MePheSTO – Digital Phenotyping 4 Psychiatric Disorders from Social Interaction
Members – 2020-2023
INRIA project lead:
DFKI project lead:
Other INRIA/DFKI participants:
- Alexandra König – STARS team
- Rachid Guerchouche – STARS team
- Hali Lindsay – COS, Saarbruecken
- Andrey Girenko – COS, Saarbruecken
- Michel Musiol – SEMAGRAMME team
- Nice University Clinic (Prof. Dr. Philippe Robert, University Côte d’Azur)
- University Clinic of Saarland (Prof. Dr. Matthias Riemenschneider)
- Centre Psychothérapique de Nancy (Prof. Dr Vincent Laprevote)
- Dept. Of Psychiatry, University of Oldenburg, Karl Jaspers Klinik (Prof. Dr. Dr. René Hurlemann)
Contact : maxime.amblard[at]univ-lorraine.fr
MePheSTO is an interdisciplinary research project that envisions a scientifically sound methodology based on artificial intelligence methods for the identification and classification of objective, and thus measurable, digital phenotypes of psychiatric disorders. MePheSTO has a solid foundation of clinically motivated scenarios and use-cases synthesized jointly with clinical partners. Important to MePheSTO is the creation of a multimodal corpus including speech, video, and biosensors of social patient-clinician interactions, which serves as the basis for deriving methods, models and knowledge. Important project outcomes include technical tools and organizational methods for the management of medical data that implement both ELSI and GDPR requirements, demonstration scenarios covering patients’ journeys including early detection, diagnosis support, relapse prediction, therapy support, an annotated corpus, Ph.D. theses, and publications. MePheSTO builds a joint DFKI-INRIA workforce – the foundation for future R&D and innovation projects.
The MePheSTO project has been designed to significantly advance the state-of-the-art knowledge and lay a methodological foundation for technology development in the area of computer- supported diagnostics and disease handling for psychiatric disorders such as mental, affective and mood illnesses/disorders. By leveraging modern artificial intelligence methods, this project combines techniques from fields including, but not limited to, computer vision, computational linguistics, knowledge engineering, as well as behavioral science and applies them in several clinical use cases.
Therefore, the overall project goal is to develop a framework/methodological basis for scientifically sound validation of digital phenotypes for psychiatric disorders based on multimodal input, including speech, video, and bio-signals from clinical social interactions.