Improving patient safety through the prevention of medication errors is one of the highest priorities concerning the healthcare system today. In the US alone, medication errors harm at least 1.5 million people every year and cause the annual premature death of more than 220,000 patients. Adverse drug events are among the most common medical errors. Out of the 4 billion medical prescriptions that are written up annually in the US, 8 million contain life threatening errors.
The introduction of Electronic Medical Records (EMRs) and electronic prescribing systems, combined with clinical decision support systems, has only somewhat helped in reducing the number of prescription errors. However, these systems also introduce new and hazardous types of prescription errors, such as selecting the wrong drug (i.e. picking the wrong medication from a pull-down menu) and selecting the wrong patient (i.e. assigning the drug not to the patient intended, but rather to the one whose record was currently open). The currently available solutions for alerting and preventing prescription errors are focused mainly on drug interactions, dosages and allergies. These solutions detect only a fraction of the actual errors and suffer from a high false-alarm rate, leading to “alert fatigue.” Therefore, there is a real and substantive need for a solution that can detect a wider range of prescription errors and with higher precision than the existing systems.