Doctors design AI tool to predict side effects in breast cancer patients

Doctors have developed an artificial intelligence tool that can predict which breast cancer patients are more at risk of side effects after treatment.

Globally, 2 million women are diagnosed with the disease each year, which is the most common cancer in women in most countries.

Greater awareness, earlier detection and a wider range of treatment options have improved survival rates in recent years, but many patients will often experience debilitating side effects after treatment.

An international team of physicians, scientists and researchers have designed an AI tool that can indicate how likely a patient is to experience problems after surgery and radiotherapy. The technology, which is being tested in Britain, France and the Netherlands, could help patients access more personalized care.

“Fortunately, long-term survival rates for breast cancer continue to increase, but for some patients this means living with the side effects of their treatment,” said Dr. Tim Rattay, a breast surgeon and associate professor at the university. from Leicester. “These include skin changes, scarring, lymphedema, which is painful swelling of the arm, and even heart damage from radiation.

“That is why we are developing an AI tool to inform doctors and patients about the risk of chronic arm swelling after surgery and radiotherapy for breast cancer. We hope this will help doctors and patients choose radiation treatment options and reduce side effects for all patients.”

The AI ​​tool has been trained to predict lymphedema up to three years after surgery and radiotherapy using data from 6,361 breast cancer patients. Patients who are at higher risk of arm swelling may be offered alternative treatments or additional support during and after treatments.

Dr. Guido Bologna, associate professor at the University of Applied Sciences and Arts of Western Switzerland in Geneva and co-investigator on the project, said: “The final, best-performing model makes predictions using 32 different patient and treatment characteristics, including whether no patients had chemotherapy, or sentinel lymph node biopsy under the armpit was performed and the type of radiotherapy given.”

The AI ​​tool correctly predicted lymphedema in an average of 81.6% of cases and correctly identified patients who would not develop it in an average of 72.9% of cases. The overall predictive accuracy of the model was 73.4%.

“Patients identified as having a higher risk of arm swelling may receive additional supportive measures, such as wearing an arm compression sleeve during treatment, which has been shown to reduce arm swelling in the long term,” said Rattay . “Physicians can also use this information to discuss options for lymph node radiotherapy in patients, where the benefit can be quite borderline.”

Speaking at the European Breast Cancer Conference in Milan, Rattay said the technology is “an explainable AI tool, meaning it shows the reasoning behind decision-making.

“This not only makes it easier for doctors to make decisions, but also to provide data-based explanations to their patients,” he added.

The research team hopes to enroll 780 patients as part of a clinical trial called the Pre-Act Project, which will be followed over a two-year period. They are also developing a tool to predict other side effects, including skin and heart damage.

Dr. Simon Vincent, director of research, support and influence at Breast Cancer Now, said ways to improve treatments were urgently needed. “This exciting project will investigate whether the use of AI could enable people with breast cancer to receive more personalized care and support that helps minimize side effects, such as chronic swelling of the arms, after surgery and radiotherapy.

“This research is in its early stages and more evidence is needed before we can consider whether or not the AI ​​tool can be used in medical settings, and we look forward to seeing the results of the trial.”

In other developments at the conference, researchers from Italy found that the use of combined positron emission tomography-magnetic resonance imaging (PET-MRI) scans allowed doctors to detect that a breast cancer patient’s tumor had begun to spread. That meant they could benefit from an alternative treatment, such as chemotherapy or another type of surgery.

Meanwhile, researchers from the Netherlands said that young breast cancer patients who received low-dose radiotherapy at the site where their tumor was removed, in addition to whole-breast radiotherapy, remained free of local recurrence after 10 years.