TRUSTING (101080251)

Basic information

Investigator: MUDr. Filip Španiel, Ph.D.
Main recipient: Academisch Ziekenhuis Groningen
Co-recipient: National Institute of Mental Health (NIMH) and partners
Research period: 1/7/2023 – 31/1/2028
Total budget: 146,208,059 CZK
NIMH budget: 10,307,444 CZK
Supported by: European Commision

Annotation

Psychosis affects ~3% of the population worldwide, with 80% of these citizens suffering from a relapsing disease course that puts them at enormous health and safety risks. Timely detection of these medical events is difficult because of a variety of medical and human resource reasons. An accurate relapse predictor would enable to prevent psychotic relapse through timely intervention and allow abandoning long-term medication and its side effects. The aim of this project is to develop an AI monitoring system that leverages natural language processing (NLP) of speech for this purpose. Our Consortium has previously demonstrated that subtle alterations in spontaneous speech carry a predictive signal for psychosis. The monitoring system developed here will be validated cross-sectionally, across multiple languages, and retrospectively in a longitudinal cohort, after which it will be tested in a multicenter clinical trial, with the end-goal of improving clinical outcomes. To develop such a system for this medical problem in exceptionally vulnerable people requires ‘buy in’ from clinicians and patients, namely trust. A lack of trust is the biggest obstacle to the real-world implementation of an AI-based monitoring system. TRUSTING will develop a framework that systematically ensures addressing all the criteria for trustworthy AI put forward by the EU. This will ensure an empirically based and validated tool that can reliably detect pending relapse. As the core philosophy of trustworthiness is part of every aspect of the project, it will be a system more likely to be welcomed and embraced by patients and their carers. TRUSTING will generate the scientific and social foundation for disruptive technology to deliver the unmet promise of an equitable and just form of healthcare for mentally ill patients at risk of relapse.