 97 ( 27.7)
## non_epileptic = 1 (%) 14 ( 4.0)
## gtcs = 1 (%) 236 ( 67.4)
## gtcs6 = 1 (%) 123 ( 35.1)
## MRI_normal = 1 (%) 15 ( 4.3)
## MRI_side (%)
## 0 149 ( 42.6)
## 1 178 ( 50.9)
## 2 8 ( 2.3)
## 3 15 ( 4.3)
## MRI_lobar (%)
## 0 39 ( 11.1)
## 1 296 ( 84.6)
## 3 15 ( 4.3)
## MRI_temp (%)
## 0 187 ( 53.4)
## 1 148 ( 42.3)
## 3 15 ( 4.3)
## EEG_ictal_side (%)
## 0 151 ( 43.1)
## 1 152 ( 43.4)
## 2 37 ( 10.6)
## 3 10 ( 2.9)
## EEG_ictal_temp (%)
## 0 80 ( 22.9)
## 1 264 ( 75.4)
## 3 6 ( 1.7)
## EEG_ictal_focal = 1 (%) 254 ( 72.6)
## EEG_interictal_normal = 1 (%) 65 ( 18.6)
## icEEG = 0 (%) 350 (100.0)
## PET = 1 (%) 26 ( 7.4)
## PET_side (%)
## 0 16 ( 4.6)
## 1 9 ( 2.6)
## 3 325 ( 92.9)
## learning_disability = 1 (%) 17 ( 4.9)
## psychiatric_pre_any = 1 (%) 152 ( 43.4)
## opside = 1 (%) 187 ( 53.4)
## optemp = 1 (%) 313 ( 89.4)
## opextent (%)
## 0 41 ( 11.7)
## 1 302 ( 86.3)
## 2 7 ( 2.0)
## op_incomplete = 0 (%) 350 (100.0)
## pathology_HS = 1 (%) 247 ( 70.6)
## pathology_FCD = 1 (%) 11 ( 3.1)
## pathology_DNT = 1 (%) 39 ( 11.1)
## pathology_CAV = 1 (%) 27 ( 7.7)
## pathology_GL = 1 (%) 10 ( 2.9)
## pathology_dual = 1 (%) 10 ( 2.9)
## pathology_other = 1 (%) 23 ( 6.6)
## pathology_normal = 0 (%) 350 (100.0)
## acutepostszauras = 1 (%) 24 ( 6.9)
## sz = 1 (%) 100 ( 28.6)
## szaurafree1st = 1 (%) 346 ( 98.9)
## aura = 1 (%) 30 ( 8.6)
## szaura = 1 (%) 116 ( 33.1)
## began_wd = 1 (%) 314 ( 89.7)
## wd_all = 1 (%) 202 ( 57.7)
## aeds (%)
## 1 43 ( 12.3)
## 2 162 ( 46.3)
## 3 121 ( 34.6)
## 4 19 ( 5.4)
## 5 4 ( 1.1)
## 6 1 ( 0.3)data <- read_xlsx("/Users/carolinaferreiraatuesta/Documents/UCL/Reserach Project/Datasets/derivation.xlsx")
set.seed(1234567)
split <- sample.split(data$sz,SplitRatio = 0.66)
train_set<- subset(data,split==T)
test_set<- subset(data,split==F)1 Training Cohort
1.1 Univariable regression
lapply(c('auras',
'withdraw1',
'sex',
'childconvul ',
'neuro_insult',
'status_epilepticus ',
'family_history',
'non_epileptic',
'gtcs',
'gtcs6',
'numsz6',
'MRI_normal',
'MRI_side',
'MRI_lobar',
'MRI_temp',
'EEG_ictal_side',
'EEG_ictal_temp',
'EEG_ictal_focal',
'EEG_interictal_normal',
'icEEG',
'PET',
'PET_side',
'learning_disability',
'psychiatric_pre_any',
'opside',
'optemp',
'opextent',
'op_incomplete',
'pathology_HS ',
'pathology_FCD',
'pathology_DNT',
'pathology_CAV',
'pathology_GL',
'pathology_dual',
'pathology_other',
'pathology_normal',
'acutepostszauras',
'sz',
'szaurafree1st',
'aura',
'szaura',
'began_wd',
'wd_all',
'aeds',
'age_onset ',
'duration',
'age_at_surgery',
'sz_time',
'aura_time',
'szaura_time',
'began_wd_time',
'age_began_wd',
'wd_all_time',
'years_follow_up'),
function(var) {
formula <-
as.formula(paste("Surv(time = train_set$sz_time, event = train_set$sz) ~", var))
res.logist <-
coxph(formula, data = train_set)
summary(res.logist)
}
)## [[1]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## auras 1.1877 3.2796 0.3603 3.296 0.000979 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## auras 3.28 0.3049 1.619 6.645
##
## Concordance= 0.549 (se = 0.021 )
## Likelihood ratio test= 8.19 on 1 df, p=0.004
## Wald test = 10.87 on 1 df, p=0.001
## Score (logrank) test = 12.2 on 1 df, p=5e-04
##
##
## [[2]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## withdraw1 0.05682 1.05847 0.26466 0.215 0.83
##
## exp(coef) exp(-coef) lower .95 upper .95
## withdraw1 1.058 0.9448 0.6301 1.778
##
## Concordance= 0.517 (se = 0.029 )
## Likelihood ratio test= 0.05 on 1 df, p=0.8
## Wald test = 0.05 on 1 df, p=0.8
## Score (logrank) test = 0.05 on 1 df, p=0.8
##
##
## [[3]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## sex 0.03977 1.04057 0.24670 0.161 0.872
##
## exp(coef) exp(-coef) lower .95 upper .95
## sex 1.041 0.961 0.6416 1.688
##
## Concordance= 0.503 (se = 0.033 )
## Likelihood ratio test= 0.03 on 1 df, p=0.9
## Wald test = 0.03 on 1 df, p=0.9
## Score (logrank) test = 0.03 on 1 df, p=0.9
##
##
## [[4]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## childconvul -0.1477 0.8627 0.2466 -0.599 0.549
##
## exp(coef) exp(-coef) lower .95 upper .95
## childconvul 0.8627 1.159 0.532 1.399
##
## Concordance= 0.52 (se = 0.033 )
## Likelihood ratio test= 0.36 on 1 df, p=0.5
## Wald test = 0.36 on 1 df, p=0.5
## Score (logrank) test = 0.36 on 1 df, p=0.5
##
##
## [[5]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## neuro_insult -0.0925 0.9116 0.2473 -0.374 0.708
##
## exp(coef) exp(-coef) lower .95 upper .95
## neuro_insult 0.9116 1.097 0.5615 1.48
##
## Concordance= 0.526 (se = 0.033 )
## Likelihood ratio test= 0.14 on 1 df, p=0.7
## Wald test = 0.14 on 1 df, p=0.7
## Score (logrank) test = 0.14 on 1 df, p=0.7
##
##
## [[6]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## status_epilepticus 0.2791 1.3220 0.3773 0.74 0.459
##
## exp(coef) exp(-coef) lower .95 upper .95
## status_epilepticus 1.322 0.7564 0.6311 2.769
##
## Concordance= 0.513 (se = 0.019 )
## Likelihood ratio test= 0.51 on 1 df, p=0.5
## Wald test = 0.55 on 1 df, p=0.5
## Score (logrank) test = 0.55 on 1 df, p=0.5
##
##
## [[7]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## family_history 0.2789 1.3216 0.2720 1.025 0.305
##
## exp(coef) exp(-coef) lower .95 upper .95
## family_history 1.322 0.7566 0.7756 2.252
##
## Concordance= 0.53 (se = 0.029 )
## Likelihood ratio test= 1.01 on 1 df, p=0.3
## Wald test = 1.05 on 1 df, p=0.3
## Score (logrank) test = 1.06 on 1 df, p=0.3
##
##
## [[8]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## non_epileptic -0.6714 0.5110 1.0079 -0.666 0.505
##
## exp(coef) exp(-coef) lower .95 upper .95
## non_epileptic 0.511 1.957 0.07087 3.684
##
## Concordance= 0.504 (se = 0.012 )
## Likelihood ratio test= 0.56 on 1 df, p=0.5
## Wald test = 0.44 on 1 df, p=0.5
## Score (logrank) test = 0.46 on 1 df, p=0.5
##
##
## [[9]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## gtcs 0.5711 1.7703 0.2873 1.988 0.0468 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## gtcs 1.77 0.5649 1.008 3.109
##
## Concordance= 0.573 (se = 0.027 )
## Likelihood ratio test= 4.32 on 1 df, p=0.04
## Wald test = 3.95 on 1 df, p=0.05
## Score (logrank) test = 4.06 on 1 df, p=0.04
##
##
## [[10]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## gtcs6 0.5539 1.7401 0.2468 2.244 0.0248 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## gtcs6 1.74 0.5747 1.073 2.823
##
## Concordance= 0.572 (se = 0.032 )
## Likelihood ratio test= 4.92 on 1 df, p=0.03
## Wald test = 5.04 on 1 df, p=0.02
## Score (logrank) test = 5.17 on 1 df, p=0.02
##
##
## [[11]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## numsz6 0.0009617 1.0009622 0.0016044 0.599 0.549
##
## exp(coef) exp(-coef) lower .95 upper .95
## numsz6 1.001 0.999 0.9978 1.004
##
## Concordance= 0.557 (se = 0.041 )
## Likelihood ratio test= 0.31 on 1 df, p=0.6
## Wald test = 0.36 on 1 df, p=0.5
## Score (logrank) test = 0.36 on 1 df, p=0.5
##
##
## [[12]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## MRI_normal -1.707e+01 3.856e-08 3.080e+03 -0.006 0.996
##
## exp(coef) exp(-coef) lower .95 upper .95
## MRI_normal 3.856e-08 25933319 0 Inf
##
## Concordance= 0.522 (se = 0.007 )
## Likelihood ratio test= 5.35 on 1 df, p=0.02
## Wald test = 0 on 1 df, p=1
## Score (logrank) test = 2.73 on 1 df, p=0.1
##
##
## [[13]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## MRI_side -0.2343 0.7911 0.1935 -1.211 0.226
##
## exp(coef) exp(-coef) lower .95 upper .95
## MRI_side 0.7911 1.264 0.5414 1.156
##
## Concordance= 0.52 (se = 0.032 )
## Likelihood ratio test= 1.57 on 1 df, p=0.2
## Wald test = 1.47 on 1 df, p=0.2
## Score (logrank) test = 1.47 on 1 df, p=0.2
##
##
## [[14]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## MRI_lobar -0.4203 0.6568 0.2649 -1.587 0.113
##
## exp(coef) exp(-coef) lower .95 upper .95
## MRI_lobar 0.6568 1.522 0.3908 1.104
##
## Concordance= 0.527 (se = 0.022 )
## Likelihood ratio test= 2.67 on 1 df, p=0.1
## Wald test = 2.52 on 1 df, p=0.1
## Score (logrank) test = 2.43 on 1 df, p=0.1
##
##
## [[15]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## MRI_temp -0.3500 0.7047 0.2102 -1.665 0.0959 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## MRI_temp 0.7047 1.419 0.4668 1.064
##
## Concordance= 0.541 (se = 0.032 )
## Likelihood ratio test= 3.1 on 1 df, p=0.08
## Wald test = 2.77 on 1 df, p=0.1
## Score (logrank) test = 2.77 on 1 df, p=0.1
##
##
## [[16]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## EEG_ictal_side -0.1395 0.8698 0.1680 -0.831 0.406
##
## exp(coef) exp(-coef) lower .95 upper .95
## EEG_ictal_side 0.8698 1.15 0.6257 1.209
##
## Concordance= 0.532 (se = 0.035 )
## Likelihood ratio test= 0.71 on 1 df, p=0.4
## Wald test = 0.69 on 1 df, p=0.4
## Score (logrank) test = 0.69 on 1 df, p=0.4
##
##
## [[17]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## EEG_ictal_temp -0.1287 0.8792 0.2585 -0.498 0.618
##
## exp(coef) exp(-coef) lower .95 upper .95
## EEG_ictal_temp 0.8792 1.137 0.5297 1.459
##
## Concordance= 0.515 (se = 0.028 )
## Likelihood ratio test= 0.25 on 1 df, p=0.6
## Wald test = 0.25 on 1 df, p=0.6
## Score (logrank) test = 0.25 on 1 df, p=0.6
##
##
## [[18]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## EEG_ictal_focal 0.3744 1.4541 0.3011 1.243 0.214
##
## exp(coef) exp(-coef) lower .95 upper .95
## EEG_ictal_focal 1.454 0.6877 0.8059 2.624
##
## Concordance= 0.531 (se = 0.028 )
## Likelihood ratio test= 1.66 on 1 df, p=0.2
## Wald test = 1.55 on 1 df, p=0.2
## Score (logrank) test = 1.56 on 1 df, p=0.2
##
##
## [[19]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## EEG_interictal_normal -0.3119 0.7321 0.3434 -0.908 0.364
##
## exp(coef) exp(-coef) lower .95 upper .95
## EEG_interictal_normal 0.7321 1.366 0.3734 1.435
##
## Concordance= 0.537 (se = 0.021 )
## Likelihood ratio test= 0.89 on 1 df, p=0.3
## Wald test = 0.82 on 1 df, p=0.4
## Score (logrank) test = 0.83 on 1 df, p=0.4
##
##
## [[20]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## icEEG NA NA 0 NA NA
##
## exp(coef) exp(-coef) lower .95 upper .95
## icEEG NA NA NA NA
##
## Concordance= 0.5 (se = 0 )
## Likelihood ratio test= 0 on 0 df, p=1
## Wald test = NA on 0 df, p=NA
## Score (logrank) test = 0 on 0 df, p=1
##
##
## [[21]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## PET -0.8071 0.4462 0.7193 -1.122 0.262
##
## exp(coef) exp(-coef) lower .95 upper .95
## PET 0.4462 2.241 0.1089 1.827
##
## Concordance= 0.519 (se = 0.014 )
## Likelihood ratio test= 1.64 on 1 df, p=0.2
## Wald test = 1.26 on 1 df, p=0.3
## Score (logrank) test = 1.33 on 1 df, p=0.2
##
##
## [[22]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## PET_side 0.2442 1.2766 0.2491 0.98 0.327
##
## exp(coef) exp(-coef) lower .95 upper .95
## PET_side 1.277 0.7833 0.7834 2.08
##
## Concordance= 0.517 (se = 0.014 )
## Likelihood ratio test= 1.2 on 1 df, p=0.3
## Wald test = 0.96 on 1 df, p=0.3
## Score (logrank) test = 1 on 1 df, p=0.3
##
##
## [[23]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## learning_disability -0.1504 0.8604 0.7186 -0.209 0.834
##
## exp(coef) exp(-coef) lower .95 upper .95
## learning_disability 0.8604 1.162 0.2104 3.518
##
## Concordance= 0.501 (se = 0.012 )
## Likelihood ratio test= 0.05 on 1 df, p=0.8
## Wald test = 0.04 on 1 df, p=0.8
## Score (logrank) test = 0.04 on 1 df, p=0.8
##
##
## [[24]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## psychiatric_pre_any 0.1958 1.2163 0.2474 0.792 0.429
##
## exp(coef) exp(-coef) lower .95 upper .95
## psychiatric_pre_any 1.216 0.8222 0.749 1.975
##
## Concordance= 0.525 (se = 0.032 )
## Likelihood ratio test= 0.62 on 1 df, p=0.4
## Wald test = 0.63 on 1 df, p=0.4
## Score (logrank) test = 0.63 on 1 df, p=0.4
##
##
## [[25]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## opside -0.1053 0.9001 0.2467 -0.427 0.67
##
## exp(coef) exp(-coef) lower .95 upper .95
## opside 0.9001 1.111 0.555 1.46
##
## Concordance= 0.51 (se = 0.033 )
## Likelihood ratio test= 0.18 on 1 df, p=0.7
## Wald test = 0.18 on 1 df, p=0.7
## Score (logrank) test = 0.18 on 1 df, p=0.7
##
##
## [[26]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## optemp 0.02514 1.02546 0.40008 0.063 0.95
##
## exp(coef) exp(-coef) lower .95 upper .95
## optemp 1.025 0.9752 0.4681 2.246
##
## Concordance= 0.497 (se = 0.022 )
## Likelihood ratio test= 0 on 1 df, p=0.9
## Wald test = 0 on 1 df, p=0.9
## Score (logrank) test = 0 on 1 df, p=0.9
##
##
## [[27]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## opextent 0.06502 1.06718 0.32128 0.202 0.84
##
## exp(coef) exp(-coef) lower .95 upper .95
## opextent 1.067 0.937 0.5685 2.003
##
## Concordance= 0.505 (se = 0.021 )
## Likelihood ratio test= 0.04 on 1 df, p=0.8
## Wald test = 0.04 on 1 df, p=0.8
## Score (logrank) test = 0.04 on 1 df, p=0.8
##
##
## [[28]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## op_incomplete NA NA 0 NA NA
##
## exp(coef) exp(-coef) lower .95 upper .95
## op_incomplete NA NA NA NA
##
## Concordance= 0.5 (se = 0 )
## Likelihood ratio test= 0 on 0 df, p=1
## Wald test = NA on 0 df, p=NA
## Score (logrank) test = 0 on 0 df, p=1
##
##
## [[29]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## pathology_HS 0.3497 1.4186 0.2873 1.217 0.224
##
## exp(coef) exp(-coef) lower .95 upper .95
## pathology_HS 1.419 0.7049 0.8078 2.491
##
## Concordance= 0.535 (se = 0.029 )
## Likelihood ratio test= 1.57 on 1 df, p=0.2
## Wald test = 1.48 on 1 df, p=0.2
## Score (logrank) test = 1.5 on 1 df, p=0.2
##
##
## [[30]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## pathology_FCD -0.04376 0.95718 0.71907 -0.061 0.951
##
## exp(coef) exp(-coef) lower .95 upper .95
## pathology_FCD 0.9572 1.045 0.2338 3.918
##
## Concordance= 0.499 (se = 0.013 )
## Likelihood ratio test= 0 on 1 df, p=1
## Wald test = 0 on 1 df, p=1
## Score (logrank) test = 0 on 1 df, p=1
##
##
## [[31]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## pathology_DNT -0.07201 0.93052 0.40001 -0.18 0.857
##
## exp(coef) exp(-coef) lower .95 upper .95
## pathology_DNT 0.9305 1.075 0.4249 2.038
##
## Concordance= 0.501 (se = 0.02 )
## Likelihood ratio test= 0.03 on 1 df, p=0.9
## Wald test = 0.03 on 1 df, p=0.9
## Score (logrank) test = 0.03 on 1 df, p=0.9
##
##
## [[32]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## pathology_CAV -0.3493 0.7052 0.5161 -0.677 0.499
##
## exp(coef) exp(-coef) lower .95 upper .95
## pathology_CAV 0.7052 1.418 0.2565 1.939
##
## Concordance= 0.518 (se = 0.015 )
## Likelihood ratio test= 0.51 on 1 df, p=0.5
## Wald test = 0.46 on 1 df, p=0.5
## Score (logrank) test = 0.46 on 1 df, p=0.5
##
##
## [[33]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## pathology_GL 0.1205 1.1280 0.7184 0.168 0.867
##
## exp(coef) exp(-coef) lower .95 upper .95
## pathology_GL 1.128 0.8865 0.276 4.611
##
## Concordance= 0.503 (se = 0.012 )
## Likelihood ratio test= 0.03 on 1 df, p=0.9
## Wald test = 0.03 on 1 df, p=0.9
## Score (logrank) test = 0.03 on 1 df, p=0.9
##
##
## [[34]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## pathology_dual -0.5614 0.5704 1.0085 -0.557 0.578
##
## exp(coef) exp(-coef) lower .95 upper .95
## pathology_dual 0.5704 1.753 0.07902 4.118
##
## Concordance= 0.507 (se = 0.008 )
## Likelihood ratio test= 0.37 on 1 df, p=0.5
## Wald test = 0.31 on 1 df, p=0.6
## Score (logrank) test = 0.32 on 1 df, p=0.6
##
##
## [[35]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## pathology_other -1.0125 0.3633 0.7183 -1.41 0.159
##
## exp(coef) exp(-coef) lower .95 upper .95
## pathology_other 0.3633 2.752 0.0889 1.485
##
## Concordance= 0.525 (se = 0.014 )
## Likelihood ratio test= 2.78 on 1 df, p=0.1
## Wald test = 1.99 on 1 df, p=0.2
## Score (logrank) test = 2.16 on 1 df, p=0.1
##
##
## [[36]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## pathology_normal NA NA 0 NA NA
##
## exp(coef) exp(-coef) lower .95 upper .95
## pathology_normal NA NA NA NA
##
## Concordance= 0.5 (se = 0 )
## Likelihood ratio test= 0 on 0 df, p=1
## Wald test = NA on 0 df, p=NA
## Score (logrank) test = 0 on 0 df, p=1
##
##
## [[37]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## acutepostszauras -0.7892 0.4542 0.5916 -1.334 0.182
##
## exp(coef) exp(-coef) lower .95 upper .95
## acutepostszauras 0.4542 2.202 0.1424 1.448
##
## Concordance= 0.522 (se = 0.017 )
## Likelihood ratio test= 2.28 on 1 df, p=0.1
## Wald test = 1.78 on 1 df, p=0.2
## Score (logrank) test = 1.87 on 1 df, p=0.2
##
##
## [[38]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## sz 2.306e+01 1.032e+10 4.646e+03 0.005 0.996
##
## exp(coef) exp(-coef) lower .95 upper .95
## sz 1.032e+10 9.689e-11 0 Inf
##
## Concordance= 0.917 (se = 0.011 )
## Likelihood ratio test= 249.3 on 1 df, p=<2e-16
## Wald test = 0 on 1 df, p=1
## Score (logrank) test = 327.6 on 1 df, p=<2e-16
##
##
## [[39]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## szaurafree1st NA NA 0 NA NA
##
## exp(coef) exp(-coef) lower .95 upper .95
## szaurafree1st NA NA NA NA
##
## Concordance= 0.53 (se = 0.017 )
## Likelihood ratio test= 29.04 on 0 df, p=<2e-16
## Wald test = NA on 0 df, p=NA
## Score (logrank) test = 343 on 0 df, p=<2e-16
##
##
## [[40]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## aura 0.3711 1.4493 0.4000 0.928 0.354
##
## exp(coef) exp(-coef) lower .95 upper .95
## aura 1.449 0.69 0.6617 3.174
##
## Concordance= 0.519 (se = 0.02 )
## Likelihood ratio test= 0.78 on 1 df, p=0.4
## Wald test = 0.86 on 1 df, p=0.4
## Score (logrank) test = 0.87 on 1 df, p=0.4
##
##
## [[41]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## szaura 2.146e+01 2.099e+09 2.958e+03 0.007 0.994
##
## exp(coef) exp(-coef) lower .95 upper .95
## szaura 2.099e+09 4.763e-10 0 Inf
##
## Concordance= 0.888 (se = 0.013 )
## Likelihood ratio test= 197.2 on 1 df, p=<2e-16
## Wald test = 0 on 1 df, p=1
## Score (logrank) test = 222.1 on 1 df, p=<2e-16
##
##
## [[42]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## began_wd -0.04439 0.95658 0.42996 -0.103 0.918
##
## exp(coef) exp(-coef) lower .95 upper .95
## began_wd 0.9566 1.045 0.4119 2.222
##
## Concordance= 0.501 (se = 0.019 )
## Likelihood ratio test= 0.01 on 1 df, p=0.9
## Wald test = 0.01 on 1 df, p=0.9
## Score (logrank) test = 0.01 on 1 df, p=0.9
##
##
## [[43]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## wd_all 0.1267 1.1351 0.2494 0.508 0.611
##
## exp(coef) exp(-coef) lower .95 upper .95
## wd_all 1.135 0.881 0.6962 1.851
##
## Concordance= 0.525 (se = 0.032 )
## Likelihood ratio test= 0.26 on 1 df, p=0.6
## Wald test = 0.26 on 1 df, p=0.6
## Score (logrank) test = 0.26 on 1 df, p=0.6
##
##
## [[44]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## aeds 0.2668 1.3058 0.1431 1.865 0.0622 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## aeds 1.306 0.7658 0.9864 1.729
##
## Concordance= 0.568 (se = 0.036 )
## Likelihood ratio test= 3.35 on 1 df, p=0.07
## Wald test = 3.48 on 1 df, p=0.06
## Score (logrank) test = 3.47 on 1 df, p=0.06
##
##
## [[45]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## age_onset -0.00123 0.99877 0.01292 -0.095 0.924
##
## exp(coef) exp(-coef) lower .95 upper .95
## age_onset 0.9988 1.001 0.9738 1.024
##
## Concordance= 0.498 (se = 0.037 )
## Likelihood ratio test= 0.01 on 1 df, p=0.9
## Wald test = 0.01 on 1 df, p=0.9
## Score (logrank) test = 0.01 on 1 df, p=0.9
##
##
## [[46]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## duration 0.01242 1.01250 0.01029 1.207 0.228
##
## exp(coef) exp(-coef) lower .95 upper .95
## duration 1.012 0.9877 0.9923 1.033
##
## Concordance= 0.533 (se = 0.039 )
## Likelihood ratio test= 1.43 on 1 df, p=0.2
## Wald test = 1.46 on 1 df, p=0.2
## Score (logrank) test = 1.46 on 1 df, p=0.2
##
##
## [[47]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## age_at_surgery 0.01565 1.01577 0.01195 1.309 0.191
##
## exp(coef) exp(-coef) lower .95 upper .95
## age_at_surgery 1.016 0.9845 0.9922 1.04
##
## Concordance= 0.541 (se = 0.038 )
## Likelihood ratio test= 1.69 on 1 df, p=0.2
## Wald test = 1.71 on 1 df, p=0.2
## Score (logrank) test = 1.72 on 1 df, p=0.2
##
##
## [[48]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## sz_time -8.074e+01 8.638e-36 6.341e+01 -1.273 0.203
##
## exp(coef) exp(-coef) lower .95 upper .95
## sz_time 8.638e-36 1.158e+35 9.106e-90 8.195e+18
##
## Concordance= 0.995 (se = 0.001 )
## Likelihood ratio test= 459.2 on 1 df, p=<2e-16
## Wald test = 1.62 on 1 df, p=0.2
## Score (logrank) test = 117 on 1 df, p=<2e-16
##
##
## [[49]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## aura_time -0.04384 0.95710 0.02301 -1.905 0.0567 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## aura_time 0.9571 1.045 0.9149 1.001
##
## Concordance= 0.594 (se = 0.038 )
## Likelihood ratio test= 3.77 on 1 df, p=0.05
## Wald test = 3.63 on 1 df, p=0.06
## Score (logrank) test = 3.66 on 1 df, p=0.06
##
##
## [[50]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## szaura_time -0.53076 0.58816 0.05968 -8.894 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## szaura_time 0.5882 1.7 0.5232 0.6611
##
## Concordance= 0.977 (se = 0.007 )
## Likelihood ratio test= 166.5 on 1 df, p=<2e-16
## Wald test = 79.1 on 1 df, p=<2e-16
## Score (logrank) test = 105.8 on 1 df, p=<2e-16
##
##
## [[51]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## began_wd_time -0.04632 0.95474 0.03578 -1.294 0.196
##
## exp(coef) exp(-coef) lower .95 upper .95
## began_wd_time 0.9547 1.047 0.8901 1.024
##
## Concordance= 0.588 (se = 0.036 )
## Likelihood ratio test= 1.95 on 1 df, p=0.2
## Wald test = 1.68 on 1 df, p=0.2
## Score (logrank) test = 1.7 on 1 df, p=0.2
##
##
## [[52]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## age_began_wd 0.007294 1.007321 0.010962 0.665 0.506
##
## exp(coef) exp(-coef) lower .95 upper .95
## age_began_wd 1.007 0.9927 0.9859 1.029
##
## Concordance= 0.515 (se = 0.038 )
## Likelihood ratio test= 0.44 on 1 df, p=0.5
## Wald test = 0.44 on 1 df, p=0.5
## Score (logrank) test = 0.44 on 1 df, p=0.5
##
##
## [[53]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## wd_all_time -0.04287 0.95803 0.02481 -1.728 0.084 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## wd_all_time 0.958 1.044 0.9126 1.006
##
## Concordance= 0.619 (se = 0.036 )
## Likelihood ratio test= 3.27 on 1 df, p=0.07
## Wald test = 2.99 on 1 df, p=0.08
## Score (logrank) test = 3.02 on 1 df, p=0.08
##
##
## [[54]]
## Call:
## coxph(formula = formula, data = train_set)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## years_follow_up -0.04003 0.96076 0.02340 -1.711 0.0871 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## years_follow_up 0.9608 1.041 0.9177 1.006
##
## Concordance= 0.582 (se = 0.037 )
## Likelihood ratio test= 3.04 on 1 df, p=0.08
## Wald test = 2.93 on 1 df, p=0.09
## Score (logrank) test = 2.95 on 1 df, p=0.091.2 Kaplan-Meier
km_train<- survfit(Surv(train_set$sz_time, train_set$sz) ~ 1, data= train_set, type =
"kaplan-meier", conf.type = "plain")
summary(km_train, times = c(0,1,2,5,10,15, 20,23))## Call: survfit(formula = Surv(train_set$sz_time, train_set$sz) ~ 1,
## data = train_set, type = "kaplan-meier", conf.type = "plain")
##
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 0 231 0 1.000 0.0000 1.000 1.000
## 1 228 6 0.974 0.0105 0.954 0.995
## 2 217 22 0.877 0.0217 0.835 0.920
## 5 147 23 0.765 0.0289 0.709 0.822
## 10 91 12 0.692 0.0330 0.627 0.757
## 15 46 3 0.658 0.0371 0.585 0.730
## 20 17 0 0.658 0.0371 0.585 0.730
## 23 4 0 0.658 0.0371 0.585 0.730km1_train<- ggsurvplot(km_train, data = train_set, xlab = "Time (years)", ylab = "Proportion of seizure free patients after withdrawal", palette = 'black', xlim = c(0,15),ylim = c(0,1), break.time.by = 5, font.x =14 ,font.y = 14, font.tickslab = 10, show.legend.text = F)
km1_train
1.3 Model: Predicting seizure relapse after AED withdrawal after surgery
model1_train <-
coxph(
Surv(time = train_set$sz_time, event = train_set$sz) ~ train_set$auras + train_set$began_wd_time + train_set$duration + train_set$aeds+ train_set$gtcs + train_set$MRI_temp + train_set$MRI_normal + train_set$pathology_HS,
x = TRUE,
y = TRUE,
data = train_set
)
print(model1_train)## Call:
## coxph(formula = Surv(time = train_set$sz_time, event = train_set$sz) ~
## train_set$auras + train_set$began_wd_time + train_set$duration +
## train_set$aeds + train_set$gtcs + train_set$MRI_temp +
## train_set$MRI_normal + train_set$pathology_HS, data = train_set,
## x = TRUE, y = TRUE)
##
## coef exp(coef) se(coef) z p
## train_set$auras 1.517e+00 4.560e+00 3.832e-01 3.960 7.5e-05
## train_set$began_wd_time -7.298e-02 9.296e-01 3.777e-02 -1.932 0.0533
## train_set$duration -1.232e-03 9.988e-01 1.157e-02 -0.106 0.9152
## train_set$aeds 2.718e-01 1.312e+00 1.519e-01 1.789 0.0736
## train_set$gtcs 6.067e-01 1.834e+00 2.906e-01 2.088 0.0368
## train_set$MRI_temp -4.883e-02 9.523e-01 2.513e-01 -0.194 0.8459
## train_set$MRI_normal -1.717e+01 3.496e-08 3.644e+03 -0.005 0.9962
## train_set$pathology_HS 2.075e-01 1.231e+00 3.091e-01 0.671 0.5020
##
## Likelihood ratio test=27.75 on 8 df, p=0.0005241
## n= 231, number of events= 661.4 Stepwise reduction using AIC
step(model1_train, direction = "both")## Start: AIC=664.62
## Surv(time = train_set$sz_time, event = train_set$sz) ~ train_set$auras +
## train_set$began_wd_time + train_set$duration + train_set$aeds +
## train_set$gtcs + train_set$MRI_temp + train_set$MRI_normal +
## train_set$pathology_HS
##
## Df AIC
## - train_set$duration 1 662.63
## - train_set$MRI_temp 1 662.66
## - train_set$pathology_HS 1 663.08
## <none> 664.62
## - train_set$aeds 1 665.73
## - train_set$MRI_normal 1 665.75
## - train_set$began_wd_time 1 667.33
## - train_set$gtcs 1 667.39
## - train_set$auras 1 674.27
##
## Step: AIC=662.63
## Surv(time = train_set$sz_time, event = train_set$sz) ~ train_set$auras +
## train_set$began_wd_time + train_set$aeds + train_set$gtcs +
## train_set$MRI_temp + train_set$MRI_normal + train_set$pathology_HS
##
## Df AIC
## - train_set$MRI_temp 1 660.67
## - train_set$pathology_HS 1 661.10
## <none> 662.63
## - train_set$aeds 1 663.77
## - train_set$MRI_normal 1 663.78
## + train_set$duration 1 664.62
## - train_set$began_wd_time 1 665.33
## - train_set$gtcs 1 665.42
## - train_set$auras 1 672.37
##
## Step: AIC=660.67
## Surv(time = train_set$sz_time, event = train_set$sz) ~ train_set$auras +
## train_set$began_wd_time + train_set$aeds + train_set$gtcs +
## train_set$MRI_normal + train_set$pathology_HS
##
## Df AIC
## - train_set$pathology_HS 1 659.14
## <none> 660.67
## - train_set$aeds 1 661.86
## + train_set$MRI_temp 1 662.63
## + train_set$duration 1 662.66
## - train_set$MRI_normal 1 663.31
## - train_set$began_wd_time 1 663.36
## - train_set$gtcs 1 663.55
## - train_set$auras 1 670.45
##
## Step: AIC=659.14
## Surv(time = train_set$sz_time, event = train_set$sz) ~ train_set$auras +
## train_set$began_wd_time + train_set$aeds + train_set$gtcs +
## train_set$MRI_normal
##
## Df AIC
## <none> 659.14
## - train_set$aeds 1 660.24
## + train_set$pathology_HS 1 660.67
## + train_set$MRI_temp 1 661.10
## + train_set$duration 1 661.12
## - train_set$began_wd_time 1 661.69
## - train_set$gtcs 1 662.09
## - train_set$MRI_normal 1 662.34
## - train_set$auras 1 669.55## Call:
## coxph(formula = Surv(time = train_set$sz_time, event = train_set$sz) ~
## train_set$auras + train_set$began_wd_time + train_set$aeds +
## train_set$gtcs + train_set$MRI_normal, data = train_set,
## x = TRUE, y = TRUE)
##
## coef exp(coef) se(coef) z p
## train_set$auras 1.552e+00 4.722e+00 3.735e-01 4.156 3.24e-05
## train_set$began_wd_time -7.186e-02 9.307e-01 3.775e-02 -1.904 0.0569
## train_set$aeds 2.627e-01 1.300e+00 1.467e-01 1.790 0.0734
## train_set$gtcs 6.109e-01 1.842e+00 2.878e-01 2.122 0.0338
## train_set$MRI_normal -1.739e+01 2.808e-08 3.647e+03 -0.005 0.9962
##
## Likelihood ratio test=27.23 on 5 df, p=5.155e-05
## n= 231, number of events= 661.5 Final model
model1f_train <-
coxph(
Surv(time = train_set$sz_time, event = train_set$sz) ~ train_set$auras + train_set$began_wd_time + train_set$aeds + train_set$gtcs +train_set$MRI_normal
)
summary(model1f_train)## Call:
## coxph(formula = Surv(time = train_set$sz_time, event = train_set$sz) ~
## train_set$auras + train_set$began_wd_time + train_set$aeds +
## train_set$gtcs + train_set$MRI_normal)
##
## n= 231, number of events= 66
##
## coef exp(coef) se(coef) z Pr(>|z|)
## train_set$auras 1.552e+00 4.722e+00 3.735e-01 4.156 3.24e-05
## train_set$began_wd_time -7.186e-02 9.307e-01 3.775e-02 -1.904 0.0569
## train_set$aeds 2.627e-01 1.300e+00 1.467e-01 1.790 0.0734
## train_set$gtcs 6.109e-01 1.842e+00 2.878e-01 2.122 0.0338
## train_set$MRI_normal -1.739e+01 2.808e-08 3.647e+03 -0.005 0.9962
##
## train_set$auras ***
## train_set$began_wd_time .
## train_set$aeds .
## train_set$gtcs *
## train_set$MRI_normal
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## train_set$auras 4.722e+00 2.118e-01 2.2709 9.820
## train_set$began_wd_time 9.307e-01 1.075e+00 0.8643 1.002
## train_set$aeds 1.300e+00 7.690e-01 0.9754 1.734
## train_set$gtcs 1.842e+00 5.429e-01 1.0478 3.238
## train_set$MRI_normal 2.808e-08 3.561e+07 0.0000 Inf
##
## Concordance= 0.707 (se = 0.03 )
## Likelihood ratio test= 27.23 on 5 df, p=5e-05
## Wald test = 25.11 on 5 df, p=1e-04
## Score (logrank) test = 29.5 on 5 df, p=2e-051.6 Internal validadion
1.6.1 Discrimination
fitmodel1f_train <-
cph(
Surv(time = sz_time, event = sz) ~ auras + began_wd_time + aeds + gtcs +MRI_normal,
data = train_set,
x = TRUE,
y = TRUE,
surv = TRUE,
time.inc = 2
)
fitmodel1f_train## Cox Proportional Hazards Model
##
## cph(formula = Surv(time = sz_time, event = sz) ~ auras + began_wd_time +
## aeds + gtcs + MRI_normal, data = train_set, x = TRUE, y = TRUE,
## surv = TRUE, time.inc = 2)
##
## Model Tests Discrimination
## Indexes
## Obs 231 LR chi2 27.20 R2 0.117
## Events 66 d.f. 5 Dxy 0.414
## Center 0.6269 Pr(> chi2) 0.0001 g 1.019
## Score chi2 29.50 gr 2.770
## Pr(> chi2) 0.0000
##
## Coef S.E. Wald Z Pr(>|Z|)
## auras 1.5523 0.3736 4.16 <0.0001
## began_wd_time -0.0719 0.0377 -1.90 0.0569
## aeds 0.2627 0.1467 1.79 0.0734
## gtcs 0.6109 0.2878 2.12 0.0338
## MRI_normal -5.3878 9.0409 -0.60 0.5512
## rms::validate(fitmodel1f_train, dxy = TRUE, B = 1000)## index.orig training test optimism index.corrected n
## Dxy 0.4142 0.4280 0.3875 0.0405 0.3737 1000
## R2 0.1174 0.1365 0.1037 0.0328 0.0846 1000
## Slope 1.0000 1.0000 0.8531 0.1469 0.8531 1000
## D 0.0387 0.0463 0.0338 0.0125 0.0263 1000
## U -0.0030 -0.0030 0.0044 -0.0074 0.0045 1000
## Q 0.0417 0.0493 0.0294 0.0199 0.0218 1000
## g 1.0188 1.1070 0.9184 0.1886 0.8301 10001.6.2 Calibration plots
fitmode1f_train <-
cph(
Surv(time = sz_time, event = sz) ~ auras + began_wd_time + aeds + gtcs + MRI_normal,
data = train_set,
x = TRUE,
y = TRUE,
surv = TRUE,
time.inc = 2
)
calibrate1_train <- calibrate(
fitmodel1f_train,
u = 2,
cmethod = 'KM',
B = 1000,
m = 20
)## Using Cox survival estimates at 2 Daysplot(calibrate1_train, xlim = c(0,1),ylim = c(0,1))
fitmodel1f_train2 <-
cph(
Surv(time = sz_time, event = sz) ~ auras + began_wd_time + aeds + gtcs + MRI_normal,
data = test_set,
x = TRUE,
y = TRUE,
surv = TRUE,
time.inc = 5
)
calibrate_train2 <- calibrate(
fitmodel1f_train2,
u = 5,
cmethod = 'KM',
B = 1000,
m = 25
)## Using Cox survival estimates at 5 Days
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 2 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samplesplot2 <- plot(calibrate_train2, xlim = c(0,1),ylim = c(0,1))
2 Validation Cohort
2.1 Univariable Regression
lapply(c('auras',
'withdraw1',
'sex',
'childconvul ',
'neuro_insult',
'status_epilepticus ',
'family_history',
'non_epileptic',
'gtcs',
'gtcs6',
'numsz6',
'MRI_normal',
'MRI_side',
'MRI_lobar',
'MRI_temp',
'EEG_ictal_side',
'EEG_ictal_temp',
'EEG_ictal_focal',
'EEG_interictal_normal',
'icEEG',
'PET',
'PET_side',
'learning_disability',
'psychiatric_pre_any',
'opside',
'optemp',
'opextent',
'op_incomplete',
'pathology_HS ',
'pathology_FCD',
'pathology_DNT',
'pathology_CAV',
'pathology_GL',
'pathology_dual',
'pathology_other',
'pathology_normal',
'acutepostszauras',
'sz',
'szaurafree1st',
'aura',
'szaura',
'began_wd',
'wd_all',
'aeds',
'age_onset ',
'duration',
'age_at_surgery',
'sz_time',
'aura_time',
'szaura_time',
'began_wd_time',
'age_began_wd',
'wd_all_time',
'years_follow_up'),
function(var) {
formula <-
as.formula(paste("Surv(time = test_set$sz_time, event = test_set$sz) ~", var))
res.logist <-
coxph(formula, data = test_set)
summary(res.logist)
}
)## [[1]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## auras 1.5985 4.9454 0.4583 3.488 0.000487 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## auras 4.945 0.2022 2.014 12.14
##
## Concordance= 0.575 (se = 0.032 )
## Likelihood ratio test= 8.71 on 1 df, p=0.003
## Wald test = 12.16 on 1 df, p=5e-04
## Score (logrank) test = 14.96 on 1 df, p=1e-04
##
##
## [[2]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## withdraw1 -1.4318 0.2389 0.3435 -4.168 3.08e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## withdraw1 0.2389 4.186 0.1218 0.4684
##
## Concordance= 0.667 (se = 0.043 )
## Likelihood ratio test= 16.07 on 1 df, p=6e-05
## Wald test = 17.37 on 1 df, p=3e-05
## Score (logrank) test = 20.52 on 1 df, p=6e-06
##
##
## [[3]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## sex -0.5958 0.5511 0.3455 -1.724 0.0846 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## sex 0.5511 1.815 0.28 1.085
##
## Concordance= 0.582 (se = 0.045 )
## Likelihood ratio test= 3 on 1 df, p=0.08
## Wald test = 2.97 on 1 df, p=0.08
## Score (logrank) test = 3.06 on 1 df, p=0.08
##
##
## [[4]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## childconvul -0.3482 0.7059 0.3430 -1.015 0.31
##
## exp(coef) exp(-coef) lower .95 upper .95
## childconvul 0.7059 1.417 0.3604 1.383
##
## Concordance= 0.541 (se = 0.045 )
## Likelihood ratio test= 1.03 on 1 df, p=0.3
## Wald test = 1.03 on 1 df, p=0.3
## Score (logrank) test = 1.04 on 1 df, p=0.3
##
##
## [[5]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## neuro_insult 0.1259 1.1342 0.3455 0.364 0.716
##
## exp(coef) exp(-coef) lower .95 upper .95
## neuro_insult 1.134 0.8817 0.5762 2.232
##
## Concordance= 0.532 (se = 0.044 )
## Likelihood ratio test= 0.13 on 1 df, p=0.7
## Wald test = 0.13 on 1 df, p=0.7
## Score (logrank) test = 0.13 on 1 df, p=0.7
##
##
## [[6]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## status_epilepticus 0.417 1.517 0.425 0.981 0.327
##
## exp(coef) exp(-coef) lower .95 upper .95
## status_epilepticus 1.517 0.659 0.6597 3.49
##
## Concordance= 0.537 (se = 0.037 )
## Likelihood ratio test= 0.89 on 1 df, p=0.3
## Wald test = 0.96 on 1 df, p=0.3
## Score (logrank) test = 0.98 on 1 df, p=0.3
##
##
## [[7]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## family_history 0.5873 1.7992 0.3462 1.696 0.0898 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## family_history 1.799 0.5558 0.9128 3.546
##
## Concordance= 0.579 (se = 0.044 )
## Likelihood ratio test= 2.78 on 1 df, p=0.1
## Wald test = 2.88 on 1 df, p=0.09
## Score (logrank) test = 2.96 on 1 df, p=0.09
##
##
## [[8]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## non_epileptic -0.06787 0.93438 0.72910 -0.093 0.926
##
## exp(coef) exp(-coef) lower .95 upper .95
## non_epileptic 0.9344 1.07 0.2238 3.901
##
## Concordance= 0.499 (se = 0.023 )
## Likelihood ratio test= 0.01 on 1 df, p=0.9
## Wald test = 0.01 on 1 df, p=0.9
## Score (logrank) test = 0.01 on 1 df, p=0.9
##
##
## [[9]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## gtcs 0.04511 1.04614 0.38886 0.116 0.908
##
## exp(coef) exp(-coef) lower .95 upper .95
## gtcs 1.046 0.9559 0.4882 2.242
##
## Concordance= 0.5 (se = 0.04 )
## Likelihood ratio test= 0.01 on 1 df, p=0.9
## Wald test = 0.01 on 1 df, p=0.9
## Score (logrank) test = 0.01 on 1 df, p=0.9
##
##
## [[10]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## gtcs6 0.6843 1.9824 0.3463 1.976 0.0481 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## gtcs6 1.982 0.5044 1.006 3.908
##
## Concordance= 0.588 (se = 0.044 )
## Likelihood ratio test= 3.74 on 1 df, p=0.05
## Wald test = 3.91 on 1 df, p=0.05
## Score (logrank) test = 4.06 on 1 df, p=0.04
##
##
## [[11]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## numsz6 -0.005002 0.995010 0.006689 -0.748 0.455
##
## exp(coef) exp(-coef) lower .95 upper .95
## numsz6 0.995 1.005 0.982 1.008
##
## Concordance= 0.473 (se = 0.049 )
## Likelihood ratio test= 0.74 on 1 df, p=0.4
## Wald test = 0.56 on 1 df, p=0.5
## Score (logrank) test = 0.57 on 1 df, p=0.5
##
##
## [[12]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## MRI_normal 1.2842 3.6116 0.6064 2.118 0.0342 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## MRI_normal 3.612 0.2769 1.1 11.85
##
## Concordance= 0.528 (se = 0.021 )
## Likelihood ratio test= 3.21 on 1 df, p=0.07
## Wald test = 4.49 on 1 df, p=0.03
## Score (logrank) test = 5.14 on 1 df, p=0.02
##
##
## [[13]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## MRI_side 0.5203 1.6825 0.2109 2.467 0.0136 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## MRI_side 1.683 0.5944 1.113 2.544
##
## Concordance= 0.597 (se = 0.046 )
## Likelihood ratio test= 5.32 on 1 df, p=0.02
## Wald test = 6.09 on 1 df, p=0.01
## Score (logrank) test = 6.1 on 1 df, p=0.01
##
##
## [[14]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## MRI_lobar 0.3274 1.3874 0.3523 0.929 0.353
##
## exp(coef) exp(-coef) lower .95 upper .95
## MRI_lobar 1.387 0.7208 0.6955 2.768
##
## Concordance= 0.491 (se = 0.037 )
## Likelihood ratio test= 0.76 on 1 df, p=0.4
## Wald test = 0.86 on 1 df, p=0.4
## Score (logrank) test = 0.86 on 1 df, p=0.4
##
##
## [[15]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## MRI_temp 0.2819 1.3256 0.2318 1.216 0.224
##
## exp(coef) exp(-coef) lower .95 upper .95
## MRI_temp 1.326 0.7544 0.8416 2.088
##
## Concordance= 0.508 (se = 0.047 )
## Likelihood ratio test= 1.34 on 1 df, p=0.2
## Wald test = 1.48 on 1 df, p=0.2
## Score (logrank) test = 1.48 on 1 df, p=0.2
##
##
## [[16]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## EEG_ictal_side 0.009289 1.009332 0.240699 0.039 0.969
##
## exp(coef) exp(-coef) lower .95 upper .95
## EEG_ictal_side 1.009 0.9908 0.6297 1.618
##
## Concordance= 0.528 (se = 0.045 )
## Likelihood ratio test= 0 on 1 df, p=1
## Wald test = 0 on 1 df, p=1
## Score (logrank) test = 0 on 1 df, p=1
##
##
## [[17]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## EEG_ictal_temp 0.3130 1.3675 0.4244 0.737 0.461
##
## exp(coef) exp(-coef) lower .95 upper .95
## EEG_ictal_temp 1.367 0.7313 0.5952 3.141
##
## Concordance= 0.535 (se = 0.036 )
## Likelihood ratio test= 0.58 on 1 df, p=0.4
## Wald test = 0.54 on 1 df, p=0.5
## Score (logrank) test = 0.55 on 1 df, p=0.5
##
##
## [[18]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## EEG_ictal_focal 0.2032 1.2254 0.4045 0.502 0.615
##
## exp(coef) exp(-coef) lower .95 upper .95
## EEG_ictal_focal 1.225 0.8161 0.5545 2.708
##
## Concordance= 0.528 (se = 0.036 )
## Likelihood ratio test= 0.26 on 1 df, p=0.6
## Wald test = 0.25 on 1 df, p=0.6
## Score (logrank) test = 0.25 on 1 df, p=0.6
##
##
## [[19]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## EEG_interictal_normal -0.06338 0.93859 0.48430 -0.131 0.896
##
## exp(coef) exp(-coef) lower .95 upper .95
## EEG_interictal_normal 0.9386 1.065 0.3633 2.425
##
## Concordance= 0.51 (se = 0.03 )
## Likelihood ratio test= 0.02 on 1 df, p=0.9
## Wald test = 0.02 on 1 df, p=0.9
## Score (logrank) test = 0.02 on 1 df, p=0.9
##
##
## [[20]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## icEEG NA NA 0 NA NA
##
## exp(coef) exp(-coef) lower .95 upper .95
## icEEG NA NA NA NA
##
## Concordance= 0.5 (se = 0 )
## Likelihood ratio test= 0 on 0 df, p=1
## Wald test = NA on 0 df, p=NA
## Score (logrank) test = 0 on 0 df, p=1
##
##
## [[21]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## PET 0.2467 1.2798 0.7305 0.338 0.736
##
## exp(coef) exp(-coef) lower .95 upper .95
## PET 1.28 0.7814 0.3057 5.357
##
## Concordance= 0.508 (se = 0.023 )
## Likelihood ratio test= 0.11 on 1 df, p=0.7
## Wald test = 0.11 on 1 df, p=0.7
## Score (logrank) test = 0.11 on 1 df, p=0.7
##
##
## [[22]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## PET_side 0.01028 1.01034 0.31258 0.033 0.974
##
## exp(coef) exp(-coef) lower .95 upper .95
## PET_side 1.01 0.9898 0.5475 1.864
##
## Concordance= 0.493 (se = 0.022 )
## Likelihood ratio test= 0 on 1 df, p=1
## Wald test = 0 on 1 df, p=1
## Score (logrank) test = 0 on 1 df, p=1
##
##
## [[23]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## learning_disability 0.6519 1.9191 0.5330 1.223 0.221
##
## exp(coef) exp(-coef) lower .95 upper .95
## learning_disability 1.919 0.5211 0.6751 5.455
##
## Concordance= 0.537 (se = 0.032 )
## Likelihood ratio test= 1.27 on 1 df, p=0.3
## Wald test = 1.5 on 1 df, p=0.2
## Score (logrank) test = 1.55 on 1 df, p=0.2
##
##
## [[24]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## psychiatric_pre_any 0.1381 1.1480 0.3447 0.401 0.689
##
## exp(coef) exp(-coef) lower .95 upper .95
## psychiatric_pre_any 1.148 0.8711 0.5842 2.256
##
## Concordance= 0.518 (se = 0.045 )
## Likelihood ratio test= 0.16 on 1 df, p=0.7
## Wald test = 0.16 on 1 df, p=0.7
## Score (logrank) test = 0.16 on 1 df, p=0.7
##
##
## [[25]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## opside 0.4384 1.5503 0.3668 1.195 0.232
##
## exp(coef) exp(-coef) lower .95 upper .95
## opside 1.55 0.6451 0.7554 3.181
##
## Concordance= 0.558 (se = 0.043 )
## Likelihood ratio test= 1.49 on 1 df, p=0.2
## Wald test = 1.43 on 1 df, p=0.2
## Score (logrank) test = 1.45 on 1 df, p=0.2
##
##
## [[26]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## optemp 0.0446 1.0456 0.6052 0.074 0.941
##
## exp(coef) exp(-coef) lower .95 upper .95
## optemp 1.046 0.9564 0.3193 3.424
##
## Concordance= 0.501 (se = 0.025 )
## Likelihood ratio test= 0.01 on 1 df, p=0.9
## Wald test = 0.01 on 1 df, p=0.9
## Score (logrank) test = 0.01 on 1 df, p=0.9
##
##
## [[27]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## opextent 0.9500 2.5856 0.5075 1.872 0.0612 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## opextent 2.586 0.3868 0.9563 6.991
##
## Concordance= 0.554 (se = 0.021 )
## Likelihood ratio test= 3.49 on 1 df, p=0.06
## Wald test = 3.5 on 1 df, p=0.06
## Score (logrank) test = 3.21 on 1 df, p=0.07
##
##
## [[28]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## op_incomplete NA NA 0 NA NA
##
## exp(coef) exp(-coef) lower .95 upper .95
## op_incomplete NA NA NA NA
##
## Concordance= 0.5 (se = 0 )
## Likelihood ratio test= 0 on 0 df, p=1
## Wald test = NA on 0 df, p=NA
## Score (logrank) test = 0 on 0 df, p=1
##
##
## [[29]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## pathology_HS -0.1333 0.8752 0.3766 -0.354 0.723
##
## exp(coef) exp(-coef) lower .95 upper .95
## pathology_HS 0.8752 1.143 0.4183 1.831
##
## Concordance= 0.521 (se = 0.042 )
## Likelihood ratio test= 0.12 on 1 df, p=0.7
## Wald test = 0.13 on 1 df, p=0.7
## Score (logrank) test = 0.13 on 1 df, p=0.7
##
##
## [[30]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## pathology_FCD -1.603e+01 1.091e-07 4.027e+03 -0.004 0.997
##
## exp(coef) exp(-coef) lower .95 upper .95
## pathology_FCD 1.091e-07 9166920 0 Inf
##
## Concordance= 0.509 (se = 0.006 )
## Likelihood ratio test= 1.12 on 1 df, p=0.3
## Wald test = 0 on 1 df, p=1
## Score (logrank) test = 0.57 on 1 df, p=0.5
##
##
## [[31]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## pathology_DNT 0.06133 1.06325 0.53272 0.115 0.908
##
## exp(coef) exp(-coef) lower .95 upper .95
## pathology_DNT 1.063 0.9405 0.3743 3.021
##
## Concordance= 0.509 (se = 0.031 )
## Likelihood ratio test= 0.01 on 1 df, p=0.9
## Wald test = 0.01 on 1 df, p=0.9
## Score (logrank) test = 0.01 on 1 df, p=0.9
##
##
## [[32]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## pathology_CAV 0.2689 1.3085 0.6052 0.444 0.657
##
## exp(coef) exp(-coef) lower .95 upper .95
## pathology_CAV 1.309 0.7642 0.3996 4.285
##
## Concordance= 0.509 (se = 0.024 )
## Likelihood ratio test= 0.18 on 1 df, p=0.7
## Wald test = 0.2 on 1 df, p=0.7
## Score (logrank) test = 0.2 on 1 df, p=0.7
##
##
## [[33]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## pathology_GL -1.706e+01 3.898e-08 4.635e+03 -0.004 0.997
##
## exp(coef) exp(-coef) lower .95 upper .95
## pathology_GL 3.898e-08 25652025 0 Inf
##
## Concordance= 0.517 (se = 0.009 )
## Likelihood ratio test= 2.34 on 1 df, p=0.1
## Wald test = 0 on 1 df, p=1
## Score (logrank) test = 1.19 on 1 df, p=0.3
##
##
## [[34]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## pathology_dual -1.603e+01 1.090e-07 3.894e+03 -0.004 0.997
##
## exp(coef) exp(-coef) lower .95 upper .95
## pathology_dual 1.09e-07 9176479 0 Inf
##
## Concordance= 0.51 (se = 0.007 )
## Likelihood ratio test= 1.2 on 1 df, p=0.3
## Wald test = 0 on 1 df, p=1
## Score (logrank) test = 0.61 on 1 df, p=0.4
##
##
## [[35]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## pathology_other 0.9328 2.5416 0.6065 1.538 0.124
##
## exp(coef) exp(-coef) lower .95 upper .95
## pathology_other 2.542 0.3935 0.7742 8.343
##
## Concordance= 0.528 (se = 0.023 )
## Likelihood ratio test= 1.85 on 1 df, p=0.2
## Wald test = 2.37 on 1 df, p=0.1
## Score (logrank) test = 2.54 on 1 df, p=0.1
##
##
## [[36]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## pathology_normal NA NA 0 NA NA
##
## exp(coef) exp(-coef) lower .95 upper .95
## pathology_normal NA NA NA NA
##
## Concordance= 0.5 (se = 0 )
## Likelihood ratio test= 0 on 0 df, p=1
## Wald test = NA on 0 df, p=NA
## Score (logrank) test = 0 on 0 df, p=1
##
##
## [[37]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## acutepostszauras 0.9034 2.4679 0.6049 1.493 0.135
##
## exp(coef) exp(-coef) lower .95 upper .95
## acutepostszauras 2.468 0.4052 0.754 8.077
##
## Concordance= 0.521 (se = 0.022 )
## Likelihood ratio test= 1.75 on 1 df, p=0.2
## Wald test = 2.23 on 1 df, p=0.1
## Score (logrank) test = 2.39 on 1 df, p=0.1
##
##
## [[38]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## sz 2.318e+01 1.171e+10 6.767e+03 0.003 0.997
##
## exp(coef) exp(-coef) lower .95 upper .95
## sz 1.171e+10 8.541e-11 0 Inf
##
## Concordance= 0.927 (se = 0.014 )
## Likelihood ratio test= 130.3 on 1 df, p=<2e-16
## Wald test = 0 on 1 df, p=1
## Score (logrank) test = 173.1 on 1 df, p=<2e-16
##
##
## [[39]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## szaurafree1st NA NA 0 NA NA
##
## exp(coef) exp(-coef) lower .95 upper .95
## szaurafree1st NA NA NA NA
##
## Concordance= 0.519 (se = 0.019 )
## Likelihood ratio test= 9.56 on 0 df, p=<2e-16
## Wald test = NA on 0 df, p=NA
## Score (logrank) test = 118 on 0 df, p=<2e-16
##
##
## [[40]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## aura 0.6987 2.0111 0.4242 1.647 0.0995 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## aura 2.011 0.4972 0.8757 4.619
##
## Concordance= 0.532 (se = 0.029 )
## Likelihood ratio test= 2.35 on 1 df, p=0.1
## Wald test = 2.71 on 1 df, p=0.1
## Score (logrank) test = 2.82 on 1 df, p=0.09
##
##
## [[41]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## szaura 2.147e+01 2.117e+09 4.099e+03 0.005 0.996
##
## exp(coef) exp(-coef) lower .95 upper .95
## szaura 2.117e+09 4.723e-10 0 Inf
##
## Concordance= 0.895 (se = 0.018 )
## Likelihood ratio test= 102 on 1 df, p=<2e-16
## Wald test = 0 on 1 df, p=1
## Score (logrank) test = 114.4 on 1 df, p=<2e-16
##
##
## [[42]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## began_wd -1.1954 0.3026 0.5404 -2.212 0.027 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## began_wd 0.3026 3.305 0.1049 0.8727
##
## Concordance= 0.548 (se = 0.03 )
## Likelihood ratio test= 3.68 on 1 df, p=0.06
## Wald test = 4.89 on 1 df, p=0.03
## Score (logrank) test = 5.5 on 1 df, p=0.02
##
##
## [[43]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## wd_all -0.7411 0.4766 0.3465 -2.139 0.0324 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## wd_all 0.4766 2.098 0.2417 0.9399
##
## Concordance= 0.586 (se = 0.044 )
## Likelihood ratio test= 4.36 on 1 df, p=0.04
## Wald test = 4.58 on 1 df, p=0.03
## Score (logrank) test = 4.79 on 1 df, p=0.03
##
##
## [[44]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## aeds 0.4768 1.6110 0.1756 2.716 0.00662 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## aeds 1.611 0.6207 1.142 2.273
##
## Concordance= 0.622 (se = 0.048 )
## Likelihood ratio test= 6.16 on 1 df, p=0.01
## Wald test = 7.37 on 1 df, p=0.007
## Score (logrank) test = 7.23 on 1 df, p=0.007
##
##
## [[45]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## age_onset -0.01744 0.98271 0.01870 -0.933 0.351
##
## exp(coef) exp(-coef) lower .95 upper .95
## age_onset 0.9827 1.018 0.9474 1.019
##
## Concordance= 0.552 (se = 0.051 )
## Likelihood ratio test= 0.93 on 1 df, p=0.3
## Wald test = 0.87 on 1 df, p=0.4
## Score (logrank) test = 0.87 on 1 df, p=0.4
##
##
## [[46]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## duration 0.01416 1.01426 0.01362 1.039 0.299
##
## exp(coef) exp(-coef) lower .95 upper .95
## duration 1.014 0.9859 0.9875 1.042
##
## Concordance= 0.571 (se = 0.046 )
## Likelihood ratio test= 1.05 on 1 df, p=0.3
## Wald test = 1.08 on 1 df, p=0.3
## Score (logrank) test = 1.08 on 1 df, p=0.3
##
##
## [[47]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## age_at_surgery 0.005148 1.005161 0.016784 0.307 0.759
##
## exp(coef) exp(-coef) lower .95 upper .95
## age_at_surgery 1.005 0.9949 0.9726 1.039
##
## Concordance= 0.509 (se = 0.055 )
## Likelihood ratio test= 0.09 on 1 df, p=0.8
## Wald test = 0.09 on 1 df, p=0.8
## Score (logrank) test = 0.09 on 1 df, p=0.8
##
##
## [[48]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## sz_time -7.830e+01 9.845e-35 1.190e+02 -0.658 0.511
##
## exp(coef) exp(-coef) lower .95 upper .95
## sz_time 9.845e-35 1.016e+34 4.869e-136 1.991e+67
##
## Concordance= 0.992 (se = 0.003 )
## Likelihood ratio test= 203.6 on 1 df, p=<2e-16
## Wald test = 0.43 on 1 df, p=0.5
## Score (logrank) test = 56.67 on 1 df, p=5e-14
##
##
## [[49]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## aura_time -0.03964 0.96113 0.03038 -1.305 0.192
##
## exp(coef) exp(-coef) lower .95 upper .95
## aura_time 0.9611 1.04 0.9056 1.02
##
## Concordance= 0.553 (se = 0.058 )
## Likelihood ratio test= 1.8 on 1 df, p=0.2
## Wald test = 1.7 on 1 df, p=0.2
## Score (logrank) test = 1.72 on 1 df, p=0.2
##
##
## [[50]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## szaura_time -0.7953 0.4514 0.1325 -6.002 1.94e-09 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## szaura_time 0.4514 2.215 0.3482 0.5853
##
## Concordance= 0.963 (se = 0.01 )
## Likelihood ratio test= 104.3 on 1 df, p=<2e-16
## Wald test = 36.03 on 1 df, p=2e-09
## Score (logrank) test = 50.63 on 1 df, p=1e-12
##
##
## [[51]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## began_wd_time -0.04799 0.95314 0.07103 -0.676 0.499
##
## exp(coef) exp(-coef) lower .95 upper .95
## began_wd_time 0.9531 1.049 0.8293 1.096
##
## Concordance= 0.509 (se = 0.052 )
## Likelihood ratio test= 0.49 on 1 df, p=0.5
## Wald test = 0.46 on 1 df, p=0.5
## Score (logrank) test = 0.46 on 1 df, p=0.5
##
##
## [[52]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## age_began_wd 0.002429 1.002432 0.016784 0.145 0.885
##
## exp(coef) exp(-coef) lower .95 upper .95
## age_began_wd 1.002 0.9976 0.97 1.036
##
## Concordance= 0.501 (se = 0.054 )
## Likelihood ratio test= 0.02 on 1 df, p=0.9
## Wald test = 0.02 on 1 df, p=0.9
## Score (logrank) test = 0.02 on 1 df, p=0.9
##
##
## [[53]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## wd_all_time -0.03063 0.96984 0.04011 -0.764 0.445
##
## exp(coef) exp(-coef) lower .95 upper .95
## wd_all_time 0.9698 1.031 0.8965 1.049
##
## Concordance= 0.576 (se = 0.052 )
## Likelihood ratio test= 0.63 on 1 df, p=0.4
## Wald test = 0.58 on 1 df, p=0.4
## Score (logrank) test = 0.59 on 1 df, p=0.4
##
##
## [[54]]
## Call:
## coxph(formula = formula, data = test_set)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## years_follow_up -0.002974 0.997031 0.029770 -0.1 0.92
##
## exp(coef) exp(-coef) lower .95 upper .95
## years_follow_up 0.997 1.003 0.9405 1.057
##
## Concordance= 0.511 (se = 0.057 )
## Likelihood ratio test= 0.01 on 1 df, p=0.9
## Wald test = 0.01 on 1 df, p=0.9
## Score (logrank) test = 0.01 on 1 df, p=0.92.2 Kaplan-Meier
km_test<- survfit(Surv(test_set$sz_time, test_set$sz) ~ 1, data= test_set, type =
"kaplan-meier", conf.type = "plain")
summary(km_test, times = c(0,1,2,5,10,15, 20,23))## Call: survfit(formula = Surv(test_set$sz_time, test_set$sz) ~ 1, data = test_set,
## type = "kaplan-meier", conf.type = "plain")
##
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 0 119 0 1.000 0.00000 1.000 1.000
## 1 118 1 0.992 0.00837 0.975 1.000
## 2 117 12 0.890 0.02881 0.833 0.946
## 5 83 14 0.767 0.03940 0.689 0.844
## 10 48 6 0.696 0.04540 0.607 0.785
## 15 25 1 0.680 0.04714 0.588 0.772
## 20 12 0 0.680 0.04714 0.588 0.772
## 23 4 0 0.680 0.04714 0.588 0.772km1_test<- ggsurvplot(km_test, data = test_set, xlab = "Time (years)", ylab = "Proportion of seizure free patients after withdrawal", palette = 'black', xlim = c(0,15),ylim = c(0,1), break.time.by = 5, font.x =14 ,font.y = 14, font.tickslab = 10, show.legend.text = F)
km1_test
2.3 Model Validation
model1f_test <-
coxph(
Surv(time = test_set$sz_time, event = test_set$sz) ~ test_set$auras + test_set$began_wd_time + test_set$aeds + test_set$gtcs +test_set$MRI_normal
)
summary(model1f_test)## Call:
## coxph(formula = Surv(time = test_set$sz_time, event = test_set$sz) ~
## test_set$auras + test_set$began_wd_time + test_set$aeds +
## test_set$gtcs + test_set$MRI_normal)
##
## n= 119, number of events= 34
##
## coef exp(coef) se(coef) z Pr(>|z|)
## test_set$auras 1.64869 5.20015 0.46525 3.544 0.000395 ***
## test_set$began_wd_time -0.03104 0.96944 0.06896 -0.450 0.652611
## test_set$aeds 0.50945 1.66437 0.18547 2.747 0.006017 **
## test_set$gtcs -0.23101 0.79373 0.40204 -0.575 0.565572
## test_set$MRI_normal 1.27910 3.59339 0.62124 2.059 0.039500 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## test_set$auras 5.2001 0.1923 2.0893 12.943
## test_set$began_wd_time 0.9694 1.0315 0.8469 1.110
## test_set$aeds 1.6644 0.6008 1.1571 2.394
## test_set$gtcs 0.7937 1.2599 0.3610 1.745
## test_set$MRI_normal 3.5934 0.2783 1.0634 12.142
##
## Concordance= 0.696 (se = 0.045 )
## Likelihood ratio test= 18.66 on 5 df, p=0.002
## Wald test = 22.99 on 5 df, p=3e-04
## Score (logrank) test = 27.38 on 5 df, p=5e-052.3.1 Discrimination
fitmodel1f_train <-
cph(
Surv(time = sz_time, event = sz) ~ auras + began_wd_time + aeds + gtcs + MRI_normal,
data = test_set,
x = TRUE,
y = TRUE,
surv = TRUE,
time.inc = 2
)
fitmodel1f_train## Cox Proportional Hazards Model
##
## cph(formula = Surv(time = sz_time, event = sz) ~ auras + began_wd_time +
## aeds + gtcs + MRI_normal, data = test_set, x = TRUE, y = TRUE,
## surv = TRUE, time.inc = 2)
##
## Model Tests Discrimination
## Indexes
## Obs 119 LR chi2 18.66 R2 0.157
## Events 34 d.f. 5 Dxy 0.391
## Center 1.1728 Pr(> chi2) 0.0022 g 0.668
## Score chi2 27.38 gr 1.950
## Pr(> chi2) 0.0000
##
## Coef S.E. Wald Z Pr(>|Z|)
## auras 1.6486 0.4653 3.54 0.0004
## began_wd_time -0.0311 0.0690 -0.45 0.6524
## aeds 0.5098 0.1854 2.75 0.0060
## gtcs -0.2309 0.4021 -0.57 0.5657
## MRI_normal 1.2790 0.6213 2.06 0.0395
## rms::validate(fitmodel1f_train, dxy = TRUE, B = 1000)## Singularity in coxph.fit. Coefficients:
## 1 2 3 4 5
## 2.17364 -0.14269 0.07165 -0.37036 NA
## Singularity in coxph.fit. Coefficients:
## 1 2 3 4 5
## 1.64646 -0.01321 0.51558 -0.15199 NA
## Singularity in coxph.fit. Coefficients:
## 1 2 3 4 5
## 1.27426 0.03205 0.36250 -0.77127 NA
## Singularity in coxph.fit. Coefficients:
## 1 2 3 4 5
## 0.8896 -0.1590 0.1657 -0.1490 NA
## Singularity in coxph.fit. Coefficients:
## 1 2 3 4 5
## 0.9055 -0.1157 0.8098 -0.2602 NA
## Singularity in coxph.fit. Coefficients:
## 1 2 3 4 5
## NA -0.08984 0.59192 -0.30385 0.51491
## Singularity in coxph.fit. Coefficients:
## 1 2 3 4 5
## 1.17716 0.05296 0.35719 0.50849 NA
## Singularity in coxph.fit. Coefficients:
## 1 2 3 4 5
## 2.5246 -0.2839 0.5540 0.1715 NA
## Singularity in coxph.fit. Coefficients:
## 1 2 3 4 5
## 1.4630 -0.1479 0.4996 -0.8827 NA
## Singularity in coxph.fit. Coefficients:
## 1 2 3 4 5
## 1.6870 -0.1412 0.1672 -0.5383 NA
## Singularity in coxph.fit. Coefficients:
## 1 2 3 4 5
## 1.1650 -0.1081 1.0732 -1.0444 NA
## Singularity in coxph.fit. Coefficients:
## 1 2 3 4 5
## 0.458476 0.003759 0.767858 -0.250467 NA
## Singularity in coxph.fit. Coefficients:
## 1 2 3 4 5
## 1.74531 0.02041 0.85055 -0.43899 NA
## Singularity in coxph.fit. Coefficients:
## 1 2 3 4 5
## NA 0.1492 0.6256 0.5841 1.5372
## Singularity in coxph.fit. Coefficients:
## 1 2 3 4 5
## 2.6902 -0.1321 0.6105 0.1603 NA
## Singularity in coxph.fit. Coefficients:
## 1 2 3 4 5
## 0.92880 -0.03308 0.42671 0.01615 NA
## Singularity in coxph.fit. Coefficients:
## 1 2 3 4 5
## 1.3543 -0.0216 0.4564 -0.3570 NA
## Singularity in coxph.fit. Coefficients:
## 1 2 3 4 5
## 1.27694 -0.02848 0.61607 -0.79498 NA
## Singularity in coxph.fit. Coefficients:
## 1 2 3 4 5
## 1.28861 0.02672 0.53815 0.30307 NA
## Singularity in coxph.fit. Coefficients:
## 1 2 3 4 5
## 1.704178 -0.003689 0.560836 -0.460345 NA
##
## Divergence or singularity in 20 samples## index.orig training test optimism index.corrected n
## Dxy 0.3913 0.4292 0.3410 0.0882 0.3031 980
## R2 0.1570 0.1942 0.1251 0.0691 0.0879 980
## Slope 1.0000 1.0000 0.7914 0.2086 0.7914 980
## D 0.0574 0.0745 0.0444 0.0300 0.0274 980
## U -0.0065 -0.0066 0.0112 -0.0178 0.0113 980
## Q 0.0639 0.0811 0.0332 0.0479 0.0161 980
## g 0.6679 0.8124 0.6231 0.1893 0.4786 9802.3.2 Calibration plots
fitmode1f_train <-
cph(
Surv(time = sz_time, event = sz) ~ auras + began_wd_time + aeds + gtcs + MRI_normal,
data = test_set,
x = TRUE,
y = TRUE,
surv = TRUE,
time.inc = 2
)
calibrate1_train <- calibrate(
fitmodel1f_train,
u = 2,
cmethod = 'KM',
B = 1000,
m = 20
)## Using Cox survival estimates at 2 Days
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samplesplot(calibrate1_train, xlim = c(0,1),ylim = c(0,1))
fitmodel1f_train2 <-
cph(
Surv(time = sz_time, event = sz) ~ auras + began_wd_time + aeds + gtcs + MRI_normal,
data = test_set,
x = TRUE,
y = TRUE,
surv = TRUE,
time.inc = 5
)
calibrate_train2 <- calibrate(
fitmodel1f_train2,
u = 5,
cmethod = 'KM',
B = 1000,
m = 20
)## Using Cox survival estimates at 5 Days
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 2 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable auras
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 2 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 2 samples
## X matrix deemed to be singular; variable MRI_normal
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 2 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samples
## X matrix deemed to be singular; variable MRI_normal
##
## Divergence or singularity in 1 samplesplot2 <- plot(calibrate_train2, xlim = c(0,1),ylim = c(0,1))
2.4 Nomogram
``{r, warning = FALSE}
fitmodel1f_train\(Design\)label <- c( “SPSs before withdrawal (Yes=1, No=0)”, “Time to begin withdrawal (Years from surgery)”, “Number of AEDs at time of surgery”, “GTCS before surgery (Yes=1, No=0)” ) surv.fitmodel1f_train <- Survival(fitmodel1f) nom.cox1 <- nomogram( fitmodel1f, fun = list(function(x) surv.fitmodel1f(2, x), function(x) surv.fitmodel1f(5, x)), funlabel = c(“2-year seizure freedom”, “5-year seizure freedom”), lp = F, fun.at = c(0.99, 0.95, 0.9, 0.8, 0.7, 0.6, 0.5, 0.4, 0.3, 0.2) )
pdf( “nomo1.pdf”, width = cm(17), height = cm(10) ) nomo1<- plot( nom.cox1, cex.axis = 4, cex.var = 4.5, col.grid = gray(c(0.8, 0.95)), theme(text = element_text( family = “Times New Roman”, face = “bold”, size = 20 )) )
dev.off() nomo1
## Dynamic Nomogram
``{r, warning = FALSE}
ddist <- train_setdist(train_set)
options(train_setdist = 'ddist')
web <-
cph(Surv(time = time_sz, event = sz) ~ auras + time_begin + drugs + gtcs ,
train_set = train_set)
DNbuilder(
web,
train_set = train_set,
clevel = 0.95,
covariate = c("numeric"),
ptype = c("st")
)