Presentations

Date 2024-12-06 Authors Olivier Lefebvre Martin Vallières Summary Introduction : Les modèles d’apprentissage automatique sont des outils puissants pouvant soutenir la prise de décisions cliniques, en fournissant des prédictions personnalisées pour chaque patient à partir de grandes bases de données.

Date 2024-12-06 Authors Hakima Laribi Nicolas Raymond Martin Vallières Summary Introduction : L’estimation du potentiel de survie à moyen terme des patients après admission permet d’identifier ceux en fin de vie qui pourraient bénéficier de discussions sur les objectifs de soins.

Date 2023-10-13 Authors Hakima Laribi Nicolas Raymond Martin Vallières Summary Introduction Predicting long-term patient survival after admission is crucial for improving palliative care and initiating goals of care discussions.

Date 2023-10-13 Authors Olivier Lefebvre Martin Vallières Summary Introduction Machine learning models are powerful tools for clinical applications, like mortality prediction. However, they may exhibit different levels of performance, including some very poor one, for different patient groups with different profiles of attributes, despite strong global performance in external test sets.

Date 2022-10-20 Authors Mahdi Ait Lhaj Loutfi Summary Precision oncology is an important field in cancer research as its main goal is to lead towards personalized treatments.

Date 2022-10-20 Authors Hakima Laribi Summary A goal of care discussion GOC is a communication process that takes place in a hospital setting between a clinician and a patient at the end of life.

Date 2022-10-20 Authors Olivier Lefebvre Summary Machine learning is increasingly used in a variety of applications. Machine learning models can be used as decision support tools in critical contexts, such as the medical field.

Date 2022-06-02 Authors Mahdi Ait Lhaj Loutfi Summary Cancer is a heterogeneous disease with unique genomic and phenotypic characteristics that differ from patient to patient and even from tumor region to tumor region.

Date 2021-05-05 Authors Alexandre Ayotte Summary Research objective: To develop an interpretable tool for the automatic classification of renal lesions from MRI images. The classification is performed according to the nature, malignancy or benignity of the tumors and according to their subtype and grade for malignant tumors.

Date 2021-05-05 Authors Nicolas Raymond Summary Acute lymphoblastic leukemia (ALL) accounts for nearly one-third of all pediatric cancers in Canada each year. Although current treatments achieve a 5-year survival rate of 90%, we observe that more than 65% of survivors develop long-term adverse effects including dyslipidemia, hypertension and osteoporosis.