A trial is set to begin for an artificial intelligence (AI) tool designed to predict the risk of side effects in breast cancer patients
Researchers are exploring the potential of artificial intelligence (AI) to forecast the likelihood of breast cancer patients experiencing side effects from surgery or radiotherapy, with trials set to commence in the coming years. The aim is to offer more personalized care to patients by leveraging this technology.
Dr. Tim Rattay, a consultant breast surgeon and associate professor at the Leicester Cancer Research Centre, underscores the importance of addressing treatment side effects, such as scarring, skin changes, heart damage, and lymphedema. He emphasizes the significance of developing an AI tool to help inform doctors and patients about the risk of chronic arm swelling following breast cancer treatment, ultimately aiding in treatment decision-making and reducing side effects.
While AI is already being utilized in some areas of the NHS to aid in mammogram assessments, its application in predicting treatment side effects could enhance accuracy and offer tailored predictions for individual patients. Researchers trained the technology using data from 6,361 breast cancer patients to predict arm swelling up to three years post-surgery and radiotherapy.
The AI model considers various patient and treatment factors, including chemotherapy history, sentinel lymph node biopsy, and radiotherapy type, to provide predictions. Dr. Guido Bologna, co-investigator on the project, highlights that the model’s final iteration utilizes 32 different features to make predictions, offering a comprehensive assessment.
Dr. Rattay emphasizes that the AI tool is explainable, meaning it provides reasoning behind its decision-making process. This transparency not only aids doctors in decision-making but also facilitates clear communication with patients.
The current AI model will be integrated into software for evaluations by doctors and patients, undergoing testing in a clinical trial called the PRE-ACT project. Patient recruitment from the UK, France, and the Netherlands will commence later this year, with the aim of enrolling 780 participants by early 2026 for a two-year follow-up period. Additionally, the research team is working on expanding the technology to predict other side effects, including skin and heart damage.
Dr. Simon Vincent from Breast Cancer Now underscores the urgent need for research to improve breast cancer treatments, considering the high number of diagnoses annually in the UK. The exploration of AI in this context offers promising prospects for enhancing patient care and treatment outcomes.
