Sheba Researchers Find Significant Improvements in Patient Safety Standard Following Deployment of MedAware’s Machine Learning-based Platform

Sheba Medical Center, Tel Hashomer, one of Israel’s leading medical centers, today announced the findings of research validating the clinical impact of the MedAware machine learning-enabled patient safety platform designed to minimize medication-related risks.

The findings were published 7 August 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.

“Sheba Medical Center, recently named by Newsweek as one of the top ten hospitals in the world, prides itself on prioritizing the safety and well being of our patients. One way in which the leadership at Sheba does this is by remaining open to innovation – always searching for the newest, most cutting-edge technologies to improve the care of our patients,” said Dr. Eyal Zimlichman, Deputy Director and Chief Medical Officer at Sheba Medical Center. “Given the challenge of medication safety and its significant impact on patient care, we elected to work with MedAware when the company was still proving its concept.  After years of partnership, our research team set out to assess the clinical impact of the live implementation of MedAware’s platform, and the results speak for themselves.”

Preventable errors account for 1 out of 131 outpatient deaths and 1 out of 854 inpatients deaths in the US, with direct costs of over $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.

Led by Dr. Gadi Segal, Head of Internal Medicine “T,” Sheba researchers assessed the quality, accuracy and impact of MedAware’s medication safety platform.

“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 percent 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.”

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 EMR 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 percent of all prescriptions. Additional findings included:

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

“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, one of the top hospitals in the world, 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.