Machine Learning for Predicting the Low Risk of Postoperative Pancreatic Fistula After Pancreaticoduodenectomy: Toward a Dynamic and Personalized Postoperative Management Strategy
While the model showed promising performance in a single-center cohort, external validation across different surgical settings will be essential to confirm its generalizability and clinical utility. The integration of ML into clinical workflows may represent a step forward in delivering personalized and dynamic care after pancreatic surgery.
Authors
- Paolo Soda (ORCID: https://orcid.org/0000-0003-2621-072X)
- Damiano D. Caputo (ORCID: https://orcid.org/0000-0001-7058-1945)
- Roberto Cammarata (ORCID: https://orcid.org/0000-0002-3230-2869)
- Gianluca Costa (ORCID: https://orcid.org/0000-0001-5194-8908)
- Alberto Catamerò
- Roberto Coppola (ORCID: https://orcid.org/0000-0001-5798-0714)
- Vincenzo La Vaccara (ORCID: https://orcid.org/0000-0002-9355-5771)
- Valerio Guarrasi (ORCID: https://orcid.org/0000-0002-1860-7447)
- Silvia Angeletti (ORCID: https://orcid.org/0000-0002-7393-8732)
- Gennaro Melone (ORCID: https://orcid.org/0009-0008-9289-3067)
- Filippo Ruffini (ORCID: https://orcid.org/0009-0003-9759-5492)
- Federico Seghetti
Institutions
- Università Campus Bio-Medico (IT)
- Campus Bio Medico University Hospital (IT)
- Link Campus University (IT)
Publication Details
- Journal
- Cancers
- Published
- 2025-05-31
- DOI
- https://doi.org/10.3390/cancers17111846
- Citations
- 3
- Primary Topic
- Pancreatic and Hepatic Oncology Research
- Type
- article
- Field-Weighted Citation Impact
- 3.14