machine learning

This shows covid19 on a computer monitor

Experimental AI tool predicts which COVID-19 patients develop respiratory disease

AI model determined three key features that accurately predict subsequent, severe disease in COVID-19 patients. The three features were levels of the liver enzyme ALT, reported myalgia, and hemoglobin levels. Based on these three factors, the AI was able to determine ARDS risk with 80% accuracy.... Read More...
This shows the FluSense device components

Portable AI device turns coughing sounds into health data for flu and pandemic forecasting

Researchers have developed a portable surveillance device that uses machine learning to detect coughing and crowd size in real-time. The system can use the data to directly monitor flu-like illnesses, community trends, and virus spread potential. The system could help monitor the spread of infection and provide a public health response during an epidemic.... Read More...
This shows brain scans from the study

Second Type of Schizophrenia Discovered

Combining neuroimaging data with artificial intelligence, researchers have identified two distinct neuroanatomical subtypes of schizophrenia. The first, more typical subtype is associated with a lower widespread volume of gray matter compared to healthy controls. In the second subtype, gray matter volume is largely similar to healthy brains.... Read More...
This is a drawing of the brain hubs

Learning difficulties due to poor connectivity, not specific brain regions

Combining neuroimaging data with machine learning technology, researchers discover children with well-connected brain hubs have either very specific cognitive problems, such as poor listening skills, or no cognitive difficulties at all. Children with poorly connected hubs have widespread and severe cognitive difficulties.... Read More...