Detecting potential signals of adverse drug events from prescription data

Adverse drug events (ADEs) may occur and lead to severe consequences for the public, even though clinical trials are conducted in the stage of pre-market. Computational methods are still needed to fulfil the task of pharmacosurveillance. In post-market surveillance, the spontaneous reporting system (SRS) has been widely used to detect suspicious associations between medicines and ADEs. However, the passive mechanism of SRS leads to the hysteresis in ADE detection by SRS based methods, not mentioning the acknowledged problem of under-reporting and duplicate reporting in SRS. Therefore, there is a growing demand for other complementary methods utilising different types of healthcare data to assist with global pharmacosurveillance. Among those data sources, prescription data is of proved usefulness for pharmacosurveillance. However, few works have used prescription data for signalling ADEs. In this paper, we propose a data-driven method to discover medicines that are responsible for a given ADE purely from prescription data. Our method uses a logistic regression model to evaluate the associations between up to hundreds of suspected medicines and an ADE spontaneously and selects the medicines possessing the most significant associations via Lasso regularisation. To prepare data for training the logistic regression model, we adapt the design of the case-crossover study to construct case time and control time windows for the extraction of medicine use information. While the case time window can be readily determined, we propose several criteria to select the suitable control time windows providing the maximum power of comparisons. In order to address confounding situations, we have considered diverse factors in medicine utilisation in terms of the temporal effect of medicine and the frequency of prescription, as well as the individual effect of patients on the occurrence of an ADE. To assess the performance of the proposed method, we conducted a case study with a real-world prescription dataset. Validated by the existing domain knowledge, our method successfully traced a wide range of medicines that are potentially responsible for the ADE. Further experiments were also carried out according to a recognised gold standard, our method achieved a sensitivity of 65.9% and specificity of 96.2%.