Machine learning/statistical methods in cancer research

Our focus in cancer epidemiology lies in leveraging the potential of machine learning methodologies. Machine learning offers a promising avenue to unravel complex patterns and relationships within cancer data. The integration of advanced computational techniques with complex cancer data allows for a nuanced understanding of cancer dynamics, risk factors, and the interplay of diverse variables. Through machine learning algorithms, we aim to discern intricate patterns in large datasets, identifying novel biomarkers, elucidating predictive models, and optimizing interventions.


Lung cancer:

  • Machine learning-based immune phenotypes correlate with STK11/KEAP1 co-mutations and prognosis in resectable NSCLC: a sub-study of the TNM-I trial. Link to publication.
  • A Pragmatic Machine Learning Approach to Quantify Tumor-Infiltrating Lymphocytes in Whole Slide Images. Link to publication.
  • Artificial intelligence algorithm developed to predict immune checkpoint inhibitors efficacy in non–small-cell lung cancer. Link to abstract.
  • Integrative, multi-omics, analysis of blood samples improves model predictions: applications to cancer. Link to publication.

Skin cancer:

Breast cancer:

Other publications: