Sheba Medical Center validates machine learning-based meds decision support tech

The provider organization has published a study that validates the clinical impact of health IT vendor MedAware’s machine learning-enabled patient safety platform designed to minimize medication-related risks.
By Bill Siwicki
12:46 PM

Israel’s Sheba Medical Center, Tel Hashomer, one of the top 10 hospitals in the world according to Newsweek, has announced the results of a study that validates the clinical impact of health IT vendor MedAware’s machine learning-enabled patient safety platform designed to minimize medication-related risks.


The findings were published August 7, 2019, in the Journal of American Medical Informatics Association (JAMIA) in a study entitled “Reducing drug prescription errors and adverse drug events by application of a probabilistic, machine-learning based clinical decision support system in an inpatient setting.”


Preventable errors account for 1 out of 131 outpatient deaths and 1 out of 854 inpatients deaths in the U.S., with direct costs of more than $20 billion and liability costs of more than $13 billion annually, according to Sheba research authors. Often errors that take place are the result of failures in computerized health information systems, according to the research.

Led by Dr. Gadi Segal, head of internal medicine, Sheba Medical Center researchers assessed the quality, accuracy and impact of MedAware’s medication safety platform.

Physicians at Sheba analyzed results in a single medical ward, from a hospital-wide live implementation of MedAware, which had been integrated into the center’s existing EHR system. The platform monitored all medical prescriptions issued over 16 months, with the department’s staff assessing all alerts for accuracy, clinical validity and usefulness, recording all physicians’ real-time responses to alerts generated.

The results of the study demonstrated a low overall alert burden, with MedAware-generated warnings for only 0.4% of all prescriptions. Additional findings included:

  • 60% of warnings generated after a medication was already dispensed following changes in patient status.
  • 89% of all alerts were considered accurate.
  • 80% of all alerts were considered clinically useful.
  • 43% of alerts caused changes in subsequent medical orders.


“Today’s widely used rule-based systems for prevention of medication risks, including prescription errors and adverse drug events, are unsuccessful and associated with a substantial false alert burden. These alerts are ignored in nearly 95% of cases,” explained Dr. Segal. “Our study demonstrates that MedAware’s patient safety platform, which leverages a probabilistic, machine-learning approach based on outlier detection can significantly minimize such risks, with high physician acceptance of MedAware warnings that result in physician behavior change and increased patient safety.”

“We were always confident that our advanced patient safety platform would help physicians provide the highest level of care for their patients in a live inpatient setting, and our performance at Sheba confirms our ability to protect physicians and their patients from avoidable medication-related errors and risks, thereby creating a safer prescribing environment,” said Dr. Gidi Stein, co-founder and CEO of MedAware.

Twitter: @SiwickiHealthIT
Email the writer:
Healthcare IT News is a HIMSS Media publication.

Want to get more stories like this one? Get daily news updates from Healthcare IT News.
Your subscription has been saved.
Something went wrong. Please try again.