Electronic approaches to making sense of the text in the adverse event reporting system.

Benin AL, Fodeh SJ, Lee K, Koss M, Miller P, Brandt C. J Healthc Risk Manag. 2016;36:10-20.

Voluntary incident reports are critical to identifying adverse events, but reading through the text can be time-intensive. This study found that a machine learning approach to electronically analyze incident reports successfully detected both weight-based errors and patient identification errors. The authors conclude that it is feasible to apply automated text analysis to incident reports to categorize safety events and drive improvement.

PubMed citation Available at