Longitudinal clinical data resources (e.g., the Composite Health Care System) are important large-scale repositories of data from real-world medical practice that can provide significant new insights regarding the safety of approved drugs and vaccines, through the application of automated data mining. Such "secondary" use depends, however, on overcoming substantial information-handling obstacles: the original data, collected primarily for patient care and administration, are highly complex and fine-grained and unsuitable for direct analysis. The project objective is to develop innovative software capable of (1) extracting and standardizing relevant information from medical records in military health systems, (2) utilizing temporal abstraction and pattern matching to identify medical record segments that correspond to potential drug-related adverse events, (3) providing alerts to physicians when "labeled" adverse reactions are so identified, and (4) performing aggregate analyses to detect drug-event associations with greater-than-expected frequencies that may signal previously uncharacterized adverse reactions. Phase I focuses on developing temporal abstraction, pattern matching, and disproportionality analysis technologies that show promise in identifying adverse drug events when applied to moderate-scale test data. Phase II focuses on prototype completion, scale-up, and validation, on automating data extraction and on comparing results with those from other data sources (clinical trials, post-marketing surveillance, chart review).
Keywords: Longitudinal Clinical Data, Safety Data Mining, Electronic Medical Record, Adverse Drug Event, Temporal Abstraction, Temporal Pattern Matching, Dispro
