@article{Hripcsak_Knirsch_Zhou_Wilcox_Melton_2011, title={Bias Associated with Mining Electronic Health Records}, volume={6}, url={https://journals.uic.edu/ojs/index.php/jbdc/article/view/3581}, DOI={10.5210/disco.v6i0.3581}, abstractNote={Large-scale electronic health record research introduces biases compared to traditional manually curated retrospective research. We used data from a community-acquired pneumonia study for which we had a gold standard to illustrate such biases. The challenges include data inaccuracy, incompleteness, and complexity, and they can produce in distorted results. We found that a naïve approach approximated the gold standard, but errors on a minority of cases shifted mortality substantially. Manual review revealed errors in both selecting and characterizing the cohort, and narrowing the cohort improved the result. Nevertheless, a significantly narrowed cohort might contain its own biases that would be difficult to estimate.}, journal={DISCO: Journal of Biomedical Discovery and Collaboration}, author={Hripcsak, George and Knirsch, Charles and Zhou, Li and Wilcox, Adam and Melton, Genevieve}, year={2011}, month={Jun.}, pages={48–52} }