DistantNews
Support us
🇧🇪 Belgium /Health & Science

Four Flemish breast clinics test AI system to match patients with cancer treatments

From VRT NWS · () Dutch

Translated from Dutch and summarized by DistantNews. Read the original for the full story.

At a glance

News Named sources Ongoing story
  • Four Flemish breast clinics are evaluating an AI system that predicts how breast cancer patients may respond to chemotherapy, their risk of lymph-node spread and tumor size at diagnosis.
  • The system uses data from more than 8,000 patients to help doctors tailor treatment and potentially avoid unnecessary surgery.
  • Specialists are testing the system on historical patient records before a possible trial in daily practice, which developers hope to begin within a year.

An artificial intelligence system is being tested at four Flemish breast clinics to predict, at the time of diagnosis, which treatment may work best for each breast cancer patient. It estimates the likely response to chemotherapy, the risk of cancer spreading to the armpit lymph nodes and the size of the tumor.

Those are details doctors often learn only later in the treatment process, said Barbara Bussels, coordinator of the breast clinic at AZ Delta. Having them earlier could help medical teams choose a more suitable treatment, avoid unnecessary operations or intervene sooner when needed.

The goal is not to replace doctors, but to give them additional information when important treatment decisions are being made. The final decision always remains with the team treating the patient.

· Barbara BusselsThe AZ Delta breast clinic coordinator explained how the system is intended to support, rather than replace, medical teams.

“The goal is not to replace doctors, but to give them additional information when important treatment decisions are being made. The final decision always remains with the team treating the patient,” Bussels said.

By using this approach, artificial intelligence can recognize patterns that are difficult or even impossible to detect with the human eye.

· Philip PoortmansThe ZAS radiotherapy oncologist described the advantage of combining multiple patient data sources.

The Clinical Decision Support System was developed by RADar, AZ Delta’s learning and innovation center. Its AI models were trained using records from more than 8,000 breast cancer patients at AZ Delta, AZ Groeninge in Kortrijk, AZORG in Aalst and ZAS in Antwerp. Radiotherapy oncologist Philip Poortmans of ZAS said the system can identify patterns that are difficult or impossible to detect with the human eye, creating a fuller picture than a single source of information.

A more accurate prediction of lymph-node spread could help surgeons tailor armpit procedures more closely to individual patients, or avoid them altogether. That could reduce complications such as pain and restricted movement. The system is currently being assessed only against past patient records. Specialists at the four hospitals have evaluated it independently since early June. If the results are positive, the strongest models will be tested in routine care. Bussels said the team hopes to use the system in practice within a year, subject to European certification.

We hope to use the system in practice within a year.

· Barbara BusselsBussels discussed the expected timeline for clinical use.
About this summary

Originally published by VRT NWS in Dutch. Translated, summarized, and contextualized automatically by DistantNews, with a note on how the source frames the story. Not individually reviewed before publishing. How this works.

More Stories

From Our Blog