Portrait of Guillaume Dumas

Guillaume Dumas

Associate Academic Member
Associate Professor, Université de Montréal, Department of Psychiatry and Addiction
Adjunct Professor, McGill University, Department of Psychiatry
Research Topics
Computational Biology
Computational Neuroscience
Deep Learning
Dynamical Systems
Machine Learning Theory
Medical Machine Learning
Reinforcement Learning
Website
Google Scholar
LinkedIn
X

Biography

Guillaume Dumas is an associate professor of computational psychiatry in the Faculty of Medicine, Université de Montréal, and principal investigator in the Precision Psychiatry and Social Physiology laboratory at the Centre hospitalier universitaire (CHU) Sainte-Justine Research Centre. He holds the IVADO professorship for AI in Mental Health, and the Fonds de recherche du Québec - Santé (FRQS) J1 in AI and Digital Health. In 2023, Dumas was recognized as a CIFAR Azrieli Global Scholar – Brain, Mind, and Consciousness program, and nominated as a Future Leader in Canadian Brain Research by the Brain Canada Foundation.

Dumas was previously a permanent researcher in neuroscience and computational biology at the Institut Pasteur (Paris). Before that, he was a postdoctoral fellow at the Center for Complex Systems and Brain Sciences (Florida Atlanta University). He holds an engineering degree in advanced engineering and computer science (École Centrale Paris), two MSc degrees (theoretical physics, Paris-Saclay University; cognitive science, ENS/EHESS/Paris 5), and a PhD in cognitive neuroscience (Sorbonne University).

The goal of his research is to cross-fertilize AI/ML, cognitive neuroscience and digital medicine through an interdisciplinary program with two main axes:

- AI/ML for Mental Health, which aims to create new algorithms to investigate the development of human cognitive architecture and deliver personalized medicine in neuropsychiatry using data from genomes to smartphones.

- Social Neuroscience for AI/ML, which translates basic brain research and dynamical systems formalism into neurocomputational and machine learning hybrid models (NeuroML) and machines with social learning abilities (Social NeuroAI & HMI).

Current Students

Saskia Helbling
Postdoctorate - Université de Montréal
Website
Github
Google Scholar
Nadine Mohamed
Master's Research - Université de Montréal
Rémy Ramadour
Independent visiting researcher - CHU Sainte Justine / Université de Montréal
Website
Github
Mahta Ramezanian
Master's Research - Université de Montréal
Principal supervisor :
Irina Rish
Pascal Tikeng Notsawo
PhD - Université de Montréal
Principal supervisor :
Guillaume Rabusseau
Website
Github
Google Scholar

Publications

Long-term survival and functional outcomes of critically ill patients with hematologic malignancies: a Canadian multicenter prospective study
Laveena Munshi
Guillaume Dumas
Bram Rochwerg
Farah Shoukat
Michael Detsky
Dean A. Fergusson
Bruno Ferreyro
Paul Heffernan
Margaret Herridge
Sheldon Magder
Mark Minden
Rakesh Patel
Salman Qureshi
Aaron Schimmer
Santhosh Thyagu
Han Ting Wang
Sangeeta Mehta
2024-03-10
Intensive Care Medicine (published)
doi.org
Predicting Grokking Long Before it Happens: A look into the loss landscape of models which grok
Tikeng Notsawo Pascal Junior
Pascal Notsawo
Hattie Zhou
Mohammad Pezeshki
Irina Rish
Guillaume Dumas
2024-03-03
ICLR.cc/2024/Workshop/ME-FoMo (poster)
doi.org
openreview.net
Distinct social behavior and inter-brain connectivity in Dyads with autistic individuals
Quentin Moreau
Florence Brun
Anaël Ayrolles
Jacqueline Nadel
Guillaume Dumas
Autism Spectrum Disorder (ASD) is defined by distinctive socio-cognitive behaviors that deviate from typical patterns. Notably, social imita… (see more)tion skills appear to be particularly impacted, manifesting early on in development. This paper compared the behavior and inter-brain dynamics of dyads made up of two typically developing (TD) participants with mixed dyads made up of ASD and TD participants during social imitation tasks. By combining kinematics and EEG-hyperscanning, we show that individuals with ASD exhibited a preference for the follower rather than the lead role in imitating scenarios. Moreover, the study revealed inter-brain synchrony differences, with low-alpha inter-brain synchrony differentiating control and mixed dyads. The study’s findings suggest the importance of studying interpersonal phenomena in dynamic and ecological settings and using hyperscanning methods to capture inter-brain dynamics during actual social interactions.
2024-03-02
Social Neuroscience (published)
doi.org
The « jingle-jangle fallacy » of empathy: Delineating affective, cognitive and motor components of empathy from behavioral synchrony using a virtual agent
Julia Ayache
Guillaume Dumas
Alexander Sumich
D. Kuss
Darren Rhodes
Nadja Heym
2024-02-29
Personality and Individual Differences (published)
doi.org
Effective Latent Differential Equation Models via Attention and Multiple Shooting
Germán Abrevaya
Mahta Ramezanian-Panahi
Jean-christophe Gagnon-audet
Irina Rish
Pablo Polosecki
Silvina Ponce Dawson
Guillermo Cecchi
Guillaume Dumas
2024-02-25
TMLR (accepted)
openreview.net
openreview.net
Protocol for fever control using external cooling in mechanically ventilated patients with septic shock: SEPSISCOOL II randomised controlled trial
Armelle Guénégou-Arnoux
Juliette Murris
Stéphane Bechet
Camille Jung
Johann Auchabie
Julien Dupeyrat
Nadia Anguel
Pierre Asfar
Julio Badie
Dorothée Carpentier
Benjamin Chousterman
Jeremy Bourenne
Agathe Delbove
Jérôme Devaquet
Nicolas Deye
Guillaume Dumas
Anne-Florence Dureau
Jean-Baptiste Lascarrou
Stephane Legriel
Christophe Guitton … (see 14 more)
Caroline Jannière-Nartey
Jean-Pierre Quenot
Jean-Claude Lacherade
Julien Maizel
Armand Mekontso Dessap
Bruno Mourvillier
Philippe Petua
Gaetan Plantefeve
Jean-Christophe Richard
Alexandre Robert
Clément Saccheri
Ly Van Phach Vong
Sandrine Katsahian
Frédérique Schortgen
2024-01-28
BMJ Open (published)
doi.org
Arbitrary methodological decisions skew inter-brain synchronization estimates in hyperscanning-EEG studies
Marius Zimmermann
Kathrine Schultz-Nielsen
Guillaume Dumas
Ivana Konvalinka
Over the past decade, hyperscanning has emerged as an important methodology to study neural processes underlying human interaction using fMR… (see more)I, EEG, fNIRS, and MEG. However, many methodological decisions regarding preprocessing and analysis of hyperscanning data have not yet been standardized in the hyperscanning community, yet may affect inter-brain estimates. Here we systematically investigate the effects common methodological choices can have on estimates of phase-based inter-brain synchronization (IBS) measures, using real and simulated hyperscanning (dual) EEG data. Notably, we introduce a new method to compute circular correlation (CCorr) coefficients in IBS studies, which performs more reliably in comparison to the standard approach, showing that the conventional CCorr implementation leads to large fluctuations in IBS estimates due to fluctuations in circular mean directions. Furthermore, we demonstrate how short epoch durations (of 1 second or less) can lead to inflated IBS estimates in scenarios with no strong underlying interaction. Finally, we show how signal-to-noise ratios and temporal factors may confound IBS estimates, particularly when comparing e.g., resting states with conditions involving motor actions. For each of these investigated effects, we provide recommendations for future research employing hyperscanning-EEG techniques, aimed at increasing validity and replicability of inter-brain synchronization studies.
2023-12-31
Imaging Neuroscience (published)
doi.org
Challenges in multi-task learning for fMRI-based diagnosis: Benefits for psychiatric conditions and CNVs would likely require thousands of patients
Annabelle Harvey
Clara A. Moreau
Kuldeep Kumar
Guillaume Huguet
Sebastian G.W. Urchs
Hanad Sharmarke
Khadije Jizi
Charles-Olivier Martin
Nadine Younis
Petra Tamer
Jean-Louis Martineau
Pierre Orban
Ana Isabel Silva
Jeremy Hall
Marianne B.M. van den Bree
Michael J. Owen
David E.J. Linden
Sarah Lippé
Carrie E. Bearden
Guillaume Dumas … (see 2 more)
Sébastien Jacquemont
Pierre Bellec
There is a growing interest in using machine learning (ML) models to perform automatic diagnosis of psychiatric conditions; however, general… (see more)ising the prediction of ML models to completely independent data can lead to sharp decrease in performance. Patients with different psychiatric diagnoses have traditionally been studied independently, yet there is a growing recognition of neuroimaging signatures shared across them as well as rare genetic copy number variants (CNVs). In this work, we assess the potential of multi-task learning (MTL) to improve accuracy by characterising multiple related conditions with a single model, making use of information shared across diagnostic categories and exposing the model to a larger and more diverse dataset. As a proof of concept, we first established the efficacy of MTL in a context where there is clearly information shared across tasks: the same target (age or sex) is predicted at different sites of data collection in a large functional magnetic resonance imaging (fMRI) dataset compiled from multiple studies. MTL generally led to substantial gains relative to independent prediction at each site. Performing scaling experiments on the UK Biobank, we observed that performance was highly dependent on sample size: for large sample sizes (N > 6000) sex prediction was better using MTL across three sites (N = K per site) than prediction at a single site (N = 3K), but for small samples (N 500) MTL was actually detrimental for age prediction. We then used established machine-learning methods to benchmark the diagnostic accuracy of each of the 7 CNVs (N = 19–103) and 4 psychiatric conditions (N = 44–472) independently, replicating the accuracy previously reported in the literature on psychiatric conditions. We observed that MTL hurt performance when applied across the full set of diagnoses, and complementary analyses failed to identify pairs of conditions which would benefit from MTL. Taken together, our results show that if a successful multi-task diagnostic model of psychiatric conditions were to be developed with resting-state fMRI, it would likely require datasets with thousands of patients across different diagnoses.
2023-12-31
Imaging Neuroscience (published)
doi.org
Corticosteroids induce an early but limited decrease in IL-6 dependent pro-inflammatory responses in critically ill COVID-19 patients
Tomas URBINA
Paul GABARRE
Vincent BONNY
Jean-Rémi Lavillegrand
Marc GARNIER
Jérémie JOFFRE
Nathalie MARIO
Guillaume Dumas
Geoffroy HARIRI
Matthieu TURPIN
Emmanuel PARDO
Muriel FARTOUKH
Bertrand GUIDET
Eric Maury
Yannick CHANTRAN
Pierre-Yves BOELLE
Guillaume VOIRIOT
Hafid AIT-OUFELLA
2023-12-31
Minerva Anestesiologica (published)
doi.org
Resilience and Mental-Health Symptoms in ICU Healthcare Professionals Facing Repeated COVID-19 Waves
Elie Azoulay
Frédéric Pochard
Laurent Argaud
Alain Cariou
Raphael Clere-Jehl
Olivier Guisset
Vincent Labbé
Fabienne Tamion
Fabrice Bruneel
Mercé Jourdain
Danielle Reuter
Kada Klouche
Achille Kouatchet
Virginie Souppart
Alexandre Lautrette
Julien Bohé
Antoine Vieillard Baron
Jean Dellamonica
Laurent Papazian
Jean Reignier … (see 3 more)
François Barbier
Guillaume Dumas
Nancy Kentish-Barnes
2023-12-31
American Journal of Respiratory and Critical Care Medicine (published)
doi.org
Diagnosis and management of autoimmune diseases in the ICU
Guillaume Dumas
Yaseen M. Arabi
Raquel Bartz
Otavio Ranzani
Franziska Scheibe
Michael Darmon
Julie Helms
2023-12-18
Intensive Care Medicine (published)
doi.org
From physics to sentience: Deciphering the semantics of the free-energy principle and evaluating its claims: Comment on "Path integrals, particular kinds, and strange things" by Karl Friston et al.
Zahra Sheikhbahaee
Adam Safron
Casper Hesp
Guillaume Dumas
2023-11-30
Physics of Life Reviews (published)
doi.org
arxiv.org