Sick of hearing about AI? You are not alone. After all, there are only so many hours we can spend scrolling through AI slop on our phones before asking if this potentially art-propelling technology could be put to better use. For example – using AI to help scientists find better cancer treatments. Not a bad place to start, right?
Fortunately, there is already encouraging work. In a large Swedish trial, for example, AI helped doctors find more breast cancer while also reducing the number of scan readings. Win-win. Elsewhere, researchers are using it to investigate new treatments, with some predicting that decades of medical progress could happen within a few years.
It’s certainly an attractive thought, and a far better use case for the tech than the so-called slop. That being said, there is still a lot of work to be done. So with that said, how much closer is AI really getting us to curing cancer? Here are just a few examples.
AI is already helping doctors find cancer
At the risk of repeating the header, AI is already doing great work. In Sweden, mammograms are usually read by two radiologists, but for the MASAI trial, the researchers used AI to decide which scans both readers needed, and which one might go for. The software also marked suspicious areas for the doctors to examine.
In total, more than 105,000 women were randomly assigned to the AI-assisted approach or standard screening. The results, published in 2025, show that AI-supported screening detected 29 percent more cancers – about 6.4 cancers per 1000 women, compared with five per 1000 in the standard group.
This also did not come with a statistically significant increase in false positives – cases where someone is called back for further checks but does not have cancer. And since some scans only needed one reader, the number of readings fell by around 44 percent.
Published results have since found that AI-assisted screening diagnosed about 81 percent of cancers during the study period, compared with 74 percent for standard screening. Whether that translates into a longer life, however, remains to be seen.
It is still early days
Results like the MASAI trial help fuel interest in medical AI, while some developers expect progress on a much larger scale.
Enter Dario Amodei, the head of Anthropic – the company behind Claude. He outlined one such prediction in his 2024 essay Machines of Loving Grace. He suggested that powerful AI could squeeze 50-100 years of progress in biology and medicine into five to ten years. The elimination of most cancers is among the possibilities he described, although he acknowledged that some difficult cancers may remain.
There’s a pretty big condition attached to that prediction, mind. Its five-to-ten-year window only begins once a far more capable AI system than today’s familiar chatbots arrives. This technology has to be developed first – so forecasting tells us little about when a particular treatment might reach patients.
It is also worth remembering that many cancers can already be cured if they are detected early and treated effectively. The challenge is to make the treatment successful for more people, across a wide range of diseases.
The US National Cancer Institute also describes more than 100 types of cancer, and each person’s cancer has its own combination of genetic changes. Even cells in the same tumor can be different. A treatment that works for one person may not work for another, so it’s important to keep a level head and see it all as a marathon, not a sprint.
In addition to diagnostics, AI could also help researchers develop new drugs. That may involve finding a biological target—such as a protein involved in a disease—and designing a molecule to act on it.
Searching for promising molecules can, surprisingly, take a considerable amount of time. According to researchers from the US National Institutes of Health, screening a large collection of compounds can take months or years, while computer-based screening can sometimes do the job in days or even hours. That gives scientists a shortlist to investigate in the lab much earlier – although they still need to determine whether these molecules work in practice.
For example, a collaboration between the US National Cancer Institute and Department of Energy used AI with molecular simulations to study RAS proteins that are frequently altered in cancer. The goal was to understand how they interact with other proteins in the cell membrane, helping researchers figure out how to target them with treatments.
When a potential cancer drug reaches human trials, early studies examine safety, dosage and whether it appears to work. Larger phase-three trials compare it to standard treatment – allowing researchers to assess whether it offers patients something better, and whether its benefits justify its side effects.
Although AI will help scientists achieve these studies faster, patients still need to be followed over time. Researchers need to find out how long the benefits last and what problems may arise later.
That is also important
The information used to train an AI also affects how useful it will be. The National Cancer Institute warns that models may retain medical assumptions if their training data do not accurately represent the broader population. People who were poorly represented in that data also still need the resulting tool to work for them.
Testing is also important for software, as well as drugs. A good result on one set of scans or patient records does not indicate that the same tool will work equally well elsewhere. Researchers need reliable data and clinical trials to find out where it helps, where it fails and how it should fit into care.
Ultimately, there is no shortage of evidence that gives us reasons to take AI and its role in curing cancer seriously, but we are far from one of humanity’s greatest breakthroughs ever. For now, it’s best to keep a level head, and follow the science. As the tech evolves, so will our methods and discoveries. And if AI lives up to the hype, we’re right around the corner from a whole bunch more…
