Artificial intelligence is making measurable progress in cancer detection, treatment planning, and personalized care, but experts warn that a universal cure remains unlikely despite bold claims from tech leaders. While companies like OpenAI and Anthropic have partnered with research centers and pharmaceutical firms to accelerate drug discovery and treatment, the medical reality is more nuanced than the headlines suggest.

Why Can't AI Just Cure Cancer?

Cancer is not a single disease. It is a catch-all term describing the uncontrollable growth of abnormal cells, and it manifests in fundamentally different ways depending on where it appears in the body. Pancreatic cancer, breast cancer, brain tumors, and blood cancers operate under different biological rules, respond to different treatments, and carry vastly different survival rates.

Consider the brain alone. There are more than 100 types of brain tumors, far more than in any other single organ. Each type presents unique challenges for diagnosis and treatment. This complexity is why oncologists remain skeptical of sweeping promises.

"Until AI can actually think and do experiments itself at scale, I'm not sure that we're going to find a cure for all cancer or medical illness in the next 10 years," said Sherene Loi, a medical oncologist specializing in breast cancer treatment at the Peter MacCallum Cancer Centre in Melbourne.

Sherene Loi, Medical Oncologist at Peter MacCallum Cancer Centre

However, Loi and other cancer experts acknowledge that AI will likely deliver significant efficiencies in treatment, diagnostics, and pathology services, leading to more personalized and equitable cancer care.

Where Is AI Making Real Progress Today?

Medical imaging stands as one of the most promising applications for AI in oncology. Machine learning models trained on vast amounts of patient data, such as CT scans, X-rays, and tissue samples, can detect patterns and changes that may be invisible to the human eye. This capability is already being deployed clinically in some settings.

A radiologist at the Mayo Clinic has been exploring early detection of pancreatic cancer using machine learning tools since 2021. In a proof-of-concept study published in 2022, he confirmed that machine learning tools could detect pancreatic tumors, including in pancreases that appeared normal on standard radiological review, before clinical diagnosis. The research suggests that AI could identify evidence of cancer earlier, potentially improving patient outcomes.

Beyond imaging, AI is being integrated into treatment planning and patient monitoring.

"AI can improve several parts of that process by helping us identify risk, detect disease, characterize tumors, select treatments and monitor," explained Ajit Goenka, a radiologist and nuclear medicine specialist at the Mayo Clinic in Minnesota.

Ajit Goenka, Radiologist and Nuclear Medicine Specialist at Mayo Clinic

How AI Is Accelerating Treatment Decisions

One of the most tangible advances involves using AI to speed up the time between diagnosis and treatment. A European collaboration called EUcanAI is using agentic AI, a type of AI system that can plan and execute sequences of tasks autonomously, to improve how brain tumors and central nervous system cancers are treated. The goal is to make every step of a patient's journey more efficient and less burdensome.

In one case, a teenager with a brain stem tumor underwent surgery and rapid genetic sequencing to identify the mutations driving his disease. Traditionally, these results would go to a board of specialists for discussion before determining next steps. Today, results can be delivered during surgery, saving patients time and money. AI promises to accelerate this process even further, potentially allowing surgeons to receive AI-informed treatment recommendations in real time.

Steps to Understanding AI's Role in Modern Cancer Care

• Early Detection: AI models analyze medical imaging to identify tumors before they become clinically apparent, potentially catching cancers at more treatable stages.
• Personalized Treatment Selection: Machine learning algorithms analyze a patient's tumor genetics and medical history to recommend targeted therapies tailored to their specific disease.
• Workflow Optimization: AI reduces administrative burden on doctors and medical professionals, freeing them to focus on patient care rather than data processing and routine analysis tasks.
• Real-Time Clinical Support: During surgery or treatment planning, AI systems can provide rapid analysis of biopsy results and genetic data to inform immediate clinical decisions.

What Does This Mean for Patients and Families?

The gap between tech executives' proclamations and clinical reality reflects a fundamental misunderstanding of disease complexity. While AI will not deliver a universal cancer cure in five to ten years, it is already reshaping how oncologists detect, diagnose, and treat individual patients. The real promise lies not in a single breakthrough but in incremental improvements across the entire care pathway.

For patients, this means faster diagnosis, more personalized treatment plans, and reduced time spent waiting for results. For healthcare systems, it means more efficient use of specialist time and resources. For researchers, it means accelerated drug discovery and clinical trial design. These gains, while less dramatic than a cure, have the potential to save lives and improve quality of life for millions of people living with cancer.

The conversation around AI and cancer should shift from "when will AI cure cancer?" to "how can AI help us treat each patient's unique disease more effectively?" That question, while less headline-grabbing, is the one oncologists are actually working to answer.