Thesis Defense: Machine learning strategies to predict late adverse effects in childhood acute lymphoblastic leukemia survivors

Description:

Speaker: Nicolas Raymond, M. Sc. student in Computer Science, Department of Computer Science, Faculty of Science, Université de Sherbrooke

Abstract: Acute lymphoblastic leukemia is the most frequent pediatric cancer. Approximately two third of survivors develop one or more health complications known as late adverse effects following their treatments. The existing measures offered to patients during their follow-up visits to the hospital are rather standardized for all childhood cancer survivors and not necessarily personalized for childhood ALL survivors. As a result, late adverse effects may be underdiagnosed and, in most cases, only taken care of following their appearance. On the other hand, current care guidelines may also lead to more intensive follow-up than necessary; sometimes causing concern for survivors and increasing costs of care. Thus, it is necessary to predict these treatment-related conditions earlier to contribute to the health and well-being of survivors. Multiple studies have investigated the usage of specific biomarkers to predict late adverse effects and consequently provide strategies for better personalized follow-up. In particular, one study presented a machine learning model to prevent the morbidities related to the deterioration of the cardiorespiratory fitness. However, no solution integrated the usage of neural networks to date. In this work, we developed graph-based parameters-efficient neural networks and promoted their interpretability with multiple post-hoc analyses. We first proposed a new disease-specific VO2 peak prediction model that does not require patients to participate to a physical function test (e.g., 6-minute walk test). VO2 peak is recognized as the gold standard to measure cardiorespiratory fitness, which in turn is a key element for the prevention of late adverse effects such as obesity and depression. Secondly, we created an obesity prediction model using clinical variables that are available from the end of childhood ALL treatment as well as genomic variables. Our solutions were able to achieve better performance than linear and tree-based models on small cohorts of patients (<= 223) for both tasks.

Jury member, president : Aïda Ouangraoua, Professor, Department of Computer Science, Faculty of Science, Université de Sherbrooke

Jury member, internal evaluator : Félix Camirand Lemyre, Professor, Department of Mathematics, Faculty of Science, Université de Sherbrooke

Jury member, research director: Martin Vallières, Professor, Department of Computer Science, Faculty of Science, Université de Sherbrooke

All interested persons are cordially invited.

Teams link: http://bit.ly/3GB1L2O