Search

Abstract Introduction The final aim of the EXPERIENCE project is to enable individuals to record and share extended-personal realities in Virtual Reality (VR) - which entails the consideration of a person’s neurophysiological, psychological, and cognitive states. One prospective application is using this technology to aid in assessing symptoms of affective disorders. Objectives The objective is to test the ability of a pre-designed VR environment to differentiate between individuals with depressive symptoms and healthy controls (HCs) via machine learning algorithms. Methods Conducted as a pilot study in Italy, we recruited 100 volunteers, comprising 50 HCs and 50 individuals with moderate depressive symptoms assessed via the PHQ-9. Through a 40–60-minute VR engagement, comprehensive data on cognitive (inc. cognitive flexibility, sustained attention, working memory, processing speed), behavioral (exploration, attentional bias), and physiological (heart-rate variability, skin conductance) variables was collected. Subsequently, an explainable artificial intelligence model (xAI) was trained on data from 80% of the sample and tested on the remaining 20% in terms of accuracy for between-group classification. Results Following an iterative process that considered both the importance assigned to each variable in the different models and the theoretical relevance of these variables to depression the final model achieved an average accuracy of 71% (with individual trials ranging from 64.5% to 77.1%). Key predictors included exploratory behaviors and heart-rate variability during both exploration and cognitive tasks. Conclusions These results are comparable, however remain below the levels of accuracy achieved based on fMRI and DTI data alone (around 80%). Nonetheless, the EXPERIENCE system, slated for refinement beyond this pilot phase, shows potential in integrating multimodal data for evaluating affective disorder symptoms, aiming for a more objective screening and diagnostic approach at a lower cost. Acknowledgement The EXPERIENCE project is funded by the European Commission H2020 Framework Program, Grant No. 101017727. Disclosure of Interest None Declared

Abstract Endocrine disruptors (EDs) are exogenous compounds that interfere with the hormone system, affecting human health and environment. Specific legislative obligations have been introduced in the European Union (EU) to gradually eliminate EDs in water, industrial chemicals and pesticides. However, identification of EDs is the first and essential step towards regulation and appropriate risk management. Scientific criteria and guidance for ED assessment have recently been established for pesticides in the EU. In this project, the ED properties of the non‐pesticide chemical Bisphenol AF (BPAF), analogue and potential substitute of Bisphenol A were evaluated by the application of the EU criteria and guidance in the frame of human health risk assessment. A data dossier was built by a systematic literature review (WOS, Scopus, Pubmed, Embase), title/abstract screening (RAYYAN) and full‐text examination. All relevant information was extracted and systematically reported, and reliability and relevance of data were assessed (SciRAP). Data were synthesised into lines of evidence for (i) endocrine activity, (ii) adversity and (iii) general toxicity, and weight of evidence evaluation was applied. The initial analysis of the evidence showed potential endocrine adverse effects and endocrine activity, meeting the ED criteria and leading the assessment to the mode of action (MoA) analysis. The biological plausibility of the link between the adverse effects and the endocrine activity was investigated based on current scientific knowledge. Empirical support for dose–response and temporal concordance was evaluated, and the key events were assessed in terms of essentiality, consistency, analogy and specificity. Finally, an overall conclusion of the ED properties of BPAF was drawn. The EU criteria and guidance for EDs assessment were successfully applied to BPAF demonstrating its endocrine activity and adversity based on weight of evidence methodology and MoA analysis. The Fellow greatly increased her knowledge and hands‐on experience on ED assessment in the EU regulatory context contributing to implement transparency and structure in health risk assessment.