Deep Care: Patient Empowerment via a Participatory Health Project


The 'Deep Care' concept is developed with the aim of establishing synergies between 'Artificial Intelligence' (AI) and 'Care' in the sense of 'taking care of' and 'caring for' which defines an integrative vision of health, going far beyond medicine.

The general objective of the chair is to fulfill the promise of the World Health Organization (WHO) in the Ottawa charter defining health as “[the capacity of] an individual or group [to] be able to identify and to realize aspirations, to satisfy needs, and to change or cope with the environment”. Based on the principles of a predictive, personalized, preventive and participatory (4P) vision of medicine [Hood L. et al. Science 2004, Zerhouni E. et al. NEJM 2005] the Deep Care Chair assumes that AI can play a "deep" role in the integrative vision of healthcare.

The Deep Care chair focuses its efforts on Grenoble’s strong added-value in AI for Health, with the main objective to explore the hypothesis of empowerment of health and healthcare systems through the development of tools and methods derived from AI. The Deep Care chair is structured according to the four following tasks :
  • T1, Empowerment by smart data capture, focusing on the challenge of capturing information in real-life conditions, including at work. This is today a blind spot. The Deep care chair plans to design original approaches (including novel miniaturized sensors) to capture as well elements of social interaction, physiological data, weak signals of risks, characteristics of the use of medical devices, etc.
  • T2, Empowerment by smart data fusion, is to develop methods (combining mathematical and computer science skills) to mine multimodal data bases to transform into high-level information and knowledge the very heterogeneous and complex data acquired by T1, merging them with already existing data bases.
  • T3, Empowerment by Health Institution Optimization, is expected to transform the expertise acquired in T2 into decision-making tools targeting both individual life-style and work-style, and hospital organization (with methods ranging from cooperation fluidification to continuing education or novel care-cost reimbursement models).
  • T4, Empowerment of individual and collective membership models for change.
Expected results of the Deep Care chair concern the development of models and tools that will be able to offer everyone the opportunity to build a participatory health project, based on a real empowerment of complex health systems (e.g., more effective cooperation between patients and healthcare teams, more relevant healthcare organizations).

The strength of the Deep Care chair lies in the truly possibilities of multi- and interdisciplinary synergies provided by the academic and industrial environment of Grenoble around AI and health, and also regarding the historical experience and competencies of the TIMC-IMAG laboratory. In addition, 47 researchers and industrial companies involve as the human task force of the Deep Care chair.


Since its creation in 2019, June, the Deep care chair has already provided significant research activities, including highlights of multi- and interdisciplinary interests (PREDIMED as one of the only four authorized health data lake projects in France by the CNIL, a systematic search of partnerships with clinical units from the university hospital of Grenoble Alpes carried out in order to orient research objectives toward real needs and innovative models), several research projects have get funding or significant partnerships between academic and industrial companies (8 have already signed and two additional are undergoing signature), three startups are already created, and 2 patents were taken.


The Deep Care chair has already organized or contributed to organize 8 events, including the first Winter School on AI and Health, giving strong visibility for the chair (438 students registered, including over 100 internationals from 31 countries in addition to French students).
In addition, members of the chair have contributed to 4 conferences.


  • C. Cancé, C Lenne, S Artemova et al. Hypergraph based data model for complex health data exploration and its implementation in PREDIMED Clinical Data Warehouse, to be published in MEDINFO2021 proceedings

  • K. Charrière, PE Madiot, S Artemova et al. ODIASP: clinically contextualized image analysis using the PREDIMED clinical data warehouse, towards a better diagnosis of sarcopenia, to be published in MEDINFO2021 proceedings

  • S. Artemova et al. COVID-19 geographical maps and Clinical Data Warehouse PREDIMED, to be published in MEDINGO 2021 proceedings

  • J. L. Bosson et al. A program centered on smart electrically assisted bicycle outings for rehabilitation after breast cancer: a pilot study”, to appear in Medical Engineering & Physics, (2022)

  • J. L. Bosson et U. von Schenck, Utilisation des données pour améliorer la qualité et la sécurité des soins en prévenant les événements indésirables, symposium Les systèmes d’information apprenants pour une aide à la décision de confiance en santé, Rennes, 30/11/21

  • M. Cuggia et A. Moreau-Gaudry, Les systèmes d’information apprenants, un défi pour nos établissements de santé, symposium Les systèmes d’information apprenants pour une aide à la décision de confiance, Rennes, 30/11/21

  • Struber, L., Ledouit, S., Daniel, O., Barraud, P-A., & Nougier, V. (2021). Reliability of human running analysis with low-cost inertial and magnetic sensor arrays. Sensors. 21, 13, 15299-15307

  • M. Calka, P. Perrier, J. Ohayon, C. Grivot-Boichond, M. Rochette, Y. Payan, Machine-Learning based model order reduction of a biomechanical model of the human tongue, Computer Methods and Programs in Biomedicine,, (2021)

  • Petit P, Bosson-Rieutort D, Maugard C, Gondard E, Ozenfant D, Joubert N, François O, Bonneterre V. The TRACTOR Project: TRACking and MoniToring Occupational Risks in Agriculture Using French Insurance Health Data (MSA). Ann Work Expo Health. 2021 Sep 25:wxab083. 

  • F. Ghayem, B. Rivet, R. Cabral Farias, and C. Jutten, “Gradient-based algorithm with spatial regularization for optimal sensor placement,” in Proc. IEEE Int. Conf. Acoustics, Speech, and Signal Processing (ICASSP), Barcelona, Spain, May 2020, pp. 5655–5659.

  • S. Noorzadeh, B. Rivet, and C. Jutten, “3D interface for P300-speller BCI,” IEEE Transactions on Human-Machine Systems, 2020, 

  • C. Dopierala et al., "A new gastric impedancemeter for detecting the development of a visceral edema: a proof-of-concept study on an experimental endotoxemic shock," 2020. 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Montreal, QC, Canada, 2020, pp. 4433-4436.

  • F. Ghayem, B. Rivet, R. Cabral Farias, and C. Jutten, “Optimal sensor placement for signal extraction,” in Proc. IEEE Int. Conf. Acoustics, Speech, and Signal Processing (ICASSP), Brighton, UK, May 2019, pp. 4978–4982.

  • Pagonis D, Januel JM, Schieborr U, Mogenet A. Co-presentation (TIMC/Elsevier).  Développement d'un modèle de "deep learning" pour évaluer la sécurité des patients. Symposium IA, big data et aide à la décision en santé : de la théorie aux preuves, scientifiques et terrain. 03 décembre 2019, Institut Curie, Paris.

  • Achard P, Maugard C, Cancé C, Spinosi J, Ozenfant D, Maître A, Bosson-Rieutort D, Bonneterre V. Medico-administrative data combined with agricultural practices data to retrospectively estimate pesticide use by agricultural workers. J Expo Sci Environ Epidemiol. 2020 Jul;30(4):743-755. doi: 10.1038/s41370-019-0166-x. Epub 2019 Sep 4. PMID: 31484997.

  • Cindy Dopierala, Pierre-Yves Guméry, Mohamed-Ridha Frikha, Jean-Jacques Thiébault, Philippe Cinquin, François Boucher. Digital Implantable Gastric Stethoscope for the detection of early signs of acute cardiac decompensation in patients with chronic heart failure. Medinfo 2019, electronic proceedings.

  • C. Dopierala et al., "A novel bimodal stethoscope for gastric collection of heart sounds: preliminary results," 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Berlin, Germany, 2019, pp. 4926-4929, doi: 10.1109/EMBC.2019.8857315.

  • Christophe Cancé, Pierre-Ephrem Madiot, Christian Lenne, Svetlana Artemova, Brigitte Cohard, Marjolaine Bodin, Alban Caporossi, Jean-François Blatier, Jerôme Fauconnier, Frédérique Olive, Daniel Pagonis, Dominique Le Magny, Jean-Luc Bosson, Katia Charriere, Ivan Paturel, Bruno Lavaire, Gabriel Schummer, Joseph Eterno, Jean-Noël Ravey, Ivan Bricault, Gilbert Ferretti, Sébastien Chanoine, Pierrick Bedouch, Emmanuel Barbier, Julien Thevenon, Pascal Mossuz, Alexandre Moreau-Gaudry, " Cohort Creation and Visualization Using Graph Model in the PREDIMED Health Data Warehouse". Medinfo 2019, Studies in Health Technology and Informatics.

Published on  January 23, 2024
Updated on January 23, 2024