RAANANA, Israel, January 19, 2017 /PRNewswire/ --
- A recent Harvard clinical research of almost 800,000 lives demonstrated that MedAware's new data-driven technology establishes a ground breaking path to eliminating prescription errors and potentially saving millions of patients affected by it, annually.
- The study reveals that MedAware's data-driven approach identified prescription errors, which were missed by existing clinical decision support (CDS) systems, while demonstrating a high degree of accuracy.
- In fact, three-quarters of alerts generated by MedAware's system were directly relevant to identifying potentially life threatening prescription errors.
Raanana, Israel - (Jan. 16, 2017) - MedAware, an algorithm-rich software startup dedicated to eradicating prescription errors, is pleased to report today the findings of a landmark study carried out by Harvard Medical School.
The study analysed records from almost 800,000 patients in order to assess the efficacy of MedAware's innovative and unique solution, and the results have provided a comprehensive validation of MedAware's disruptive solution.
Dr. David Bates, a leading national Patient Safety expert and opinion leader, Professor of Medicine at Harvard Medical School, and a Professor of Health Policy and Management at the Harvard School of Public Health said:
"It has been hard to find medication errors which come completely out of the blue - likely a medication used only in pregnant women which is ordered for an elderly male - but this approach detects orders which appear to be anomalous in some way, and it represents a very exciting new way to pick these errors up before they get to the patient."
Dr. Gidi Stein, MD, PhD, MedAware's Co-Founder and CEO stated that:
"Minimizing these errors is clearly of the utmost importance, as at the end of the day, it's our patients and loved ones who are at risk, and we must do everything in our power to reduce that risk. We need to find innovative ways to identify and eliminate errors, while reducing alert fatigue - hence our solution."
The findings, published on 19 January 2019, in the Journal of American Medical Informatics Association (JAMIA) revealed that MedAware's technology establishes a new standard for prescription alerts and patient safety vis-à-vis traditional rule-based systems. These out-dated solutions, can only detect a fraction of the actual errors, only those that they were pre-set to identify, and these solutions are not built to identify random or complex errors. Moreover, since current CDS systems are not patient-specific and not self-adaptive, they suffer from high false alarm rates, directly contributing to a phenomenon known as "alert fatigue", where physicians simply learn to disregard alerts.
"There is a need for innovative solutions to address the current prescription errors that result in substantial morbidity, mortality, and wasteful healthcare cost. 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).
The report found that MedAware's technology both identifies errors otherwise undetected and minimizes challenges associated with provider alert fatigue, and thus could reduce prescription errors with high accuracy, reducing medical costs and saving lives.
In the US healthcare market, more than $20bn is lost, annually, as a result of prescription errors and their consequences. Beyond the financial ramifications, it's clear that errors in prescriptions can, and are, very damaging to patients, leading to prolonged illness, contraction of new disease and often death. Prescription errors are also found to be one of the main causes for extended lengths of stay and hospital readmissions.
Harvard Medical School chose to assess MedAware's technology, as they were particularly interested in evaluating the new types of alerts generated by the MedAware system, which are mostly unaddressed by current systems. Dr. Gordon Schiff, PI and Associate Professor Harvard Medical School said:
"Clinical decision support to alert for potential medication problems has a long way to go to achieve the goal of meaningfully and effectively alerting clinicians, without missing too many errors while at the time not over-alerting busy doctors (for errors that not important or relevant for that patient).
Our study of the MedAware system found that it was able to generate alerts based on screening for "outliers" some of which might be missed with existing CDS systems."
The study conducted by Harvard was carried out on almost 800,000 lives at the Brigham and Women's Hospital's (BWH), Center for Patient Safety Research and Practice (CPSRP); as well as making use of retrospective data from Partners HealthCare BWH and Massachusetts General Hospital (MGH) homegrown outpatient electronic health record (EHR).
A full abstract of the study was first published in JAMIA and available 19 January 2017, in full.
MedAware is an algorithm-rich software company developing machine learning enabled decision support solutions, is the developer of the MedAware Rx Alert solution, dedicated to eradicating prescription errors. MedAware harnesses patterns from thousands of physicians treating millions of patients to identify and alert on prescription errors in real-time.
The company's self-learning, self-adaptive system has proven to dramatically reduce healthcare costs while improving patient safety, outcomes, and experience. MedAware's flagship product is the first in a suite of decision support solutions that transform real physician practice data into actionable clinical knowledge.
MedAware, Ltd. MedAware was not involved in any of the coding scheme development, chart review, data analysis, data interpretation, or manuscript preparation for the Harvard Study.
About the technology
Analyzing historical electronic medical records, the system automatically generates, for each medication, a computational model that captures the population that is likely to be prescribed the medication and the clinical environment in which it is likely to be prescribed.
This model can then be used to identify prescriptions that are significant statistical outliers given patients' clinical situations, i.e., medications that are rarely or never prescribed to patients in similar situations, such as birth control pills to a baby boy. Such prescriptions are flagged by the system as potential medication errors.
Contact The PR Office for Media: Marc Cohen, Raj Aujla, Oli Sonenfield