Universiteit Leiden

nl en

New collaboration aims to predict cancer survival

Predicting cancer survival with machine learning, that is the aim of a new collaboration between the Mathematical Institute, the European Organisation for Research and Treatment of Cancer (EORTC) in Brussels and Leiden University Medical Center. The focus of this project is to characterise the model behaviour and to measure the performance of various machine-learning methods in predicting survival for bone tumor patients.


This research project considers various predictive models for modelling sarcoma survival and disease progression. Over the last decade interest and publications on machine learning (ML) approaches in medical and specifically cancer research has grown, with analyses chiefly involving data with large numbers of risk factors, such as genomic data. A very limited amount of this research has focused on survival outcomes specifically, and even less on clinical data with few prognostic factors. The scarce research in this area coupled with the increasing popularity of ML methods in general has prompted a study into the potential of ML for analysing clinical data with a small number of risk factors associated to survival.

Aims and approach

An in-depth comparison between traditional mathematical models employed to predict survival and ML methods – such as artificial neural networks and random survival forests – will be performed in an application and simulation study with the purpose of identifying advantages and pitfalls. Of particular interest is the trade-off between flexibility, interpretability, and model stability.

This is one of the projects of the DASPO group.


  • Associate Prof. Dr. M. Fiocco, Mathematical Institute Leiden University, Department of Biomedical Data Science Leiden University Medical Center & Princess Máxima Center for Pediatric Oncology Utrecht
  • Prof. Dr. H. Gelderblom, Department of Medical Oncology at the Leiden University Medical Centre
  • Dr. S. Litiere, Associate Head of statistics Department EORTC
  • G. Kantidakis PhD candidate 
This website uses cookies.  More information.