HeKA is a common project-team of Inria, Inserm and Université Paris Cité. HeKA is affiliated with the “Centre de Recherche des Cordeliers” and Inria Paris.

HeKA is a multidisciplinary team composed of researchers, clinicians-researchers, teacher-researchers from Inria, Inserm, University Paris Cité and AP-HP, associated with departments of the European Hospital Georges Pompidou, Necker Hospital and the Imagine Institute. Our Research themes are biomedical informatics, biostatistics and applied mathematics for clinical decision support. In March 2022, the HeKA team relocated to PariSanté Campus, a hub where research teams, health-tech companies, health digital and innovation administrative agencies converge within a collaborative ecosystem.

Today, HeKA brings together a highly interdisciplinary and complementary group of experts with diverse skills in computer science, medical informatics, applied mathematics, public health, epidemiology, and biostatistics. Their collective mission is to develop methods, models, and tools with the overarching objective of creating, evaluating, and validating learning health systems, i.e., a health system that leverages clinical data collected to extract agilely and reliably novel medical knowledge that, in turn, continuously improves healthcare. We rely on the availability of EHRs (Electronic Health Records), clinical trials, cohorts and other linked data to develop models for stratification and prediction with the potential of improving the precision and the personalization of treatments, and in turn the quality of healthcare.

HeKA research activity follows three interdependent axes

(1) Patient phenotyping and representation learning, in order to go from patient data to patient representations.

(2) Stochastic and data-driven predictive models for decision guiding, to go from patient data to prediction and decision.

(3) Designs of next generation clinical trials, to go from models to improved patient-related knowledge.

Our team is involved in major National and European collaborative projects

The PEPR Digital Health, wich is a program centered around the development and exploitation of the concept of digital twin in health. HeKA is involved within multiple projects of the PEPR : (1) ShareFAIR, to learn protocols from clinical data collected along healthcare activity in EHRs to explicitize the medical decision processes and the management of particular conditions or (2) REWIND, to develop of new mathematical and statistical approaches for the analysis of multimodal multiscale longitudinal data to predict patient’s response

INVENTS, an European project aiming to provide clinical trial trialists, researchers and regulators with a global framework encompassing methods, workflows and evidence assessment tools to be implemented in orphan and paediatric drug development. This area of medicine evaluation has proven challenging for several reasons, among which are the small patient sample sizes, heterogeneity of patients and diseases and heterogeneity in disease knowledge. At the end of this 5 years project starting in 2024, the European industry will be able to exploit novel and improved clinical trial designs, in silico trials and RWD analysis approaches supporting drug development in RD.

Our research activity is developped through partnerships with innovative industrials and start-ups

Project COMBO with Sanofi, as well as the Health Data Hub and the Centre Léon Bérard. The objective of the project is to identify promising families of drug combinations in oncology using multisource and multi-modal data modelling and prediction, including RWD, and then use these models to determine dose-regimen and build dose-finding trial designs for the combinations to be evaluated through formal clinical trials

Cifre PhD grant partnerships have been established within the team, allowing doctoral students to be supervised by permanent researchers, clinician-researchers or teacher-researchers from HeKA.

Keywords: Data-driven medicine, Model-based medicine, Learning health system, Precision medicine, Knowledge acquisition, Representation learning, Predictive modelling, Next generation clinical trials, Small samples, Translational research, Electronic Health Records, Machine learning, Bayesian inference .

HeKA is both a reference of the Egyptian goddess of medicine and an acronym for Health data- and model- driven Knowledge Acquisition. HeKA is the follow-up of the Team 22 (Information Sciences to support Personalized Medicine) led by Prof. Anita Burgun at the “Centre de Recherche des Corderliers” (Inserm, Université Paris Cité).

Comments are closed.