A computer tool tried to predict which brain tumor spots would grow back
Original title: Pre-treatment machine learning prediction of local failure and time to local failure after Gamma Knife radiosurgery for radioresistant brain metastases.
How far along is this research?
- Lab cells
- Animals
- Review
- Tested in people
This was tested in people. That is the most reliable kind of research we share.
The tool was only tested on old patient records, not in real care.
The short version
Researchers built a computer tool to guess which brain tumor spots may grow back after focused radiation.
What was studied. Doctors looked back at old records from one hospital. They studied 893 brain tumor spots that came from melanoma or kidney cancer, all treated with stereotactic radiosurgery: Radiation aimed at a small target, in one visit or a few. There is no cutting, despite the name. See the glossary focused radiation.
What they found. Of the 893 spots, 228 (25.5%) grew back after treatment. The tool was then tested on 179 spots it had not seen before. It did a fair job of sorting higher risk from lower risk. Age, how well the person was doing day to day, and tumor size mattered most.
What this means, and what it doesn't
What it could mean: A tool like this could one day help a doctor talk about your risk before radiation. It might also help decide how often you need scans afterward.
What it doesn't mean: This is not a treatment, and it is not a cure. The tool was only run on old records from one hospital. It was never used on new patients in real time. You cannot get it at a clinic today, and it does not change the radiation itself.
Source: PubMed, November 2, 2026 · Read the original
This plain-language summary was written by AI and published automatically after passing our automatic safety checks. How we write.