Using a machine learning system to identify and prevent medication prescribing errors: A clinical and cost analysis evaluation

Rozenblum R, Rodriguez-Monguio R, Volk LA, Forsythe KJ, Myers S, McGurrin M, Williams DH, Bates DW, Schiff G, Seoane-Vazquez E. Using a Machine Learning System to Identify and Prevent Medication Prescribing Errors: A Clinical and Cost Analysis Evaluation. The Joint Commission Journal on Quality and Patient Safety. 2019/11/27/, 2019

Clinical decision support (CDS) tools help identify and reduce medication errors but are limited by the rules and types of errors programmed into their alerting logic and their high alerting rates and false positives, which can contribute to alert fatigue. This retrospective study evaluates the clinical validity and value of using a machine learning system (MedAware) for CDS as compared to an existing CDS system. Chart-reviewed MedAware alerts were accurate (92%) and clinically valid (79.7%). Overall, 68.2% of MedAware alerts would not have been generated by the CDS tool and estimated cost savings associated with the adverse events potentially prevented via MedAware alerts were substantial ($60/drug alert).

PubMed citation

Related editorial