A study demonstrated the international portability of a Taiwanese artificial intelligence model for detecting medication errors in EHR systems in the United States.
The study was jointly conducted by Taiwan-based medical AI startup Aesop Technology, Taipei Medical University, Harvard Medical School, and Brigham and Women’s Hospital. Its results were announced last week in a press release.
WHY IS IT IMPORTANT
According to Dr Yu-Chuan Jack Li, professor at Taipei Medical University, the “biggest challenge” in data-driven medicine is the successful implementation of data-driven applications in clinical practice, globally, without compromising patient safety and confidentiality.
The study, the results of which were published in the Journal of Medical Internet Research – Medical Informatics in January, found “good” portability of Aesop’s machine learning model into the EHR systems of two Harvard Medical School training schools – Brigham and Women’s Hospital and Massachusetts General Hospital.
A federated learning (FL) approach was applied to the model, which improved its performance. This approach is an emerging technique that addresses the issues of isolated data islands and privacy.
“FL provides the solution by training algorithms collaboratively without exchanging the data itself,” said Dr. Yu-Chuan.
“The study showed that the model formed by federated learning achieves remarkable performance comparable to the other two models formed by individual data sets,” said Jim Long, co-founder and CEO of Aesop Technology.
Incorporated into Aesop’s MedGuard system, the AI drug safety model was formed using the 1.3 billion prescription data set from the National Health Insurance Administration of Taiwan.
In the statement, Aesop said its system could “immediately” provide adaptive suggestions to help doctors fill their prescriptions better. The AI model has since been extended to hospitals in the eastern and western United States.
THE BIGGEST TREND
Despite the widespread adoption and optimization of EHR systems in U.S. hospitals, these systems still pose risks given varying safety performance, according to a Study 2020 by researchers at the University of Utah and Brigham and Women’s Hospital.
Medical errors cost the United States an estimated $ 20 billion each year, resulting in more than 250,000 deaths. These can occur at any stage of the medication process, and prescribing errors occur half the time.
The use of an AI system to prevent medication errors has already been validated as early as 2017 by researchers at Harvard Medical School. That same year, MedAware, the Israel-based startup that developed the algorithmic system, raised $ 8 million to scale up its AI-based solutions.
“Reducing medication errors at the source is essential. However, to help physicians be better informed and make better decisions, they need more specific suggestions and alerts. machine learning can help make better decisions and improve patient safety and the quality of care, ”said Dr David W. Bates, chief of general internal medicine and primary care at Brigham and Women’s Hospital and professor of Medicine at Harvard Medical School.