Skip to main content
. 2023 Dec 13;9:e50110. doi: 10.2196/50110

Table 2.

Prevalence of the use of pharmaceutical agents in patients with EOCRC and controls using eXtreme Gradient Boosting from data covering the period 2001-2019.

ATCa class ATC description Prevalence of use in cases, n (%) Prevalence of use in controls, n (%) Rate of runs in which an association with CRCb was observedc (%) Rate of runs with a global SHAPd value ≥97.5% of the distributione (%)
c07aa05 Propranolol 42 (4.5) 228 (2.4) 70 5
c09aa02 Enalapril 44 (4.7) 161 (2.8) 60 3
n05cm09 Valerian 47 (5) 291 (3.1) 58 2
n06ab05 Paroxetine 15 (1.6) 376 (4) 54 10
c10aa01 Simvastatin 99 (10.5) 724 (7.7) 50 4
a10ba02 Metformin 40 (4.3) 234 (2.5) 46 2
d04aa13 Dimetindene 67 (7.1) 906 (9.6) 40 1
s01ca01 Dexamethansone 175 (18.6) 1986 (21.1) 36 3
d07ac13 Mometasone 103 (10.9) 1249 (13.3) 32 1
d11ax18 Diclofenac 86 (9.1) 672 (7.1) 30 1
a02ba03 Famotidine 161 (17.1) 1381 (14.7) 28 1
s01aa01 Chloramphenicol 301 (32) 2782 (29.6) 24 2
j01ce02 Phenoxymethylpenicillin 335 (35.6) 3443 (36.6) 20 1
r01ba52 Pseuroephedrine, combination 243 (25.8) 2631 (28) 20 1
b03ad01 Ferrous amino acid complex 174 (18.5) 1590 (16.9) 16 1
g01aa10 Clindamycin 79 (8.4) 685 (7.3) 10 1
r03ac03 Terbutaline 51 (5.4) 451 (4.8) 2 1

aATC: Anatomical Therapeutic Chemical classification system.

bCRC: colorectal cancer.

cBased on global SHAP values calculated for each of 50 runs. A global SHAP value >0 for a given feature was considered evidence for an association with the outcome.

dSHAP: Shapley additive explanation.

eConsidering each of the 50 different global SHAP values distributions individually.