Timezone: »

 
Oral
Discriminative Network Models of Schizophrenia
Guillermo Cecchi · Irina Rish · Benjamin Thyreau · Bertrand Thirion · Marion Plaze · Jean-Luc Martinot · Marie Laure Paillere-Martinot · Jean-Baptiste Poline

Tue Dec 08 03:00 PM -- 03:20 PM (PST) @
in Oral Session 3: Deep Learning and Network Models »

Schizophrenia is a complex psychiatric disorder that has eluded a characterization in terms of local abnormalities of brain activity, and is hypothesized to affect the collective, "emergent'' working of the brain. We propose a novel data-driven approach to capture emergent features using functional brain networks [Eguiluzet al] extracted from fMRI data, and demonstrate its advantage over traditional region-of-interest (ROI) and local, task-specific linear activation analyzes. Our results suggest that schizophrenia is indeed associated with disruption of global, emergent brain properties related to its functioning as a network, which cannot be explained by alteration of local activation patterns. Moreover, further exploitation of interactions by sparse Markov Random Field classifiers shows clear gain over linear methods, such as Gaussian Naive Bayes and SVM, allowing to reach 86% accuracy (over 50% baseline - random guess), which is quite remarkable given that it is based on a single fMRI experiment using a simple auditory task.

Author Information

Guillermo Cecchi (IBM Research)
Irina Rish (Mila/UdeM/LAION)
Benjamin Thyreau (CEA-INSERM)
Bertrand Thirion (INRIA)
Marion Plaze
Jean-Luc Martinot
Marie Laure Paillere-Martinot (AP-HP, Cochin hospital)
Jean-Baptiste Poline (CEA-INSERM)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors