A computer tool to predict leftover pituitary tumor after surgery
Original title: Multiple Machine Learning Algorithms for Predicting Postoperative Residual Tumor in Pituitary Neuroendocrine Tumors.
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 built from past patient records and still needs more testing.
The short version
Doctors built a computer tool to guess who may have tumor left after surgery.
What was studied. Doctors looked back at 584 people who had surgery for a pituitary tumor at one hospital. They tested nine computer programs to predict leftover tumor seen on MRI scans.
What they found. Leftover tumor was found in 72 of these patients, or 12.3%. One program, called random forest, made the most correct guesses in testing. The tool used eight things, like tumor size, the person's age, and how far the tumor had spread.
What this means, and what it doesn't
What it could mean: Someday a tool like this may help a surgeon plan ahead. It could point out who needs closer watching after surgery. For now it is not part of regular care.
What it doesn't mean: This is not a treatment, and it is not a cure. The tool was built and tested at one hospital only. The authors say it is not yet proven to work for other patients. More testing is needed before doctors can use it in the clinic.
Source: PubMed, November 1, 2026 · Read the original
This plain-language summary was written by AI and published automatically after passing our automatic safety checks. How we write.