Artificial intelligence tool developed to predict side effects in cancer

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

Every year, 2 million women around the world are diagnosed with the dangerous disease, which is the most common type of cancer in women in most countries, writes The Guardian.

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

An international team of doctors, scientists and researchers have developed an artificial intelligence tool that can indicate how likely a patient is to have problems after surgery and radiotherapy. The technology, trialled in the UK, France and the Netherlands, could help patients access more personalized care.

“Fortunately, long-term survival rates for breast cancer continue to improve, but for some patients this means they have to endure the side effects of treatment,” says Dr Tim Rattay, consultant breast surgeon and associate professor at the University of Leicester. “These include skin changes, scarring, lymphedema, which is painful swelling of the arm, and even heart damage from radiation therapy. That’s why we’re developing an artificial intelligence tool to inform doctors and patients about the risk of chronic arm swelling after breast cancer surgery and radiation therapy. We hope this will help clinicians and patients navigate their radiation treatment options and reduce side effects for all patients.”

The artificial intelligence tool was trained to predict lymphedema up to three years after surgery and radiotherapy using data from 6,361 breast cancer patients. Patients at increased risk of hand swelling may be offered alternative treatments or additional support during and after treatment, writes The Guardian.

Dr Guido Bologna, associate professor at the University of Applied Sciences and Arts of Western Switzerland in Geneva and co-author of the project, said: “The final, best-performing model made predictions using 32 different patient and treatment characteristics, including whether patients had chemotherapy or had a biopsy. sentinel lymph node, surgery was performed under the armpit and a type of radiation therapy was prescribed.”

The artificial intelligence tool correctly predicted lymphedema an average of 81.6% of the time and correctly identified patients who would not have developed it an average of 72.9% of the time. The overall prediction accuracy of the model was 73.4%.

“Patients identified as being at higher risk for arm swelling may be offered additional supportive measures, such as wearing a compression sleeve during treatment, which has been shown to reduce arm swelling in the long term,” Rattay said. “Clinicians can also use this information to discuss options for lymph node irradiation in patients where its benefit may be quite limited.”

Speaking at the European Breast Cancer Conference in Milan, Rattay said the technology is an “explainable artificial intelligence tool, which means it shows the logic behind decision making.

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

The research team hopes to enroll 780 patients in a clinical trial called the Pre-Act project, who will be followed for two years. They are also developing a tool to predict other side effects, including skin and heart damage.

Dr Simon Vincent, director of research, support and impact at Breast Cancer Now, says ways to improve treatments are urgently needed. “This exciting project will explore whether the use of artificial intelligence can enable people with breast cancer to receive more personalized care and support that helps minimize side effects, such as chronic arm swelling, following surgery and radiotherapy. This research is at an early stage and more evidence is needed before we can consider whether the AI ​​tool can be used in healthcare settings, and we look forward to the results of the trial.”

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

Meanwhile, researchers from the Netherlands reported that young breast cancer patients who received low-dose radiation therapy to the site where their tumor was removed, in addition to radiation therapy to the entire breast, had no local recurrences after 10 years.