BPG is committed to discovery and dissemination of knowledge
Retrospective Study
©The Author(s) 2025.
World J Gastroenterol. Nov 14, 2025; 31(42): 112180
Published online Nov 14, 2025. doi: 10.3748/wjg.v31.i42.112180
Table 3 Logistic regression based on 10 machine learnings for predicting myelosuppression
MLsUnivariate logistic regression
Multivariate logistic regression
OR (95%CI)
P value
OR (95%CI)
P value
Adaptive boosting49.558 (15.807-155.376)0.0000.083 (0.003-2.486)0.151
Artificial neural network54.444 (13.032-227.465)0.0001.572 (0.043-57.273)0.805
Decision tree10.587 (5.084-22.047)0.0000.563 (0.102-3.109)0.510
Extra trees390.471 (75.734-2013.192)0.00031.948 (2.468-413.586)0.008
Gradient boosting machine104.831 (32.579-337.322)0.0002.169 (0.176-26.731)0.546
K-Nearest neighbors24.992 (9.652-64.711)0.0003.081 (0.419-22.650)0.269
Logistic regression279.116 (24.997-3116.614)0.0000.225 (0.000-129.448)0.646
Random forest404.139 (88.973-1835.710)0.00094.621 (1.178-7597.788)0.042
Support vector machine4.180 (0.332-52.698)0.26923.780 (0.434-1303.403)0.121
Extreme gradient boosting131.875 (39.641-438.709)0.0002.669 (0.170-41.930)0.485


Write to the Help Desk