Study: Machine learning could help reduce Rx errors

A study published in the January 2020 issue of The Joint Commission Journal on Quality and Patient Safety used retrospective data to evaluate the ability of a machine learning system to generate clinically valid alerts for medication errors not previously programmed into an existing clinical decision support (CDS) system. The researchers examined more than 10,000 alerts and concluded two-thirds would not have been generated by the CDS without the machine learning system. Further examination of a random sample of the alerts determined 92% were accurate and 80% were clinically valid. “Estimated cost of adverse events potentially prevented in an outpatient setting was more than $60 per drug alert and $1.3 million when extrapolating study findings to the full patient population,” the researchers wrote. The annual U.S. cost of prescription drug errors has been estimated at more than $20 billion.