# Artificial Intelligence for Risk–Benefit Assessment in Hepatopancreatobiliary Oncologic Surgery: A Systematic Review of Current Applications and Future Directions on Behalf of TROGSS—The Robotic Global Surgical Society

## TL;DR

Artificial intelligence can help predict outcomes in complex liver and pancreatic cancer surgeries, but more real-world testing is needed before it can be widely used.

## Contribution

This systematic review evaluates the current state of AI applications in hepatopancreatobiliary cancer surgery and identifies key gaps for future research.

## Key findings

- AI models can predict cancer risk, complications, and survival with reasonable accuracy in research settings.
- Most AI studies in HPB surgery are small, retrospective, and lack real-world clinical validation.
- Few studies address cost-effectiveness, patient perspectives, or integration into clinical workflows.

## Abstract

Hepatopancreatobiliary (HPB) cancer surgery is one of the most challenging areas in cancer treatment, requiring highly accurate decisions about risks and benefits for each patient. In recent years, artificial intelligence (AI) has shown promise in helping doctors predict important outcomes, such as the likelihood of cancer, possible complications after surgery, and long-term survival. We reviewed all available studies that used AI to assist in these decisions for HPB cancer surgery. We found that while AI can make accurate predictions in research settings, most studies were small, retrospective, and rarely tested in real-world clinical practice. Important factors such as cost, patient perspectives, and integration into everyday surgical care have not yet been addressed. This review highlights the potential of AI in improving decision-making for complex cancer surgeries and outlines the next steps needed to bring these tools into routine clinical use.

Background: Hepatopancreatobiliary (HPB) surgery is among the most complex domains in oncologic care, where decisions entail significant risk–benefit considerations. Artificial intelligence (AI) has emerged as a promising tool for improving individualized decision-making through enhanced risk stratification, complication prediction, and survival modeling. However, its role in HPB oncologic surgery has not been comprehensively assessed. Methods: This systematic review was conducted in accordance with PRISMA guidelines and registered with PROSPERO ID: CRD420251114173. A comprehensive search across six databases was performed through 30 May 2025. Eligible studies evaluated AI applications in risk–benefit assessment in HPB cancer surgery. Inclusion criteria encompassed peer-reviewed, English-language studies involving human s ubjects. Two independent reviewers conducted study selection, data extraction, and quality appraisal. Results: Thirteen studies published between 2020 and 2024 met the inclusion criteria. Most studies employed retrospective designs with sample sizes ranging from small institutional cohorts to large national databases. AI models were developed for cancer risk prediction (n = 9), postoperative complication modeling (n = 4), and survival prediction (n = 3). Common algorithms included Random Forest, XGBoost, Decision Trees, Artificial Neural Networks, and Transformer-based models. While internal performance metrics were generally favorable, external validation was reported in only five studies, and calibration metrics were often lacking. Integration into clinical workflows was described in just two studies. No study addressed cost-effectiveness or patient perspectives. Overall risk of bias was moderate to high, primarily due to retrospective designs and incomplete reporting. Conclusions: AI demonstrates early promise in augmenting risk–benefit assessment for HPB oncologic surgery, particularly in predictive modeling. However, its clinical utility remains limited by methodological weaknesses and a lack of real-world integration. Future research should focus on prospective, multicenter validation, standardized reporting, clinical implementation, cost-effectiveness analysis, and the incorporation of patient-centered outcomes.