Application of machine learning models to identify predictors of good outcome after laparoscopic fundoplication
Although male sex and degree of intact peristalsis are significant predictors for outcomes after laparoscopic fundoplication, prediction of individual patient outcome was relatively poor, and ML prediction models provided only marginal improvement in accuracy. Clinical acumen and a discussion with patients to set realistic postoperative expectations cannot be replaced by regression models or standard ML prediction algorithms at the present time.
Authors
- David I. Watson (ORCID: https://orcid.org/0000-0002-7683-2693)
- Richard John Woodman (ORCID: https://orcid.org/0000-0002-4094-1222)
- Jennifer C. Myers (ORCID: https://orcid.org/0000-0003-2157-7098)
- Sarah K. Thompson (ORCID: https://orcid.org/0000-0002-9908-6208)
- Tim Bright (ORCID: https://orcid.org/0000-0003-3700-5262)
- Rippan N. Shukla
Institutions
- Flinders University (AU)
- Flinders Medical Centre (AU)
- Queen Elizabeth Hospital (AU)
Publication Details
- Journal
- Journal of Gastrointestinal Surgery
- Published
- 2025-03-22
- DOI
- https://doi.org/10.1016/j.gassur.2025.102029
- Citations
- 2
- Primary Topic
- Gastroesophageal reflux and treatments
- Type
- article
- Field-Weighted Citation Impact
- 3.62