Mount Sinai researchers build models using machine learning technique to enhance predictions of COVID-19 outcomes

January 18, 2021

Mount Sinai researchers have published one of the first studies using a machine learning technique called "federated learning" to examine electronic health records to better predict how COVID-19 patients will progress. The study was published in the Journal of Medical Internet Research - Medical Informatics on January 18.

The researchers said the emerging technique holds promise to create more robust machine learning models that extend beyond a single health system without compromising patient privacy. These models, in turn, can help triage patients and improve the quality of their care.

Federated learning is a technique that trains an algorithm across multiple devices or servers holding local data samples but avoids clinical data aggregation, which is undesirable for reasons including patient privacy issues. Mount Sinai researchers implemented and assessed federated learning models using data from electronic health records at five separate hospitals within the Health System to predict mortality in COVID-19 patients. They compared the performance of a federated model against ones built using data from each hospital separately, referred to as local models. After training their models on a federated network and testing the data of local models at each hospital, the researchers found the federated models demonstrated enhanced predictive power and outperformed local models at most of the hospitals.

"Machine learning models in health care often require diverse and large-scale data to be robust and translatable outside the patient population they were trained on," said the study's corresponding author, Benjamin Glicksberg, PhD, Assistant Professor of Genetics and Genomic Sciences at the Icahn School of Medicine at Mount Sinai, and member of the Hasso Plattner Institute for Digital Health at Mount Sinai and the Mount Sinai Clinical Intelligence Center. "Federated learning is gaining traction within the biomedical space as a way for models to learn from many sources without exposing any sensitive patient data. In our work, we demonstrate that this strategy can be particularly useful in situations like COVID-19."

Machine learning models built within a hospital are not always effective for other patient populations, partially due to models being trained on data from a single group of patients which is not representative of the entire population.

"Machine learning in health care continues to suffer a reproducibility crisis," said the study's first author, Akhil Vaid, MD, postdoctoral fellow in the Department of Genetics and Genomic Sciences at the Icahn School of Medicine at Mount Sinai, and member of the Hasso Plattner Institute for Digital Health at Mount Sinai and the Mount Sinai Clinical Intelligence Center. "We hope that this work showcases benefits and limitations of using federated learning with electronic health records for a disease that has a relative dearth of data in an individual hospital. Models built using this federated approach outperform those built separately from limited sample sizes of isolated hospitals. It will be exciting to see the results of larger initiatives of this kind."
-end-
About the Mount Sinai Health System

The Mount Sinai Health System is New York City's largest academic medical system, encompassing eight hospitals, a leading medical school, and a vast network of ambulatory practices throughout the greater New York region. Mount Sinai is a national and international source of unrivaled education, translational research and discovery, and collaborative clinical leadership ensuring that we deliver the highest quality care--from prevention to treatment of the most serious and complex human diseases. The Health System includes more than 7,200 physicians and features a robust and continually expanding network of multispecialty services, including more than 400 ambulatory practice locations throughout the five boroughs of New York City, Westchester, and Long Island. The Mount Sinai Hospital is ranked No. 14 on U.S. News & World Report's "Honor Roll" of the Top 20 Best Hospitals in the country and the Icahn School of Medicine as one of the Top 20 Best Medical Schools in country. Mount Sinai Health System hospitals are consistently ranked regionally by specialty and our physicians in the top 1% of all physicians nationally by U.S. News & World Report.

For more information, visit https://www.mountsinai.org or find Mount Sinai on Facebook, Twitter and YouTube.

The Mount Sinai Hospital / Mount Sinai School of Medicine

Related Health Care Articles from Brightsurf:

Study evaluates new World Health Organization Labor Care Guide for maternity care providers
The World Health Organization developed the new Labor Care Guide to support clinicians in providing good quality, women-centered care during labor and childbirth.

Six ways primary care "medical homes" are lowering health care spending
New analysis of 394 U.S. primary care practices identifies the aspects of care delivery that are associated with lower health care spending and lower utilization of emergency care and hospital admissions.

Modifiable health risks linked to more than $730 billion in US health care costs
Modifiable health risks, such as obesity, high blood pressure, and smoking, were linked to over $730 billion in health care spending in the US in 2016, according to a study published in The Lancet Public Health.

Spending on primary care vs. other US health care expenditures
National health care survey data were used to assess the amount of money spent on primary care relative to other areas of health care spending in the US from 2002 to 2016.

MU Health Care neurologist publishes guidance related to COVID-19 and stroke care
A University of Missouri Health Care neurologist has published more than 40 new recommendations for evaluating and treating stroke patients based on international research examining the link between stroke and novel coronavirus (COVID-19).

Large federal program aimed at providing better health care underfunds primary care
Despite a mandate to help patients make better-informed health care decisions, a ten-year research program established under the Affordable Care Act has funded a relatively small number of studies that examine primary care, the setting where the majority of patients in the US receive treatment.

International medical graduates care for Medicare patients with greater health care needs
A study by a Massachusetts General Hospital research team indicates that internal medicine physicians who are graduates of medical schools outside the US care for Medicare patients with more complex medical needs than those cared for by graduates of American medical schools.

The Lancet Global Health: Improved access to care not sufficient to improve health, as epidemic of poor quality care revealed
Of the 8.6 million deaths from conditions treatable by health care, poor-quality care is responsible for an estimated 5 million deaths per year -- more than deaths due to insufficient access to care (3.6 million) .

Under Affordable Care Act, Americans have had more preventive care for heart health
By reducing out-of-pocket costs for preventive treatment, the Affordable Care Act appears to have encouraged more people to have health screenings related to their cardiovascular health.

High-deductible health care plans curb both cost and usage, including preventive care
A team of researchers based at IUPUI has conducted the first systematic review of studies examining the relationship between high-deductible health care plans and the use of health care services.

Read More: Health Care News and Health Care Current Events
Brightsurf.com is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to Amazon.com.