Presentation

Team presentation

The PreMeDICaL team (Precision Medicine by Data Integration and Causal Learning) is a joint team between Inria and Inserm (Idesp) located in Montpellier. It is composed of researchers in statistics, machine learning, AI, as well as clinicians. One unique aspect of our team is the presence of PhD students in applied mathematics who also hold medical degrees, combining medical expertise with AI research. These profiles are crucial for enhancing the adoption, utilization, and transfer of new technologies, as well as fostering innovation development.

 

We specialize in developing precision medicine methods through causal learning and federated learning, ensuring the confidentiality of medical data.Our objectives include accelerating the availability of targeted medications on the market and deploying decision support algorithms with highly accurate prediction confidence quantification. We contribute to bridging the gap between fundamental research and its effective utilization, particularly through software development and by involving all stakeholders (patients, clinicians, regulators, companies, etc.)

 

Research themes

PreMeDICaL has three main research axes:

  1. Personalized medicine by optimal prescription of treatment.

We develop causal inference techniques for (dynamic) policy learning (allocating the best treatment for each person at the right time), that handle missing values and leverage both RCTs and observational data. Using both data sources allow to better design future RCTs and in the longer term to rethink the evidence needed to bring treatments to the market and to do so more quickly.

    2. Personalized medicine by integration of different data sources.

We build predictive models for heterogeneous data: for instance, given monitoring data in continuous time, images and clinical data what is the risk for an event to occur? Is it useful to have all the sources or do they provide the same information? We additionally develop solutions to learn from decentralized data (federated learning), to handle missing values in a supervised learning setting and to improve the confidence of the outputs of the predictive models.

    3. Personalized medicine with privacy and fairness guarantees.

We develop approaches to ensure the confidentiality of medical data and guarantee that models do not leak sensitive information. We additionally build methods to handle fairness constraints to ensure that models exhibit similar performance across different population groups.

 

Premedical aim is to guide decisions made by clinicians and authorities and provides a unique opportunity for trans-disciplinary research and collaboration. Beyond methodological developments, innovative responses to the public health challenge first posed by respiratory allergies are targeted.

International and industrial relations

Industrial collaborations:  Adène, AdviceMedica, ALK,Capgemini Invent, Drago, Elixir, Quinten Health, Sanofi.

 
 

Comments are closed.