Metabolic Survival analysis
Girish Tillu, Ashwini Mathur, Vinay Mahajan
27 May 2018
1 Metabolic : M10.0 Medoroga
## Warning in .add_surv_median(p, fit, type = surv.median.line, fun = fun, :
## Median survival not reached.1.1 Kaplan Meier table
## Call: survfit(formula = Surv(disdur, status) ~ patient_gender, data = tmp)
##
## patient_gender=F
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 1 2098 71 0.966 0.00395 0.958 0.974
## 2 1135 5 0.962 0.00437 0.953 0.970
## 3 953 2 0.960 0.00458 0.951 0.969
## 4 845 1 0.959 0.00472 0.950 0.968
## 7 671 3 0.955 0.00516 0.945 0.965
## 13 489 4 0.948 0.00614 0.936 0.960
## 25 292 0 0.948 0.00614 0.936 0.960
## 37 164 0 0.948 0.00614 0.936 0.960
## 49 77 0 0.948 0.00614 0.936 0.960
## 61 32 0 0.948 0.00614 0.936 0.960
##
## patient_gender=M
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 1 2349 48 0.980 0.00292 0.974 0.985
## 2 1265 4 0.976 0.00330 0.970 0.983
## 3 1058 2 0.975 0.00354 0.968 0.982
## 4 952 0 0.975 0.00354 0.968 0.982
## 7 749 2 0.972 0.00395 0.964 0.980
## 13 542 6 0.963 0.00536 0.953 0.974
## 25 315 1 0.960 0.00615 0.948 0.972
## 37 197 0 0.960 0.00615 0.948 0.972
## 49 95 0 0.960 0.00615 0.948 0.972
## 61 48 0 0.960 0.00615 0.948 0.9721.2 Survival plot
1.3 Hazard ratio plot
## Call:
## coxph(formula = Surv(disdur, status) ~ patient_gender, data = tmp)
##
## coef exp(coef) se(coef) z p
## patient_genderM -0.429 0.651 0.166 -2.58 0.0097
##
## Likelihood ratio test=6.78 on 1 df, p=0.00922
## n= 4447, number of events= 149
2 Metabolic : M10.1 Medoroga - Sthula medho roga
## Warning in .add_surv_median(p, fit, type = surv.median.line, fun = fun, :
## Median survival not reached.2.1 Kaplan Meier table
## Call: survfit(formula = Surv(disdur, status) ~ patient_gender, data = tmp)
##
## patient_gender=F
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 1 2098 302 0.856 0.00766 0.841 0.871
## 2 1039 33 0.829 0.00876 0.812 0.846
## 3 856 15 0.814 0.00938 0.796 0.833
## 4 746 11 0.802 0.00991 0.783 0.822
## 7 582 12 0.787 0.01066 0.766 0.808
## 13 430 12 0.768 0.01179 0.745 0.791
## 25 255 10 0.742 0.01394 0.715 0.770
## 37 138 4 0.725 0.01613 0.694 0.757
## 49 65 1 0.715 0.01865 0.679 0.753
## 61 28 2 0.686 0.02708 0.635 0.741
##
## patient_gender=M
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 1 2349 170 0.928 0.00535 0.917 0.938
## 2 1201 20 0.912 0.00627 0.900 0.925
## 3 996 8 0.905 0.00674 0.892 0.918
## 4 892 4 0.901 0.00701 0.887 0.915
## 7 696 4 0.896 0.00735 0.882 0.911
## 13 501 4 0.890 0.00797 0.874 0.905
## 25 285 9 0.870 0.01020 0.850 0.890
## 37 176 5 0.851 0.01325 0.825 0.877
## 49 91 1 0.844 0.01486 0.815 0.873
## 61 44 0 0.844 0.01486 0.815 0.8732.2 Survival plot
2.3 Hazard ratio plot
## Call:
## coxph(formula = Surv(disdur, status) ~ patient_gender, data = tmp)
##
## coef exp(coef) se(coef) z p
## patient_genderM -0.7367 0.4787 0.0833 -8.85 <2e-16
##
## Likelihood ratio test=82.1 on 1 df, p=0
## n= 4447, number of events= 627
3 Metabolic : M10.2 Medoroga - Sukshma medho roga
## Warning in .add_surv_median(p, fit, type = surv.median.line, fun = fun, :
## Median survival not reached.3.1 Kaplan Meier table
## Call: survfit(formula = Surv(disdur, status) ~ patient_gender, data = tmp)
##
## patient_gender=F
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 1 2098 35 0.983 0.00280 0.978 0.989
## 2 1158 3 0.981 0.00315 0.975 0.987
## 3 975 3 0.978 0.00359 0.971 0.985
## 4 861 2 0.975 0.00393 0.968 0.983
## 7 683 5 0.969 0.00488 0.959 0.979
## 13 499 1 0.967 0.00513 0.957 0.977
## 25 297 1 0.965 0.00557 0.954 0.976
## 37 172 0 0.965 0.00557 0.954 0.976
## 49 80 0 0.965 0.00557 0.954 0.976
## 61 34 0 0.965 0.00557 0.954 0.976
##
## patient_gender=M
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 1 2349 96 0.959 0.00408 0.951 0.967
## 2 1235 12 0.950 0.00485 0.940 0.959
## 3 1030 8 0.942 0.00547 0.932 0.953
## 4 921 4 0.938 0.00582 0.927 0.950
## 7 720 8 0.929 0.00670 0.916 0.942
## 13 519 10 0.913 0.00818 0.897 0.929
## 25 296 4 0.904 0.00937 0.886 0.922
## 37 183 0 0.904 0.00937 0.886 0.922
## 49 89 1 0.895 0.01304 0.870 0.921
## 61 45 0 0.895 0.01304 0.870 0.9213.2 Survival plot
3.3 Hazard ratio plot
## Call:
## coxph(formula = Surv(disdur, status) ~ patient_gender, data = tmp)
##
## coef exp(coef) se(coef) z p
## patient_genderM 0.964 2.622 0.164 5.87 4.4e-09
##
## Likelihood ratio test=39 on 1 df, p=4.19e-10
## n= 4447, number of events= 193
4 Metabolic : M2.0 Madhumeha
4.1 Kaplan Meier table
## Call: survfit(formula = Surv(disdur, status) ~ patient_gender, data = tmp)
##
## patient_gender=F
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 1 2098 285 0.864 0.00748 0.850 0.879
## 2 1078 56 0.819 0.00919 0.801 0.837
## 3 890 32 0.790 0.01023 0.770 0.810
## 4 775 21 0.768 0.01096 0.747 0.790
## 7 602 43 0.719 0.01260 0.695 0.744
## 13 420 45 0.657 0.01454 0.629 0.686
## 25 239 29 0.600 0.01672 0.568 0.634
## 37 142 17 0.549 0.01946 0.512 0.588
## 49 63 4 0.527 0.02184 0.486 0.571
## 61 23 2 0.501 0.02746 0.450 0.558
##
## patient_gender=M
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 1 2349 521 0.778 0.00857 0.762 0.795
## 2 1129 81 0.722 0.00995 0.703 0.742
## 3 921 49 0.684 0.01083 0.663 0.706
## 4 819 37 0.653 0.01147 0.631 0.676
## 7 620 60 0.597 0.01255 0.573 0.623
## 13 447 60 0.532 0.01373 0.506 0.560
## 25 244 58 0.446 0.01558 0.417 0.478
## 37 139 34 0.374 0.01734 0.342 0.410
## 49 73 6 0.356 0.01808 0.322 0.393
## 61 32 0 0.356 0.01808 0.322 0.3934.2 Survival plot
4.3 Hazard ratio plot
## Call:
## coxph(formula = Surv(disdur, status) ~ patient_gender, data = tmp)
##
## coef exp(coef) se(coef) z p
## patient_genderM 0.4750 1.6080 0.0546 8.71 <2e-16
##
## Likelihood ratio test=78.3 on 1 df, p=0
## n= 4447, number of events= 1441
5 Metabolic : P5.0 Prameha
5.1 Kaplan Meier table
## Call: survfit(formula = Surv(disdur, status) ~ patient_gender, data = tmp)
##
## patient_gender=F
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 1 2098 399 0.810 0.00857 0.793 0.827
## 2 1033 69 0.756 0.01017 0.736 0.776
## 3 833 29 0.729 0.01093 0.708 0.751
## 4 722 21 0.708 0.01155 0.686 0.731
## 7 551 22 0.683 0.01235 0.659 0.707
## 13 385 37 0.626 0.01444 0.598 0.655
## 25 208 36 0.550 0.01750 0.517 0.585
## 37 108 28 0.451 0.02238 0.409 0.497
## 49 47 6 0.417 0.02458 0.372 0.468
## 61 16 1 0.404 0.02705 0.355 0.461
##
## patient_gender=M
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 1 2349 541 0.770 0.00869 0.753 0.787
## 2 1106 69 0.722 0.00988 0.703 0.741
## 3 902 29 0.698 0.01046 0.678 0.719
## 4 802 31 0.671 0.01113 0.650 0.694
## 7 593 48 0.623 0.01233 0.599 0.648
## 13 405 49 0.561 0.01395 0.534 0.589
## 25 213 46 0.482 0.01623 0.451 0.515
## 37 115 20 0.421 0.01920 0.385 0.461
## 49 45 14 0.357 0.02287 0.315 0.404
## 61 18 2 0.334 0.02652 0.286 0.3915.2 Survival plot
5.3 Hazard ratio plot
## Call:
## coxph(formula = Surv(disdur, status) ~ patient_gender, data = tmp)
##
## coef exp(coef) se(coef) z p
## patient_genderM 0.1866 1.2051 0.0522 3.58 0.00035
##
## Likelihood ratio test=12.9 on 1 df, p=0.000332
## n= 4447, number of events= 1497
6 Metabolic : P5.1 Prameha - Krusha
## Warning in .add_surv_median(p, fit, type = surv.median.line, fun = fun, :
## Median survival not reached.6.1 Kaplan Meier table
## Call: survfit(formula = Surv(disdur, status) ~ patient_gender, data = tmp)
##
## patient_gender=F
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 1 2098 4 0.998 0.000952 0.996 1
## 2 1172 0 0.998 0.000952 0.996 1
## 3 988 0 0.998 0.000952 0.996 1
## 4 875 0 0.998 0.000952 0.996 1
## 7 697 0 0.998 0.000952 0.996 1
## 13 510 0 0.998 0.000952 0.996 1
## 25 306 0 0.998 0.000952 0.996 1
## 37 174 0 0.998 0.000952 0.996 1
## 49 82 0 0.998 0.000952 0.996 1
## 61 34 0 0.998 0.000952 0.996 1
##
## patient_gender=M
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 1 2349 5 0.998 0.000951 0.996 1
## 2 1283 0 0.998 0.000951 0.996 1
## 3 1080 0 0.998 0.000951 0.996 1
## 4 975 0 0.998 0.000951 0.996 1
## 7 771 0 0.998 0.000951 0.996 1
## 13 564 0 0.998 0.000951 0.996 1
## 25 329 0 0.998 0.000951 0.996 1
## 37 205 0 0.998 0.000951 0.996 1
## 49 102 0 0.998 0.000951 0.996 1
## 61 50 0 0.998 0.000951 0.996 16.2 Survival plot
6.3 Hazard ratio plot
## Call:
## coxph(formula = Surv(disdur, status) ~ patient_gender, data = tmp)
##
## coef exp(coef) se(coef) z p
## patient_genderM 0.110 1.117 0.671 0.16 0.87
##
## Likelihood ratio test=0.03 on 1 df, p=0.869
## n= 4447, number of events= 9
7 Metabolic : P5.2 Prameha - Pidaka
## Warning in .add_surv_median(p, fit, type = surv.median.line, fun = fun, :
## Median survival not reached.7.1 Kaplan Meier table
## Call: survfit(formula = Surv(disdur, status) ~ patient_gender, data = tmp)
##
## patient_gender=F
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 1 2098 4 0.998 0.000952 0.996 1
## 2 1172 1 0.997 0.001277 0.995 1
## 3 989 0 0.997 0.001277 0.995 1
## 4 875 0 0.997 0.001277 0.995 1
## 7 697 0 0.997 0.001277 0.995 1
## 13 510 0 0.997 0.001277 0.995 1
## 25 306 0 0.997 0.001277 0.995 1
## 37 174 0 0.997 0.001277 0.995 1
## 49 82 0 0.997 0.001277 0.995 1
## 61 34 0 0.997 0.001277 0.995 1
##
## patient_gender=M
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 1 2349 10 0.996 0.00134 0.993 0.998
## 2 1281 1 0.995 0.00155 0.992 0.998
## 3 1076 0 0.995 0.00155 0.992 0.998
## 4 971 0 0.995 0.00155 0.992 0.998
## 7 768 1 0.994 0.00192 0.990 0.998
## 13 563 0 0.994 0.00192 0.990 0.998
## 25 328 0 0.994 0.00192 0.990 0.998
## 37 205 0 0.994 0.00192 0.990 0.998
## 49 102 0 0.994 0.00192 0.990 0.998
## 61 50 0 0.994 0.00192 0.990 0.9987.2 Survival plot
7.3 Hazard ratio plot
## Call:
## coxph(formula = Surv(disdur, status) ~ patient_gender, data = tmp)
##
## coef exp(coef) se(coef) z p
## patient_genderM 0.767 2.153 0.532 1.44 0.15
##
## Likelihood ratio test=2.26 on 1 df, p=0.133
## n= 4447, number of events= 17
8 Metabolic : P5.3 Prameha - Sthula
## Warning in .add_surv_median(p, fit, type = surv.median.line, fun = fun, :
## Median survival not reached.8.1 Kaplan Meier table
## Call: survfit(formula = Surv(disdur, status) ~ patient_gender, data = tmp)
##
## patient_gender=F
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 1 2098 19 0.991 0.00207 0.987 0.995
## 2 1164 3 0.988 0.00253 0.983 0.993
## 3 978 0 0.988 0.00253 0.983 0.993
## 4 865 0 0.988 0.00253 0.983 0.993
## 7 686 1 0.987 0.00282 0.982 0.993
## 13 501 0 0.987 0.00282 0.982 0.993
## 25 300 0 0.987 0.00282 0.982 0.993
## 37 172 0 0.987 0.00282 0.982 0.993
## 49 81 0 0.987 0.00282 0.982 0.993
## 61 34 0 0.987 0.00282 0.982 0.993
##
## patient_gender=M
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 1 2349 15 0.994 0.00164 0.990 0.997
## 2 1277 0 0.994 0.00164 0.990 0.997
## 3 1072 0 0.994 0.00164 0.990 0.997
## 4 968 0 0.994 0.00164 0.990 0.997
## 7 763 1 0.992 0.00205 0.988 0.996
## 13 559 0 0.992 0.00205 0.988 0.996
## 25 325 3 0.985 0.00448 0.977 0.994
## 37 202 1 0.982 0.00560 0.971 0.993
## 49 101 0 0.982 0.00560 0.971 0.993
## 61 49 0 0.982 0.00560 0.971 0.9938.2 Survival plot
8.3 Hazard ratio plot
## Call:
## coxph(formula = Surv(disdur, status) ~ patient_gender, data = tmp)
##
## coef exp(coef) se(coef) z p
## patient_genderM -0.252 0.777 0.306 -0.83 0.41
##
## Likelihood ratio test=0.68 on 1 df, p=0.408
## n= 4447, number of events= 43
9 Metabolic : P5.4 Prameha - Upadrava
## Warning in .add_surv_median(p, fit, type = surv.median.line, fun = fun, :
## Median survival not reached.9.1 Kaplan Meier table
## Call: survfit(formula = Surv(disdur, status) ~ patient_gender, data = tmp)
##
## patient_gender=F
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 1 2098 42 0.980 0.00306 0.974 0.986
## 2 1153 8 0.973 0.00387 0.966 0.981
## 3 967 1 0.972 0.00399 0.964 0.980
## 4 853 0 0.972 0.00399 0.964 0.980
## 7 677 1 0.971 0.00418 0.963 0.979
## 13 493 1 0.969 0.00444 0.961 0.978
## 25 295 4 0.960 0.00643 0.947 0.973
## 37 168 0 0.960 0.00643 0.947 0.973
## 49 78 0 0.960 0.00643 0.947 0.973
## 61 32 0 0.960 0.00643 0.947 0.973
##
## patient_gender=M
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 1 2349 71 0.970 0.00353 0.963 0.977
## 2 1252 9 0.963 0.00420 0.955 0.971
## 3 1050 4 0.959 0.00457 0.950 0.968
## 4 946 2 0.957 0.00478 0.948 0.967
## 7 750 4 0.952 0.00534 0.942 0.963
## 13 544 1 0.951 0.00552 0.940 0.962
## 25 317 0 0.951 0.00552 0.940 0.962
## 37 197 1 0.947 0.00647 0.935 0.960
## 49 97 1 0.942 0.00854 0.925 0.959
## 61 46 0 0.942 0.00854 0.925 0.9599.2 Survival plot
9.3 Hazard ratio plot
## Call:
## coxph(formula = Surv(disdur, status) ~ patient_gender, data = tmp)
##
## coef exp(coef) se(coef) z p
## patient_genderM 0.385 1.469 0.168 2.29 0.022
##
## Likelihood ratio test=5.36 on 1 df, p=0.0206
## n= 4447, number of events= 150
10 Metabolic : S16.0 Sthaulya
## Warning in .add_surv_median(p, fit, type = surv.median.line, fun = fun, :
## Median survival not reached.10.1 Kaplan Meier table
## Call: survfit(formula = Surv(disdur, status) ~ patient_gender, data = tmp)
##
## patient_gender=F
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 1 2098 429 0.796 0.00881 0.778 0.813
## 2 1030 56 0.752 0.01005 0.733 0.772
## 3 829 21 0.733 0.01062 0.713 0.754
## 4 728 16 0.717 0.01112 0.696 0.739
## 7 558 28 0.684 0.01222 0.661 0.709
## 13 396 13 0.665 0.01298 0.640 0.691
## 25 229 16 0.633 0.01469 0.605 0.662
## 37 132 3 0.621 0.01603 0.590 0.653
## 49 64 2 0.606 0.01858 0.571 0.644
## 61 27 0 0.606 0.01858 0.571 0.644
##
## patient_gender=M
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 1 2349 306 0.870 0.00694 0.856 0.883
## 2 1188 40 0.840 0.00811 0.825 0.856
## 3 970 19 0.824 0.00879 0.807 0.841
## 4 861 8 0.816 0.00911 0.799 0.834
## 7 676 16 0.798 0.00996 0.779 0.818
## 13 482 5 0.791 0.01040 0.771 0.812
## 25 275 8 0.774 0.01189 0.751 0.797
## 37 167 2 0.767 0.01268 0.743 0.792
## 49 84 0 0.767 0.01268 0.743 0.792
## 61 44 0 0.767 0.01268 0.743 0.79210.2 Survival plot
10.3 Hazard ratio plot
## Call:
## coxph(formula = Surv(disdur, status) ~ patient_gender, data = tmp)
##
## coef exp(coef) se(coef) z p
## patient_genderM -0.5314 0.5878 0.0647 -8.21 2.2e-16
##
## Likelihood ratio test=68.9 on 1 df, p=1.11e-16
## n= 4447, number of events= 989