Based on the data, we can find new and effective ways to detect rare and unexpected side effects of medicines. Our company develops methods for data-driven detection, facilitating the analysis of high volumes of incoming reports of potential side effects of medicines. Detailed review of large numbers of reports may not be a feasible or effective approach to signal detection and assessment. Methods for data-driven detection help guide the attention of human experts towards the most interesting and relevant case series to review and reveal important reporting patterns impacting signal assessment. Key data-driven research. List of clinically related adverse events. An area of intense research focus is methods to better represent and reflect information on adverse events. With cluster analysis, we seek to discover patterns in data from adverse event reports based on all recorded signs, symptoms, and diagnoses. Additionally, the algorithm groups adverse event reports based on the clinical conditions described in them, like human experts would do. With distributional semantics of our programme, we can obtain data-driven vector representations of medicines and adverse events based on reporting patterns in the database. This enables grouping of adverse events that tend to be reported in similar contexts, based on their position in the data-driven vector space and independent of their position in a hierarchical terminology like MedDRA (international dictionary of adverse reactions arising from using medicines for medical purposes). Risk factor identification Knowing which individuals are at risk of developing specific side effects can help patients and healthcare professionals make wiser therapeutic decisions in their use of medicines. Researchers are actively proposing and evaluating approaches to highlight patterns in observational medical data that may reflect risk factors related to specific side effects. Examples include drug-drug interactions, pharmaco-ethnic vulnerabilities, age- and gender-associated risks, pregnancy, and body mass index. Monitoring Center has also developed a method for data-driven exploration of reporting patterns that can be used for this and several other purposes. Statistical signal detection Effective analysis of individual case reports may rely on statistical signal detection methods to direct and facilitate expert clinical review. Confounding and heterogeneity Reporting patterns in large collections of individual case reports differ over time, by geographic regions and across demographic groups, which can lead to both missed and artificial associations. We developed and evaluated several methods to mitigate these effects. They include shrinkage logistic regression to reduce masking by and signal leakage from co-reported medicines and vaccines, systematic use of subgrouping and stratification to reveal patterns unique to specific categories of reports, as well as a simple approach to unmasking associations that have been hidden by the massive reporting of related medicine-adverse event combinations.