Skip to main content
2025 ASCRS Annual Scientific Meeting Main banner
Final Program


Visit ASCRS U
Icon Legend
This session is not in your schedule.
This session is in your schedule. Click again to remove it.
Presentation Icons
CME
CME
Invitation/Ticketed Event
Invitation/Ticketed Event
Invited Lectureship
Invited Lectureship
Award Recipient
Award Recipient
Self-Assessment
Self-Assessment
Social
Social
Industry
Industry
Back

Session: ePoster: Colon and Colorectal Cancer 18 (Tue8)

EP927 - Beyond Resection: Relationship Between Arterial Stump and Lymph Nodes in the Recurrence of Right Colon Cancer in a Machine Learning

Tuesday, May 13, 2025
8:21 AM – 8:26 AM PT

    Senior Author(s)

  • RZ

    Rogelio Zayas Borquez, n/a

    Fellowship
    INCMNSZ
    SANTA URSULA IXTLA, Distrito Federal, Mexico

    All of the relevant financial relationships listed below have been mitigated.
    This individual has no financial relationships with ineligible companies.

    • ePoster Presenter(s)

  • OS

    Oscar Santes, MD, MRCS (Ed), FEBS (Coloproctology) (he/him/his)

    Consultant Colorectal Surgeon
    Instituto Nacional de Ciencias Medicas y Nutricion Salvador Zubiran
    Mexico City, Distrito Federal, Mexico

    All of the relevant financial relationships listed below have been mitigated.
    This individual has no financial relationships with ineligible companies.

All of the relevant financial relationships listed below have been mitigated.
Rogelio Zayas Borquez, n/a: This individual has no financial relationships with ineligible companies.
Oscar Santes, MD, MRCS (Ed), FEBS (Coloproctology): This individual has no financial relationships with ineligible companies.
Image or Table (Do Not add text here):

Purpose/Background: Background:
Colorectal cancer (CRC) is a common neoplasm and a global health concern. Despite advances in surgery and adjuvant therapy, tumor recurrence remains a significant challenge. Identifying factors influencing recurrence, such as the number of evaluated lymph nodes and the length of the arterial stump, is crucial to improve patient prognosis.

Methods/Interventions:

Objective:
To explore the relationship between arterial stump length and the number of evaluated lymph nodes and to develop a predictive model for tumor recurrence in right colon cancer using machine learning.

Design:
A retrospective observational study analyzing clinical, radiological, and histopathological data of patients with CRC.
Setting:
National Institute of Medical Sciences and Nutrition Salvador Zubirán.
Patients:
A total of 64 patients with right colon cancer who underwent surgical interventions.
Intervention(s):
None. This study is purely observational.

Results/Outcomes: Main Outcome Measures:
The study focused on the prediction of tumor recurrence using a Random Forest model, with variables including age, sex, lymphatic/vascular invasion, histological grade, margin status, and the number of evaluated lymph nodes. Additionally, the relationship between arterial stump length and the number of evaluated lymph nodes was examined.

Results:
The Random Forest model demonstrated an overall accuracy of 81% and an AUC of 0.92, identifying the number of evaluated lymph nodes as the most influential factor (~0.4 importance). A simplified model with the four most relevant features maintained an accuracy of 87% for the test data. A decreasing linear relationship between stump length and the number of evaluated lymph nodes was also observed.

Conclusion/Discussion:

Conclusions:
Adequate lymph node evaluation and arterial stump length are key factors in predicting tumor recurrence in CRC. The developed model may aid in intraoperative and postoperative decision-making, emphasizing the need for standardized criteria and future prospective studies.