Nikos Koutsouleris
banner
koutsouleris.bsky.social
Nikos Koutsouleris
@koutsouleris.bsky.social
interested in finding ways to prevent severe mental disorders using computational methods.
It matters if we try to predict single snapshot of mental phenotypes or stable outcomes over time. Great new paper from my PhD student, Madalina Buciuman, who used the PRONIA dataset to predict functional outcomes in early psychosis and depression:
www.biologicalpsychiatryjournal.com/article/S000...
From Snapshots to Stable Outcomes: rs-fMRI-based Prognosis of Functioning in Patients with Psychosis Risk or Recent-Onset Depression
Early recovery of functioning is critical for favorable outcomes in psychotic and affective disorders. Transdiagnostic brain activity patterns may capture pathways for poor outcomes before clinical ma...
www.biologicalpsychiatryjournal.com
July 11, 2025 at 6:43 PM
Excited to share our new preprint (www.researchsquare.com/article/rs-6...). We show that heterogeneous clinical high-risk criteria impede detection of biomarkers for early psychosis detection. Integrating cognitive basic symptoms and their neural surrogates may help to improve precision.
Refining Schizophrenia Risk Assessment: Machine Learning Delineates a Brain Signature of Cognitive Basic Symptoms
Biological risk signatures could aid the early detection of schizophrenia, but their precision likely depends on the clinical risk definitions they are derived from. Using machine learning, we analyze...
www.researchsquare.com
April 1, 2025 at 7:59 AM