E-Mail
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
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 performa
Date Time
Clear, reliable, up to date
Family physicians, or GP’s, are the first port of call for nearly all questions concerning health or illness. Accordingly, they need to be able to access sources of information which cover as wide a spectrum as possible of the various fields of medicine, but which are also precise enough to be of use in specific individual cases. Together with the Cochrane Collaboration and the University of Freiburg, a team of researchers at FAU have investigated how GP’s access medical information and what they look for in digital material. The systematic review of qualitative and quantitative studies funded by the innovation fund of the Federal Joint Committee as part of the project dealing with well-informed communication between doctors and patients, ‘Gut informierte Kommunikation zwischen Arzt und Patient (GAP)’, has now been published in the Journal of Medical Internet Research.
Mickaël Ringeval, the lead author of the study, says wearing a fitness tracker and setting a daily step goal proved to be more efficient than receiving a call from a physician to stay active.
Study Finds That Gaming Is Objectively Beneficial for Kids Fighting Cancer Jan 20, 2021 13:00 EST
A study promoted by the Juegaterapia Foundation and published in the Journal of Medical Internet Research shows that gaming is objectively beneficial for kids that are fighting cancer.
The scientific research took place in the Hospital La Paz (Madrid) and showed the following key points:
20% less morphine while playing games
The pain these children felt can be objectively considered reduced, as shown by a 20% decrease in the daily usage of morphine. This refers to basal pain but also the general mood, with a reduction of 44% in incidental pain. This was measured with a Visual Analogue Scale.