ConvSCCS: convolutional self-controlled case series model for lagged adverse event detection

TL;DR

ConvSCCS introduces a scalable convolutional self-controlled case series model that improves adverse event detection in large EHR datasets by modeling multiple exposures without predefined risk periods.

Contribution

This paper presents a novel convolutional SCCS model that enhances adverse drug reaction detection by jointly modeling multiple exposures and outcomes without requiring precise risk period specifications.

Findings

Improves relative risk estimation accuracy on simulations.

Demonstrates effectiveness on large French health insurance data.

Handles multiple exposures simultaneously.

Abstract

With the increased availability of large databases of electronic health records (EHRs) comes the chance of enhancing health risks screening. Most post-marketing detections of adverse drug reaction (ADR) rely 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 model also known as self-controlled case series (SCCS). We model the intensity of outcomes using a convolution between exposures and step functions, that are penalized using a combination of group-Lasso and total-variation. This approach does not require the specification of precise risk periods, and allows to study in the same model several exposures at the same time. We illustrate the fact that this approach improves the state-of-the-art for the estimation of the relative risks both on simulations and on a cohort of diabetic patients, extracted from the large French national health insurance database (SNIIRAM), a SQL database built around medical reimbursements of more than 65 million people. This work has been done in the context of a research partnership between Ecole Polytechnique and CNAMTS (in charge of SNIIRAM).