An international team of researchers is pioneering a new frontier in breast cancer treatment with the development of an AI tool aimed at predicting potential side effects in patients undergoing surgery and radiotherapy.
This innovation was announced by Dr. Tim Rattay at the 14th European Breast Cancer Conference in Milan, marking a significant step forward in personalized patient care.
Set to be tested in a clinical trial across France, The Netherlands, and the UK later this year, this AI tool stands out for its explainability.
It doesn’t just make predictions; it also provides the reasoning behind its decisions.
This transparency is crucial, as it helps doctors understand the tool’s recommendations, making it easier to discuss treatment options and potential side effects with patients.
The project, named PRE-ACT (Prediction of Radiotherapy side Effects using explainable AI for patient Communication and Treatment modification), is focused on enhancing the accuracy of side effect predictions for each individual.
It aims to mitigate long-term treatment consequences such as skin changes, scarring, lymphoedema (painful arm swelling), and even heart damage caused by radiation.
By leveraging data from three European datasets involving 6,361 breast cancer patients, the researchers trained machine learning algorithms to predict the risk of arm swelling up to three years post-surgery and radiotherapy.
The tool considers a range of patient and treatment features, such as chemotherapy history, sentinel lymph node biopsy, and radiotherapy type, to make its predictions.
With significant lymphoedema occurring in 6% of patients across the datasets, the AI demonstrated a high degree of accuracy, correctly predicting lymphoedema in 81.6% of cases and accurately identifying patients who would not develop it 72.9% of the time.
This technology not only aids in identifying patients at higher risk of lymphoedema, allowing for preventative measures like arm compression sleeves to be offered, but also enables discussions about treatment options tailored to reduce side effects.
As the PRE-ACT-01 clinical trial gears up, the AI model will be incorporated into software that can directly support doctors and patients in making informed decisions.
The trial also plans to collect additional data, such as genetic markers and imaging, to further refine the AI’s predictive capabilities, though these will not influence predictions in the initial trial.
Looking ahead, the trial aims to enroll around 780 patients by early 2026, with a follow-up period of two years.
This ambitious project exemplifies the power of international collaboration in harnessing AI to improve clinical outcomes, offering a more tailored approach to breast cancer treatment and patient care.
If you care about wellness, please read studies about how ultra-processed foods and red meat influence your longevity, and why seafood may boost healthy aging.
For more information about wellness, please see recent studies that olive oil may help you live longer, and vitamin D could help lower the risk of autoimmune diseases.
The research findings can be found in Cell Host & Microbe.
Copyright © 2024 Knowridge Science Report. All rights reserved.
