ODIASP: Clinically Contextualized Image Analysis Using the PREDIMED Clinical Data Warehouse, Towards a Better Diagnosis of Sarcopenia

Katia Charrière (1) , Pierre-Ephrem Madiot (2) , Svetlana Artemova (1, 2) , Pungponhavoan Tep (1) , Christian Lenne (1) , Brigitte Cohard (2) , Alban Caporossi (1, 2, 3) , Isabelle Boudry (1) , Juliette Meyzenc (1) , Gilbert Ferretti (2) , Ivan Bricault (1, 2, 3) , Joris Giai (2, 4, 1) , Jean-Luc Bosson (1, 2, 3) , Eric Fontaine (2, 5) , Cécile Bétry (2, 4) , Alexandre Moreau-Gaudry (1, 2, 3)

1 CIC Grenoble - Centre d'Investigation Clinique [Grenoble]
2 CHUGA - Centre Hospitalier Universitaire [CHU Grenoble]
3 TIMC - Translational Innovation in Medicine and Complexity / Recherche Translationnelle et Innovation en Médecine et Complexité - UMR 5525
4 TIMC-MESP - Modélisation et Évaluation des données complexes en Santé Publique
5 LBFA - Laboratory of Fundamental and Applied Bioenergetics = Laboratoire de bioénergétique fondamentale et appliquée

Big Data and Deep Learning approaches offer new opportunities for medical data analysis. With these technologies, PREDIMED, the clinical data warehouse of Grenoble Alps University Hospital, sets up first clinical studies on retrospective data. In particular, ODIASP study, aims to develop and evaluate deep learning-based tools for automatic sarcopenia diagnosis, while using data collected via PREDIMED, in particular, medical images. Here we describe a methodology of data preparation for a clinical study via PREDIMED.

Mots clés: Clinical data warehouse; Deep Learning; Big Data; Sarcope- nia; Artificial Intelligence; Nutrition

Domaines: Statistiques [stat]; Informatique [cs]; Mathématiques [math]; Alimentation et Nutrition

Katia Charrière, Pierre-Ephrem Madiot, Svetlana Artemova, Pungponhavoan Tep, Christian Lenne, et al.. ODIASP: Clinically Contextualized Image Analysis Using the PREDIMED Clinical Data Warehouse, Towards a Better Diagnosis of Sarcopenia. Studies in Health Technology and Informatics, 2022, Studies in Health Technology and Informatics, 290, pp.1068-1069. ⟨10.3233/SHTI220271⟩. ⟨hal-03836846⟩