A new study by Harvard Medical School shows that software developed by Israeli startup MedAware helps reduce prescription errors, potentially saving the lives of patients.
Ra’anana-based MedAware has developed software that uses algorithms and machine learning based on data and patterns gathered from thousands of physicians who treat millions of patients.
The data is used to identify and give alerts about prescription errors in real time.
The company says its self-learning, self-adaptive system is proven to dramatically reduce healthcare costs while improving patient safety.
The Harvard study analyzed records from almost 800,000 patients to assess the efficacy of MedAware’s software.
The report found that MedAware’s technology identifies errors otherwise undetected by current systems in use, minimizes the risks arising from fatigued doctors who are used to getting false alerts from current systems, and reduces prescription errors with high accuracy.
The findings, published on Sunday in the Journal of American Medical Informatics Association (JAMIA), showed that MedAware’s technology sets a new standard for prescription alerts and patient safety vis-à-vis traditional safety systems, which only detect a fraction of actual errors, and are not geared up to identify random or complex errors, like prescribing a medication used only in pregnant women for an elderly make, for example.
The current clinical decision support (CDS) systems that are used by physicians are not patient-specific and suffer from high false alarm rates — which create a phenomenon known as “alert fatigue,” in which physicians simply learn to disregard notifications, a statement issued by MedAware said.
In the US healthcare market, more than $20 billion is lost, annually, as a result of prescription errors and their consequences, the statement said.
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, MedAware says on its website.
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.
“MedAware’s medication error detection system appears to have the ability to generate novel alerts that might otherwise be missed with existing clinical decision support systems,” said Dr. Ronen Rozenblum, project co-investigator and assistant professor at Harvard Medical School, in the statement.
The study conducted by Harvard was carried out at the Brigham and Women’s Hospital’s (BWH) Center for Patient Safety Research and Practice (CPSRP).
It also made use of retrospective data from Partners HealthCare BWH and Massachusetts General Hospital (MGH) homegrown outpatient electronic health record (EHR).
MedAware is a part of OurCrowd’s portfolio of companies.