Development of Multicenter Deep Learning Models for Predicting Surgical Complexity and Surgical Site Infection in Abdominal Wall Reconstruction, a Pilot Study
The study demonstrated the successful development of a multicenter DLM for SSI prediction in AWR, highlighting the impact of patient factors over surgical practice variability in predicting SSIs with DLMs. The CST model's prediction remained challenging, which we hypothesize reflects the subjective nature of surgical decisions and varying institutional practices. Our findings underscore the potential of AI-enhanced surgical risk calculators to risk stratify patients and potentially improve patient outcomes.
Authors
- Hadley H. Wilson (ORCID: https://orcid.org/0009-0009-4603-0460)
- Jeffrey E. Janis (ORCID: https://orcid.org/0000-0001-6103-4798)
- Benjamin A. Sarac (ORCID: https://orcid.org/0000-0001-7825-4957)
- Brittany S Mead
- W Lorenz (ORCID: https://orcid.org/0000-0002-1265-1973)
- B. Todd Heniford (ORCID: https://orcid.org/0000-0003-1864-6048)
- Alexis M Holland (ORCID: https://orcid.org/0009-0009-3893-0864)
- Keith J. Murphy (ORCID: https://orcid.org/0000-0002-8865-0467)
- Sullivan A. Ayuso (ORCID: https://orcid.org/0000-0002-8722-4669)
- Gregory T. Scarola
- Samantha W Kerr
Institutions
- University of North Carolina at Charlotte (US)
- Carolinas Medical Center (US)
Publication Details
- Journal
- Journal of Abdominal Wall Surgery
- Published
- 2025-04-14
- DOI
- https://doi.org/10.3389/jaws.2025.14371
- Citations
- 2
- Primary Topic
- Hernia repair and management
- Type
- article
- Field-Weighted Citation Impact
- 4.01