Standard-based comprehensive detection of adverse drug reaction signals from nursing statements and laboratory results in electronic health records.

摘要: Objective. We propose 2 Medical Dictionary for Regulatory Activities–enabled pharmacovigilance algorithms, MetaLAB and MetaNurse, powered by a per-year meta-analysis technique improved subject sampling strategy. Matrials methods. This study developed novel laboratory abnormalities MetaNurse standard nursing statements, as significantly versions of our previous electronic health record (EHR)–based method, called CLEAR. Adverse drug reaction (ADR) signals from 117 1357 statements all precautionary drugs ( n   = 101) were comprehensively detected validated against SIDER (Side Effect Resource) 11 817 76 457 drug-ADR pairs, respectively. Results. demonstrate that (area under the curve, AUC = 0.61 ± 0.18) outperformed CLEAR (AUC = 0.55 ± 0.06) when we applied same 470 drug-event pairs gold standard, in research. Receiver operating characteristic curves 101 terms Activities Preferred Terms obtained (0.69 ± 0.11; 0.62 ± 0.07), which complemented each other ADR signal coverage. Novel discovered successfully spontaneous reports US Food Drug Administration Event Reporting System database. Discussion. The present demonstrates symbiosis test results detection their system organ class coverage performance profiles. Conclusion. Systematic discovery evaluation wide spectrum using standard-based observational data across many institutions will affect development use, well postmarketing surveillance regulation.