Friday, May 7, 2021
Home Life Style Health & Fitness Techniques To Predict COVID Outcomes

Techniques To Predict COVID Outcomes

Novel ML techniques to enhance predictions of Covid outcomes

Researchers have published one of the first studies using a Machine Learning (ML) technique called “federated learning” to examine electronic health records to better predict how Covid-19 patients will progress.

The study, published in the Journal of Medical Internet Research – Medical Informatics, indicates that 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.

“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 co-author Benjamin Glicksberg, Assistant Professor at Mount Sinai.

Sputnik V
The Drug Controller General of India (DCGI) has granted approval to Dr Reddy’s, a global pharmaceutical company headquartered in India to Sputnik V made by Russia. Pixabay

“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 co-author Benjamin Glicksberg, Assistant Professor at Mount Sinai.

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.

For the study, the 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.

ALSO READ: Using Nanoparticle of Coronavirus Protein For COVID Vaccine

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. (IANS)

STAY CONNECTED

19,512FansLike
362FollowersFollow
1,773FollowersFollow

Most Popular

Fix Your Gummy Smile By These Treatment Options

Everyone tends to experience something they are self-conscious about. For some people, a gummy smile which is known as an excessive gingival display is...

Participate In Fitness Challenges And Win Some Great Prizes

As the pandemic continues to grip the country, it is becoming challenging for us to keep our spirits high. Fitness is no longer a...

Study: COVID Precautions Causing Dermatitis In Two-Thirds Of The Population

More than two-thirds of people may now have hand dermatitis due to stringent hand washing and using alcohol-based rubs during the Covid-19 pandemic, indicating...

Natural Herbs For Stress And Anxiety Relief

The ongoing Covid-19 pandemic has struck both people's mental health and physical health, with necessary protocols like social distancing and restricted mobility making the...

Google Planning To Give Users More Controls About How Their Data Is Used By Apps

After Apple gave users more control over their data sharing with app developers, Google has now pre-announced an upcoming safety section in Google Play...

Lancet: COVID Pneumonia Puts 1 In Every 3 Women At Lung Damage Risk

Most patients hospitalized for Covid-19 infection return to full health, but one in three may develop lung damage even after a year, according to...

Report: Immediate Action Is Needed To Reduce Methane Emissions

A Global Methane Assessment released on Thursday by the Climate and Clean Air Coalition (CCAC) and the United Nations Environment Programme (UNEP) showed that...

Racism In The United States Has a Long History

By- Khushi Bisht It was 1915, and India was still fighting for freedom when a man with his wife and three children chose to flee...

Recent Comments