Posts Tagged “AI”
An AI-based patient safety solution developed by Israeli medical tech startup MedAware identified over 10,000 potential medical errors and adverse drug events, with an accuracy rate of over 90 percent, according to a new study co-authored by Harvard researchers.
The study, published last month by the Joint Commission Journal on Quality and Patient Safety, analyzed MedAware’s machine learning-enabled clinical decision support platform, designed to prevent medication-related errors, at the outpatient clinics of Massachusetts General and Brigham and Women’s Hospitals. The system flagged 10,668 potential errors and adverse drug events in retrospect on 373,992 patients.
The study found that 92 percent of warnings generated by MedAware were accurate based on the data available, and 72.7 percent of those warnings were considered “clinically valid.” In addition, 68.2 percent of the warnings would not have been flagged by existing decision support systems, according to the findings.
MedAware said that the implementation of the technology at those hospitals translated to savings of some $1.3 million during the study’s duration. If one takes into account the average number of outpatient visits in the US annually, this translates to a potential cost savings of $800 million and prevention of over 13 million medication errors, MedAware argued.
“This study shows that MedAware’s system performed well in identifying important medication-related errors in the ambulatory setting, and that implementing it could result in substantial cost savings,” said Dr. David Bates, a study co-author, Professor at Harvard Medical School, and Director of the Center for Patient Safety Research & Practice at Brigham and Women’s Hospital
“MedAware’s application enables systems to catch errors they didn’t know they had and which would not have been caught using existing systems—these can be very serious and have major consequences,” said Dr. Bates.
Indeed, medical errors are very dangerous. In a widely circulated study published in 2016 by the Maryland-based John Hopkins School of Medicine, researchers argued that medical error was the third-leading cause of death in the United States (after heart disease and cancer). According to the study, more than 250,000 deaths per year in the US are due to medical mistakes. The findings have been disputed and a different study published in 2019 found that the number of deaths per annum due to adverse effects of medical treatment (AEMT) including adverse drug events, medication-related errors, and medical misadventures (accidental treatment or dosage, for example) may be up to 80 times lower.
These errors are also very costly and can amount to over $20 billion per year in wasteful spending in the United States, says Dr. Gidi Stein, a practicing physician who is also CEO and co-founder of MedAware.
Dr. Stein founded MedAware in 2012 with Tuvik Beker, to detect and minimize catatrosphic medication errors and transform patient safety standards through sophisticated tech.
“When you consider that this study took place in two of the safest, most advanced outpatient clinics in the US, and there was still a positive ROI due to errors prevented, you can understand how implementing MedAware’s technology across the healthcare system has the potential to save the healthcare system hundreds of millions of dollars in outpatient settings alone,” Dr. Stein tells NoCamels.
Dr. Ronen Rozenblum, assistant professor at Harvard Medical School and director of business development for the Center for Patient Safety Research & Practice at Brigham and Women’s Hospital was the lead author of the study. He said that MedAware “offers both measurable improvement in patient safety and significant potential cost savings to hospitals at a time when healthcare systems must find every opportunity to drive efficiencies from a financial perspective.”
“Because it is not rule-based, MedAware represents a paradigm shift in medication-related risk mitigation and an innovative approach to improving patient safety,” added Dr. Bates.
Prescriptions deviating greatly from the spectrum of standard treatment patterns are flagged as potential errors, with high specificity and low alert fatigue. Alerts are displayed at the point of prescribing but also asynchronously, following a change in the patient’s status that might render one of the active medications dangerous to the patient.
A new technological breakthrough is using AI and facial analysis to make it easier to diagnose genetic disorders. DeepGestalt is a deep learning technology created by a team of Israeli and American researchers and computer scientists for the FDNA company based in Boston. The company specializes in building AI-based, next-generation phenotyping (NGP) technologies to “capture, structure and analyze complex human physiological data to produce actionable genomic insights.”
Portions of this article were originally reported in NoCamels.com
DeepGestalt uses novel facial analysis to study photographs of faces and help doctors narrow down the possibilities. While some genetic disorders are easy to diagnose based on facial features, with over 7,000 distinct rare diseases affecting some 350 million people globally, according to the World Health Organization, it can also take years – and dozens of doctor’s appointments – to identify a syndrome.
“With today’s workflow, it can mean about six years for a diagnosis. If you have data in the first year, you can improve a child’s life tremendously. It is very frustrating for a family not to know the diagnosis,” Yaron Gurovich, Chief Technology Officer at FDNA and an Israeli expert in computer vision, tells NoCamels. “Even if you don’t have a cure, to know what to expect, to know what you’re dealing with helps you manage tomorrow.”
DeepGestalt — a combination of the words ‘deep’ for deep learning and the German word ‘gestalt’ which is a pattern of physical phenomena — is a novel facial analysis framework that highlights the facial phenotypes of hundreds of diseases and genetic variations.
According to the Rare Disease Day organization, 1 in 20 people will live with a rare disease at some point in their life. And while this number is high, there is no cure for the majority of rare diseases and many go undiagnosed.
“For years, we’ve relied solely on the ability of medical professionals to identify genetically linked disease. We’ve finally reached a reality where this work can be augmented by AI, and we’re on track to continue developing leading AI frameworks using clinical notes, medical images, and video and voice recordings to further enhance phenotyping in the years to come,” Dekel Gelbman, CEO of FDNA, said in a statement.
DeepGestalt’s neural network is trained on a dataset of over 150,000 patients, curated through Face2Gene, a community-driven phenotyping platform. The researchers trained DeepGestalt on 17,000 images and watched as it correctly labeled more than 200 genetic syndromes.
In another test, the artificial intelligence technology sifted through another 502 photographs to identify potential genetic disorders.
DeepGestalt provided the correct answer 91 percent of the time.
Indeed, FDNA, a leader in artificial intelligence and precision medicine, in collaboration with a team of scientists and researchers, published a milestone study earlier this year, entitled “Identifying Facial Phenotypes of Genetic Disorders Using Deep Learning” in the peer-reviewed journal Nature Medicine.