Schizophrenia affects a staggering 21 million people worldwide, with 80% of these citizens suffering from a relapsing disease, putting their health and safety at enormous risk. Timely detection of these psychotic relapses would require very frequent contact with clinicians, which is neither desirable nor feasible. An accurate online relapse predictor could alert clinicians of subtle deterioration, which enables timely intervention and allow safe discontinuation of long-term medication, which so many affected citizens desire. Our Consortium demonstrated that subtle alterations in speech carry a predictive signal for psychosis onset. This project will develop an AI monitoring system that leverages spoken language processing (SLP) and natural language processing (NLP) of speech recorded at home to calculate the relapse risk. The monitoring tool we develop will be validated retrospectively in a longitudinal cohort, cross-sectionally, across six languages, after which it will be tested prospectively in a multicenter randomized trial, with the end goal of improving functional and clinical outcomes of those affected by schizophrenia. Developing such a system for exceptionally vulnerable people requires ‘buy-in’ from clinicians and mental health care service users, namely trust. A lack of trust is the biggest obstacle to the real-world implementation of a speech-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 service users and their carers. TRUSTING generates the scientific and social foundation for disruptive technology to deliver the unmet promise of an equitable and just form of healthcare for people at risk of relapse.

ImpleMentAll will develop, apply, and evaluate tailored implementation strategies in the context of on-going eHealth implementation initiatives in the EU and beyond. Common mental health disorders account for an alarming proportion of the global burden of disease. Being regarded as an evidence-based psychotherapeutic eHealth intervention, Internet-based Cognitive Behavioural Therapy (iCBT), has the potential to answer to this societal challenge by providing an efficacious and efficient treatment from which more people can benefit. As a result, various iCBT implementation projects are currently conducted across the world. We propose to use this natural laboratory to develop and evaluate a toolkit for tailored implementation strategies that is expected to make implementation trajectories more efficient. The objectives for ImpleMentAll are: 1) To develop a generic Integrated Theory-based Framework for Intervention Tailoring Strategies (the ItFits-toolkit) for data-driven tailored implementation of evidence-based eHealth services. 2) To demonstrate the impact of the ItFits toolkit on the implementation of eHealth for common mental disorders, in 9 European countries, 2 LMIC, and Australia. 3) To disseminate the validated toolkit in various healthcare contexts across Europe. ImpleMentAll is a true multidisciplinary international collaboration that unites key experts in clinical practice, health innovation, clinical research, and implementation science. Combined with it’s unique setup, ImpleMentAll will be able to test if tailoring implementation strategies lead to more efficient implementation. The resulting ItFits-toolkit will enable data driven evaluation of eHealth implementation projects in terms key performance indicators for process, effectiveness, and efficiency outcomes. Its methods, materials, and strategies will provide concrete guidance on tuning implementation interventions to local determinant of practice across a variety of health care systems.

A key problem in Mental Health is that up to one third of patients suffering from major mental disorders develop resistance against drug therapy. However, patients showing early signs of treatment resistance (TR) do not receive adequate early intensive pharmacological treatment but instead they undergo a stepwise trial-and-error treatment approach. This situation originates from three major knowledge and translation gaps: i.) we lack effective methods to identify individuals at risk for TR early in the disease process, ii.) we lack effective, personalized treatment strategies grounded in insights into the biological basis of TR, and iii.) we lack efficient processes to translate scientific insights about TR into clinical practice, primary care and treatment guidelines. It is the central goal of PSYCH-STRATA to bridge these gaps and pave the way for a shift towards a treatment decision-making process tailored for the individual at risk for TR. To that end, we aim to establish evidence-based criteria to make decisions of early intense treatment in individuals at risk for TR across the major psychiatric disorders of schizophrenia, bipolar disorder and major depression. PSYCH-STRATA will i.) dissect the biological basis of TR and establish criteria to enable early detection of individuals at risk for TR based on the integrated analysis of an unprecedented collection of genetic, biological, digital mental health, and clinical data. ii.) Moreover, we will determine effective treatment strategies of individuals at risk for TR early in the treatment process, based on pan-European clinical trials in SCZ, BD and MDD. These efforts will enable the establishment of novel multimodal machine learning models to predict TR risk and treatment response. Lastly, iii.) we will enable the translation of these findings into clinical practice by prototyping the integration of personalized treatment decision support and patient-oriented decision-making mental health boards.