
ConvSCCS: convolutional self-controlled case-seris model for lagged adverser event detection
Morel, Maryan; Bacry, Emmanuel; Gaïffas, Stéphane; Guilloux, Agathe; Leroy, Fanny (2019), ConvSCCS: convolutional self-controlled case-seris model for lagged adverser event detection, Biostatistics. 10.1093/biostatistics/kxz003
View/ Open
Type
Article accepté pour publication ou publiéDate
2019Journal name
BiostatisticsPublication identifier
Metadata
Show full item recordAuthor(s)
Morel, MaryanCentre de Mathématiques Appliquées - Ecole Polytechnique [CMAP]
Bacry, Emmanuel

CEntre de REcherches en MAthématiques de la DEcision [CEREMADE]
Gaïffas, Stéphane
Laboratoire de Probabilités et Modèles Aléatoires [LPMA]
Guilloux, Agathe
Centre de Mathématiques Appliquées - Ecole Polytechnique [CMAP]
Leroy, Fanny
Caisse Nationale d'Assurance Maladie
Abstract (EN)
With the increased availability of large electronic health records databases comes the chance of enhancing health risks screening. Most post-marketing detection of adverse drug reaction (ADR) relies on physicians' spontaneous reports, leading to under-reporting. To take up this challenge, we develop a scalable model to estimate the effect of multiple longitudinal features (drug exposures) on a rare longitudinal outcome. Our procedure is based on a conditional Poisson regression model also known as self-controlled case series (SCCS). To overcome the need of precise risk periods specification, we model the intensity of outcomes using a convolution between exposures and step functions, which are penalized using a combination of group-Lasso and total-variation. Up to our knowledge, this is the first SCCS model with flexible intensity able to handle multiple longitudinal features in a single model. We show that this approach improves the state-of-the-art in terms of mean absolute error and computation time for the estimation of relative risks on simulated data. We apply this method on an ADR detection problem, using a cohort of diabetic patients extracted from the large French national health insurance database (SNIIRAM), a claims database containing medical reimbursements of more than 53 million people. This work has been done in the context of a research partnership between Ecole Polytechnique and CNAMTS (in charge of SNIIRAM).Subjects / Keywords
Conditional Poisson model; Penalization; Risk screening; Scalability; Self-controlled case series; Total variationRelated items
Showing items related by title and author.
-
Morel, Maryan; Bouyer, Benjamin; Guilloux, Agathe; LAANANI, Moussa; Leroy, Fanny; Nguyen, Dinh Phong; Sebiat, Youcef; Bacry, Emmanuel; Gaïffas, Stéphane (2021) Document de travail / Working paper
-
Bacry, Emmanuel; Gaiffas, Stéphane; Leroy, Fanny; Morel, Maryan; Nguyen, D.P.; Sebiat, Youcef; Sun, D. (2019) Document de travail / Working paper
-
Bacry, Emmanuel; Gaïffas, Stéphane; Leroy, Fanny; Morel, Maryan; Nguyen, Dinh-Phong; Sebiat, Youcef; Sun, Dian (2020) Article accepté pour publication ou publié
-
Kabeshova, Anastasiia; Yu, Yiyang; Lukacs, Bertrand; Bacry, Emmanuel; Gaïffas, Stéphane (2020) Article accepté pour publication ou publié
-
Bompaire, Martin; Gaïffas, Stéphane; Bacry, Emmanuel (2018) Document de travail / Working paper