Reset filters

Search publications


Search by keyword
List by department / centre / faculty

No publications found.

 

Large language models deconstruct the clinical intuition behind diagnosing autism

Author(s): Stanley J; Rabot E; Reddy S; Belilovsky E; Mottron L; Bzdok D;

Efforts to use genome-wide assays or brain scans to diagnose autism have seen diminishing returns. Yet the clinical intuition of healthcare professionals, based on longstanding first-hand experience, remains the gold standard for diagnosis of autism. We leveraged deep learning to deconstruct and interrogate the logic of expert clinician intuition from cli ...

Article GUID: 40147442


Utilizing large language models for detecting hospital-acquired conditions: an empirical study on pulmonary embolism

Author(s): Cheligeer C; Southern DA; Yan J; Wu G; Pan J; Lee S; Martin EA; Jafarpour H; Eastwood CA; Zeng Y; Quan H;

Objectives: Adverse event detection from Electronic Medical Records (EMRs) is challenging due to the low incidence of the event, variability in clinical documentation, and the complexity of data formats. Pulmonary embolism as an adverse event (PEAE) is particularly difficult to identify using exi ...

Article GUID: 40105654


A synthetic model of bioinspired liposomes to study cancer-cell derived extracellular vesicles and their uptake by recipient cells

Author(s): López RR; Ben El Khyat CZ; Chen Y; Tsering T; Dickinson K; Bustamante P; Erzingatzian A; Bartolomucci A; Ferrier ST; Douanne N; Mounier C; Stiharu I; Nerguizian V; Burnier JV;

Extracellular vesicles (EVs) are secreted by most cell types and play a central role in cell-cell communication. These naturally occurring nanoparticles have been particularly implicated in cancer, but EV heterogeneity and lengthy isolation methods with low yield make them difficult to study. To ...

Article GUID: 40069225


Leveraging deep learning for nonlinear shape representation in anatomically parameterized statistical shape models

Author(s): Gheflati B; Mirzaei M; Rottoo S; Rivaz H;

Purpose: Statistical shape models (SSMs) are widely used for morphological assessment of anatomical structures. However, a key limitation is the need for a clear relationship between the model's shape coefficients and clinically relevant anatomical parameters. To address this limitation, this paper proposes a novel deep learning-based anatomically par ...

Article GUID: 39953355


Toward cognitive models of misophonia

Author(s): Savard MA; Coffey EBJ;

Misophonia is a disorder in which specific common sounds such as another person breathing or chewing, or the ticking of a clock, cause an atypical negative emotional response. Affected individuals may experience anger, irritability, annoyance, disgust, and anxiety, as well as physiological autonomic responses, and may find everyday environments and contex ...

Article GUID: 39874936


Face Boundary Formulation for Harmonic Models: Face Image Resembling

Author(s): Huang HT; Li ZC; Wei Y; Suen CY;

This paper is devoted to numerical algorithms based on harmonic transformations with two goals: (1) face boundary formulation by blending techniques based on the known characteristic nodes and (2) some challenging examples of face resembling. The formulation of the face boundary is imperative for face recognition, transformation, and combination. Mapping ...

Article GUID: 39852327


Beyond the Illusion of Controlled Environments: How to Embrace Ecological Pertinence in Research?

Author(s): Cassandre Vielle

Through the lens of preclinical research on substance use disorders (SUD), I propose a reflection aimed at re-evaluating animal models in neuroscience, with a focus on ecological relevance. While rodent models have provided valuable insights into the neurobiology of SUD, the field currently faces a validation crisis, with findings often failing to transla ...

Article GUID: 39777969


Deep clustering analysis via variational autoencoder with Gamma mixture latent embeddings

Author(s): Guo J; Fan W; Amayri M; Bouguila N;

This article proposes a novel deep clustering model based on the variational autoencoder (VAE), named GamMM-VAE, which can learn latent representations of training data for clustering in an unsupervised manner. Most existing VAE-based deep clustering methods use the Gaussian mixture model (GMM) as a prior on the latent space. We employ a more flexible asy ...

Article GUID: 39662201


Ion channel classification through machine learning and protein language model embeddings

Author(s): Ghazikhani H; Butler G;

Ion channels are critical membrane proteins that regulate ion flux across cellular membranes, influencing numerous biological functions. The resource-intensive nature of traditional wet lab experiments for ion channel identification has led to an increasing emphasis on computational techniques. This study extends our previous work on protein language mode ...

Article GUID: 39572876


Predictive heating load management and energy flexibility analysis in residential sector using an archetype gray-box modeling approach: Application to an experimental house in Québec

Author(s): Abtahi M; Athienitis A; Delcroix B;

This paper presents a methodology to develop archetype gray-box models and use them in an economic model-based predictive control algorithm to simulate optimal heating load management in response to a newly-introduced static time-of-use tariff for Québec's residential sector, rate Flex-D. The methodology is evaluated through a case study, wherein in s ...

Article GUID: 39507415


A guide to exploratory structural equation modeling (ESEM) and bifactor-ESEM in body image research

Author(s): Swami V; Maïano C; Morin AJS;

Traditionally, assessments of factor validity of body image instruments have relied on exploratory or confirmatory factor analysis. However, the emergence of exploratory structural equation modeling (ESEM), a resurgence of interest in bifactor models, and the ability to combine both models (bifactor-ESEM) is beginning to shape the future of body image res ...

Article GUID: 39492241


-   Page 1 / 3   >