Artificial intelligence (AI) is increasingly being applied across the cancer care pathway, from early detection to personalised treatment strategies, according to a review of emerging AI applications published in npj Precision Oncology.
The authors describe how several AI approaches—including machine learning, deep learning, reinforcement learning, natural language processing, and generative models—are being used to analyse complex biomedical datasets in oncology. These tools can integrate information from pathology images, genomic sequencing, clinical records, and imaging studies to support cancer diagnosis, risk stratification,n and treatment planning.
CLINICAL SUMMARY
What was examined
A review examined current and emerging applications of artificial intelligence across the cancer care pathway.
Key findings
-
AI methods—including machine learning, deep learning, ng and natural language processing—are being applied to cancer detection, pathology analysis, and treatment prediction.
-
AI tools may also help integrate genomic and clinical data to support precision oncology and drug discovery.
Clinical implications
-
AI technologies may support diagnostic workflows and personalised treatment planning.
-
Further clinical validation and integration into healthcare systems will be needed before widespread implementation.
One rapidly expanding area is AI-assisted pathology, where deep learning algorithms analyse histopathology slides to support tumour classification, grading, and biomarker assessment. Such tools may help automate time-consuming tasks and improve efficiency in pathology workflows.
The review also highlights the role of AI in precision oncology, including the identification of genomic alterations, prediction of treatment response,e and discovery of potential drug targets. Machine learning approaches are increasingly used to analyse multi-omics datasets and identify therapeutic vulnerabilities across tumour types.
Featured Event
However, the authors note that challenges remain before widespread clinical implementation. These include data quality and interoperability issues, algorithm transparencyn,c,y and the need for robust clinical validation.
Overall, the review suggests that while AI is unlikely to replace clinicians, it may become an important tool for supporting cancer diagnosis, research, and personalised treatment strategies.
Paper: Li, J., Zhang, L., Yu, Z. et al. The impact of AI on modern oncology from early detection to personalized cancer treatment. npj Precis. Onc. 10, 69 (2026). Access online here.
