Cristina Longo’s research focuses primarily on optimizing maternal and child asthma outcomes. As a perinatal and pediatric pharmacoepidemiologist, she integrates advanced statistical methods such as machine learning and causal inference to identify interventions that may be beneficial to both mother and child, particularly those who have asthma. By leveraging high-dimensional data from administrative health records, clinical, and biological data sources, her work contributes to identifying causal factors, including critical in-utero exposures, that may contribute to or prevent the development and progression of childhood asthma and discovering mechanisms that determine response to treatment and optimized outcomes.
One of the key aspects of her research is the personalization of asthma treatment. Through comparative effectiveness research and machine learning models, she aims to optimize asthma outcomes by tailoring interventions based on individual patient characteristics. This has the potential to not only reduce the frequency of asthma exacerbations but also improves long-term clinical outcomes for children. Her research program incorporates the latest methods in causal inference, which allow for more precise assessments of the safety and effectiveness of treatments in real-world settings.
Career Summary
Cristina Longo is an Assistant Professor in Pharmacoepidemiology at the Faculty of Pharmacy, Université de Montréal, and a regular researcher at the Centre de recherche Azrieli du CHU Sainte-Justine. She holds a PhD in Primary Care with a specialization in pediatric pharmacoepidemiology from McGill University and completed postdoctoral fellowships at Université de Montréal and Amsterdam University Medical Center, where she specialized in perinatal/pediatric pharmacoepidemiology, precision medicine, and machine learning.
She is also the co-lead of the Methods and Artificial Intelligence Pharmacoepidemiology Platform at the Quebec Network for Medication Research and invited methodologist of the European Respiratory Society’s Task Force on Defining Remission in Asthma. She is recognized for her innovative work in causal inference and target trial emulation in perinatal/pediatric drug safety and effectiveness studies, in machine learning to predict response to treatment and asthma outcomes in children and their mothers as well as in identifying potential new therapeutic strategies for children who do not respond adequately to currently available therapies. She has received several distinctions, including a CAAIF/CIHR Early Career Research Award in Asthma, an FRQ-S Junior 1 Scholarship in Artificial Intelligence and Health, as well as an IVADO Professorship.
She is the principal investigator of several funded research projects, including an international study on the safety and effectiveness of asthma biologic medications during pregnancy on maternal and child outcomes, a big data study aiming to identify new therapeutic targets for pediatric wheeze and asthma and to develop a machine learning model that can inform decision-making about the best treatment approach, as well as methods studies on how deep learning could be used to reduce bias in how we estimate treatment effects. Her work has been funded by prestigious organizations such as the Canadian Institutes of Health Research (CIHR), the Fonds de recherche du Québec - Santé (FRQS), the Canadian Women’s Health Foundation, and the CHU Sainte-Justine Foundation.