Letter to the editor: prediction of survival in colorectal cancer using artificial intelligence

We have read with great interest the article published in Gut by Bibault et al .1 The authors carried out a retrospective study including 154 900 patients from the prostate, lung colorectal and ovarian cancer screening trial to comprehensively train and validate a model to predict survival in colorectal cancer (CRC), using a gradient-boosted machine (GBM). Bibault et al 1 found that physical activity, T stage and tumour grade were the three most critical features among all relevant features. The study showed that the developed model has significant predictive power for survival in patients with CRC. We appreciate their efforts to provide insights into the survival prediction of patients with CRC. However, some points are worthy of further discussion. First, the essential prognostic factors of patients with CRC, including lymphovascular …