PRE-ACT

Prediction of Radiotherapy side Effects using explainable AI for patient Communication and Treatment modification

Radiotherapy is a common cancer treatment, but some patients experience side effects. In the case of breast cancer, these side effects may include breast atrophy, arm lymphoedema or heart damage. One of the objectives of this project is to predict the risk of arm lymphoedema, a condition that significantly impacts the daily lives of those affected.

The project relies on datasets from three patient cohorts to design and implement an AI tool that predicts the risk of side effects. At HEPIA, we are developing this tool specifically for lymphoedema and provide explanations of the predictions obtained by AI models in the form of rules similar to those used in expert systems. Predicting the risk of side effects and explaining the contributing factors facilitates shared decision-making between patients and doctors.