Machine-Learning Model May Predict Oxaliplatin Benefit in Colon Cancer

Get Permission

The novel COLOXIS machine learning model may accurately predict which patients with colon cancer are most likely to derive benefit from oxaliplatin, according to a recent study published by Chen et al in the Journal of Clinical Oncology. The findings could ultimately allow physicians to better tailor treatment regimens for their patients.


The current standard of care for treating patients with stage III colon cancer is adjuvant therapy with FOLFOX (fluorouracil, leucovorin, and oxaliplatin). Although effective, the use of oxaliplatin can lead to known adverse events such as chronic neurotoxicity.

Study Methods and Results

In the recent study, researchers used data from the NSABP C-07 and C-08 trials—involving 1,065 patients who received oxaliplatin as part of their colon cancer treatment—to test the COLOXIS model. Among the patients, 644 of them received FOLFOX and 421 of them received fluorouracil and leucovorin.  

The novel model dichotomized the patients into two groups, where those in the signature-positive group (n = 526) benefited from oxaliplatin and those in the signature-negative group (n = 539) did not benefit from the treatment.

The researchers found that the signature-positive prediction was prognostic for the patients who were treated with fluorouracil and leucovorin (hazard ratio [HR] = 1.52, 95% confidence interval [CI] = 1.07–2.15, P = .017). The model was also predictive of oxaliplatin benefit. They discovered that the patients in the signature-positive group benefited from oxaliplatin (HR = 0.65, 95% CI = 0.48–0.89, P = .0065, int P = .03), whereas those in the signature-negative group did not benefit (HR = 1.08, 95% CI = 0.77–1.52, P = .65).  


The researchers emphasized that the recent findings may help illuminate the benefit of reserving the use of oxaliplatin-containing regimens for specific patients. Further studies may be needed to validate the novel COLOXIS model and establish its application in clinical practice.

“The goal of COLOXIS was to determine if we could isolate which patients benefit from the addition of oxaliplatin and which did not derive benefit. Understanding this could help minimize unnecessary adverse events for those who do not benefit,” concluded co–study author Katherine L. Pogue-Geile, PhD, of NRG Oncology.

Disclosure: The research in this study was funded by the National Library of Medicine, National Cancer Institute at the National Institutes of Health, U.S. Department of Health and Human Services, Public Health Service, Korea Health Technology R&D Project through the Korean Health Industry Development Institute, Ministry of Health and Welfare, Republic of Korea, Sanofi-Synthelabo, and Genentech. For full disclosures of the study authors, visit

The content in this post has not been reviewed by the American Society of Clinical Oncology, Inc. (ASCO®) and does not necessarily reflect the ideas and opinions of ASCO®.