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: Benign Anorectal 2 (Sun1230)

EP412 - Development of Evaluation Tool for Predicting Postoperative Recurrence of Perianal Fistula Using MRI and Machine Learning Model

Sunday, May 11, 2025
12:57 PM – 1:02 PM PT
Location: Monitor 2, Sails Pavilion, Upper Level

    ePoster Presenter(s)

  • YL

    Yicheng Liu, Resident

    Resident
    Baoshan Hospital of Integrated Traditional Chinese and Western Medicine
    Shanghai, Shanghai, China (People's Republic)

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

    • Senior Author(s)

  • QW

    Qingming Wang, Doctor

    professor
    Shuguang Hospital Affiliated to Shanghai University of Traditional Chinese Medicine
    ShangHai, Shanghai, China (People's Republic)

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

    • Author(s)

  • BC

    Bo Chen, n/a

    student
    Shuguang Hospital affiliated with Shanghai University of Traditional Chinese Medicine
    Shanghai, Shanghai, China (People's Republic)

    Disclosure information not submitted.

  • Qianqian Ye

    Doctor
    Shuguang Hospital Affiliated to Shanghai University of Traditional Chinese Medicine
    ShangHai, Shanghai, China (People's Republic)

    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.
Yicheng Liu, Resident: This individual has no financial relationships with ineligible companies.
Qingming Wang, Doctor: This individual has no financial relationships with ineligible companies.
Qianqian Ye: This individual has no financial relationships with ineligible companies.
Image or Table (Do Not add text here):

Purpose/Background: To develop and validate an evaluation tool based on preoperative MRI (pPMR) for predicting recurrence of perianal fistula (PAF).

Methods/Interventions: A retrospective cohort study examined 253 patients from two centers who underwent preoperative MRI for PAF. Features were extracted using pyradiomics and selected via Pearson correlation and LASSO regression. A Logistic Regression (LR) model was then developed, with its performance validated through five-fold cross-validation and assessed using metrics such as AUC, precision, and recall.

Results/Outcomes: The developed pPMR model, incorporating MRI and clinical features with multiple factors, achieved AUC values of 0.851 and 0.787 in the training, and test sets, respectively. It was shown to be superior to models based on individual imaging sequences and demonstrated high potential for clinical applicability.

Conclusion/Discussion: The pPMR model presents an effective and non-invasive predictive tool that significantly enhances prognosis evaluation in PAF management, potentially leading to personalized surgical strategies. However, larger multi-centric studies with expanded clinical variables are recommended to confirm the evaluation tool's generalizability and effectiveness.