Keynote by Dr. Weber on From Understanding to Dialogue: AI-based Models for Depression Evaluation, 18 November 2025
Tuesday, 18 November 2025, 4.15 pm CET, ZOOM
About Samantha Weber
Dr. Samantha Weber is a Postdoctoral Researcher at the University Hospital of Psychiatry in Zurich and the Faculty of Medicine, University of Zurich. She received her PhD in Neuroscience from the University of Bern in 2022, focusing on multivariate analyses of neurobiological and stress-related mechanisms underlying symptom formation in neuropsychiatric disorders, for which she was awarded twice. Her current research centres on the development of AI-powered tools for suicide prevention and depression assessment, with a strong focus on LLM fine-tuning, chatbot development, and clinical transition. Working at the intersection of AI and psychiatry, she aims to build bridges between computational methods and mental healthcare, ensuring that technological innovations address clinically relevant needs and are both safe and effective in real-world use. Her broader research vision is to advance responsible, data-driven psychiatry by developing patient-oriented AI systems that complement clinical expertise. Through close collaborations with clinicians and patients, her work seeks to translate advances in language modelling into digital therapeutics within suicide prevention in psychiatric care.
About the Lecture
As part of a larger interdisciplinary project (MULTICAST [https://www.multicast.uzh.ch/en.html]) on the prediction and treatment of suicidality, this lecture will give insights into how large language models can transform clinical depression assessment – from automated scoring to interactive interviewing. Starting with the limitations of traditional rating scales for depression assessment, Dr. Weber introduces MADRS-BERT, a fine-tuned BERT-based model for symptom-specific depression evaluation, and its clinical application within MADRS-Chat, an AI-based conversational system designed to conduct structured psychiatric interviews. Together, these projects exemplify how computational psychiatry can move from understanding to dialogue – from automated scoring to interactive, patient-centred assessments. The talk highlights both the technical development and the human evaluation of these tools, emphasising feasibility, acceptability, and the responsible integration of AI into psychiatric care.
We are pleased to invite you to join this guest lecture, which is part of our CDHI Lecture Series Digital Health Forum. Registration is not required. Please be aware that we will be recording this guest lecture and will be making it available in our teaching library. If you have any questions, please contact Victoria Brügger (victoria.bruegger@unisg.ch) prior to the start of the guest lecture.
Prof. Dr. Tobias Kowatsch, Associate Professor for Digital Health Interventions, Institute for Implementation Science in Health Care, University of Zurich; Director, School of Medicine, University of St.Gallen (HSG); Scientific Director, Centre for Digital Health Interventions (CDHI), ETH Zurich & HSG; Principal Investigator, Future Health Technologies programme, Campus for Research Excellence and Technological Enterprise (CREATE), Singapore-ETH Centre, Singapore
Prof. Dr. Elgar Fleisch, Professor of Information Management, ETH Zürich; Professor of Technology Management, University of St.Gallen; Advisory Board Member, CDHI, ETH Zürich & University of St.Gallen; Principal Investigator, Future Health Technologies programme, Campus for Research Excellence and Technological Enterprise (CREATE), Singapore-ETH Centre, Singapore
Prof. Dr. Florian von Wangenheim, Professor of Technology Marketing, ETH Zurich & Advisory Board Member, CDHI; Principal Investigator, Future Health Technologies programme, Campus for Research Excellence and Technological Enterprise (CREATE), Singapore-ETH Centre, Singapore
