Prediction of radiotherapy side effects using explainable AI

In the upcoming 3 years, the PRE-ACT consortium is going to predict the risk of radiotherapy side effects, including arm lymphedema in breast cancer patients by using explainable Artificial Intelligence (AI).

Introduction

To tackle this problem, the PRE-ACT consortium combines the multi-faceted expertise in computing, AI, radiation oncology, medical physics, genetics, psychology and health economics. The clinical impact will be investigated in an interventional clinical randomized controlled phase III trial to support important treatment decisions regarding the loco-regional irradiation of breast drainage lymph that lie close to the nerves, lymphatic and blood vessels going into the arm. The outcomes of the project will advance an array of fields such as AI applications to medicine, personalized radiotherapy, identification of risk factors and biomarkers and new clinical trial designs for AI prediction.

Horizon Europe Grants

This work was conducted in the context of the Horizon Europe project PRE-ACT (Prediction of Radiotherapy side effects using explainable AI for patient communication and treatment modification). Ιt was supported by the European Commission through the Horizon Europe Program (Grant Agreement number 101057746), by the Swiss State Secretariat for Education, Research and Innovation (SERI) under contract number 22 00058, and by the UK government (Innovate UK application number 10061955).

Full image