Prediction of Ureteral Injury During Colorectal Surgery Using Machine Learning

Public Deposited
Analytics

Downloadable Content

Download PDF
Request Version for Screen Reader
Creator
  • Chen, Kevin A.
    • Affiliation: School of Medicine, Department of Surgery
  • Joisa, Chinmaya U.
    • Affiliation: School of Medicine, Joint Department of Biomedical Engineering, North Carolina State University
  • Stem, Jonathan M.
    • Affiliation: School of Medicine, Department of Surgery
  • Guillem, Jose G.
    • Affiliation: School of Medicine, Department of Surgery
  • Gomez, Shawn M.
    • Affiliation: School of Medicine, Joint Department of Biomedical Engineering, North Carolina State University
  • Kapadia, Muneera R.
    • Affiliation: School of Medicine, Department of Surgery
Abstract
  • Background Ureteral injury (UI) is a rare but devastating complication during colorectal surgery. Ureteral stents may reduce UI but carry risks themselves. Risk predictors for UI could help target the use of stents, but previous efforts have relied on logistic regression (LR), shown moderate accuracy, and used intraoperative variables. We sought to use an emerging approach in predictive analytics, machine learning, to create a model for UI. Methods Patients who underwent colorectal surgery were identified in the National Surgical Quality Improvement Program (NSQIP) database. Patients were split into training, validation, and test sets. The primary outcome was UI. Three machine learning approaches were tested including random forest (RF), gradient boosting (XGB), and neural networks (NN), and compared with traditional LR. Model performance was assessed using area under the curve (AUROC). Results The data set included 262,923 patients, of whom 1519 (.578%) experienced UI. Of the modeling techniques, XGB performed the best, with an AUROC score of .774 (95% CI .742-.807) compared with .698 (95% CI .664-.733) for LR. Random forest and NN performed similarly with scores of .738 and .763, respectively. Type of procedure, work RVUs, indication for surgery, and mechanical bowel prep showed the strongest influence on model predictions. Conclusions Machine learning-based models significantly outperformed LR and previous models and showed high accuracy in predicting UI during colorectal surgery. With proper validation, they could be used to support decision making regarding the placement of ureteral stents preoperatively.
Date of publication
Keyword
DOI
Identifier
Resource type
  • Article
Rights statement
  • In Copyright
Rights holder
  • Southeastern Surgical Congress
License
  • Attribution-NonCommercial 4.0 International
Journal title
  • The American Surgeon™
Journal volume
  • 89
Journal issue
  • 12
Page start
  • 5702
Page end
  • 5710
Funder
  • National Institutes of Health
ISSN
  • 1555-9823
  • 0003-1348
Copyright date
  • 2023
Publisher
  • SAGE Publications

Relations

Parents:

This work has no parents.

In Collection:

Items

Thumbnail Title Date Uploaded Visibility Actions
file details 10.1177_00031348231173981.pdf 2024-01-11 Public Download