Project 11: Learning from multimodal medical records for better cancer management

Ndèye Maguette Mbaye

Advisor: Chloé-Agathe Azencott

Project description

The goal of this project is to develop and apply novel machine learning techniques to predict cancer outcome (for example, recurrence or survival) from multi-modal patient data (including, medical notes in natural languages and the outcome of various lab analyses, and multiple genomic data modalities, such as copy number variation, gene expression or epigenetic data). I will investigate mathematical and computational frameworks to represent and learn from such heterogeneous data, and apply them on real data available through collaborations with cancer hospitals.


  1. Learning from multimodal health data for improved Depression treatment
    Host: Max Planck Institute of Psychiatry
    Planned date: November 2020 – January 2021
  2. Inferring causal relations from health records
    Host: IBM
    Planned date: December 2021 – February 2022