Oncology Needs Living Evidence, Not More AI Summaries | Opinion

Precision oncology has given physicians more treatment options for cancer, but it has also created a new challenge: keeping up with the constantly changing evidence needed to determine the best treatment for each patient. At the 2026 Annual Meeting of the American Society of Clinical Oncology, over 7,000 studies were presented on various types of cancer, covering survival, recurrence, disease progression, and quality of life.

This shows the progress in medical research, but also highlights the difficulty in managing evidence effectively. Oncologists often need to consult various sources, including clinical guidelines, published studies, regulatory decisions, biomarker information, clinical trials, and conference findings. However, each source serves a different purpose, and the information is not always organized around the specific patient in front of the physician.

This creates a paradox: while medicine is becoming more precise, the evidence infrastructure supporting those decisions remains fragmented. Clinical guidelines and systematic literature reviews are still essential, but they were not designed for an environment where evidence changes continuously. The future of AI in oncology should focus on creating systems that continuously maintain and update the evidence itself.

AI can quickly scan large amounts of information, identify relevant publications, extract findings, and connect information across sources. However, the ability to trace where information came from, how it was evaluated, and whether it remains current is crucial when it influences treatment decisions. Pharmaceutical companies also face the same expanding evidence environment in their development decisions, regulatory strategies, and reimbursement discussions.

Instead of discarding clinical guidelines and systematic literature reviews, the industry should build a continuously updated evidence foundation and use it to answer specific questions about patients, interventions, comparisons, and outcomes. This shift is essential as the life sciences industry moves from AI experimentation to practical deployment, as many companies struggle to scale AI effectively.