MDMarie-Pier Domingue

Marie-Pier Domingue

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Marie-Pier Domingue has a total of 13 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Operationalizing transparency regarding the use of health data for research: a cross-sectional survey of citizens’ perspectives

    by Annabelle Cumyn, Jean-Frédéric Ménard, Emmanuel Bilodeau, Roxanne Dault, Jean-Philippe Morissette, Marie-Pier Domingue, Félix Camirand Lemyre, Denis Boutin, Jean-François Ethier

    Background: Secondary use of health data can accelerate discovery and enable personalized care, yet social acceptability relies on autonomy, transparency, and trust, especially in the context of security breaches and concerns about misuse. In Quebec, as in many Western settings, there is no formal mechanism to inform individuals about such use, underscoring the need for practical solutions. This quantitative cross-sectional study assessed whether transparency mechanisms increase trust in the use of health data for research; examined their perceived priority and acceptability; and explored effects across population subgroups. Methods: We conducted a cross-sectional telephone survey among 366 adults in Quebec (Canada) selected via stratified random sampling. The sample included a random selection of adult household members based on age. Descriptive statistics, chi-square tests, and exploratory multivariate logistic regressions were performed. Results: More than half of respondents were unaware that their health data may be used for research. Trust was higher for public-sector than private-sector researchers. Overall, 76% indicated that access to information would increase their trust, particularly younger adults (OR = 1.98, 95% CI: 1.10–3.57). Over 90% judged implementing transparency mechanisms within five years as important, with stronger support among those aware of current data use (OR = 4.63, 95% CI: 1.33–16.20). A secure website was considered acceptable by 75% of respondents as a transparency mechanism. Individuals with high trust in public-sector researchers (OR: 2.06, 95% CI: 1.08–3.94) and younger adults (OR: 2.05, 95% CI: 1.13–3.71) were more likely to consider it important. Exploratory analyses suggested that awareness of current data use for research and pre-existing trust predict increased trust in researchers from various public and private organizations if a secure website is implemented. Conclusion: Providing information through a transparency mechanism, particularly via a secure website, appears acceptable, valued, and potentially effective for increasing trust in the use of health data for research. Our findings support the feasibility of a web-based transparency portal and suggest tailoring communication to demographic, trust and awareness profiles.

  • Open Access

    VALORIS : repenser les recettes pour l’analyse de données de santé distribuées

    by Marie-Pier Domingue, Félix Camirand Lemyre

    En combinant les multiples données de santé générées par une même personne, il devient possible de mieux comprendre les trajectoires du vieillissement. Pourtant, des contraintes légales et éthiques empêchent le partage de ces données individuelles entre organisations. Comme les méthodes usuelles pour analyser ces données ont été bâties pour le cadre dans lequel les données sont centralisées, les recettes existantes pour ces analyses ont dû être entièrement repensées afin de développer des méthodes dites distribuées. C'est ainsi qu'est né VALORIS, un algorithme distribué pour le modèle de régression logistique. VALORIS ouvre la voie à de nouvelles possibilités pour la recherche concernant les trajectoires du vieillissement. Marie-Pier Domingue est doctorante en mathématiques et en biostatistiques au sein du Groupe de recherche interdisciplinaire en informatique de la santé (GRIIS), en cotutelle entre l’Université de Sherbrooke et l’Université Paris Cité. Félix Camirand Lemyre, chercheur au Centre de recherche sur le vieillissement et professeur agrégé en mathématiques à l’Université de Sherbrooke. Il est codirecteur scientifique du GRIIS et directeur du Centre de consultation statistique de l’Université de Sherbrooke. Il est titulaire de la chaire de recherche en méthodologies statistiques appliquées aux enjeux de santé et phénomènes sociaux.

  • Open Access

    VALORIS: A privacy-aware logistic regression method for vertically partitioned data within a novel privacy risk assessment framework

    by Félix Camirand Lemyre, Marie-Pier Domingue, Jean-Philippe Morissette, Anita Burgun, Jean-François Ethier

    Life sciences research increasingly relies on variables held by different entities, such as clinical, laboratory, environmental, and genomic data. Due to legal, ethical, and social acceptability constraints, these data often cannot be shared across organizations holding them. As a result, they cannot be pooled, and analyses must be conducted within the framework of vertically partitioned data. Supporting such analyses requires methods that protect privacy. However, the mere fact that line-level data are not exchanged should not be mistaken for true privacy protection. We introduce VALORIS (Vertically partitioned Analytics under the LOgistic Regression model for Inference in Statistics), a novel method that enables statistical inference under a logistic regression model without disclosing any individual-level data—including the outcome variable. VALORIS is a practical, communication-efficient algorithm that requires no third-party coordinator. Most importantly, it includes a novel framework for evaluating privacy, allowing users to distinguish among different levels of privacy preservation.

  • Open Access

    Revisiting VERTIGO and VERTIGO-CI: Identifying confidentiality breaches and introducing a statistically sound, efficient alternative

    by Marie-Pier Domingue, Jean-François Ethier, Jean-Philippe Morissette, Simon Lévesque, Anita Burgun, Félix Camirand Lemyre

    Objectives: This study aims to guide future use of the VERTIGO and VERTIGO-CI algorithms by (1) Highlighting confidentiality issues; (2) minimizing the number of communication rounds required; (3) offering an alternative algorithm that excludes the intercept from the penalty. Materials and Methods: Quantities exchanged in the original algorithms were inspected and linear algebra was used to uncover reverse-engineering processes that the coordinating center can perform to re-create raw data. The objective function of the optimization problem was investigated to propose an alternative where one communication is needed to run the algorithm while being able to exclude the intercept from the penalty. Results: It was shown that the coordinating center can retrieve all individual data using matrix operations when VERTIGO-CI is run. Individual data could also be retrieved in the case where parameter estimates associated with binary covariates are shared. The VERTIGO algorithm was adapted with reduced communications, and an algorithm was proposed to exclude the intercept from the penalty. Discussion: While the use of VERTIGO-CI or VERTIGO with binary covariates does not imply directly sharing raw data, this works highlights the risks of reverse-engineering enabling the coordination node to effectively obtain the raw dataset of a data node. While inspecting quantities exchanged allowed to reduce the number of communications rounds, investigating the modeling choice, which translates as including or not the intercept in the penalty, was essential for interpretation matters. Conclusion: This work highlights confidentiality breaches that may arise in distributed analytics methods, but also proposes an improved algorithm with reduced operational costs and enriching model interpretablity.

  • Open Access

    Correction: Distributed Statistical Analyses: A Scoping Review and Examples of Operational Frameworks Adapted to Health Analytics

    by Félix Camirand Lemyre, Simon Lévesque, Marie-Pier Domingue, Klaus Herrmann, Jean-François Ethier

    Background: Data from multiple organizations are crucial for advancing learning health systems. However, ethical, legal, and social concerns may restrict the use of standard statistical methods that rely on pooling data. Although distributed algorithms offer alternatives, they may not always be suitable for health frameworks. Objective: This study aims to support researchers and data custodians in three ways: (1) providing a concise overview of the literature on statistical inference methods for horizontally partitioned data, (2) describing the methods applicable to generalized linear models (GLMs) and assessing their underlying distributional assumptions, and (3) adapting existing methods to make them fully usable in health settings. Methods: A scoping review methodology was used for the literature mapping, from which methods presenting a methodological framework for GLM analyses with horizontally partitioned data were identified and assessed from the perspective of applicability in health settings. Statistical theory was used to adapt methods and derive the properties of the resulting estimators. Results: From the review, 41 articles were selected and 6 approaches were extracted to conduct standard GLM-based statistical analysis. However, these approaches assumed evenly and identically distributed data across nodes. Consequently, statistical procedures were derived to accommodate uneven node sample sizes and heterogeneous data distributions across nodes. Workflows and detailed algorithms were developed to highlight information sharing requirements and operational complexity. Conclusions: This study contributes to the field of health analytics by providing an overview of the methods that can be used with horizontally partitioned data by adapting these methods to the context of heterogeneous health data and clarifying the workflows and quantities exchanged by the methods discussed. Further analysis of the confidentiality preserved by these methods is needed to fully understand the risk associated with the sharing of summary statistics.

  • Open Access

    Distributed Statistical Analyses: A Scoping Review and Examples of Operational Frameworks Adapted to Health Analytics

    by Félix Camirand Lemyre, Simon Lévesque, Marie-Pier Domingue, Klaus Herrmann, Jean-François Ethier

    Background: Data from multiple organizations are crucial for advancing learning health systems. However, ethical, legal, and social concerns may restrict the use of standard statistical methods that rely on pooling data. Although distributed algorithms offer alternatives, they may not always be suitable for health frameworks. Objective: This study aims to support researchers and data custodians in three ways: (1) providing a concise overview of the literature on statistical inference methods for horizontally partitioned data, (2) describing the methods applicable to generalized linear models (GLMs) and assessing their underlying distributional assumptions, and (3) adapting existing methods to make them fully usable in health settings. Methods: A scoping review methodology was used for the literature mapping, from which methods presenting a methodological framework for GLM analyses with horizontally partitioned data were identified and assessed from the perspective of applicability in health settings. Statistical theory was used to adapt methods and derive the properties of the resulting estimators. Results: From the review, 41 articles were selected and 6 approaches were extracted to conduct standard GLM-based statistical analysis. However, these approaches assumed evenly and identically distributed data across nodes. Consequently, statistical procedures were derived to accommodate uneven node sample sizes and heterogeneous data distributions across nodes. Workflows and detailed algorithms were developed to highlight information sharing requirements and operational complexity. Conclusions: This study contributes to the field of health analytics by providing an overview of the methods that can be used with horizontally partitioned data by adapting these methods to the context of heterogeneous health data and clarifying the workflows and quantities exchanged by the methods discussed. Further analysis of the confidentiality preserved by these methods is needed to fully understand the risk associated with the sharing of summary statistics.


  • Open Access

    Distributed Statistical Analyses: A Scoping Review and Examples of Operational Frameworks Adapted to Healthcare

    by Félix Camirand Lemyre, Simon Lévesque, Marie-Pier Domingue, Klaus Herrmann, Jean-François Ethier

    Data from multiple organizations are crucial for advancing learning health systems. However, ethical, legal, and social concerns may restrict the use of standard statistical methods that rely on pooling data. Although distributed algorithms offer alternatives, they may not always be suitable for healthcare research frameworks. This paper aims to support researchers and data custodians in three ways: (1) providing a concise overview of the literature on statistical inference methods for horizontally partitioned data; (2) describing the methods applicable to generalized linear models (GLM) and assessing their underlying distributional assumptions; (3) adapting existing methods to make them fully usable in healthcare research. A scoping review methodology was employed for the literature mapping, from which methods presenting a methodological framework for GLM analyses with horizontally partitioned data were identified and assessed from the perspective of applicability in healthcare research. From the review, 41 articles were selected, and six approaches were extracted for conducting standard GLM-based statistical analysis. However, these approaches assumed evenly and identically distributed data across nodes. Consequently, statistical procedures were derived to accommodate uneven node sample sizes and heterogeneous data distributions across nodes. Workflows and detailed algorithms were developed to highlight information-sharing requirements and operational complexity.