Knowledge discovery in big results

Abstract Observational healthcare data, such as electronic health records and administrative claims, provide longitudinal clinical information at the individual level. These data may cover tens of millions of patients and present unprecedented opportunities to evaluate the post-market safety of medical products. Analyzing patient-level databases yields population-level inferences, or ‘results,’ such as the strength of association between medical product exposure and subsequent outcomes. With 1000s of drugs, 1000s of outcomes, and 1000s of alternative analysis strategies, the big patient-level data offers the potential to produce “big results.” Using data from the Observational Medical Outcomes Partnership (OMOP), this paper demonstrates the value of machine learning/knowledge discovery methods in extracting clinically relevant knowledge from a large scale result set, or “big results.” This database consists of risk assessments for 399 medical product-outcome pairs analyzed across five observational databases using seven statistical methods (where each method has between a few dozen and a few hundred variants). Our analyses are both scientifically and methodologically valuable as they reveal information about how methods/algorithms perform under various circumstances and provide a basis for comparison of these methods.