TRUSTING Project Showcased at International Conferences in March 2026
At the end of March 2026, the TRUSTING project gained strong visibility across two major international conferences, reinforcing its role in advancing innovative and trustworthy approaches in mental health research. From 25–29 March 2026, TRUSTING was represented at the Schizophrenia International Research Society (SIRS) Conference in Florence. The event connected leading experts in psychosis research, […]
Can Speech Alone Reveal Psychosis Symptoms? TRUSTING Study Shows Promising Results
The EU-funded TRUSTING Project has achieved a major research milestone in Work Package 2 (WP2). Showing that speech recordings alone can help predict symptom severity in people living with psychosis, without analysing what is actually being said. Predicting Psychosis Symptoms Using Speech Audio Only In a large international, multi-centre retrospective study covering ten languages. Researchers […]
Inside TRUSTING: New Video Series Shows How AI and Speech Could Transform Psychosis Care
How can everyday speech help predict relapse in psychosis? And how can artificial intelligence support clinicians and patients in identifying early warning signs in a safe and trustworthy way? To answer these questions, the TRUSTING project has released two new videos offering an inside look at the clinical study and the technology behind its speech-based […]
Recruitment Begins Across Europe in Major Clinical Study Milestone
The EU-funded TRUSTING Project has reached a major new phase as participant recruitment officially begins across international study sites under Work Package 4 (WP4). Ethical Approval Completed Across All TRUSTING Study Sites A key milestone for the TRUSTING clinical study has been the successful completion of ethical approval at all participating research centres. This confirms […]
TRUSTING Research Takes Centre Stage at World Congress of Psychiatry 2025
As part of Work Package 3 activities, the TRUSTING research project gained international visibility in October 2025 when its work on trustworthy speech technology in mental health research was presented at the World Congress of Psychiatry in Prague. During the congress, Dr. Sandra A. Just delivered a talk titled “How to evaluate the real-world impact […]
Help Improve Psychotic Relapse Detection: TRUSTING Launches New European Surveys
Two new European surveys have been launched as part of the TRUSTING Project, an EU-funded research initiative aiming to improve early detection and prevention of psychotic relapse using innovative digital tools and artificial intelligence. The surveys invite both service users and clinicians to share their experiences and professional practices in assessing relapse risk. Insights gathered […]
Prompt Engineering an Informational Chatbot for Education on Mental Health Using a Multiagent Approach for Enhanced Compliance With Prompt Instructions: Algorithm Development and Validation
Background:People with schizophrenia often present with cognitive impairments that may hinder their ability to learn about their condition. Education platforms powered by large language models (LLMs) have the potential to improve the accessibility of mental health information. However, the black-box nature of LLMs raises ethical and safety concerns regarding the controllability of chatbots. In particular, […]
Approximating the semantic space: word embedding techniques in psychiatric speech analysis
Large language models provide high-dimensional representations (embeddings) of word meaning, which allow quantifying changes in the geometry of the semantic space in mental disorders. A pattern of a more condensed (‘shrinking’) semantic space marked by an increase in mean semantic similarity between words has been recently documented in psychosis across several languages. We aimed to […]
A single composite index of semantic behavior tracks symptoms of psychosis over time
Semantic variables automatically extracted from spontaneous speech characterize anomalous semantic associations generated by groups with schizophrenia spectrum disorders (SSD). However, with the use of different language models and numerous aspects of semantic associations that could be tracked, the semantic space has become very high-dimensional, challenging both theoretical understanding and practical applications. This study aimed to […]
How the TRUSTING App Assesses Relapse Risk Through Speech
Can language reveal early signs of relapse in psychosis and how can AI help assess risk in a safe and trustworthy way? Roya Hüppi, MSc, PhD student at the Psychiatric University Clinic Zurich and the University of Zurich, explains the scientific thinking behind TRUSTING’s speech-based approach. Roya discusses: This video highlights how TRUSTING combines clinical […]
