Danilo Bzdok
Associate Professor, Department of Biomedical Engineering
Canada CIFAR Artificial Intelligence Chair
Mila - Quebec AI Institute
Danilo Bzdok is a medical doctor (M.D.) by training with a unique dual background in systems neuroscience and machine learning algorithms. After medical training at RWTH Aachen University (Germany), Universit茅 de Lausanne (Switzerland), and Harvard Medical School (USA), he completed one Ph.D. in cognitive neuroscience (Research Center Juelich, Germany) and one Ph.D. in computer science in machine learning statistics at INRIA Saclay and Neurospin (France). Danilo currently serves as Associate Professor at 91社区's Faculty of Medicine and as Canada CIFAR AI Chair at Mila - Quebec Artificial Intelligence Institute, Montreal, Canada, including cross-appointments at the McConnell Brain Imaging Center, Montreal Neurological Institute, Ludmer Centre for Neuroinformatics and Mental Health, and the School of Computer Science at 91社区. His interdisciplinary research activity centers on narrowing knowledge gaps in the brain basis of human-defining types of thinking, with a special focus on the higher association cortex in health and disease.
Danilo Bzdok is a medical doctor and computer scientist with a dual background in systems neuroscience and machine learning algorithms. After training at RWTH Aachen University (Germany), Universit茅 de Lausanne (Switzerland), and Harvard Medical School (USA), he completed one Ph.D. in cognitive neuroscience (Research Center Juelich, Germany) and one Ph.D. in computer science in machine learning statistics at INRIA Saclay and Neurospin (France). Danilo currently serves as Associate Professor at 91社区's Faculty of Medicine and as Canada CIFAR AI Chair at Mila - Quebec Artificial Intelligence Institute, Montreal, Canada, including cross-appointments at the McConnell Brain Imaging Center, Montreal Neurological Institute, Ludmer Centre for Neuroinformatics and Mental Health, and the School of Computer Science at 91社区. His interdisciplinary research activity centers on narrowing knowledge gaps in the brain basis of human-defining types of thinking, with a special focus on the higher association cortex in health and disease.
There is now increasing momentum in data sharing, open access, and data collection consortia that build richly annotated "big data" repositories for brain and behavior. This unprecedented data setting creates a rapidly growing potential to provide new answers to old questions on human brain organization and its disturbances in brain disease. Dr. Bzdok will take the opportunity to explore, formalize, and predict brain phenotypes of hidden population variation by capitalising on heterogeneous data sources to tackle open questions in systems neuroscience in a way that also paves new ways for precision medicine in brain health.
His research group is dedicated to such interdisciplinary challenges in a domain-agnostic approach (especially high- but also low-level cognitive processes) leveraging several recently emerged population datasets (such as UK Biobank, HCP, CamCAN, ABCD) across levels of observation (brain structure and function, consequences from brain lesion, or common-variant genetics) using a broad toolkit of bioinformatic methods (machine-learning, high-dimensional statistics, and probabilistic Bayesian hierarchical modeling).
Future Work:
The key ambition is to bring closer neuroscience and learning predictive patterns from data. Due to the complexity of the patterns that need to be detected in life experience, neural processing, and genomics, human intuition alone may not be sufficient to provide explicit, fine-detailed brain mechanisms. His combination of backgrounds allows identifying pressing questions in medical imaging and health, reframing them as machine learning problems, and translating new insight into biomedicine. His research team is focused on data-guided analysis techniques for large datasets from a systems neuroscience perspective. He believes that strong interdisciplinarity, with an equal footing in research object and research method, is a prerequisite for forward progress in quantitative neuroscience and personalized medicine.
Bzdok D, Altman N, Krzywinski M. Statistics versus machine learning. Nature Methods, 2018, 15:233-234.
Bzdok D, Ioannidis JPA. Exploration, inference and prediction in neuroscience and biomedicine. Trends in Neurosciences, Cell Press, 42:251-262, 2019.
Bzdok D, Nichols TE, Smith SM. Towards Algorithmic Analytics for Large-scale Datasets. Nature Machine Intelligence, 1:296-306, 2019.
Bzdok D, Engemann D, Thirion B. Inference and prediction diverge in biomedicine, Patterns, Cell Press, 2020.
Hartwigsen G, Bengio Y, Bzdok D. How does hemispheric specialization contribute to human-defining cognition?, Neuron, Cell Press, 2021.
Smallwood J, Bernhardt B, Leech R, Bzdok D, Jefferies E, Margulies D. The role the default mode network in cognition: a topographic perspective, Nature Reviews Neuroscience, 2021.
Kernbach J, Yeo BTT, Smallwood J, Margulies D, Thiebaut de Schotten M, Walter H, Sabuncu M, Holmes A, Gramfort A, Varoquaux G, Thirion B, Bzdok D. Subspecialization within Default Mode Nodes Characterized in 10,000 UK Biobank Participants. Proceedings of the National Academy of Sciences of the USA, 115:12295-12300, 2018.
Kiesow H, Dunbar RIM, Kable JW, Kalenscher T, Vogeley K, Schilbach L, Marquand AF, Wiecki TV, Bzdok D. 10,000 Social Brains: Sex Differentiation in Human Brain Anatomy. Science Advances, AAAS journal, 6:aaz1170, 2020.
Schulz MA, Yeo BTT, Vogelstein JT, Mourao-Miranada J, Kather JN, Kording K, Richards B, Bzdok D. Different scaling of linear models and deep learning in UKBiobank brain images versus machine-learning datasets. Nature Communications, 2020.
Spreng RN, Dimas E, Mwilambwe-Tshilobo L, Dagher A, Koellinger P, Nave G, Ong A, Kernbach JM, Wiecki TV, Ge T, Li Y, Holmes A, Yeo BTT, Dunbar RIM, Bzdok D. The Default Network of the Human Brain Is Associated With Perceived Social Isolation. Nature Communications, 2020.
Bzdok D, Michael Eickenberg, Ga毛l Varoquaux, Bertrand Thirion. Hierarchical Region-Network Sparsity for High-Dimensional Inference in Brain Imaging. Information Processing in Medical Imaging (IPMI), 2017, pp. 323-335.
Bzdok D, Eickenberg M, Grisel O, Thirion B, Varoquaux G. Semi-supervised Factored Logistic Regression for High-Dimensional Neuroimaging Data. Advances in Neural Information Processing Systems (NeurIPS), 2015.
