Harnessing Artificial Intelligence for the Management of Patients With GI Cancers

Clinical Snapshot

Key Findings

• Effect Size: Not quantified - qualitative assessment only

• Primary Outcome: AI shows promise across multiple GI cancer applications but requires careful implementation

• Nnt Or Sensitivity: Increased adenoma detection rates mentioned for endoscopic AI but specific values not provided

Clinical Application

Variable - depends on institutional resources, regulatory approval, and clinician training Relevant to Australian practice given similar healthcare infrastructure; TGA approval would be required for diagnostic AI tools; integration with existing electronic health records and clinical workflows would be essential Patients with GI malignancies in well-resourced healthcare systems with advanced IT infrastructure

Abstract

Artificial intelligence (AI) has the potential of reshaping GI oncology by enabling more nuanced interpretation of complex clinical, imaging, and molecular data, while supporting more timely and patient-centered decisions. This article synthesizes perspectives across the GI cancer continuum, beginning with a framework for context-aware AI that emphasizes metadata, multimodal integration, and lifecycle quality and safety as foundations for trustworthy tools that clarify, rather than conceal, uncertainty. Next, AI in endoscopy is highlighted as an example in clinic practice, focusing on computer-aided detection and diagnosis systems that not only increase adenoma detection rates but also raise questions about surveillance burden, real-world effectiveness, and the balance between skill enhancement and potential deskilling of endoscopists. Another section explores how AI can help GI oncologists design, prioritize, and implement highly innovative clinical trials-particularly multi-omic and imaging-driven approaches-while envisioning a future in which far more patients participate in trials that align with their goals and values. The final section reviews emerging AI-enabled clinical trial matching pipelines, including large language model-based retrieval and prescreening tools that operate on real-world electronic health record and protocol data, and discusses challenges related to bias, privacy, explainability, and workflow integration. Together, these contributions argue that the greatest impact of AI in GI oncology will come from deliberately aligning technical capabilities with highly relevant patient-centered clinical questions, ethical governance, and implementation strategies that expand access to trials and improve outcomes for patients with GI malignancies.

References

1. 1.Goyal, L., Chung, C., Mori, Y., Hall, W. A., Kehl, K. L., & Feng, M. (2026). Harnessing artificial intelligence for the management of patients with GI cancers. American Society of Clinical Oncology Educational Book. https://doi.org/10.1200/EDBK-26-515754