A computer tool tried to guess blood loss in meningioma surgery
Original title: Deep Learning-based Regression of Intraoperative Estimated Blood Loss from Preoperative Magnetic Resonance Imaging in Patients Undergoing Intracranial Meningioma Surgery.
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.
This was only tested on past scans and records, not used in real care yet.
The short version
A computer tool read brain scans to guess how much blood is lost during surgery.
What was studied. Researchers looked back at records from 632 people who had surgery for a meningioma. Each person had an MRI scan before surgery. The tool learned from 442 of these people and was then tested on 64 others.
What they found. The tool's guesses were only fair, not strong. On average, its guess was off by 382.1 mL of blood. Still, it did better than simply guessing the average amount, cutting that error by 37.2%.
What this means, and what it doesn't
What it could mean: Someday a tool like this might tell the surgery team who is likely to bleed more. That could help them plan ahead and have blood ready. For now, the guesses are too far off to guide your care.
What it doesn't mean: This does not mean a tool like this is used in hospitals now. It was only tested on old scans from one group of patients. The authors say its real worth in the clinic is still unclear. It does not treat a tumor, and it is not a cure. It needs testing at other hospitals before anyone can trust it.
Source: PubMed, October 29, 2026 · Read the original
This plain-language summary was written by AI and published automatically after passing our automatic safety checks. How we write.