Computational Approaches for Pharmacovigilance Signal Detection: Toward Integrated and Semantically-Enriched Frameworks

摘要: Computational signal detection constitutes a key element of postmarketing drug monitoring and surveillance. Diverse data sources are considered within the ‘search space’ pharmacovigilance scientists, respective analysis methods employed, all with their qualities shortcomings, towards more timely accurate detection. Recent systematic comparative studies highlighted not only event-based data-source-based differential performance across but also complementarity. These findings reinforce arguments for exploiting possible information safety parallel use multiple methods. Combinatorial has been pursued in few up to now, employing rather limited number illustrating well-promising outcomes. However, large-scale realization this approach requires frameworks address challenges concurrent setting. In paper, we argue that semantic technologies provide means some these challenges, particularly highlight contribution (a) annotating quality attributes facilitate selection given scope; (b) consistently defining study parameters such as health outcomes drugs interest, providing guidance setup; (c) expressing common format enabling sharing comparisons; (d) assessing/supporting novelty aggregated through access reference knowledge related safety. A semantically-enriched framework can seamless different computational an integrated fashion, bringing new perspective large-scale, knowledge-intensive