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:
- Personalized medicine through optimal treatment prescription
The objective is to develop causal inference techniques for dynamic policy learning—allocating the best treatment to each individual at the right time—by leveraging both experimental data from Randomized Controlled Trials (RCTs) and non-experimental data (e.g., observational data from Electronic Health Records, cohorts, etc.). Combining these data sources will enable better design of future RCTs and, in the longer term, may transform the standards of evidence required to bring treatments to market, potentially allowing for the launch of new drugs without traditional RCTs, and doing so more efficiently.
2. Personalized medicine through integration of diverse data sources
Our purpose is to learn (e.g. build predictive models) from heterogeneous data, such as continuous time monitoring data and static clinical data, and from decentralized data using federated learning while handling missing values and increasing the reliability and confidence of predictive model outputs.
3. Personalized medicine with privacy and fairness guarantees.
We seek to 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: Capgemini Invent, Drago, Elixir, L’Oréal, Sanofi, Theremia, Withings
Download the team presentation
