Traumatic Brain Injury Analysis

Report 1: Data Management and Exploratory Analysis

Chong Kim

1/20/2018

Objective

This project is based on a pilot study that was conducted with 32 patients that had acute Traumatic Brain Injury (TBI) at the University of Pennsylvania and Unviersity of Alabama Birmingham Hospital. The goal of the project was to determine the change in plasma von Willebrand (VWF) antigen levels.

In the context of this project, the goal is to determine if there are any other variables other than the VWF, such as the ADAMTS13 or other non-molecular clinical factors (e.g. hospital length of stay) that can be predictive of certain outcomes such as mortality, modified Rankin scale, or neurosurgery.

Given that we have a very small group of population, it is highly likely that we won’t be able to find statistically significant difference between groups based on parametric assumptions. Despite the small sample, we will still see if there are differences in the clinical and demographic variables among the different outcome groups and see if there are insights that can be generated from this data.

Data Management

Loading Data

Based on the .xlsx extension, we use the library(readxl) package and load the data to check basic statistics using numerical and visual means.

There are many variables… in fact there are 79 variables. Initial variable creation/merging/manipulation have been done previously and consult Dr. Monisha Kumar. The first few columns (i.e. vwfag_D[0-5]) are clinical parameters taken by individuals at 5 different times. The variables with _avg at the end indicate the averge of the values (taken based on non-missing values).

Creating Variables and Changing Type

Here we will dichotomize the dc_mrs variable such that >=3 will be set as 1 and < 3 will be set as 0. Also some variables that are binary will be changed to character or factor variables for easy analysis

Numeric Check

  nbr.val nbr.null nbr.na min max range sum median mean SE.mean CI.mean.0.95 var std.dev coef.var
tbitbsubjectid 32 0 0 28 78 50 1646 46.5 51.44 2.949 6.014 278.3 16.68 0.3243
vwfag_D0 10 0 22 0.9598 6.633 5.673 28.29 2.452 2.829 0.5085 1.15 2.586 1.608 0.5685
vwfag_D1 16 0 16 1.001 5.928 4.927 49.29 2.947 3.081 0.3557 0.7581 2.024 1.423 0.4618
vwfag_D2 20 0 12 1.817 15.27 13.45 87.34 3.598 4.367 0.6544 1.37 8.565 2.927 0.6702
vwfag_D3 21 1 11 0 17.45 17.45 105.3 4.233 5.012 0.9429 1.967 18.67 4.321 0.8621
vwfag_D5 18 0 14 1.727 15 13.27 88.78 4.507 4.932 0.6788 1.432 8.295 2.88 0.584
VWFAg avg 32 0 0 0.9803 17.45 16.47 139.1 3.649 4.348 0.6226 1.27 12.4 3.522 0.8099
vwfact_D0 10 0 22 0.674 6.856 6.182 24.13 1.937 2.413 0.5385 1.218 2.899 1.703 0.7058
vwfact_D1 17 0 15 0.68 4.061 3.381 46.1 2.776 2.712 0.248 0.5258 1.046 1.023 0.3771
vwfact_D2 20 0 12 1.159 6.015 4.856 63.96 3.315 3.198 0.2678 0.5606 1.435 1.198 0.3745
vwfact_D3 20 0 12 0.922 6.228 5.306 61.05 2.733 3.052 0.2759 0.5774 1.522 1.234 0.4042
vwfact_D5 18 0 14 0.89 8.469 7.579 60.37 3.104 3.354 0.359 0.7575 2.32 1.523 0.4542
VWFAc avg 32 0 0 0.6845 6.786 6.101 97.29 2.781 3.04 0.2317 0.4726 1.718 1.311 0.4311
ratio_D0 10 0 22 0.544 1.063 0.5189 8.337 0.7985 0.8337 0.05843 0.1322 0.03414 0.1848 0.2216
ratio_D1 17 0 15 0.4303 1.304 0.8739 15.49 0.9533 0.9114 0.06511 0.138 0.07207 0.2685 0.2945
ratio_D2 20 0 12 0.3939 1.348 0.9541 16.61 0.7914 0.8307 0.06663 0.1395 0.0888 0.298 0.3587
ratio_D3 20 0 12 0.347 1.356 1.009 14.24 0.6146 0.7122 0.06671 0.1396 0.089 0.2983 0.4189
ratio_D5 18 0 14 0.3828 1.182 0.7995 13.15 0.7376 0.7304 0.04936 0.1041 0.04386 0.2094 0.2868
Ratio avg 32 0 0 0.357 1.226 0.8689 26.27 0.8185 0.8209 0.04271 0.0871 0.05837 0.2416 0.2943
a13_d0 10 0 22 0.3001 0.9517 0.6515 5.896 0.5737 0.5896 0.07038 0.1592 0.04953 0.2226 0.3775
a13_d1 17 0 15 0.1443 1.332 1.188 12.06 0.6203 0.7093 0.07588 0.1609 0.09789 0.3129 0.4411
a13_d2 20 0 12 0.2437 1.705 1.461 15.06 0.7092 0.753 0.07747 0.1621 0.12 0.3464 0.4601
a13_d3 20 0 12 0.2085 1.312 1.104 15.12 0.742 0.7558 0.06659 0.1394 0.08869 0.2978 0.394
a13_d5 18 0 14 0.1963 1.467 1.271 13.96 0.7723 0.7755 0.09094 0.1919 0.1488 0.3858 0.4975
A13 average 32 0 0 0.2162 1.322 1.106 24.43 0.7538 0.7634 0.05099 0.104 0.08319 0.2884 0.3778
a13act_vwfagD0 10 0 22 0.07615 0.9214 0.8453 2.876 0.2713 0.2876 0.07782 0.176 0.06056 0.2461 0.8557
a13act_vwfagD1 16 0 16 0.09128 0.8842 0.793 4.855 0.2105 0.3034 0.06008 0.1281 0.05776 0.2403 0.792
a13act_vwfagD2 20 0 12 0.0451 0.4597 0.4146 4.253 0.2072 0.2127 0.02639 0.05523 0.01393 0.118 0.5549
a13act_vwfagD3 20 0 12 0.04227 0.3846 0.3424 3.701 0.1918 0.1851 0.02073 0.04339 0.008594 0.0927 0.501
a13act_vwfagD5 18 0 14 0.0268 0.3733 0.3465 3.282 0.1796 0.1824 0.02195 0.04631 0.008673 0.09313 0.5107
A13VWFratio average 32 0 0 0.04104 0.8842 0.8432 8.038 0.2193 0.2512 0.03389 0.06912 0.03675 0.1917 0.7632
hnp-d0 10 1 22 0 55.05 55.05 137.7 5.286 13.77 5.947 13.45 353.6 18.81 1.366
hnp d1 18 0 14 0.994 55.16 54.16 374.1 12.65 20.79 4.628 9.765 385.6 19.64 0.9447
hnp d2 20 0 12 3.334 134.5 131.2 501.2 16.55 25.06 6.791 14.21 922.3 30.37 1.212
hnp d3 20 0 12 3.027 82.09 79.06 480.3 21.25 24.01 4.469 9.353 399.4 19.98 0.8322
hnp d5 18 0 14 1.146 111.4 110.3 550.6 24.2 30.59 6.283 13.26 710.7 26.66 0.8715
HNP average 32 0 0 0.994 95.6 94.6 729.3 14.25 22.79 3.804 7.759 463.1 21.52 0.9442
**tbitbsubjectid__1** 32 0 0 28 78 50 1646 46.5 51.44 2.949 6.014 278.3 16.68 0.3243
fall 32 14 0 0 1 1 18 1 0.5625 0.0891 0.1817 0.254 0.504 0.896
mechanismofinjury 32 4 0 0 5 5 82 3 2.562 0.215 0.4386 1.48 1.216 0.4747
Mechanism NA NA NA NA NA NA NA NA NA NA NA NA NA NA
CCI score 32 18 0 0 9 9 47 0 1.469 0.3888 0.793 4.838 2.199 1.498
sdh 32 14 0 0 1 1 18 1 0.5625 0.0891 0.1817 0.254 0.504 0.896
edh 32 27 0 0 1 1 5 0 0.1562 0.06521 0.133 0.1361 0.3689 2.361
tsah 32 10 0 0 1 1 22 1 0.6875 0.08325 0.1698 0.2218 0.4709 0.685
Contusion 27 14 5 0 1 1 13 0 0.4815 0.09799 0.2014 0.2593 0.5092 1.058
dai 32 30 0 0 1 1 2 0 0.0625 0.04348 0.08867 0.06048 0.2459 3.935
skullfx 32 31 0 0 1 1 1 0 0.03125 0.03125 0.06373 0.03125 0.1768 5.657
age 32 0 0 18 85 67 1453 42 45.41 3.975 8.106 505.5 22.48 0.4952
sex_binary NA NA NA NA NA NA NA NA NA NA NA NA NA NA
race_black 32 19 0 0 1 1 13 0 0.4062 0.08821 0.1799 0.249 0.499 1.228
race_binary NA NA NA NA NA NA NA NA NA NA NA NA NA NA
mortality_atdischarge NA NA NA NA NA NA NA NA NA NA NA NA NA NA
mrs36 32 15 0 0 1 1 17 1 0.5312 0.08963 0.1828 0.2571 0.507 0.9544
dc_mrs 32 1 0 0 6 6 96 3 3 0.333 0.6792 3.548 1.884 0.6279
surgery NA NA NA NA NA NA NA NA NA NA NA NA NA NA
Discharge Disposition NA NA NA NA NA NA NA NA NA NA NA NA NA NA
dc_dispo 32 10 0 0 3 3 34 1 1.062 0.1676 0.3419 0.8992 0.9483 0.8925
homedischarge 32 19 0 0 1 1 13 0 0.4062 0.08821 0.1799 0.249 0.499 1.228
hosp_los 32 0 0 2 59 57 517 12 16.16 2.542 5.185 206.8 14.38 0.8901
icu_los 31 0 1 2 27 25 345 10 11.13 1.352 2.761 56.65 7.527 0.6763
e_gcsadm 31 0 1 1 4 3 69 1 2.226 0.257 0.5248 2.047 1.431 0.6428
v_gcsadm 31 0 1 1 5 4 79 2 2.548 0.3274 0.6686 3.323 1.823 0.7153
m_gcsadm 31 0 1 1 6 5 107 4 3.452 0.4169 0.8515 5.389 2.321 0.6726
gcs_adm 32 0 0 3 15 12 270 7.5 8.438 0.9524 1.943 29.03 5.388 0.6386
midlineshift_mm 1 0 31 8 8 0 8 8 8 NA NA NA NA NA
sbpadm 26 0 6 102 216 114 3755 144.5 144.4 5.364 11.05 748.1 27.35 0.1894
dbp_adm 25 0 7 56 122 66 2148 85 85.92 3.407 7.032 290.2 17.04 0.1983
triagemap 19 0 13 73 137 64 1916 97 100.8 3.676 7.722 256.7 16.02 0.1589
triagehr 30 0 2 53 139 86 2765 89 92.17 4.235 8.662 538.1 23.2 0.2517
triagetemp 29 0 3 96 100.9 4.9 2832 97.6 97.66 0.2104 0.431 1.284 1.133 0.0116
volumeofresuscitationml 31 2 1 0 2610 2610 41205 1201 1329 143.9 293.9 641863 801.2 0.6027
pt 31 0 1 11.9 16.9 5 439.4 14.1 14.17 0.2382 0.4864 1.759 1.326 0.09356
inr 31 0 1 1 1.4 0.4 36.6 1.2 1.181 0.02244 0.04583 0.01561 0.125 0.1058
ptt 31 0 1 16.5 47.6 31.1 944.6 29.2 30.47 1.077 2.2 35.99 5.999 0.1969
basedeficit NA NA NA NA NA NA NA NA NA NA NA NA NA NA
pharterial NA NA NA NA NA NA NA NA NA NA NA NA NA NA
**X__1** NA NA NA NA NA NA NA NA NA NA NA NA NA NA
**X__2** NA NA NA NA NA NA NA NA NA NA NA NA NA NA
dc_mrs_bin NA NA NA NA NA NA NA NA NA NA NA NA NA NA

Visual Check

Before going onto checking every single variable, we will focus mostly on the average values, demographic variables, and clinical outcome indicators. We will describe them more as we go.

Figure 1

## [[1]]

## 
## [[2]]

## 
## [[3]]

## 
## [[4]]

## 
## [[5]]

## 
## [[6]]

## 
## [[7]]

## 
## [[8]]

## 
## [[9]]

## 
## [[10]]

## 
## [[11]]