The workshop is organized by the SPS Data Science Initiative and endorsed by IEEE Brain and IEEE AgeTech Initiatives.
The workshop is organized by the IEEE SPS Data Science Initiative (DSI) as part of the Data Science and Learning Workshop (DSLW) series.
The workshop will bring together researchers developing multimodal AI methods for mental healthcare using speech, language, video, behavioral signals, mobile and wearable sensing, electroencephalography, and structural and functional neuroimaging.
The workshop will foster interdisciplinary collaboration across signal processing, machine learning, medicine, and healthcare. It will promote reproducible, clinically relevant AI for mental healthcare across the lifespan, including for older adults. The workshop is endorsed by IEEE Brain and IEEE AgeTech Intiatives.
Workshop Composition
Keynote speakers
Contributed talk of full papers (to appear in IEEEXplore).
Experts panel
Poster session of last-minute contributions (only abstract required, will not appear in IEEEXplore)
Shrikanth (Shri) Narayanan, University of Southern California (USC), USA
Mohsen Naqvi, Newcastle University, UK
Alex Mihailidis, AGE-WELL, Canada
Tülay Adali, UMBC, USA
Aristotle Voineskos, Center for Addiction and Mental Health, Canada
David Linden, Maastricht University, The Netherlands
Vince D. Calhoun, TReNDS (GSU, GATech, Emory), Atlanta, Georgia, USA
Submit papers through the ICASSP-2027 paper management system.
Paper Submission URL
Paper Revision URL
The papers should follow the ICASSP-2027 rules for paper style, format, and length
(paper submission guidelines).
Accepted papers will be included in ICASSP-2027 proceedings and will be available on IEEEXplore.
Workshop Paper Submission Deadline:
Wednesday, November 11, 2026
The topics covered by the workshop include, but are not limited to:
Mental health epidemiology and societal and economic impact
Limitations of current diagnostic methodologies in the era of digital health
Community-based mental healthcare using speech, language, video---captured by wearable, mobile, and behavioral sensing
Multimodal mental health datasets, benchmarking, privacy, and ethical data sharing
Structural and functional MRI, EEG, and multimodal neuroimaging
Modeling of brain dynamics
Behavioral and physiological paradigms and beyond-mental health screening
AI and personalized mental healthcare
Predictive modeling for diagnosis, prognosis, and treatment response
Explainable, trustworthy, and physics-informed AI for mental healthcare
Translation of multimodal AI technologies to clinical practice
Mental health for elderly people
Brain development and developmental biomarkers