Responsible Integration of AI in Cancer Genomics: Barriers, Risks, and Pathways to Trustworthy Clinical Translation
2026-08-31 • Artificial Intelligence
Artificial IntelligenceComputation and Language
AI summaryⓘ
The authors explain that while AI and natural language processing are good at analyzing cancer genetics, using these tools regularly in hospitals is still difficult. They say the problem isn't about making smarter computers, but about making sure the AI fits well and can be trusted in medical workflows. They point out four main challenges: inconsistent evidence, unclear AI decisions, managing data properly, and making different systems work together. The authors suggest a big-picture plan to fix these issues by validating methods carefully, handling uncertainty, creating compatible systems, following rules, and involving humans throughout the AI use process.
Artificial IntelligenceNatural Language ProcessingCancer GenomicsVariant InterpretationClinical Workflow IntegrationExplainabilityData GovernanceInteroperabilityKnowledge GraphUncertainty
Authors
Bahar İlgen, Yiannos Tolias, Denise Kühnert, Paraskevi Papadopoulou, Magnus Westerlund, Dominik Heider, Katharina Ladewig, Georges Hattab
Abstract
Artificial intelligence (AI) and natural language processing (NLP) are increasingly used to extract, integrate, and interpret biomedical knowledge relevant to cancer genomics, yet their translation into routine clinical oncology has been comparatively slow. The central challenge is not computational capability alone, but trustworthy integration into clinical workflows. This review examines how NLP and AI support the cancer genomics pipeline, from literature mining and automated variant interpretation to clinical trial matching, knowledge graph construction, and multimodal data integration. We identify four interrelated translational failure domains: evidence inconsistency, explainability and uncertainty, data governance and reproducibility, and interoperability. Rather than considering these challenges in isolation, we take a systems-level view, focusing on their interaction across the translational pathway. We propose a conceptual framework and roadmap for addressing these domains through rigorous validation, uncertainty-aware methods, interoperable infrastructures, regulatory alignment, and human oversight across the AI lifecycle. Progress toward routine clinical use will depend less on further improving model capability than on systematically addressing these interacting failure domains from development through deployment and post-deployment monitoring.