You are here

Article Text

Article menu
Download PDFPDF
PostScript
Letter
Letter to the editor: prediction of survival in colorectal cancer using artificial intelligence
  1. Ai Guan,
  2. Lejia Sun,
  3. Meixi Liu,
  4. Yilei Mao
  1. Department of Liver Surgery, Peking Union Medical College Hospital, Dongcheng-qu, China
  1. Correspondence to Dr Yilei Mao, Peking Union Medical College Hospital, Dongcheng-qu, Beijing, China; pumch-liver{at}hotmail.com

https://doi.org/10.1136/gutjnl-2020-323382

Statistics from Altmetric.com

    Request Permissions

    If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.

    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 …

    View Full Text

    Footnotes

    • AG and LS contributed equally.

    • Contributors AG and LS conceived the manuscript. All authors wrote and reviewed the manuscript.

    • Funding This work was supported by grants from CAMS Innovation Fundfor Medical Sciences (CIFMS) (No.2016-I2M-1-001) and TsinghuaUniversity-Peking Union Medical College Hospital Cooperation Project(PTQH201904552).

    • Competing interests None declared.

    • Provenance and peer review Not commissioned; internally peer reviewed.