Breast Cancer Screening

Breast Cancer is a major health concern.  Is one of the most frequently diagnosed type of cancer in women and is also among the top leading cause of cancer-related death among women. 
 

 
In contrast with other cancers, where a single risk factor can explain most cases, breast cancer is related with multiple risk factors that can be modifiable and non-modifiable. Among the modifiable factors, the roles of lifestyle and nutritional aspects have been investigated. The International Agency for Research on Cancer (IARC) is a specialized cancer agency of the World Health Organization (WHO) and have been coordinated The European Prospective Investigation into Cancer and Nutrition (EPIC) Study.  
 
The EPIC dataset is one of the largest cohort studies in the world, with more than a half million participants recruited from 10 Western European countries, with extensive information on nutrition, lifestyle and environmental factors. 

In this project, IARC is collaborating with CERN, to develop an AI-based algorithm to predict breast cancer risk, based mainly in modifiable factors, using the EPIC dataset. Several classical and modern machine learning and deep learning algorithms have been extensively explored, along with explainability methods to investigate and identify the variables most strongly associated with the models’ predictions. 

The CAFEIN^® platform will be essential to simulate federated learning on this dataset and may provide insights for the future application in other countries.  This study aims to help to support clinical care optimization, screening protocols and tailored disease management strategies.