Mount Sinai researchers have published one of the first studies using a machine learning method called “federated learning” to examine electronic health records to better predict how COVID-19 patients develop onwards. The study was published in the Journal of Medical Internet Research – Medical Informatics on 18 January.
The researchers said the emerging innovation promises to create more robust machine learning models that extend beyond a single health system without compromising patient privacy. These models can, in turn, help patients improve the quality of their care.
Integrated learning is a method of training an algorithm across multiple devices or servers that holds local data samples but avoids the collection of clinical data, which is not desirable for reasons including patient privacy issues . Mount Sinai researchers implemented and evaluated integrated learning models using data from electronic health records at five individual hospitals within the Health System to predict mortality in COVID-19 patients. They compared the performance of an integrated model with those constructed using data from each individual hospital, called local models. After training their models on an integrated network and testing local model data at each hospital, the researchers found that the federated models showed improved predictive power and outperformed the local models. at most hospitals.
“Machine learning models in healthcare often require robust and large-scale diverse data and the ability to translate outside the population of trained patients,” said the corresponding author of the study , Benjamin Glicksberg, PhD, Associate Professor of Genetics and Genomic Sciences at the Icahn School of Medicine at Mount Sinai, and a member of the Hasso Plattner Institute for Digital Health at Mount Sinai and the Mount Sinai Clinical Information Center. “Federal learning is gaining traction within the biochemical space as a way to learn models from multiple sources without revealing any sensitive data about patients. In our work, we show that this strategy may be particularly useful in situations such as COVID-19. ”
Machine learning models built within a hospital are not always effective for other patient numbers, in part because models are trained on data from one group of patients who do not represent the patient. whole population.
“Machine learning in health care is still experiencing a replication crisis,” said the study’s first author, Akhil Vaid, MD, a graduate of the Department of Genetics and Genomic Sciences at Icahn School of Medicine at Mount Sinai, and a member of Hasso Plattner Institute for Digital Health at Mount Sinai and Mount Sinai Clinical Information Center. “We hope this work demonstrates the benefits and limitations of using integrated learning with electronic health records for a data-intensive disease in an individual hospital. Models built using the This integrated approach performs better than those taken separately from limited sample sizes of remote hospitals. It will be encouraging to see the results of larger initiatives of this nature. “
###
About the Mount Sinai health system
Mount Sinai Health System is the largest academic medical system in New York City, comprising eight hospitals, a major medical school, and a large network of mobile practices throughout the New York area. Mount Sinai is a national and international source of unparalleled education, translational discovery and discovery, and collaborative clinical leadership ensuring we deliver the highest quality care – from prevention to treatment of the worst and most complex human diseases. The Health System comprises more than 7,200 physicians and features a strong and growing network of multidisciplinary services, including over 400 mobile use spaces across five urban areas. New York, Westchester, and Long Island. Mount Sinai Hospital is ranked 14th on the US News & World Report “Honor Roll” of the Top 20 Hospitals in the Country and Icahn School of Medicine is one of the top 20 medical schools in the country. Mount Sinai Health System hospitals are consistently ranked regionally by specific experience and our physicians are in the top 1% of physicians nationally by US News & World Report.
For more information, visit https: /
Disclaimer: AAAS and EurekAlert! they are not responsible for the accuracy of press releases posted to EurekAlert! by sending institutions or for using any information through the EurekAlert system.