Identification of intraoperative hypoxemia and hypoproteinemia as prognostic indicators in anastomotic leakage post-radical gastrectomy: an 8-year multicenter study utilizing machine learning techniques

HIGHLIGHTS

• What: This study assessed risk prediction models constructed using three machine_learning algorithms, with XGBoost emerging as the most accurate. Similar to previous studies, this study has also demonstrated that tumors with higher invasiveness, lymph node metastasis, and PNI are associated with a higher risk of poor prognosis in patients. This study has identified the key high-risk factors influencing patient prognosis. In future research, the authors aim to further validate and refine the specific roles of these risk factors across varied clinical contexts by leveraging larger patient cohorts and conducting more detailed analyses in conjunction with treatment . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or Email

  Password

  Remember me

  Lost your password?

  If you don't have an account, you can create one here.