{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/convsccs-convolutional-self-controlled-case","title":"ConvSCCS: convolutional self-controlled case series model for lagged adverse event detection","arxiv_id":"1712.08243","date":"2017-12-21","proceeding":null,"authors":["Maryan Morel","Emmanuel Bacry","Stéphane Gaïffas","Agathe Guilloux","Fanny Leroy"],"abstract":"With the increased availability of large databases of electronic health\nrecords (EHRs) comes the chance of enhancing health risks screening. Most\npost-marketing detections of adverse drug reaction (ADR) rely on physicians'\nspontaneous reports, leading to under reporting. To take up this challenge, we\ndevelop a scalable model to estimate the effect of multiple longitudinal\nfeatures (drug exposures) on a rare longitudinal outcome. Our procedure is\nbased on a conditional Poisson model also known as self-controlled case series\n(SCCS). We model the intensity of outcomes using a convolution between\nexposures and step functions, that are penalized using a combination of\ngroup-Lasso and total-variation. This approach does not require the\nspecification of precise risk periods, and allows to study in the same model\nseveral exposures at the same time. We illustrate the fact that this approach\nimproves the state-of-the-art for the estimation of the relative risks both on\nsimulations and on a cohort of diabetic patients, extracted from the large\nFrench national health insurance database (SNIIRAM), a SQL database built\naround medical reimbursements of more than 65 million people. This work has\nbeen done in the context of a research partnership between Ecole Polytechnique\nand CNAMTS (in charge of SNIIRAM).","url_abs":"http://arxiv.org/abs/1712.08243v2","url_pdf":"http://arxiv.org/pdf/1712.08243v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"convsccs-convolutional-self-controlled-case","repo_url":"https://github.com/MaryanMorel/ConvSCCS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"event-detection","task_name":"Event Detection"},{"task_slug":"marketing","task_name":"Marketing"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}