Search

Showing total 3 results
Start Over Topic [stat.me]statistics [stat]/methodology [stat.me]
3 results

1. Mixture modeling for identifying subtypes in disease course mapping

Author

Stanley Durrleman, Pierre-Emmanuel Poulet, Algorithms, models and methods for images and signals of the human brain (ARAMIS), Sorbonne Université (SU)-Inria de Paris, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Institut du Cerveau et de la Moëlle Epinière = Brain and Spine Institute (ICM), Institut National de la Santé et de la Recherche Médicale (INSERM)-CHU Pitié-Salpêtrière [AP-HP], Sorbonne Université-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-CHU Pitié-Salpêtrière [AP-HP], Sorbonne Université-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS), This research has received funding from the program 'Investissements d’avenir' ANR-10-IAIHU-06. This work was also funded in part by the French government under management of Agence Nationale de la Recherche as part of the 'Investissements d’avenir' program, reference ANR-19-P3IA-0001 (PRAIRIE 3IA Institute)., Aasa Feragen, Stefan Sommer, Julia Schnabel, Mads Nielsen, ANR-19-P3IA-0001,PRAIRIE,PaRis Artificial Intelligence Research InstitutE(2019), Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-CHU Pitié-Salpêtrière [AP-HP], Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS), Institut du Cerveau et de la Moëlle Epinière = Brain and Spine Institute (ICM), Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Institut du Cerveau = Paris Brain Institute (ICM), Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Institut National de la Santé et de la Recherche Médicale (INSERM)-CHU Pitié-Salpêtrière [AP-HP], Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU)-Sorbonne Université (SU)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Institut National de la Santé et de la Recherche Médicale (INSERM)-CHU Pitié-Salpêtrière [AP-HP], Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS), Institut du Cerveau = Paris Brain Institute (ICM), Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU)-Sorbonne Université (SU)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS), This paper is funded in part by grant number 678304 (ERC), 826421 (TVB-Cloud) from H2020 programme, and ANR-10-IAIHU-06 (IHU ICM), ANR-19-P3IA-0001 (PRAIRIE) and ANR-19-JPW2-000 (E-DADS) from ANR., Poulet, Pierre-Emmanuel, PaRis Artificial Intelligence Research InstitutE - - PRAIRIE2019 - ANR-19-P3IA-0001 - P3IA - VALID, Sorbonne Université (SU)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-CHU Pitié-Salpêtrière [AP-HP], Sorbonne Université (SU)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS), and Sorbonne Université (SU)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)

Subjects
Computer science, Population, Stochastic approximation, Machine learning, computer.software_genre, 01 natural sciences, Synthetic data, 010104 statistics & probability, 03 medical and health sciences, 0302 clinical medicine, [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], Alzheimer's disease subtypes, mixed-effect models, 0101 mathematics, Cognitive decline, mixture models, education, Cluster analysis, Non-linear mixed-effect model, ComputingMilieux_MISCELLANEOUS, Mixture model, Ground truth, education.field_of_study, MCMC-SAEM, business.industry, Contrast (statistics), Disease course mapping, Disease progression modelling, [STAT.ML] Statistics [stat]/Machine Learning [stat.ML], Artificial intelligence, business, computer, [STAT.ME]Statistics [stat]/Methodology [stat.ME], 030217 neurology & neurosurgery
Abstract

International audience; Disease modeling techniques summarize the possible trajectories of progression from multimodal and longitudinal data. These techniques often assume that individuals form a homogeneous cluster, thus ignoring possible disease subtypes within the population. We extend a non-linear mixed-effect model used for disease course mapping with a mixture framework. We jointly estimate model parameters and subtypes with a tempered version of a stochastic approximation of the Expectation Maximisation algorithm. We show that our model recovers the ground truth parameters from synthetic data, in contrast to the naive solution consisting in post hoc clustering of individual parameters from a one-class model. Applications to Alzheimer's disease data allows the unsupervised identification of disease subtypes associated with distinct relationship between cognitive decline and progression of imaging and biological biomarkers.

Published
2021
Full Text
View/download PDF

2. Assessing the impact of preventive mass vaccination campaigns on yellow fever outbreaks in Africa : a population-level self-controlled case-series study

Author

Arran Hamlet, Hanaya Raad, Tini Garske, Katy A. M. Gaythorpe, Kévin Jean, Daniel R Hogan, Tewodaj Mengistu, Judith E. Mueller, Mounia N. Hocine, Heather Whitaker, Laboratoire Modélisation, épidémiologie et surveillance des risques sanitaires (MESuRS), Conservatoire National des Arts et Métiers [CNAM] (CNAM), Pasteur-Cnam Risques infectieux et émergents (PACRI), Institut Pasteur [Paris]-Conservatoire National des Arts et Métiers [CNAM] (CNAM), Imperial College London, École des Hautes Études en Santé Publique [EHESP] (EHESP), Chercheur indépendant, Public Health England [London], This work was carried out as part of the Vaccine Impact Modelling Consortium (www.vaccineimpact.org), but the views expressed are those of the authors and not necessarily those of the Consortium or its funders. The funders were given the opportunity to review this paper prior to publication, but the final decision on the content of the publication was taken by the authors. Dr Jean, Mr Hamlet, Dr Gaythorpe, and Dr Garske acknowledge joint Centre funding from the UK Medical Research Council and Department for International Development (MR/R015600/1) and report grant from The Bill & Melinda Gates Foundation (grant number OPP1157270). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript, HESAM Université - Communauté d'universités et d'établissements Hautes écoles Sorbonne Arts et métiers université (HESAM)-HESAM Université - Communauté d'universités et d'établissements Hautes écoles Sorbonne Arts et métiers université (HESAM), and Institut Pasteur [Paris] (IP)-Conservatoire National des Arts et Métiers [CNAM] (CNAM)

Subjects
medicine.medical_specialty, Disease surveillance, business.industry, Public health, 030231 tropical medicine, Yellow fever, Outbreak, medicine.disease, 3. Good health, 03 medical and health sciences, 0302 clinical medicine, Environmental health, Epidemiology, Pandemic, Cohort, medicine, [SDV.SPEE]Life Sciences [q-bio]/Santé publique et épidémiologie, 030212 general & internal medicine, business, [STAT.ME]Statistics [stat]/Methodology [stat.ME], Cohort study
Abstract

Introduction The Eliminate Yellow fever Epidemics (EYE) strategy was launched in 2017 in response to the resurgence of yellow fever in Africa and the Americas. The strategy relies on several vaccination activities, including preventive mass vaccination campaigns (PMVCs). However, by how much PMVCs are associated with a decreased risk of outbreak to occur has not yet been quantified. Methods and Findings We used the self-controlled case series (SCCS) method to assess the association between the occurrence of yellow fever outbreaks and the implementation of PMVCs at the province level in the African endemic region. As all time-invariant confounders are implicitly controlled for, the SCCS method is an alternative to classical cohort or case-control study designs when the risk of residual confounding is high, in particular confounding by indication. The location and dates of outbreaks were identified from international epidemiological records, and information on PMVCs was provided by coordinators of vaccination activities and international funders. The study sample consisted of provinces that were both affected by an outbreak and targeted for a PMVC between 2005 and 2018. We compared the relative incidence of outbreaks before and after the implementation of a PMVC. The sensitivity of our estimates to a range of assumptions was explored, and the results of the SCCS method were compared to those obtained through a retrospective cohort study design. We further derived the number of yellow fever outbreaks that have been prevented by PMVCs. The study sample consisted of 33 provinces from 11 African countries. Among these, outbreaks occurred during the pre-PMVC period in 26 (79%) provinces versus 7 (21%) occurring in the post-PMVC period. At the province level, the post-PMVC period was associated with a 86% reduction (95% Confidence interval 66% to 94%, p-value A limitation of our study is the fact that it does not account for potential time-varying confounders, such as changing environmental drivers of yellow fever or possibly improved disease surveillance. Conclusion In this study, we provide new empirical evidence of the high preventive impact of PMVCs on yellow fever outbreaks. This study illustrates that the SCCS method can be advantageously applied at the population level in order to evaluate a public health intervention. AUTHOR SUMMARY Why Was This Study Done? Yellow fever is a mosquito-borne vaccine-preventable disease that may cause large urban outbreaks, especially in tropical African regions. Since 2006, Preventive Mass Vaccination Campaigns (PMVCs) have been implemented in many African provinces. These are large scale vaccination campaigns targeting all or most age group in a specific area. The preventive impact PMVCs may have on the risk of yellow fever outbreak has not been quantified yet. What Did the Researchers Do and Find? We used the self-controlled case series (SCCS) method to assess the association between PMVCs and outbreak risk at the province level over 34 African countries between 2005 and 2018. Using this method, we compared pre- and post-PMVC period are compared within each province individually, thus controlling for all possible confounders that do not vary in time, especially the fact that provinces indicated for PMVCs are generally those considered at highest baseline risk of yellow fever (ie confounding by indication). At the province level, we estimated that implementation of PMVCs was associated with an 86% reduction (66% to 94%) in the risk of yellow fever outbreak. Results from a complete cohort analysis provided less reliable results than the SCCS method, likely because of confounding by indication that was not entirely controlled for by adjusting on known drivers of yellow fever. We further estimated that all PMVCs conducted between 2006 and 2018 in Africa may have reduced the total number of yellow fever outbreaks by 34% (22% to 45%). What Do These Findings Mean? These results provide new empirical evidence of the high preventive impact of PMVCs on yellow fever outbreaks. These results may encourage rapid re-scheduling of yellow fever PMVCs that have been postponed due to the COVID-19 pandemic. The SCCS design may be advantageously applied at the population level to assess the impact of public health interventions.

Published
2020

3. A test for gene-environment interaction in the presence of measurement error in the environmental variable

Author

Hugues Aschard, Donna Spiegelman, Molin Wang, Vincent Laville, Pete Kraft, Centre de Bioinformatique, Biostatistique et Biologie Intégrative (C3BI), Institut Pasteur [Paris]-Centre National de la Recherche Scientifique (CNRS), Harvard T.H. Chan School of Public Health, The authors thank the reviewers for their helpful comments that have improved the paper. This research is supported by grant R01CA050597 from the National Cancer Institute (NCI) and R21HG007687 from the National Human Genome Research Institute (NHGRI). The authors have no conflict of interest to declare., and Institut Pasteur [Paris] (IP)-Centre National de la Recherche Scientifique (CNRS)

Subjects
0301 basic medicine, Epidemiology, Genome-wide association study, Breast Neoplasms, MESH: Logistic Models, Interaction, Logistic regression, 01 natural sciences, Article, Correlation, 010104 statistics & probability, 03 medical and health sciences, Bias, Statistics, Linear regression, MESH: Bias, Humans, normal discriminant analysis, MESH: Genetic Variation, MESH: Models, Genetic, 0101 mathematics, Gene–environment interaction, gene-environment interaction test, Genetics (clinical), Mathematics, [STAT.AP]Statistics [stat]/Applications [stat.AP], Observational error, MESH: Humans, Models, Genetic, Genetic Variation, Reproducibility of Results, MESH: Gene-Environment Interaction, Linear discriminant analysis, 3. Good health, MESH: Reproducibility of Results, 030104 developmental biology, Logistic Models, [SDV.GEN.GH]Life Sciences [q-bio]/Genetics/Human genetics, genome-wide association studies, MESH: Genome-Wide Association Study, Gene-Environment Interaction, [SDV.SPEE]Life Sciences [q-bio]/Santé publique et épidémiologie, [INFO.INFO-BI]Computer Science [cs]/Bioinformatics [q-bio.QM], [STAT.ME]Statistics [stat]/Methodology [stat.ME], measurement error, MESH: Breast Neoplasms, Genome-Wide Association Study
Abstract

International audience; The identification of gene-environment interactions in relation to risk of human diseases has been challenging. One difficulty has been that measurement error in the exposure can lead to massive reductions in the power of the test, as well as in bias toward the null in the interaction effect estimates. Leveraging previous work on linear discriminant analysis, we develop a new test of interaction between genetic variants and a continuous exposure that mitigates these detrimental impacts of exposure measurement error in ExG testing by reversing the role of exposure and the diseases status in the fitted model, thus transforming the analysis to standard linear regression. Through simulation studies, we show that the proposed approach is valid in the presence of classical exposure measurement error as well as when there is correlation between the exposure and the genetic variant. Simulations also demonstrated that the reverse test has greater power compared to logistic regression. Finally, we confirmed that our approach eliminates bias from exposure measurement error in estimation. Computing times are reduced by as much as fivefold in this new approach. For illustrative purposes, we applied the new approach to an ExGWAS study of interactions with alcohol and body mass index among 1,145 cases with invasive breast cancer and 1,142 controls from the Cancer Genetic Markers of Susceptibility study.

Published
2018
Full Text
View/download PDF