Obstructive sleep apnea (OSA) is associated with various negative health consequences including increased risk of heart disease, hypertension and daytime sleepiness causing road accidents. The economic burden of OSA is rising as almost 1 billion people worldwide are estimated to have OSA. The current diagnostic metric, however, relates poorly to these symptoms and comorbidities. It merely measures the frequency of breathing cessations without assessing OSA severity in any other physiologically relevant way. Furthermore, the clinical methods for analyzing PSG signals are outdated, expensive and laborious. Due to this, the majority of OSA patients remain without diagnosis or have an inaccurate diagnosis leading to sub-optimal treatment. Thus, it is evident that more personalized diagnostics are required including predictive and preventive health care and patient participation. The SLEEP REVOLUTION aims to develop machine learning techniques to better estimate OSA severity and treatment needs to improve health outcomes and quality of life. These techniques are implemented to high-end wearables developed in this project to alleviate the costs and increase the availability of PSGs. Finally, we aim to design a digital platform that functions as a bridge between researchers, patients and healthcare professionals. We will achieve these ambitious goals throughout extensive collaboration between sleep specialists, computer scientists and industry partners. The collaboration network consists of over 30 sleep centers working together to provide the needed retrospective data (over 10.000 sleep studies). The multi-center prospective trials involve experts and end-users to assess and validate the new SLEEP REVOLUTION diagnostic algorithms, wearables and platforms. With the commitment of the European Sleep Research Society and Assembly of National Sleep Societies (over 8000 members), we have the unique possibility to create new standardized guidelines for sleep medicine in the EU.

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.

Relieving serious health-related suffering for patients in palliative and end-of-life care, be it physical, psychological, social, or spiritual, is a global ethical responsibility. However, the profound psycho-emotional and existential distress entailed by such suffering, despite often being an enormous burden for both patients and their loved ones, remains a field largely overlooked by health care providers and the scientific community. Those people may develop mood or anxiety disorder for which neither non-pharmacological nor pharmacological interventions exist. In this context, we believe it is now time to target these unmet needs in the palliative care population. We want to initiate a paradigm shift at the boundaries between palliative care, psychiatry, psychology, neuroscience, and spiritual care. Our starting point is the preliminary results being reported for administration of psilocybin, the main psychoactive compound of so-called ‘psychedelic mushrooms’, in patients with depression. The objective of our project is thus to examine the clinical effect of a cutting-edge, individualised and patient-centred, open and standardised Psilocybin Therapy, addressing these unmet needs of patients in palliative care. We will show high quality evidence via a multi-centre Randomised Clinical Trial of the value of our therapeutic model in patients (and for the following four conditions: COPD, Atypical Parkinsonian Disorders, ALS, and Multiple Sclerosis), their loved ones and care providers, in a diverse sample of the European population, in addition to better understand the mechanisms of therapeutic change of our model. Finally, our project will establish a sustainable, multi-disciplinary, ecosystem of key European stakeholders jointly contributing to the medical use of psychedelic research and innovation, paving the way towards an ethical and cost-effective deployment of such a new line of care for patients in European palliative care service providers.

The richness of chemical signalling in the brain supports the flexible neural dynamics required for adaptive behaviour. The NMDA receptor, one of the most ubiquitous receptors in the brain, controls synaptic plasticity and mediates learning and memory formation. Its dysfunction is theorised to be one of the mechanisms of schizophrenia. Profiling the changes and dysfunctions of ion channel receptors can elucidate the biological substrate of functional brain impairments and facilitate individual patients’ personalised treatment strategies. The aims of this project are two-fold: methodological—developing a robust and translational dynamic causal model able to profile NMDA-R dynamics—and clinical—studying NMDA-R dysfunctions and their trajectory within a longitudinal study of a large cohort of schizophrenic patients. The NMDA-R DCM will first be developed and validated on animal data with a high signal-to-noise ratio. The ground-truth dataset comes from a repeated measures study, with one of the measurements involving a pharmacological intervention using an NMDA-R blocker. Next, the model will be translated to human rsEEG data with the same within-subject design. Finally, the validated NMDA-R DCM will be applied to schizophrenic patients. The prospective design of the study will allow for the assessment of the predictive power of generative embedding for individual patients’ clinical trajectories. This approach might help clinicians predict clinical outcomes and tailor treatments to individual patients. We plan to disseminate the project’s results through two main channels: peer-reviewed publications of both methodological and clinical advancements, and by sharing the relevant source code for the analyses, including the envisioned additions to the TAPAS package, thereby fostering replicability, reproducibility, and rapid distribution within the community. Ultimately, this project aims to help establish computational assays as a standard procedure in clinical practice.

The European Commission’s latest strategy for fighting child sexual abuse highlights a harsh reality that, globally, we are ‘losing the battle’ against online child sexual abuse and exploitation (OCSEA). Various projects funded through the EU are working diligently to identify the source of CSAM on both the Clearnet and Darknet and are establishing stronger awareness of the needs and requirements of LEAs to fight the overloading volume of images, text, media files, etc. However, the IOCTA 2021 report also brings a chilling honesty that the prevalence of materials shows no sign of slowing or stabilising. The adage that prevention is better than the cure never seemed more fitting. The 2PS project condemns all forms of sexual abuse and exploitation – and there are no excuses that justify behaviours and actions that harm or victimise children. However, to reduce the number of abused children and those at risk of exploitation, we need to address various challenges. Several of those relate to people with a sexual interest in children and their needs to divert them from abusing. 2PS, which stands for Prevent & Protect Through Support is a highly innovative action offering a paradigm shift in the approach to tackling child sexual abuse and exploitation (CSAE) across Europe. The highly qualified and diverse consortium – together with leading global actors – are committed to laying the foundations for new coherent modus operandi that complement the reactive approaches currently favoured. This is achieved by addressing the support needs of people with a sexual interest in children and people who feel they might offend. We will share the best practices for guidance, therapy and treatment methods – combined with new training and awareness for frontline support workers and LEAs. We aim to move preventive actions to the forefront, offering alternative courses of action to existing offenders and people who fear they might offend– including people with a sexual interest in children.